| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.4708549211906576, |
| "eval_steps": 500, |
| "global_step": 70000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00033632494370761253, |
| "grad_norm": 1.274348497390747, |
| "learning_rate": 0.0001, |
| "loss": 9.9462, |
| "num_input_tokens_seen": 13107200, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0006726498874152251, |
| "grad_norm": 0.3978561758995056, |
| "learning_rate": 0.0002, |
| "loss": 8.361, |
| "num_input_tokens_seen": 26214400, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.0010089748311228376, |
| "grad_norm": 0.41306379437446594, |
| "learning_rate": 0.0003, |
| "loss": 7.6593, |
| "num_input_tokens_seen": 39321600, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.0013452997748304501, |
| "grad_norm": 0.3370315134525299, |
| "learning_rate": 0.0004, |
| "loss": 7.1018, |
| "num_input_tokens_seen": 52428800, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.0016816247185380627, |
| "grad_norm": 0.6396230459213257, |
| "learning_rate": 0.0005, |
| "loss": 6.6331, |
| "num_input_tokens_seen": 65536000, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.002017949662245675, |
| "grad_norm": 0.5036832690238953, |
| "learning_rate": 0.0006, |
| "loss": 6.2646, |
| "num_input_tokens_seen": 78643200, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.002354274605953288, |
| "grad_norm": 0.4829367399215698, |
| "learning_rate": 0.0007, |
| "loss": 5.9656, |
| "num_input_tokens_seen": 91750400, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.0026905995496609002, |
| "grad_norm": 0.6319091320037842, |
| "learning_rate": 0.0008, |
| "loss": 5.7098, |
| "num_input_tokens_seen": 104857600, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.003026924493368513, |
| "grad_norm": 0.8607974648475647, |
| "learning_rate": 0.0009000000000000001, |
| "loss": 5.5012, |
| "num_input_tokens_seen": 117964800, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.0033632494370761253, |
| "grad_norm": 0.4290812611579895, |
| "learning_rate": 0.001, |
| "loss": 5.3179, |
| "num_input_tokens_seen": 131072000, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.0033632494370761253, |
| "eval_loss": 5.179312705993652, |
| "eval_runtime": 100.6159, |
| "eval_samples_per_second": 49.694, |
| "eval_steps_per_second": 12.423, |
| "num_input_tokens_seen": 131072000, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.003699574380783738, |
| "grad_norm": 0.407632052898407, |
| "learning_rate": 0.001, |
| "loss": 5.1431, |
| "num_input_tokens_seen": 144179200, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.00403589932449135, |
| "grad_norm": 0.31742918491363525, |
| "learning_rate": 0.001, |
| "loss": 4.9611, |
| "num_input_tokens_seen": 157286400, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.004372224268198963, |
| "grad_norm": 0.3897629678249359, |
| "learning_rate": 0.001, |
| "loss": 4.8043, |
| "num_input_tokens_seen": 170393600, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.004708549211906576, |
| "grad_norm": 0.41930389404296875, |
| "learning_rate": 0.001, |
| "loss": 4.6617, |
| "num_input_tokens_seen": 183500800, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.005044874155614189, |
| "grad_norm": 0.4283705949783325, |
| "learning_rate": 0.001, |
| "loss": 4.5535, |
| "num_input_tokens_seen": 196608000, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.0053811990993218005, |
| "grad_norm": 0.3931107521057129, |
| "learning_rate": 0.001, |
| "loss": 4.4556, |
| "num_input_tokens_seen": 209715200, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.005717524043029413, |
| "grad_norm": 0.3258611857891083, |
| "learning_rate": 0.001, |
| "loss": 4.3808, |
| "num_input_tokens_seen": 222822400, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.006053848986737026, |
| "grad_norm": 0.3562588095664978, |
| "learning_rate": 0.001, |
| "loss": 4.3136, |
| "num_input_tokens_seen": 235929600, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.006390173930444639, |
| "grad_norm": 0.3626460134983063, |
| "learning_rate": 0.001, |
| "loss": 4.2557, |
| "num_input_tokens_seen": 249036800, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.006726498874152251, |
| "grad_norm": 0.4001849293708801, |
| "learning_rate": 0.001, |
| "loss": 4.208, |
| "num_input_tokens_seen": 262144000, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.006726498874152251, |
| "eval_loss": 4.108783721923828, |
| "eval_runtime": 101.5418, |
| "eval_samples_per_second": 49.241, |
| "eval_steps_per_second": 12.31, |
| "num_input_tokens_seen": 262144000, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.007062823817859863, |
| "grad_norm": 0.36548155546188354, |
| "learning_rate": 0.001, |
| "loss": 4.1537, |
| "num_input_tokens_seen": 275251200, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.007399148761567476, |
| "grad_norm": 0.33794787526130676, |
| "learning_rate": 0.001, |
| "loss": 4.1062, |
| "num_input_tokens_seen": 288358400, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.007735473705275089, |
| "grad_norm": 0.3374481499195099, |
| "learning_rate": 0.001, |
| "loss": 4.0703, |
| "num_input_tokens_seen": 301465600, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.0080717986489827, |
| "grad_norm": 0.3061329126358032, |
| "learning_rate": 0.001, |
| "loss": 4.0253, |
| "num_input_tokens_seen": 314572800, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.008408123592690313, |
| "grad_norm": 0.3140158951282501, |
| "learning_rate": 0.001, |
| "loss": 4.0128, |
| "num_input_tokens_seen": 327680000, |
| "step": 1250 |
| }, |
| { |
| "epoch": 0.008744448536397926, |
| "grad_norm": 0.3002954125404358, |
| "learning_rate": 0.001, |
| "loss": 3.9762, |
| "num_input_tokens_seen": 340787200, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.009080773480105539, |
| "grad_norm": 0.2994467318058014, |
| "learning_rate": 0.001, |
| "loss": 3.9485, |
| "num_input_tokens_seen": 353894400, |
| "step": 1350 |
| }, |
| { |
| "epoch": 0.009417098423813152, |
| "grad_norm": 0.25649985671043396, |
| "learning_rate": 0.001, |
| "loss": 3.9298, |
| "num_input_tokens_seen": 367001600, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.009753423367520764, |
| "grad_norm": 0.2627107501029968, |
| "learning_rate": 0.001, |
| "loss": 3.904, |
| "num_input_tokens_seen": 380108800, |
| "step": 1450 |
| }, |
| { |
| "epoch": 0.010089748311228377, |
| "grad_norm": 0.29527419805526733, |
| "learning_rate": 0.001, |
| "loss": 3.8864, |
| "num_input_tokens_seen": 393216000, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.010089748311228377, |
| "eval_loss": 3.8075473308563232, |
| "eval_runtime": 99.5484, |
| "eval_samples_per_second": 50.227, |
| "eval_steps_per_second": 12.557, |
| "num_input_tokens_seen": 393216000, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.010426073254935988, |
| "grad_norm": 0.26328331232070923, |
| "learning_rate": 0.001, |
| "loss": 3.8701, |
| "num_input_tokens_seen": 406323200, |
| "step": 1550 |
| }, |
| { |
| "epoch": 0.010762398198643601, |
| "grad_norm": 0.2574864625930786, |
| "learning_rate": 0.001, |
| "loss": 3.8575, |
| "num_input_tokens_seen": 419430400, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.011098723142351214, |
| "grad_norm": 0.2445235550403595, |
| "learning_rate": 0.001, |
| "loss": 3.8277, |
| "num_input_tokens_seen": 432537600, |
| "step": 1650 |
| }, |
| { |
| "epoch": 0.011435048086058826, |
| "grad_norm": 0.2726516127586365, |
| "learning_rate": 0.001, |
| "loss": 3.8171, |
| "num_input_tokens_seen": 445644800, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.01177137302976644, |
| "grad_norm": 0.2658848166465759, |
| "learning_rate": 0.001, |
| "loss": 3.8026, |
| "num_input_tokens_seen": 458752000, |
| "step": 1750 |
| }, |
| { |
| "epoch": 0.012107697973474052, |
| "grad_norm": 0.30301713943481445, |
| "learning_rate": 0.001, |
| "loss": 3.7838, |
| "num_input_tokens_seen": 471859200, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.012444022917181665, |
| "grad_norm": 0.24884650111198425, |
| "learning_rate": 0.001, |
| "loss": 3.7685, |
| "num_input_tokens_seen": 484966400, |
| "step": 1850 |
| }, |
| { |
| "epoch": 0.012780347860889277, |
| "grad_norm": 0.2728760540485382, |
| "learning_rate": 0.001, |
| "loss": 3.759, |
| "num_input_tokens_seen": 498073600, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.013116672804596888, |
| "grad_norm": 0.24091999232769012, |
| "learning_rate": 0.001, |
| "loss": 3.7496, |
| "num_input_tokens_seen": 511180800, |
| "step": 1950 |
| }, |
| { |
| "epoch": 0.013452997748304501, |
| "grad_norm": 0.2559104561805725, |
| "learning_rate": 0.001, |
| "loss": 3.7289, |
| "num_input_tokens_seen": 524288000, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.013452997748304501, |
| "eval_loss": 3.654578447341919, |
| "eval_runtime": 99.6741, |
| "eval_samples_per_second": 50.164, |
| "eval_steps_per_second": 12.541, |
| "num_input_tokens_seen": 524288000, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.013789322692012114, |
| "grad_norm": 0.24713733792304993, |
| "learning_rate": 0.001, |
| "loss": 3.7259, |
| "num_input_tokens_seen": 537395200, |
| "step": 2050 |
| }, |
| { |
| "epoch": 0.014125647635719727, |
| "grad_norm": 0.2594991624355316, |
| "learning_rate": 0.001, |
| "loss": 3.7121, |
| "num_input_tokens_seen": 550502400, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.01446197257942734, |
| "grad_norm": 0.2594399154186249, |
| "learning_rate": 0.001, |
| "loss": 3.6975, |
| "num_input_tokens_seen": 563609600, |
| "step": 2150 |
| }, |
| { |
| "epoch": 0.014798297523134952, |
| "grad_norm": 0.21877750754356384, |
| "learning_rate": 0.001, |
| "loss": 3.6868, |
| "num_input_tokens_seen": 576716800, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.015134622466842565, |
| "grad_norm": 0.23657166957855225, |
| "learning_rate": 0.001, |
| "loss": 3.6853, |
| "num_input_tokens_seen": 589824000, |
| "step": 2250 |
| }, |
| { |
| "epoch": 0.015470947410550178, |
| "grad_norm": 0.24121630191802979, |
| "learning_rate": 0.001, |
| "loss": 3.6718, |
| "num_input_tokens_seen": 602931200, |
| "step": 2300 |
| }, |
| { |
| "epoch": 0.01580727235425779, |
| "grad_norm": 0.25701209902763367, |
| "learning_rate": 0.001, |
| "loss": 3.6658, |
| "num_input_tokens_seen": 616038400, |
| "step": 2350 |
| }, |
| { |
| "epoch": 0.0161435972979654, |
| "grad_norm": 0.22402645647525787, |
| "learning_rate": 0.001, |
| "loss": 3.6704, |
| "num_input_tokens_seen": 629145600, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.016479922241673016, |
| "grad_norm": 0.2358316332101822, |
| "learning_rate": 0.001, |
| "loss": 3.6464, |
| "num_input_tokens_seen": 642252800, |
| "step": 2450 |
| }, |
| { |
| "epoch": 0.016816247185380627, |
| "grad_norm": 0.23835696280002594, |
| "learning_rate": 0.001, |
| "loss": 3.6424, |
| "num_input_tokens_seen": 655360000, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.016816247185380627, |
| "eval_loss": 3.560713768005371, |
| "eval_runtime": 100.1074, |
| "eval_samples_per_second": 49.946, |
| "eval_steps_per_second": 12.487, |
| "num_input_tokens_seen": 655360000, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.01715257212908824, |
| "grad_norm": 0.20949696004390717, |
| "learning_rate": 0.001, |
| "loss": 3.6346, |
| "num_input_tokens_seen": 668467200, |
| "step": 2550 |
| }, |
| { |
| "epoch": 0.017488897072795852, |
| "grad_norm": 0.21765078604221344, |
| "learning_rate": 0.001, |
| "loss": 3.6123, |
| "num_input_tokens_seen": 681574400, |
| "step": 2600 |
| }, |
| { |
| "epoch": 0.017825222016503463, |
| "grad_norm": 0.21167752146720886, |
| "learning_rate": 0.001, |
| "loss": 3.6173, |
| "num_input_tokens_seen": 694681600, |
| "step": 2650 |
| }, |
| { |
| "epoch": 0.018161546960211078, |
| "grad_norm": 0.22060410678386688, |
| "learning_rate": 0.001, |
| "loss": 3.62, |
| "num_input_tokens_seen": 707788800, |
| "step": 2700 |
| }, |
| { |
| "epoch": 0.01849787190391869, |
| "grad_norm": 0.21778976917266846, |
| "learning_rate": 0.001, |
| "loss": 3.6009, |
| "num_input_tokens_seen": 720896000, |
| "step": 2750 |
| }, |
| { |
| "epoch": 0.018834196847626303, |
| "grad_norm": 0.21130047738552094, |
| "learning_rate": 0.001, |
| "loss": 3.5882, |
| "num_input_tokens_seen": 734003200, |
| "step": 2800 |
| }, |
| { |
| "epoch": 0.019170521791333914, |
| "grad_norm": 0.20137132704257965, |
| "learning_rate": 0.001, |
| "loss": 3.5923, |
| "num_input_tokens_seen": 747110400, |
| "step": 2850 |
| }, |
| { |
| "epoch": 0.01950684673504153, |
| "grad_norm": 0.24937641620635986, |
| "learning_rate": 0.001, |
| "loss": 3.5872, |
| "num_input_tokens_seen": 760217600, |
| "step": 2900 |
| }, |
| { |
| "epoch": 0.01984317167874914, |
| "grad_norm": 0.20992155373096466, |
| "learning_rate": 0.001, |
| "loss": 3.5786, |
| "num_input_tokens_seen": 773324800, |
| "step": 2950 |
| }, |
| { |
| "epoch": 0.020179496622456754, |
| "grad_norm": 0.24723300337791443, |
| "learning_rate": 0.001, |
| "loss": 3.5846, |
| "num_input_tokens_seen": 786432000, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.020179496622456754, |
| "eval_loss": 3.502939462661743, |
| "eval_runtime": 99.6836, |
| "eval_samples_per_second": 50.159, |
| "eval_steps_per_second": 12.54, |
| "num_input_tokens_seen": 786432000, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.020515821566164365, |
| "grad_norm": 0.22368234395980835, |
| "learning_rate": 0.001, |
| "loss": 3.5744, |
| "num_input_tokens_seen": 799539200, |
| "step": 3050 |
| }, |
| { |
| "epoch": 0.020852146509871976, |
| "grad_norm": 0.20934642851352692, |
| "learning_rate": 0.001, |
| "loss": 3.5666, |
| "num_input_tokens_seen": 812646400, |
| "step": 3100 |
| }, |
| { |
| "epoch": 0.02118847145357959, |
| "grad_norm": 0.1929185688495636, |
| "learning_rate": 0.001, |
| "loss": 3.5624, |
| "num_input_tokens_seen": 825753600, |
| "step": 3150 |
| }, |
| { |
| "epoch": 0.021524796397287202, |
| "grad_norm": 0.20416973531246185, |
| "learning_rate": 0.001, |
| "loss": 3.5491, |
| "num_input_tokens_seen": 838860800, |
| "step": 3200 |
| }, |
| { |
| "epoch": 0.021861121340994816, |
| "grad_norm": 0.20873814821243286, |
| "learning_rate": 0.001, |
| "loss": 3.5509, |
| "num_input_tokens_seen": 851968000, |
| "step": 3250 |
| }, |
| { |
| "epoch": 0.022197446284702427, |
| "grad_norm": 0.22235794365406036, |
| "learning_rate": 0.001, |
| "loss": 3.5453, |
| "num_input_tokens_seen": 865075200, |
| "step": 3300 |
| }, |
| { |
| "epoch": 0.022533771228410042, |
| "grad_norm": 0.2174178808927536, |
| "learning_rate": 0.001, |
| "loss": 3.5378, |
| "num_input_tokens_seen": 878182400, |
| "step": 3350 |
| }, |
| { |
| "epoch": 0.022870096172117653, |
| "grad_norm": 0.2016495019197464, |
| "learning_rate": 0.001, |
| "loss": 3.5352, |
| "num_input_tokens_seen": 891289600, |
| "step": 3400 |
| }, |
| { |
| "epoch": 0.023206421115825267, |
| "grad_norm": 0.1864960640668869, |
| "learning_rate": 0.001, |
| "loss": 3.524, |
| "num_input_tokens_seen": 904396800, |
| "step": 3450 |
| }, |
| { |
| "epoch": 0.02354274605953288, |
| "grad_norm": 0.19614097476005554, |
| "learning_rate": 0.001, |
| "loss": 3.528, |
| "num_input_tokens_seen": 917504000, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.02354274605953288, |
| "eval_loss": 3.4472692012786865, |
| "eval_runtime": 101.0365, |
| "eval_samples_per_second": 49.487, |
| "eval_steps_per_second": 12.372, |
| "num_input_tokens_seen": 917504000, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.02387907100324049, |
| "grad_norm": 0.18501116335391998, |
| "learning_rate": 0.001, |
| "loss": 3.53, |
| "num_input_tokens_seen": 930611200, |
| "step": 3550 |
| }, |
| { |
| "epoch": 0.024215395946948104, |
| "grad_norm": 0.1863412857055664, |
| "learning_rate": 0.001, |
| "loss": 3.5145, |
| "num_input_tokens_seen": 943718400, |
| "step": 3600 |
| }, |
| { |
| "epoch": 0.024551720890655715, |
| "grad_norm": 0.1979917287826538, |
| "learning_rate": 0.001, |
| "loss": 3.5143, |
| "num_input_tokens_seen": 956825600, |
| "step": 3650 |
| }, |
| { |
| "epoch": 0.02488804583436333, |
| "grad_norm": 0.1991748809814453, |
| "learning_rate": 0.001, |
| "loss": 3.5065, |
| "num_input_tokens_seen": 969932800, |
| "step": 3700 |
| }, |
| { |
| "epoch": 0.02522437077807094, |
| "grad_norm": 0.19475233554840088, |
| "learning_rate": 0.001, |
| "loss": 3.5011, |
| "num_input_tokens_seen": 983040000, |
| "step": 3750 |
| }, |
| { |
| "epoch": 0.025560695721778555, |
| "grad_norm": 0.195469468832016, |
| "learning_rate": 0.001, |
| "loss": 3.506, |
| "num_input_tokens_seen": 996147200, |
| "step": 3800 |
| }, |
| { |
| "epoch": 0.025897020665486166, |
| "grad_norm": 0.19666293263435364, |
| "learning_rate": 0.001, |
| "loss": 3.4936, |
| "num_input_tokens_seen": 1009254400, |
| "step": 3850 |
| }, |
| { |
| "epoch": 0.026233345609193777, |
| "grad_norm": 0.20198987424373627, |
| "learning_rate": 0.001, |
| "loss": 3.4873, |
| "num_input_tokens_seen": 1022361600, |
| "step": 3900 |
| }, |
| { |
| "epoch": 0.02656967055290139, |
| "grad_norm": 0.18537157773971558, |
| "learning_rate": 0.001, |
| "loss": 3.4939, |
| "num_input_tokens_seen": 1035468800, |
| "step": 3950 |
| }, |
| { |
| "epoch": 0.026905995496609002, |
| "grad_norm": 0.18743236362934113, |
| "learning_rate": 0.001, |
| "loss": 3.4784, |
| "num_input_tokens_seen": 1048576000, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.026905995496609002, |
| "eval_loss": 3.4036922454833984, |
| "eval_runtime": 99.4277, |
| "eval_samples_per_second": 50.288, |
| "eval_steps_per_second": 12.572, |
| "num_input_tokens_seen": 1048576000, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.027242320440316617, |
| "grad_norm": 0.18962019681930542, |
| "learning_rate": 0.001, |
| "loss": 3.4848, |
| "num_input_tokens_seen": 1061683200, |
| "step": 4050 |
| }, |
| { |
| "epoch": 0.027578645384024228, |
| "grad_norm": 0.19415706396102905, |
| "learning_rate": 0.001, |
| "loss": 3.4934, |
| "num_input_tokens_seen": 1074790400, |
| "step": 4100 |
| }, |
| { |
| "epoch": 0.027914970327731842, |
| "grad_norm": 0.17727437615394592, |
| "learning_rate": 0.001, |
| "loss": 3.4835, |
| "num_input_tokens_seen": 1087897600, |
| "step": 4150 |
| }, |
| { |
| "epoch": 0.028251295271439453, |
| "grad_norm": 0.18400466442108154, |
| "learning_rate": 0.001, |
| "loss": 3.4843, |
| "num_input_tokens_seen": 1101004800, |
| "step": 4200 |
| }, |
| { |
| "epoch": 0.028587620215147068, |
| "grad_norm": 0.19114799797534943, |
| "learning_rate": 0.001, |
| "loss": 3.4713, |
| "num_input_tokens_seen": 1114112000, |
| "step": 4250 |
| }, |
| { |
| "epoch": 0.02892394515885468, |
| "grad_norm": 0.18681153655052185, |
| "learning_rate": 0.001, |
| "loss": 3.4601, |
| "num_input_tokens_seen": 1127219200, |
| "step": 4300 |
| }, |
| { |
| "epoch": 0.02926027010256229, |
| "grad_norm": 0.20739078521728516, |
| "learning_rate": 0.001, |
| "loss": 3.4628, |
| "num_input_tokens_seen": 1140326400, |
| "step": 4350 |
| }, |
| { |
| "epoch": 0.029596595046269904, |
| "grad_norm": 0.18018484115600586, |
| "learning_rate": 0.001, |
| "loss": 3.4521, |
| "num_input_tokens_seen": 1153433600, |
| "step": 4400 |
| }, |
| { |
| "epoch": 0.029932919989977515, |
| "grad_norm": 0.18144090473651886, |
| "learning_rate": 0.001, |
| "loss": 3.4536, |
| "num_input_tokens_seen": 1166540800, |
| "step": 4450 |
| }, |
| { |
| "epoch": 0.03026924493368513, |
| "grad_norm": 0.17444822192192078, |
| "learning_rate": 0.001, |
| "loss": 3.4509, |
| "num_input_tokens_seen": 1179648000, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.03026924493368513, |
| "eval_loss": 3.3682761192321777, |
| "eval_runtime": 100.0421, |
| "eval_samples_per_second": 49.979, |
| "eval_steps_per_second": 12.495, |
| "num_input_tokens_seen": 1179648000, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.03060556987739274, |
| "grad_norm": 0.21026909351348877, |
| "learning_rate": 0.001, |
| "loss": 3.4493, |
| "num_input_tokens_seen": 1192755200, |
| "step": 4550 |
| }, |
| { |
| "epoch": 0.030941894821100355, |
| "grad_norm": 0.1758560836315155, |
| "learning_rate": 0.001, |
| "loss": 3.4416, |
| "num_input_tokens_seen": 1205862400, |
| "step": 4600 |
| }, |
| { |
| "epoch": 0.03127821976480797, |
| "grad_norm": 0.1979188174009323, |
| "learning_rate": 0.001, |
| "loss": 3.4353, |
| "num_input_tokens_seen": 1218969600, |
| "step": 4650 |
| }, |
| { |
| "epoch": 0.03161454470851558, |
| "grad_norm": 0.17621161043643951, |
| "learning_rate": 0.001, |
| "loss": 3.435, |
| "num_input_tokens_seen": 1232076800, |
| "step": 4700 |
| }, |
| { |
| "epoch": 0.03195086965222319, |
| "grad_norm": 0.18691854178905487, |
| "learning_rate": 0.001, |
| "loss": 3.4367, |
| "num_input_tokens_seen": 1245184000, |
| "step": 4750 |
| }, |
| { |
| "epoch": 0.0322871945959308, |
| "grad_norm": 0.17202869057655334, |
| "learning_rate": 0.001, |
| "loss": 3.4426, |
| "num_input_tokens_seen": 1258291200, |
| "step": 4800 |
| }, |
| { |
| "epoch": 0.032623519539638414, |
| "grad_norm": 0.17097769677639008, |
| "learning_rate": 0.001, |
| "loss": 3.439, |
| "num_input_tokens_seen": 1271398400, |
| "step": 4850 |
| }, |
| { |
| "epoch": 0.03295984448334603, |
| "grad_norm": 0.1845879703760147, |
| "learning_rate": 0.001, |
| "loss": 3.4263, |
| "num_input_tokens_seen": 1284505600, |
| "step": 4900 |
| }, |
| { |
| "epoch": 0.03329616942705364, |
| "grad_norm": 0.18462544679641724, |
| "learning_rate": 0.001, |
| "loss": 3.4273, |
| "num_input_tokens_seen": 1297612800, |
| "step": 4950 |
| }, |
| { |
| "epoch": 0.033632494370761254, |
| "grad_norm": 0.18930740654468536, |
| "learning_rate": 0.001, |
| "loss": 3.4252, |
| "num_input_tokens_seen": 1310720000, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.033632494370761254, |
| "eval_loss": 3.3413195610046387, |
| "eval_runtime": 101.3099, |
| "eval_samples_per_second": 49.354, |
| "eval_steps_per_second": 12.338, |
| "num_input_tokens_seen": 1310720000, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.033968819314468865, |
| "grad_norm": 0.1741451472043991, |
| "learning_rate": 0.001, |
| "loss": 3.4216, |
| "num_input_tokens_seen": 1323827200, |
| "step": 5050 |
| }, |
| { |
| "epoch": 0.03430514425817648, |
| "grad_norm": 0.18628782033920288, |
| "learning_rate": 0.001, |
| "loss": 3.418, |
| "num_input_tokens_seen": 1336934400, |
| "step": 5100 |
| }, |
| { |
| "epoch": 0.034641469201884094, |
| "grad_norm": 0.17286072671413422, |
| "learning_rate": 0.001, |
| "loss": 3.4126, |
| "num_input_tokens_seen": 1350041600, |
| "step": 5150 |
| }, |
| { |
| "epoch": 0.034977794145591705, |
| "grad_norm": 0.18905507028102875, |
| "learning_rate": 0.001, |
| "loss": 3.4169, |
| "num_input_tokens_seen": 1363148800, |
| "step": 5200 |
| }, |
| { |
| "epoch": 0.035314119089299316, |
| "grad_norm": 0.17675209045410156, |
| "learning_rate": 0.001, |
| "loss": 3.4229, |
| "num_input_tokens_seen": 1376256000, |
| "step": 5250 |
| }, |
| { |
| "epoch": 0.03565044403300693, |
| "grad_norm": 0.19063080847263336, |
| "learning_rate": 0.001, |
| "loss": 3.4099, |
| "num_input_tokens_seen": 1389363200, |
| "step": 5300 |
| }, |
| { |
| "epoch": 0.035986768976714545, |
| "grad_norm": 0.1875571757555008, |
| "learning_rate": 0.001, |
| "loss": 3.4185, |
| "num_input_tokens_seen": 1402470400, |
| "step": 5350 |
| }, |
| { |
| "epoch": 0.036323093920422156, |
| "grad_norm": 1.0721184015274048, |
| "learning_rate": 0.001, |
| "loss": 3.4298, |
| "num_input_tokens_seen": 1415577600, |
| "step": 5400 |
| }, |
| { |
| "epoch": 0.03665941886412977, |
| "grad_norm": 0.1907675564289093, |
| "learning_rate": 0.001, |
| "loss": 3.4268, |
| "num_input_tokens_seen": 1428684800, |
| "step": 5450 |
| }, |
| { |
| "epoch": 0.03699574380783738, |
| "grad_norm": 0.18285758793354034, |
| "learning_rate": 0.001, |
| "loss": 3.4036, |
| "num_input_tokens_seen": 1441792000, |
| "step": 5500 |
| }, |
| { |
| "epoch": 0.03699574380783738, |
| "eval_loss": 3.31872820854187, |
| "eval_runtime": 101.3489, |
| "eval_samples_per_second": 49.335, |
| "eval_steps_per_second": 12.334, |
| "num_input_tokens_seen": 1441792000, |
| "step": 5500 |
| }, |
| { |
| "epoch": 0.037332068751544996, |
| "grad_norm": 0.18330691754817963, |
| "learning_rate": 0.001, |
| "loss": 3.3926, |
| "num_input_tokens_seen": 1454899200, |
| "step": 5550 |
| }, |
| { |
| "epoch": 0.03766839369525261, |
| "grad_norm": 0.16875725984573364, |
| "learning_rate": 0.001, |
| "loss": 3.3975, |
| "num_input_tokens_seen": 1468006400, |
| "step": 5600 |
| }, |
| { |
| "epoch": 0.03800471863896022, |
| "grad_norm": 0.18510381877422333, |
| "learning_rate": 0.001, |
| "loss": 3.3964, |
| "num_input_tokens_seen": 1481113600, |
| "step": 5650 |
| }, |
| { |
| "epoch": 0.03834104358266783, |
| "grad_norm": 0.16602838039398193, |
| "learning_rate": 0.001, |
| "loss": 3.3819, |
| "num_input_tokens_seen": 1494220800, |
| "step": 5700 |
| }, |
| { |
| "epoch": 0.03867736852637544, |
| "grad_norm": 0.16771391034126282, |
| "learning_rate": 0.001, |
| "loss": 3.3968, |
| "num_input_tokens_seen": 1507328000, |
| "step": 5750 |
| }, |
| { |
| "epoch": 0.03901369347008306, |
| "grad_norm": 0.16801221668720245, |
| "learning_rate": 0.001, |
| "loss": 3.3921, |
| "num_input_tokens_seen": 1520435200, |
| "step": 5800 |
| }, |
| { |
| "epoch": 0.03935001841379067, |
| "grad_norm": 0.16846245527267456, |
| "learning_rate": 0.001, |
| "loss": 3.3841, |
| "num_input_tokens_seen": 1533542400, |
| "step": 5850 |
| }, |
| { |
| "epoch": 0.03968634335749828, |
| "grad_norm": 0.17359821498394012, |
| "learning_rate": 0.001, |
| "loss": 3.372, |
| "num_input_tokens_seen": 1546649600, |
| "step": 5900 |
| }, |
| { |
| "epoch": 0.04002266830120589, |
| "grad_norm": 0.1578226536512375, |
| "learning_rate": 0.001, |
| "loss": 3.3826, |
| "num_input_tokens_seen": 1559756800, |
| "step": 5950 |
| }, |
| { |
| "epoch": 0.04035899324491351, |
| "grad_norm": 0.17228208482265472, |
| "learning_rate": 0.001, |
| "loss": 3.3953, |
| "num_input_tokens_seen": 1572864000, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.04035899324491351, |
| "eval_loss": 3.293433666229248, |
| "eval_runtime": 100.6763, |
| "eval_samples_per_second": 49.664, |
| "eval_steps_per_second": 12.416, |
| "num_input_tokens_seen": 1572864000, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.04069531818862112, |
| "grad_norm": 0.18091177940368652, |
| "learning_rate": 0.001, |
| "loss": 3.3783, |
| "num_input_tokens_seen": 1585971200, |
| "step": 6050 |
| }, |
| { |
| "epoch": 0.04103164313232873, |
| "grad_norm": 0.17565099895000458, |
| "learning_rate": 0.001, |
| "loss": 3.3773, |
| "num_input_tokens_seen": 1599078400, |
| "step": 6100 |
| }, |
| { |
| "epoch": 0.04136796807603634, |
| "grad_norm": 0.1635759323835373, |
| "learning_rate": 0.001, |
| "loss": 3.3823, |
| "num_input_tokens_seen": 1612185600, |
| "step": 6150 |
| }, |
| { |
| "epoch": 0.04170429301974395, |
| "grad_norm": 0.19144974648952484, |
| "learning_rate": 0.001, |
| "loss": 3.3665, |
| "num_input_tokens_seen": 1625292800, |
| "step": 6200 |
| }, |
| { |
| "epoch": 0.04204061796345157, |
| "grad_norm": 0.1741226762533188, |
| "learning_rate": 0.001, |
| "loss": 3.3637, |
| "num_input_tokens_seen": 1638400000, |
| "step": 6250 |
| }, |
| { |
| "epoch": 0.04237694290715918, |
| "grad_norm": 0.17072845995426178, |
| "learning_rate": 0.001, |
| "loss": 3.3627, |
| "num_input_tokens_seen": 1651507200, |
| "step": 6300 |
| }, |
| { |
| "epoch": 0.04271326785086679, |
| "grad_norm": 0.16942182183265686, |
| "learning_rate": 0.001, |
| "loss": 3.3729, |
| "num_input_tokens_seen": 1664614400, |
| "step": 6350 |
| }, |
| { |
| "epoch": 0.043049592794574404, |
| "grad_norm": 0.16412265598773956, |
| "learning_rate": 0.001, |
| "loss": 3.3616, |
| "num_input_tokens_seen": 1677721600, |
| "step": 6400 |
| }, |
| { |
| "epoch": 0.04338591773828202, |
| "grad_norm": 0.17044900357723236, |
| "learning_rate": 0.001, |
| "loss": 3.3574, |
| "num_input_tokens_seen": 1690828800, |
| "step": 6450 |
| }, |
| { |
| "epoch": 0.04372224268198963, |
| "grad_norm": 0.18034328520298004, |
| "learning_rate": 0.001, |
| "loss": 3.3625, |
| "num_input_tokens_seen": 1703936000, |
| "step": 6500 |
| }, |
| { |
| "epoch": 0.04372224268198963, |
| "eval_loss": 3.2744550704956055, |
| "eval_runtime": 101.1801, |
| "eval_samples_per_second": 49.417, |
| "eval_steps_per_second": 12.354, |
| "num_input_tokens_seen": 1703936000, |
| "step": 6500 |
| }, |
| { |
| "epoch": 0.044058567625697244, |
| "grad_norm": 0.169066920876503, |
| "learning_rate": 0.001, |
| "loss": 3.3569, |
| "num_input_tokens_seen": 1717043200, |
| "step": 6550 |
| }, |
| { |
| "epoch": 0.044394892569404855, |
| "grad_norm": 0.1789105087518692, |
| "learning_rate": 0.001, |
| "loss": 3.3636, |
| "num_input_tokens_seen": 1730150400, |
| "step": 6600 |
| }, |
| { |
| "epoch": 0.044731217513112466, |
| "grad_norm": 0.2083519697189331, |
| "learning_rate": 0.001, |
| "loss": 3.3565, |
| "num_input_tokens_seen": 1743257600, |
| "step": 6650 |
| }, |
| { |
| "epoch": 0.045067542456820084, |
| "grad_norm": 0.16989745199680328, |
| "learning_rate": 0.001, |
| "loss": 3.3562, |
| "num_input_tokens_seen": 1756364800, |
| "step": 6700 |
| }, |
| { |
| "epoch": 0.045403867400527695, |
| "grad_norm": 0.16275504231452942, |
| "learning_rate": 0.001, |
| "loss": 3.3625, |
| "num_input_tokens_seen": 1769472000, |
| "step": 6750 |
| }, |
| { |
| "epoch": 0.045740192344235306, |
| "grad_norm": 0.17771874368190765, |
| "learning_rate": 0.001, |
| "loss": 3.3477, |
| "num_input_tokens_seen": 1782579200, |
| "step": 6800 |
| }, |
| { |
| "epoch": 0.04607651728794292, |
| "grad_norm": 0.1635473072528839, |
| "learning_rate": 0.001, |
| "loss": 3.3513, |
| "num_input_tokens_seen": 1795686400, |
| "step": 6850 |
| }, |
| { |
| "epoch": 0.046412842231650535, |
| "grad_norm": 0.17198441922664642, |
| "learning_rate": 0.001, |
| "loss": 3.3461, |
| "num_input_tokens_seen": 1808793600, |
| "step": 6900 |
| }, |
| { |
| "epoch": 0.046749167175358146, |
| "grad_norm": 0.174327552318573, |
| "learning_rate": 0.001, |
| "loss": 3.3519, |
| "num_input_tokens_seen": 1821900800, |
| "step": 6950 |
| }, |
| { |
| "epoch": 0.04708549211906576, |
| "grad_norm": 0.17880085110664368, |
| "learning_rate": 0.001, |
| "loss": 3.3387, |
| "num_input_tokens_seen": 1835008000, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.04708549211906576, |
| "eval_loss": 3.2563092708587646, |
| "eval_runtime": 100.9949, |
| "eval_samples_per_second": 49.507, |
| "eval_steps_per_second": 12.377, |
| "num_input_tokens_seen": 1835008000, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.04742181706277337, |
| "grad_norm": 0.18561717867851257, |
| "learning_rate": 0.001, |
| "loss": 3.3436, |
| "num_input_tokens_seen": 1848115200, |
| "step": 7050 |
| }, |
| { |
| "epoch": 0.04775814200648098, |
| "grad_norm": 0.17194584012031555, |
| "learning_rate": 0.001, |
| "loss": 3.3391, |
| "num_input_tokens_seen": 1861222400, |
| "step": 7100 |
| }, |
| { |
| "epoch": 0.0480944669501886, |
| "grad_norm": 0.16629651188850403, |
| "learning_rate": 0.001, |
| "loss": 3.3419, |
| "num_input_tokens_seen": 1874329600, |
| "step": 7150 |
| }, |
| { |
| "epoch": 0.04843079189389621, |
| "grad_norm": 0.1665981113910675, |
| "learning_rate": 0.001, |
| "loss": 3.3422, |
| "num_input_tokens_seen": 1887436800, |
| "step": 7200 |
| }, |
| { |
| "epoch": 0.04876711683760382, |
| "grad_norm": 0.17213182151317596, |
| "learning_rate": 0.001, |
| "loss": 3.3389, |
| "num_input_tokens_seen": 1900544000, |
| "step": 7250 |
| }, |
| { |
| "epoch": 0.04910344178131143, |
| "grad_norm": 0.18480969965457916, |
| "learning_rate": 0.001, |
| "loss": 3.3257, |
| "num_input_tokens_seen": 1913651200, |
| "step": 7300 |
| }, |
| { |
| "epoch": 0.04943976672501905, |
| "grad_norm": 0.17105132341384888, |
| "learning_rate": 0.001, |
| "loss": 3.3339, |
| "num_input_tokens_seen": 1926758400, |
| "step": 7350 |
| }, |
| { |
| "epoch": 0.04977609166872666, |
| "grad_norm": 0.17547503113746643, |
| "learning_rate": 0.001, |
| "loss": 3.3364, |
| "num_input_tokens_seen": 1939865600, |
| "step": 7400 |
| }, |
| { |
| "epoch": 0.05011241661243427, |
| "grad_norm": 0.16320562362670898, |
| "learning_rate": 0.001, |
| "loss": 3.3349, |
| "num_input_tokens_seen": 1952972800, |
| "step": 7450 |
| }, |
| { |
| "epoch": 0.05044874155614188, |
| "grad_norm": 0.16704347729682922, |
| "learning_rate": 0.001, |
| "loss": 3.3459, |
| "num_input_tokens_seen": 1966080000, |
| "step": 7500 |
| }, |
| { |
| "epoch": 0.05044874155614188, |
| "eval_loss": 3.241454601287842, |
| "eval_runtime": 100.6752, |
| "eval_samples_per_second": 49.665, |
| "eval_steps_per_second": 12.416, |
| "num_input_tokens_seen": 1966080000, |
| "step": 7500 |
| }, |
| { |
| "epoch": 0.05078506649984949, |
| "grad_norm": 0.18855977058410645, |
| "learning_rate": 0.001, |
| "loss": 3.3298, |
| "num_input_tokens_seen": 1979187200, |
| "step": 7550 |
| }, |
| { |
| "epoch": 0.05112139144355711, |
| "grad_norm": 0.16146792471408844, |
| "learning_rate": 0.001, |
| "loss": 3.324, |
| "num_input_tokens_seen": 1992294400, |
| "step": 7600 |
| }, |
| { |
| "epoch": 0.05145771638726472, |
| "grad_norm": 0.1644527018070221, |
| "learning_rate": 0.001, |
| "loss": 3.3306, |
| "num_input_tokens_seen": 2005401600, |
| "step": 7650 |
| }, |
| { |
| "epoch": 0.05179404133097233, |
| "grad_norm": 0.17106670141220093, |
| "learning_rate": 0.001, |
| "loss": 3.33, |
| "num_input_tokens_seen": 2018508800, |
| "step": 7700 |
| }, |
| { |
| "epoch": 0.05213036627467994, |
| "grad_norm": 0.1606895476579666, |
| "learning_rate": 0.001, |
| "loss": 3.3188, |
| "num_input_tokens_seen": 2031616000, |
| "step": 7750 |
| }, |
| { |
| "epoch": 0.052466691218387554, |
| "grad_norm": 0.16948160529136658, |
| "learning_rate": 0.001, |
| "loss": 3.3306, |
| "num_input_tokens_seen": 2044723200, |
| "step": 7800 |
| }, |
| { |
| "epoch": 0.05280301616209517, |
| "grad_norm": 0.20683230459690094, |
| "learning_rate": 0.001, |
| "loss": 3.3203, |
| "num_input_tokens_seen": 2057830400, |
| "step": 7850 |
| }, |
| { |
| "epoch": 0.05313934110580278, |
| "grad_norm": 0.161922886967659, |
| "learning_rate": 0.001, |
| "loss": 3.3161, |
| "num_input_tokens_seen": 2070937600, |
| "step": 7900 |
| }, |
| { |
| "epoch": 0.053475666049510394, |
| "grad_norm": 0.1616695076227188, |
| "learning_rate": 0.001, |
| "loss": 3.3245, |
| "num_input_tokens_seen": 2084044800, |
| "step": 7950 |
| }, |
| { |
| "epoch": 0.053811990993218005, |
| "grad_norm": 0.1723030060529709, |
| "learning_rate": 0.001, |
| "loss": 3.3143, |
| "num_input_tokens_seen": 2097152000, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.053811990993218005, |
| "eval_loss": 3.2274885177612305, |
| "eval_runtime": 100.3755, |
| "eval_samples_per_second": 49.813, |
| "eval_steps_per_second": 12.453, |
| "num_input_tokens_seen": 2097152000, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.05414831593692562, |
| "grad_norm": 0.16236628592014313, |
| "learning_rate": 0.001, |
| "loss": 3.3214, |
| "num_input_tokens_seen": 2110259200, |
| "step": 8050 |
| }, |
| { |
| "epoch": 0.054484640880633234, |
| "grad_norm": 0.1676984280347824, |
| "learning_rate": 0.001, |
| "loss": 3.3152, |
| "num_input_tokens_seen": 2123366400, |
| "step": 8100 |
| }, |
| { |
| "epoch": 0.054820965824340845, |
| "grad_norm": 0.16020448505878448, |
| "learning_rate": 0.001, |
| "loss": 3.3134, |
| "num_input_tokens_seen": 2136473600, |
| "step": 8150 |
| }, |
| { |
| "epoch": 0.055157290768048456, |
| "grad_norm": 0.1649223119020462, |
| "learning_rate": 0.001, |
| "loss": 3.3121, |
| "num_input_tokens_seen": 2149580800, |
| "step": 8200 |
| }, |
| { |
| "epoch": 0.05549361571175607, |
| "grad_norm": 0.1627037674188614, |
| "learning_rate": 0.001, |
| "loss": 3.3092, |
| "num_input_tokens_seen": 2162688000, |
| "step": 8250 |
| }, |
| { |
| "epoch": 0.055829940655463685, |
| "grad_norm": 0.17913097143173218, |
| "learning_rate": 0.001, |
| "loss": 3.3032, |
| "num_input_tokens_seen": 2175795200, |
| "step": 8300 |
| }, |
| { |
| "epoch": 0.056166265599171296, |
| "grad_norm": 0.18965736031532288, |
| "learning_rate": 0.001, |
| "loss": 3.3075, |
| "num_input_tokens_seen": 2188902400, |
| "step": 8350 |
| }, |
| { |
| "epoch": 0.05650259054287891, |
| "grad_norm": 0.16027510166168213, |
| "learning_rate": 0.001, |
| "loss": 3.3086, |
| "num_input_tokens_seen": 2202009600, |
| "step": 8400 |
| }, |
| { |
| "epoch": 0.05683891548658652, |
| "grad_norm": 0.16940778493881226, |
| "learning_rate": 0.001, |
| "loss": 3.2849, |
| "num_input_tokens_seen": 2215116800, |
| "step": 8450 |
| }, |
| { |
| "epoch": 0.057175240430294136, |
| "grad_norm": 0.17754122614860535, |
| "learning_rate": 0.001, |
| "loss": 3.2975, |
| "num_input_tokens_seen": 2228224000, |
| "step": 8500 |
| }, |
| { |
| "epoch": 0.057175240430294136, |
| "eval_loss": 3.2149288654327393, |
| "eval_runtime": 101.5641, |
| "eval_samples_per_second": 49.23, |
| "eval_steps_per_second": 12.307, |
| "num_input_tokens_seen": 2228224000, |
| "step": 8500 |
| }, |
| { |
| "epoch": 0.05751156537400175, |
| "grad_norm": 0.1716330349445343, |
| "learning_rate": 0.001, |
| "loss": 3.3091, |
| "num_input_tokens_seen": 2241331200, |
| "step": 8550 |
| }, |
| { |
| "epoch": 0.05784789031770936, |
| "grad_norm": 0.16466470062732697, |
| "learning_rate": 0.001, |
| "loss": 3.2934, |
| "num_input_tokens_seen": 2254438400, |
| "step": 8600 |
| }, |
| { |
| "epoch": 0.05818421526141697, |
| "grad_norm": 0.1640830636024475, |
| "learning_rate": 0.001, |
| "loss": 3.2986, |
| "num_input_tokens_seen": 2267545600, |
| "step": 8650 |
| }, |
| { |
| "epoch": 0.05852054020512458, |
| "grad_norm": 0.16982024908065796, |
| "learning_rate": 0.001, |
| "loss": 3.3016, |
| "num_input_tokens_seen": 2280652800, |
| "step": 8700 |
| }, |
| { |
| "epoch": 0.0588568651488322, |
| "grad_norm": 0.1577749252319336, |
| "learning_rate": 0.001, |
| "loss": 3.2961, |
| "num_input_tokens_seen": 2293760000, |
| "step": 8750 |
| }, |
| { |
| "epoch": 0.05919319009253981, |
| "grad_norm": 0.1626594513654709, |
| "learning_rate": 0.001, |
| "loss": 3.293, |
| "num_input_tokens_seen": 2306867200, |
| "step": 8800 |
| }, |
| { |
| "epoch": 0.05952951503624742, |
| "grad_norm": 0.18469755351543427, |
| "learning_rate": 0.001, |
| "loss": 3.2919, |
| "num_input_tokens_seen": 2319974400, |
| "step": 8850 |
| }, |
| { |
| "epoch": 0.05986583997995503, |
| "grad_norm": 0.17915847897529602, |
| "learning_rate": 0.001, |
| "loss": 3.2914, |
| "num_input_tokens_seen": 2333081600, |
| "step": 8900 |
| }, |
| { |
| "epoch": 0.06020216492366265, |
| "grad_norm": 0.17483194172382355, |
| "learning_rate": 0.001, |
| "loss": 3.2855, |
| "num_input_tokens_seen": 2346188800, |
| "step": 8950 |
| }, |
| { |
| "epoch": 0.06053848986737026, |
| "grad_norm": 0.16408763825893402, |
| "learning_rate": 0.001, |
| "loss": 3.2817, |
| "num_input_tokens_seen": 2359296000, |
| "step": 9000 |
| }, |
| { |
| "epoch": 0.06053848986737026, |
| "eval_loss": 3.201568603515625, |
| "eval_runtime": 100.2925, |
| "eval_samples_per_second": 49.854, |
| "eval_steps_per_second": 12.464, |
| "num_input_tokens_seen": 2359296000, |
| "step": 9000 |
| }, |
| { |
| "epoch": 0.06087481481107787, |
| "grad_norm": 0.15520979464054108, |
| "learning_rate": 0.001, |
| "loss": 3.2917, |
| "num_input_tokens_seen": 2372403200, |
| "step": 9050 |
| }, |
| { |
| "epoch": 0.06121113975478548, |
| "grad_norm": 0.19632326066493988, |
| "learning_rate": 0.001, |
| "loss": 3.3164, |
| "num_input_tokens_seen": 2385510400, |
| "step": 9100 |
| }, |
| { |
| "epoch": 0.06154746469849309, |
| "grad_norm": 0.17335627973079681, |
| "learning_rate": 0.001, |
| "loss": 3.3025, |
| "num_input_tokens_seen": 2398617600, |
| "step": 9150 |
| }, |
| { |
| "epoch": 0.06188378964220071, |
| "grad_norm": 0.18116877973079681, |
| "learning_rate": 0.001, |
| "loss": 3.2857, |
| "num_input_tokens_seen": 2411724800, |
| "step": 9200 |
| }, |
| { |
| "epoch": 0.06222011458590832, |
| "grad_norm": 0.17199201881885529, |
| "learning_rate": 0.001, |
| "loss": 3.2901, |
| "num_input_tokens_seen": 2424832000, |
| "step": 9250 |
| }, |
| { |
| "epoch": 0.06255643952961594, |
| "grad_norm": 0.163723424077034, |
| "learning_rate": 0.001, |
| "loss": 3.2865, |
| "num_input_tokens_seen": 2437939200, |
| "step": 9300 |
| }, |
| { |
| "epoch": 0.06289276447332355, |
| "grad_norm": 0.17228147387504578, |
| "learning_rate": 0.001, |
| "loss": 3.2884, |
| "num_input_tokens_seen": 2451046400, |
| "step": 9350 |
| }, |
| { |
| "epoch": 0.06322908941703116, |
| "grad_norm": 0.1656276136636734, |
| "learning_rate": 0.001, |
| "loss": 3.2871, |
| "num_input_tokens_seen": 2464153600, |
| "step": 9400 |
| }, |
| { |
| "epoch": 0.06356541436073877, |
| "grad_norm": 0.16867949068546295, |
| "learning_rate": 0.001, |
| "loss": 3.2817, |
| "num_input_tokens_seen": 2477260800, |
| "step": 9450 |
| }, |
| { |
| "epoch": 0.06390173930444638, |
| "grad_norm": 0.17453493177890778, |
| "learning_rate": 0.001, |
| "loss": 3.2876, |
| "num_input_tokens_seen": 2490368000, |
| "step": 9500 |
| }, |
| { |
| "epoch": 0.06390173930444638, |
| "eval_loss": 3.190683364868164, |
| "eval_runtime": 100.5146, |
| "eval_samples_per_second": 49.744, |
| "eval_steps_per_second": 12.436, |
| "num_input_tokens_seen": 2490368000, |
| "step": 9500 |
| }, |
| { |
| "epoch": 0.064238064248154, |
| "grad_norm": 0.6719958186149597, |
| "learning_rate": 0.001, |
| "loss": 3.299, |
| "num_input_tokens_seen": 2503475200, |
| "step": 9550 |
| }, |
| { |
| "epoch": 0.0645743891918616, |
| "grad_norm": 0.19327396154403687, |
| "learning_rate": 0.001, |
| "loss": 3.2907, |
| "num_input_tokens_seen": 2516582400, |
| "step": 9600 |
| }, |
| { |
| "epoch": 0.06491071413556922, |
| "grad_norm": 0.17817369103431702, |
| "learning_rate": 0.001, |
| "loss": 3.2801, |
| "num_input_tokens_seen": 2529689600, |
| "step": 9650 |
| }, |
| { |
| "epoch": 0.06524703907927683, |
| "grad_norm": 0.16956672072410583, |
| "learning_rate": 0.001, |
| "loss": 3.2761, |
| "num_input_tokens_seen": 2542796800, |
| "step": 9700 |
| }, |
| { |
| "epoch": 0.06558336402298445, |
| "grad_norm": 0.1854093372821808, |
| "learning_rate": 0.001, |
| "loss": 3.27, |
| "num_input_tokens_seen": 2555904000, |
| "step": 9750 |
| }, |
| { |
| "epoch": 0.06591968896669206, |
| "grad_norm": 0.15702186524868011, |
| "learning_rate": 0.001, |
| "loss": 3.2792, |
| "num_input_tokens_seen": 2569011200, |
| "step": 9800 |
| }, |
| { |
| "epoch": 0.06625601391039967, |
| "grad_norm": 0.16380488872528076, |
| "learning_rate": 0.001, |
| "loss": 3.2672, |
| "num_input_tokens_seen": 2582118400, |
| "step": 9850 |
| }, |
| { |
| "epoch": 0.06659233885410729, |
| "grad_norm": 0.15908506512641907, |
| "learning_rate": 0.001, |
| "loss": 3.2665, |
| "num_input_tokens_seen": 2595225600, |
| "step": 9900 |
| }, |
| { |
| "epoch": 0.0669286637978149, |
| "grad_norm": 0.1654980629682541, |
| "learning_rate": 0.001, |
| "loss": 3.2726, |
| "num_input_tokens_seen": 2608332800, |
| "step": 9950 |
| }, |
| { |
| "epoch": 0.06726498874152251, |
| "grad_norm": 0.1780249923467636, |
| "learning_rate": 0.001, |
| "loss": 3.2632, |
| "num_input_tokens_seen": 2621440000, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.06726498874152251, |
| "eval_loss": 3.1775221824645996, |
| "eval_runtime": 100.6676, |
| "eval_samples_per_second": 49.668, |
| "eval_steps_per_second": 12.417, |
| "num_input_tokens_seen": 2621440000, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.06760131368523012, |
| "grad_norm": 0.1572471708059311, |
| "learning_rate": 0.001, |
| "loss": 3.2652, |
| "num_input_tokens_seen": 2634547200, |
| "step": 10050 |
| }, |
| { |
| "epoch": 0.06793763862893773, |
| "grad_norm": 0.1655690222978592, |
| "learning_rate": 0.001, |
| "loss": 3.2753, |
| "num_input_tokens_seen": 2647654400, |
| "step": 10100 |
| }, |
| { |
| "epoch": 0.06827396357264534, |
| "grad_norm": 0.18156391382217407, |
| "learning_rate": 0.001, |
| "loss": 3.2717, |
| "num_input_tokens_seen": 2660761600, |
| "step": 10150 |
| }, |
| { |
| "epoch": 0.06861028851635297, |
| "grad_norm": 0.1684606373310089, |
| "learning_rate": 0.001, |
| "loss": 3.269, |
| "num_input_tokens_seen": 2673868800, |
| "step": 10200 |
| }, |
| { |
| "epoch": 0.06894661346006058, |
| "grad_norm": 0.18199962377548218, |
| "learning_rate": 0.001, |
| "loss": 3.2591, |
| "num_input_tokens_seen": 2686976000, |
| "step": 10250 |
| }, |
| { |
| "epoch": 0.06928293840376819, |
| "grad_norm": 0.1662759929895401, |
| "learning_rate": 0.001, |
| "loss": 3.2674, |
| "num_input_tokens_seen": 2700083200, |
| "step": 10300 |
| }, |
| { |
| "epoch": 0.0696192633474758, |
| "grad_norm": 0.16799511015415192, |
| "learning_rate": 0.001, |
| "loss": 3.2788, |
| "num_input_tokens_seen": 2713190400, |
| "step": 10350 |
| }, |
| { |
| "epoch": 0.06995558829118341, |
| "grad_norm": 0.17926375567913055, |
| "learning_rate": 0.001, |
| "loss": 3.2742, |
| "num_input_tokens_seen": 2726297600, |
| "step": 10400 |
| }, |
| { |
| "epoch": 0.07029191323489102, |
| "grad_norm": 0.18057045340538025, |
| "learning_rate": 0.001, |
| "loss": 3.2662, |
| "num_input_tokens_seen": 2739404800, |
| "step": 10450 |
| }, |
| { |
| "epoch": 0.07062823817859863, |
| "grad_norm": 0.17588871717453003, |
| "learning_rate": 0.001, |
| "loss": 3.2577, |
| "num_input_tokens_seen": 2752512000, |
| "step": 10500 |
| }, |
| { |
| "epoch": 0.07062823817859863, |
| "eval_loss": 3.168182849884033, |
| "eval_runtime": 100.5761, |
| "eval_samples_per_second": 49.714, |
| "eval_steps_per_second": 12.428, |
| "num_input_tokens_seen": 2752512000, |
| "step": 10500 |
| }, |
| { |
| "epoch": 0.07096456312230624, |
| "grad_norm": 0.1731673628091812, |
| "learning_rate": 0.001, |
| "loss": 3.2565, |
| "num_input_tokens_seen": 2765619200, |
| "step": 10550 |
| }, |
| { |
| "epoch": 0.07130088806601385, |
| "grad_norm": 0.16532014310359955, |
| "learning_rate": 0.001, |
| "loss": 3.2511, |
| "num_input_tokens_seen": 2778726400, |
| "step": 10600 |
| }, |
| { |
| "epoch": 0.07163721300972148, |
| "grad_norm": 0.17818772792816162, |
| "learning_rate": 0.001, |
| "loss": 3.2541, |
| "num_input_tokens_seen": 2791833600, |
| "step": 10650 |
| }, |
| { |
| "epoch": 0.07197353795342909, |
| "grad_norm": 0.16863703727722168, |
| "learning_rate": 0.001, |
| "loss": 3.2485, |
| "num_input_tokens_seen": 2804940800, |
| "step": 10700 |
| }, |
| { |
| "epoch": 0.0723098628971367, |
| "grad_norm": 0.17316773533821106, |
| "learning_rate": 0.001, |
| "loss": 3.2583, |
| "num_input_tokens_seen": 2818048000, |
| "step": 10750 |
| }, |
| { |
| "epoch": 0.07264618784084431, |
| "grad_norm": 0.16366828978061676, |
| "learning_rate": 0.001, |
| "loss": 3.2502, |
| "num_input_tokens_seen": 2831155200, |
| "step": 10800 |
| }, |
| { |
| "epoch": 0.07298251278455192, |
| "grad_norm": 0.16141986846923828, |
| "learning_rate": 0.001, |
| "loss": 3.2537, |
| "num_input_tokens_seen": 2844262400, |
| "step": 10850 |
| }, |
| { |
| "epoch": 0.07331883772825953, |
| "grad_norm": 0.16185277700424194, |
| "learning_rate": 0.001, |
| "loss": 3.2453, |
| "num_input_tokens_seen": 2857369600, |
| "step": 10900 |
| }, |
| { |
| "epoch": 0.07365516267196714, |
| "grad_norm": 0.15637634694576263, |
| "learning_rate": 0.001, |
| "loss": 3.2562, |
| "num_input_tokens_seen": 2870476800, |
| "step": 10950 |
| }, |
| { |
| "epoch": 0.07399148761567476, |
| "grad_norm": 0.16142712533473969, |
| "learning_rate": 0.001, |
| "loss": 3.2427, |
| "num_input_tokens_seen": 2883584000, |
| "step": 11000 |
| }, |
| { |
| "epoch": 0.07399148761567476, |
| "eval_loss": 3.1591553688049316, |
| "eval_runtime": 100.7501, |
| "eval_samples_per_second": 49.628, |
| "eval_steps_per_second": 12.407, |
| "num_input_tokens_seen": 2883584000, |
| "step": 11000 |
| }, |
| { |
| "epoch": 0.07432781255938237, |
| "grad_norm": 0.16285482048988342, |
| "learning_rate": 0.001, |
| "loss": 3.2556, |
| "num_input_tokens_seen": 2896691200, |
| "step": 11050 |
| }, |
| { |
| "epoch": 0.07466413750308999, |
| "grad_norm": 0.1800818145275116, |
| "learning_rate": 0.001, |
| "loss": 3.2498, |
| "num_input_tokens_seen": 2909798400, |
| "step": 11100 |
| }, |
| { |
| "epoch": 0.0750004624467976, |
| "grad_norm": 0.1587436944246292, |
| "learning_rate": 0.001, |
| "loss": 3.2454, |
| "num_input_tokens_seen": 2922905600, |
| "step": 11150 |
| }, |
| { |
| "epoch": 0.07533678739050521, |
| "grad_norm": 0.17776361107826233, |
| "learning_rate": 0.001, |
| "loss": 3.2671, |
| "num_input_tokens_seen": 2936012800, |
| "step": 11200 |
| }, |
| { |
| "epoch": 0.07567311233421282, |
| "grad_norm": 0.16090282797813416, |
| "learning_rate": 0.001, |
| "loss": 3.2582, |
| "num_input_tokens_seen": 2949120000, |
| "step": 11250 |
| }, |
| { |
| "epoch": 0.07600943727792044, |
| "grad_norm": 0.1685740053653717, |
| "learning_rate": 0.001, |
| "loss": 3.2485, |
| "num_input_tokens_seen": 2962227200, |
| "step": 11300 |
| }, |
| { |
| "epoch": 0.07634576222162805, |
| "grad_norm": 0.16622695326805115, |
| "learning_rate": 0.001, |
| "loss": 3.2517, |
| "num_input_tokens_seen": 2975334400, |
| "step": 11350 |
| }, |
| { |
| "epoch": 0.07668208716533566, |
| "grad_norm": 0.2576703131198883, |
| "learning_rate": 0.001, |
| "loss": 3.2536, |
| "num_input_tokens_seen": 2988441600, |
| "step": 11400 |
| }, |
| { |
| "epoch": 0.07701841210904327, |
| "grad_norm": 0.16928231716156006, |
| "learning_rate": 0.001, |
| "loss": 3.234, |
| "num_input_tokens_seen": 3001548800, |
| "step": 11450 |
| }, |
| { |
| "epoch": 0.07735473705275088, |
| "grad_norm": 0.16732951998710632, |
| "learning_rate": 0.001, |
| "loss": 3.2421, |
| "num_input_tokens_seen": 3014656000, |
| "step": 11500 |
| }, |
| { |
| "epoch": 0.07735473705275088, |
| "eval_loss": 3.1493282318115234, |
| "eval_runtime": 100.6579, |
| "eval_samples_per_second": 49.673, |
| "eval_steps_per_second": 12.418, |
| "num_input_tokens_seen": 3014656000, |
| "step": 11500 |
| }, |
| { |
| "epoch": 0.0776910619964585, |
| "grad_norm": 0.1627015471458435, |
| "learning_rate": 0.001, |
| "loss": 3.2449, |
| "num_input_tokens_seen": 3027763200, |
| "step": 11550 |
| }, |
| { |
| "epoch": 0.07802738694016612, |
| "grad_norm": 0.1591007262468338, |
| "learning_rate": 0.001, |
| "loss": 3.2405, |
| "num_input_tokens_seen": 3040870400, |
| "step": 11600 |
| }, |
| { |
| "epoch": 0.07836371188387373, |
| "grad_norm": 0.16861042380332947, |
| "learning_rate": 0.001, |
| "loss": 3.2371, |
| "num_input_tokens_seen": 3053977600, |
| "step": 11650 |
| }, |
| { |
| "epoch": 0.07870003682758134, |
| "grad_norm": 0.17942191660404205, |
| "learning_rate": 0.001, |
| "loss": 3.2401, |
| "num_input_tokens_seen": 3067084800, |
| "step": 11700 |
| }, |
| { |
| "epoch": 0.07903636177128895, |
| "grad_norm": 0.19918367266654968, |
| "learning_rate": 0.001, |
| "loss": 3.2522, |
| "num_input_tokens_seen": 3080192000, |
| "step": 11750 |
| }, |
| { |
| "epoch": 0.07937268671499656, |
| "grad_norm": 0.20974946022033691, |
| "learning_rate": 0.001, |
| "loss": 3.2476, |
| "num_input_tokens_seen": 3093299200, |
| "step": 11800 |
| }, |
| { |
| "epoch": 0.07970901165870417, |
| "grad_norm": 0.17063277959823608, |
| "learning_rate": 0.001, |
| "loss": 3.2461, |
| "num_input_tokens_seen": 3106406400, |
| "step": 11850 |
| }, |
| { |
| "epoch": 0.08004533660241178, |
| "grad_norm": 0.17285390198230743, |
| "learning_rate": 0.001, |
| "loss": 3.2389, |
| "num_input_tokens_seen": 3119513600, |
| "step": 11900 |
| }, |
| { |
| "epoch": 0.08038166154611939, |
| "grad_norm": 0.16399264335632324, |
| "learning_rate": 0.001, |
| "loss": 3.2354, |
| "num_input_tokens_seen": 3132620800, |
| "step": 11950 |
| }, |
| { |
| "epoch": 0.08071798648982702, |
| "grad_norm": 0.17166489362716675, |
| "learning_rate": 0.001, |
| "loss": 3.2393, |
| "num_input_tokens_seen": 3145728000, |
| "step": 12000 |
| }, |
| { |
| "epoch": 0.08071798648982702, |
| "eval_loss": 3.1431546211242676, |
| "eval_runtime": 100.4686, |
| "eval_samples_per_second": 49.767, |
| "eval_steps_per_second": 12.442, |
| "num_input_tokens_seen": 3145728000, |
| "step": 12000 |
| }, |
| { |
| "epoch": 0.08105431143353463, |
| "grad_norm": 0.16976477205753326, |
| "learning_rate": 0.001, |
| "loss": 3.2367, |
| "num_input_tokens_seen": 3158835200, |
| "step": 12050 |
| }, |
| { |
| "epoch": 0.08139063637724224, |
| "grad_norm": 0.17778240144252777, |
| "learning_rate": 0.001, |
| "loss": 3.2346, |
| "num_input_tokens_seen": 3171942400, |
| "step": 12100 |
| }, |
| { |
| "epoch": 0.08172696132094985, |
| "grad_norm": 0.17096461355686188, |
| "learning_rate": 0.001, |
| "loss": 3.235, |
| "num_input_tokens_seen": 3185049600, |
| "step": 12150 |
| }, |
| { |
| "epoch": 0.08206328626465746, |
| "grad_norm": 0.16154351830482483, |
| "learning_rate": 0.001, |
| "loss": 3.2263, |
| "num_input_tokens_seen": 3198156800, |
| "step": 12200 |
| }, |
| { |
| "epoch": 0.08239961120836507, |
| "grad_norm": 0.23045915365219116, |
| "learning_rate": 0.001, |
| "loss": 3.2295, |
| "num_input_tokens_seen": 3211264000, |
| "step": 12250 |
| }, |
| { |
| "epoch": 0.08273593615207268, |
| "grad_norm": 0.17755016684532166, |
| "learning_rate": 0.001, |
| "loss": 3.2465, |
| "num_input_tokens_seen": 3224371200, |
| "step": 12300 |
| }, |
| { |
| "epoch": 0.0830722610957803, |
| "grad_norm": 0.17216768860816956, |
| "learning_rate": 0.001, |
| "loss": 3.2353, |
| "num_input_tokens_seen": 3237478400, |
| "step": 12350 |
| }, |
| { |
| "epoch": 0.0834085860394879, |
| "grad_norm": 0.166086345911026, |
| "learning_rate": 0.001, |
| "loss": 3.231, |
| "num_input_tokens_seen": 3250585600, |
| "step": 12400 |
| }, |
| { |
| "epoch": 0.08374491098319553, |
| "grad_norm": 0.1681985855102539, |
| "learning_rate": 0.001, |
| "loss": 3.2343, |
| "num_input_tokens_seen": 3263692800, |
| "step": 12450 |
| }, |
| { |
| "epoch": 0.08408123592690314, |
| "grad_norm": 0.1611029952764511, |
| "learning_rate": 0.001, |
| "loss": 3.2386, |
| "num_input_tokens_seen": 3276800000, |
| "step": 12500 |
| }, |
| { |
| "epoch": 0.08408123592690314, |
| "eval_loss": 3.135470390319824, |
| "eval_runtime": 99.9587, |
| "eval_samples_per_second": 50.021, |
| "eval_steps_per_second": 12.505, |
| "num_input_tokens_seen": 3276800000, |
| "step": 12500 |
| }, |
| { |
| "epoch": 0.08441756087061075, |
| "grad_norm": 0.16823448240756989, |
| "learning_rate": 0.001, |
| "loss": 3.2315, |
| "num_input_tokens_seen": 3289907200, |
| "step": 12550 |
| }, |
| { |
| "epoch": 0.08475388581431836, |
| "grad_norm": 0.17325358092784882, |
| "learning_rate": 0.001, |
| "loss": 3.2258, |
| "num_input_tokens_seen": 3303014400, |
| "step": 12600 |
| }, |
| { |
| "epoch": 0.08509021075802597, |
| "grad_norm": 0.16828718781471252, |
| "learning_rate": 0.001, |
| "loss": 3.2251, |
| "num_input_tokens_seen": 3316121600, |
| "step": 12650 |
| }, |
| { |
| "epoch": 0.08542653570173359, |
| "grad_norm": 0.3836762309074402, |
| "learning_rate": 0.001, |
| "loss": 3.2279, |
| "num_input_tokens_seen": 3329228800, |
| "step": 12700 |
| }, |
| { |
| "epoch": 0.0857628606454412, |
| "grad_norm": 0.17255236208438873, |
| "learning_rate": 0.001, |
| "loss": 3.221, |
| "num_input_tokens_seen": 3342336000, |
| "step": 12750 |
| }, |
| { |
| "epoch": 0.08609918558914881, |
| "grad_norm": 0.2381184846162796, |
| "learning_rate": 0.001, |
| "loss": 3.2228, |
| "num_input_tokens_seen": 3355443200, |
| "step": 12800 |
| }, |
| { |
| "epoch": 0.08643551053285642, |
| "grad_norm": 0.3065573573112488, |
| "learning_rate": 0.001, |
| "loss": 3.2251, |
| "num_input_tokens_seen": 3368550400, |
| "step": 12850 |
| }, |
| { |
| "epoch": 0.08677183547656404, |
| "grad_norm": 0.1801990419626236, |
| "learning_rate": 0.001, |
| "loss": 3.2488, |
| "num_input_tokens_seen": 3381657600, |
| "step": 12900 |
| }, |
| { |
| "epoch": 0.08710816042027165, |
| "grad_norm": 0.17388571798801422, |
| "learning_rate": 0.001, |
| "loss": 3.2309, |
| "num_input_tokens_seen": 3394764800, |
| "step": 12950 |
| }, |
| { |
| "epoch": 0.08744448536397927, |
| "grad_norm": 0.16619688272476196, |
| "learning_rate": 0.001, |
| "loss": 3.2158, |
| "num_input_tokens_seen": 3407872000, |
| "step": 13000 |
| }, |
| { |
| "epoch": 0.08744448536397927, |
| "eval_loss": 3.128695011138916, |
| "eval_runtime": 101.514, |
| "eval_samples_per_second": 49.254, |
| "eval_steps_per_second": 12.314, |
| "num_input_tokens_seen": 3407872000, |
| "step": 13000 |
| }, |
| { |
| "epoch": 0.08778081030768688, |
| "grad_norm": 0.16921883821487427, |
| "learning_rate": 0.001, |
| "loss": 3.2157, |
| "num_input_tokens_seen": 3420979200, |
| "step": 13050 |
| }, |
| { |
| "epoch": 0.08811713525139449, |
| "grad_norm": 0.16760320961475372, |
| "learning_rate": 0.001, |
| "loss": 3.2057, |
| "num_input_tokens_seen": 3434086400, |
| "step": 13100 |
| }, |
| { |
| "epoch": 0.0884534601951021, |
| "grad_norm": 0.16922198235988617, |
| "learning_rate": 0.001, |
| "loss": 3.2281, |
| "num_input_tokens_seen": 3447193600, |
| "step": 13150 |
| }, |
| { |
| "epoch": 0.08878978513880971, |
| "grad_norm": 0.1857660859823227, |
| "learning_rate": 0.001, |
| "loss": 3.2107, |
| "num_input_tokens_seen": 3460300800, |
| "step": 13200 |
| }, |
| { |
| "epoch": 0.08912611008251732, |
| "grad_norm": 0.1746143400669098, |
| "learning_rate": 0.001, |
| "loss": 3.217, |
| "num_input_tokens_seen": 3473408000, |
| "step": 13250 |
| }, |
| { |
| "epoch": 0.08946243502622493, |
| "grad_norm": 0.16841556131839752, |
| "learning_rate": 0.001, |
| "loss": 3.2241, |
| "num_input_tokens_seen": 3486515200, |
| "step": 13300 |
| }, |
| { |
| "epoch": 0.08979875996993256, |
| "grad_norm": 0.1724822223186493, |
| "learning_rate": 0.001, |
| "loss": 3.2158, |
| "num_input_tokens_seen": 3499622400, |
| "step": 13350 |
| }, |
| { |
| "epoch": 0.09013508491364017, |
| "grad_norm": 0.17045529186725616, |
| "learning_rate": 0.001, |
| "loss": 3.2135, |
| "num_input_tokens_seen": 3512729600, |
| "step": 13400 |
| }, |
| { |
| "epoch": 0.09047140985734778, |
| "grad_norm": 0.18234893679618835, |
| "learning_rate": 0.001, |
| "loss": 3.2109, |
| "num_input_tokens_seen": 3525836800, |
| "step": 13450 |
| }, |
| { |
| "epoch": 0.09080773480105539, |
| "grad_norm": 0.16932611167430878, |
| "learning_rate": 0.001, |
| "loss": 3.2117, |
| "num_input_tokens_seen": 3538944000, |
| "step": 13500 |
| }, |
| { |
| "epoch": 0.09080773480105539, |
| "eval_loss": 3.1214168071746826, |
| "eval_runtime": 100.8175, |
| "eval_samples_per_second": 49.595, |
| "eval_steps_per_second": 12.399, |
| "num_input_tokens_seen": 3538944000, |
| "step": 13500 |
| }, |
| { |
| "epoch": 0.091144059744763, |
| "grad_norm": 0.17800532281398773, |
| "learning_rate": 0.001, |
| "loss": 3.2005, |
| "num_input_tokens_seen": 3552051200, |
| "step": 13550 |
| }, |
| { |
| "epoch": 0.09148038468847061, |
| "grad_norm": 0.15552346408367157, |
| "learning_rate": 0.001, |
| "loss": 3.2165, |
| "num_input_tokens_seen": 3565158400, |
| "step": 13600 |
| }, |
| { |
| "epoch": 0.09181670963217822, |
| "grad_norm": 0.1732388734817505, |
| "learning_rate": 0.001, |
| "loss": 3.2159, |
| "num_input_tokens_seen": 3578265600, |
| "step": 13650 |
| }, |
| { |
| "epoch": 0.09215303457588583, |
| "grad_norm": 0.17064529657363892, |
| "learning_rate": 0.001, |
| "loss": 3.2213, |
| "num_input_tokens_seen": 3591372800, |
| "step": 13700 |
| }, |
| { |
| "epoch": 0.09248935951959344, |
| "grad_norm": 0.18150164186954498, |
| "learning_rate": 0.001, |
| "loss": 3.2207, |
| "num_input_tokens_seen": 3604480000, |
| "step": 13750 |
| }, |
| { |
| "epoch": 0.09282568446330107, |
| "grad_norm": 0.16305723786354065, |
| "learning_rate": 0.001, |
| "loss": 3.2112, |
| "num_input_tokens_seen": 3617587200, |
| "step": 13800 |
| }, |
| { |
| "epoch": 0.09316200940700868, |
| "grad_norm": 0.17140090465545654, |
| "learning_rate": 0.001, |
| "loss": 3.2064, |
| "num_input_tokens_seen": 3630694400, |
| "step": 13850 |
| }, |
| { |
| "epoch": 0.09349833435071629, |
| "grad_norm": 0.3770304024219513, |
| "learning_rate": 0.001, |
| "loss": 3.2129, |
| "num_input_tokens_seen": 3643801600, |
| "step": 13900 |
| }, |
| { |
| "epoch": 0.0938346592944239, |
| "grad_norm": 0.15605700016021729, |
| "learning_rate": 0.001, |
| "loss": 3.2194, |
| "num_input_tokens_seen": 3656908800, |
| "step": 13950 |
| }, |
| { |
| "epoch": 0.09417098423813151, |
| "grad_norm": 0.18392467498779297, |
| "learning_rate": 0.001, |
| "loss": 3.2057, |
| "num_input_tokens_seen": 3670016000, |
| "step": 14000 |
| }, |
| { |
| "epoch": 0.09417098423813151, |
| "eval_loss": 3.1151933670043945, |
| "eval_runtime": 100.6439, |
| "eval_samples_per_second": 49.68, |
| "eval_steps_per_second": 12.42, |
| "num_input_tokens_seen": 3670016000, |
| "step": 14000 |
| }, |
| { |
| "epoch": 0.09450730918183912, |
| "grad_norm": 0.17042067646980286, |
| "learning_rate": 0.001, |
| "loss": 3.2079, |
| "num_input_tokens_seen": 3683123200, |
| "step": 14050 |
| }, |
| { |
| "epoch": 0.09484363412554674, |
| "grad_norm": 0.1771795153617859, |
| "learning_rate": 0.001, |
| "loss": 3.2074, |
| "num_input_tokens_seen": 3696230400, |
| "step": 14100 |
| }, |
| { |
| "epoch": 0.09517995906925435, |
| "grad_norm": 0.18254883587360382, |
| "learning_rate": 0.001, |
| "loss": 3.1999, |
| "num_input_tokens_seen": 3709337600, |
| "step": 14150 |
| }, |
| { |
| "epoch": 0.09551628401296196, |
| "grad_norm": 0.17174501717090607, |
| "learning_rate": 0.001, |
| "loss": 3.2066, |
| "num_input_tokens_seen": 3722444800, |
| "step": 14200 |
| }, |
| { |
| "epoch": 0.09585260895666958, |
| "grad_norm": 0.15733762085437775, |
| "learning_rate": 0.001, |
| "loss": 3.1931, |
| "num_input_tokens_seen": 3735552000, |
| "step": 14250 |
| }, |
| { |
| "epoch": 0.0961889339003772, |
| "grad_norm": 0.17221161723136902, |
| "learning_rate": 0.001, |
| "loss": 3.2055, |
| "num_input_tokens_seen": 3748659200, |
| "step": 14300 |
| }, |
| { |
| "epoch": 0.0965252588440848, |
| "grad_norm": 0.2117476761341095, |
| "learning_rate": 0.001, |
| "loss": 3.2046, |
| "num_input_tokens_seen": 3761766400, |
| "step": 14350 |
| }, |
| { |
| "epoch": 0.09686158378779242, |
| "grad_norm": 0.19019798934459686, |
| "learning_rate": 0.001, |
| "loss": 3.2086, |
| "num_input_tokens_seen": 3774873600, |
| "step": 14400 |
| }, |
| { |
| "epoch": 0.09719790873150003, |
| "grad_norm": 0.1791025549173355, |
| "learning_rate": 0.001, |
| "loss": 3.2002, |
| "num_input_tokens_seen": 3787980800, |
| "step": 14450 |
| }, |
| { |
| "epoch": 0.09753423367520764, |
| "grad_norm": 0.1800592541694641, |
| "learning_rate": 0.001, |
| "loss": 3.2121, |
| "num_input_tokens_seen": 3801088000, |
| "step": 14500 |
| }, |
| { |
| "epoch": 0.09753423367520764, |
| "eval_loss": 3.1071391105651855, |
| "eval_runtime": 101.3171, |
| "eval_samples_per_second": 49.35, |
| "eval_steps_per_second": 12.337, |
| "num_input_tokens_seen": 3801088000, |
| "step": 14500 |
| }, |
| { |
| "epoch": 0.09787055861891525, |
| "grad_norm": 0.15765570104122162, |
| "learning_rate": 0.001, |
| "loss": 3.2046, |
| "num_input_tokens_seen": 3814195200, |
| "step": 14550 |
| }, |
| { |
| "epoch": 0.09820688356262286, |
| "grad_norm": 0.16369874775409698, |
| "learning_rate": 0.001, |
| "loss": 3.2059, |
| "num_input_tokens_seen": 3827302400, |
| "step": 14600 |
| }, |
| { |
| "epoch": 0.09854320850633047, |
| "grad_norm": 0.16802681982517242, |
| "learning_rate": 0.001, |
| "loss": 3.1967, |
| "num_input_tokens_seen": 3840409600, |
| "step": 14650 |
| }, |
| { |
| "epoch": 0.0988795334500381, |
| "grad_norm": 0.1722741425037384, |
| "learning_rate": 0.001, |
| "loss": 3.2189, |
| "num_input_tokens_seen": 3853516800, |
| "step": 14700 |
| }, |
| { |
| "epoch": 0.0992158583937457, |
| "grad_norm": 0.17442888021469116, |
| "learning_rate": 0.001, |
| "loss": 3.2079, |
| "num_input_tokens_seen": 3866624000, |
| "step": 14750 |
| }, |
| { |
| "epoch": 0.09955218333745332, |
| "grad_norm": 0.18931840360164642, |
| "learning_rate": 0.001, |
| "loss": 3.1978, |
| "num_input_tokens_seen": 3879731200, |
| "step": 14800 |
| }, |
| { |
| "epoch": 0.09988850828116093, |
| "grad_norm": 0.17893177270889282, |
| "learning_rate": 0.001, |
| "loss": 3.202, |
| "num_input_tokens_seen": 3892838400, |
| "step": 14850 |
| }, |
| { |
| "epoch": 0.10022483322486854, |
| "grad_norm": 0.18453757464885712, |
| "learning_rate": 0.001, |
| "loss": 3.2004, |
| "num_input_tokens_seen": 3905945600, |
| "step": 14900 |
| }, |
| { |
| "epoch": 0.10056115816857615, |
| "grad_norm": 0.17419569194316864, |
| "learning_rate": 0.001, |
| "loss": 3.1936, |
| "num_input_tokens_seen": 3919052800, |
| "step": 14950 |
| }, |
| { |
| "epoch": 0.10089748311228376, |
| "grad_norm": 0.1765667200088501, |
| "learning_rate": 0.001, |
| "loss": 3.2015, |
| "num_input_tokens_seen": 3932160000, |
| "step": 15000 |
| }, |
| { |
| "epoch": 0.10089748311228376, |
| "eval_loss": 3.1014840602874756, |
| "eval_runtime": 100.8594, |
| "eval_samples_per_second": 49.574, |
| "eval_steps_per_second": 12.393, |
| "num_input_tokens_seen": 3932160000, |
| "step": 15000 |
| }, |
| { |
| "epoch": 0.10123380805599137, |
| "grad_norm": 0.18003995716571808, |
| "learning_rate": 0.001, |
| "loss": 3.2003, |
| "num_input_tokens_seen": 3945267200, |
| "step": 15050 |
| }, |
| { |
| "epoch": 0.10157013299969898, |
| "grad_norm": 0.16458339989185333, |
| "learning_rate": 0.001, |
| "loss": 3.1917, |
| "num_input_tokens_seen": 3958374400, |
| "step": 15100 |
| }, |
| { |
| "epoch": 0.1019064579434066, |
| "grad_norm": 0.6094233393669128, |
| "learning_rate": 0.001, |
| "loss": 3.2255, |
| "num_input_tokens_seen": 3971481600, |
| "step": 15150 |
| }, |
| { |
| "epoch": 0.10224278288711422, |
| "grad_norm": 0.20225363969802856, |
| "learning_rate": 0.001, |
| "loss": 3.2114, |
| "num_input_tokens_seen": 3984588800, |
| "step": 15200 |
| }, |
| { |
| "epoch": 0.10257910783082183, |
| "grad_norm": 0.19048044085502625, |
| "learning_rate": 0.001, |
| "loss": 3.2135, |
| "num_input_tokens_seen": 3997696000, |
| "step": 15250 |
| }, |
| { |
| "epoch": 0.10291543277452944, |
| "grad_norm": 0.17177866399288177, |
| "learning_rate": 0.001, |
| "loss": 3.1954, |
| "num_input_tokens_seen": 4010803200, |
| "step": 15300 |
| }, |
| { |
| "epoch": 0.10325175771823705, |
| "grad_norm": 0.17647191882133484, |
| "learning_rate": 0.001, |
| "loss": 3.2036, |
| "num_input_tokens_seen": 4023910400, |
| "step": 15350 |
| }, |
| { |
| "epoch": 0.10358808266194466, |
| "grad_norm": 0.16163323819637299, |
| "learning_rate": 0.001, |
| "loss": 3.1913, |
| "num_input_tokens_seen": 4037017600, |
| "step": 15400 |
| }, |
| { |
| "epoch": 0.10392440760565227, |
| "grad_norm": 0.18218201398849487, |
| "learning_rate": 0.001, |
| "loss": 3.1963, |
| "num_input_tokens_seen": 4050124800, |
| "step": 15450 |
| }, |
| { |
| "epoch": 0.10426073254935989, |
| "grad_norm": 0.17650413513183594, |
| "learning_rate": 0.001, |
| "loss": 3.1925, |
| "num_input_tokens_seen": 4063232000, |
| "step": 15500 |
| }, |
| { |
| "epoch": 0.10426073254935989, |
| "eval_loss": 3.0995914936065674, |
| "eval_runtime": 99.8658, |
| "eval_samples_per_second": 50.067, |
| "eval_steps_per_second": 12.517, |
| "num_input_tokens_seen": 4063232000, |
| "step": 15500 |
| }, |
| { |
| "epoch": 0.1045970574930675, |
| "grad_norm": 0.1616327166557312, |
| "learning_rate": 0.001, |
| "loss": 3.1924, |
| "num_input_tokens_seen": 4076339200, |
| "step": 15550 |
| }, |
| { |
| "epoch": 0.10493338243677511, |
| "grad_norm": 0.16149432957172394, |
| "learning_rate": 0.001, |
| "loss": 3.189, |
| "num_input_tokens_seen": 4089446400, |
| "step": 15600 |
| }, |
| { |
| "epoch": 0.10526970738048273, |
| "grad_norm": 0.2035779058933258, |
| "learning_rate": 0.001, |
| "loss": 3.1927, |
| "num_input_tokens_seen": 4102553600, |
| "step": 15650 |
| }, |
| { |
| "epoch": 0.10560603232419034, |
| "grad_norm": 0.16653041541576385, |
| "learning_rate": 0.001, |
| "loss": 3.1874, |
| "num_input_tokens_seen": 4115660800, |
| "step": 15700 |
| }, |
| { |
| "epoch": 0.10594235726789795, |
| "grad_norm": 0.16677066683769226, |
| "learning_rate": 0.001, |
| "loss": 3.1831, |
| "num_input_tokens_seen": 4128768000, |
| "step": 15750 |
| }, |
| { |
| "epoch": 0.10627868221160557, |
| "grad_norm": 0.17420975863933563, |
| "learning_rate": 0.001, |
| "loss": 3.1933, |
| "num_input_tokens_seen": 4141875200, |
| "step": 15800 |
| }, |
| { |
| "epoch": 0.10661500715531318, |
| "grad_norm": 0.16593104600906372, |
| "learning_rate": 0.001, |
| "loss": 3.1869, |
| "num_input_tokens_seen": 4154982400, |
| "step": 15850 |
| }, |
| { |
| "epoch": 0.10695133209902079, |
| "grad_norm": 0.18399874866008759, |
| "learning_rate": 0.001, |
| "loss": 3.1894, |
| "num_input_tokens_seen": 4168089600, |
| "step": 15900 |
| }, |
| { |
| "epoch": 0.1072876570427284, |
| "grad_norm": 0.15823860466480255, |
| "learning_rate": 0.001, |
| "loss": 3.1887, |
| "num_input_tokens_seen": 4181196800, |
| "step": 15950 |
| }, |
| { |
| "epoch": 0.10762398198643601, |
| "grad_norm": 0.18964843451976776, |
| "learning_rate": 0.001, |
| "loss": 3.1796, |
| "num_input_tokens_seen": 4194304000, |
| "step": 16000 |
| }, |
| { |
| "epoch": 0.10762398198643601, |
| "eval_loss": 3.0902183055877686, |
| "eval_runtime": 100.8295, |
| "eval_samples_per_second": 49.589, |
| "eval_steps_per_second": 12.397, |
| "num_input_tokens_seen": 4194304000, |
| "step": 16000 |
| }, |
| { |
| "epoch": 0.10796030693014362, |
| "grad_norm": 0.1692574918270111, |
| "learning_rate": 0.001, |
| "loss": 3.1892, |
| "num_input_tokens_seen": 4207411200, |
| "step": 16050 |
| }, |
| { |
| "epoch": 0.10829663187385125, |
| "grad_norm": 0.162678524851799, |
| "learning_rate": 0.001, |
| "loss": 3.1849, |
| "num_input_tokens_seen": 4220518400, |
| "step": 16100 |
| }, |
| { |
| "epoch": 0.10863295681755886, |
| "grad_norm": 0.16249045729637146, |
| "learning_rate": 0.001, |
| "loss": 3.1849, |
| "num_input_tokens_seen": 4233625600, |
| "step": 16150 |
| }, |
| { |
| "epoch": 0.10896928176126647, |
| "grad_norm": 0.17242908477783203, |
| "learning_rate": 0.001, |
| "loss": 3.1791, |
| "num_input_tokens_seen": 4246732800, |
| "step": 16200 |
| }, |
| { |
| "epoch": 0.10930560670497408, |
| "grad_norm": 0.15996769070625305, |
| "learning_rate": 0.001, |
| "loss": 3.1812, |
| "num_input_tokens_seen": 4259840000, |
| "step": 16250 |
| }, |
| { |
| "epoch": 0.10964193164868169, |
| "grad_norm": 0.1693849265575409, |
| "learning_rate": 0.001, |
| "loss": 3.1762, |
| "num_input_tokens_seen": 4272947200, |
| "step": 16300 |
| }, |
| { |
| "epoch": 0.1099782565923893, |
| "grad_norm": 0.1593247950077057, |
| "learning_rate": 0.001, |
| "loss": 3.1806, |
| "num_input_tokens_seen": 4286054400, |
| "step": 16350 |
| }, |
| { |
| "epoch": 0.11031458153609691, |
| "grad_norm": 0.16207775473594666, |
| "learning_rate": 0.001, |
| "loss": 3.175, |
| "num_input_tokens_seen": 4299161600, |
| "step": 16400 |
| }, |
| { |
| "epoch": 0.11065090647980452, |
| "grad_norm": 0.17720963060855865, |
| "learning_rate": 0.001, |
| "loss": 3.1834, |
| "num_input_tokens_seen": 4312268800, |
| "step": 16450 |
| }, |
| { |
| "epoch": 0.11098723142351213, |
| "grad_norm": 0.1996976137161255, |
| "learning_rate": 0.001, |
| "loss": 3.211, |
| "num_input_tokens_seen": 4325376000, |
| "step": 16500 |
| }, |
| { |
| "epoch": 0.11098723142351213, |
| "eval_loss": 3.098728895187378, |
| "eval_runtime": 101.226, |
| "eval_samples_per_second": 49.394, |
| "eval_steps_per_second": 12.349, |
| "num_input_tokens_seen": 4325376000, |
| "step": 16500 |
| }, |
| { |
| "epoch": 0.11132355636721976, |
| "grad_norm": 0.1731133908033371, |
| "learning_rate": 0.001, |
| "loss": 3.1828, |
| "num_input_tokens_seen": 4338483200, |
| "step": 16550 |
| }, |
| { |
| "epoch": 0.11165988131092737, |
| "grad_norm": 0.21048209071159363, |
| "learning_rate": 0.001, |
| "loss": 3.1843, |
| "num_input_tokens_seen": 4351590400, |
| "step": 16600 |
| }, |
| { |
| "epoch": 0.11199620625463498, |
| "grad_norm": 0.18280939757823944, |
| "learning_rate": 0.001, |
| "loss": 3.1904, |
| "num_input_tokens_seen": 4364697600, |
| "step": 16650 |
| }, |
| { |
| "epoch": 0.11233253119834259, |
| "grad_norm": 0.15612006187438965, |
| "learning_rate": 0.001, |
| "loss": 3.1795, |
| "num_input_tokens_seen": 4377804800, |
| "step": 16700 |
| }, |
| { |
| "epoch": 0.1126688561420502, |
| "grad_norm": 0.17242297530174255, |
| "learning_rate": 0.001, |
| "loss": 3.1727, |
| "num_input_tokens_seen": 4390912000, |
| "step": 16750 |
| }, |
| { |
| "epoch": 0.11300518108575781, |
| "grad_norm": 0.170341357588768, |
| "learning_rate": 0.001, |
| "loss": 3.1828, |
| "num_input_tokens_seen": 4404019200, |
| "step": 16800 |
| }, |
| { |
| "epoch": 0.11334150602946542, |
| "grad_norm": 0.17627349495887756, |
| "learning_rate": 0.001, |
| "loss": 3.1946, |
| "num_input_tokens_seen": 4417126400, |
| "step": 16850 |
| }, |
| { |
| "epoch": 0.11367783097317304, |
| "grad_norm": 0.19702504575252533, |
| "learning_rate": 0.001, |
| "loss": 3.1737, |
| "num_input_tokens_seen": 4430233600, |
| "step": 16900 |
| }, |
| { |
| "epoch": 0.11401415591688065, |
| "grad_norm": 0.170149028301239, |
| "learning_rate": 0.001, |
| "loss": 3.188, |
| "num_input_tokens_seen": 4443340800, |
| "step": 16950 |
| }, |
| { |
| "epoch": 0.11435048086058827, |
| "grad_norm": 0.1967497169971466, |
| "learning_rate": 0.001, |
| "loss": 3.1778, |
| "num_input_tokens_seen": 4456448000, |
| "step": 17000 |
| }, |
| { |
| "epoch": 0.11435048086058827, |
| "eval_loss": 3.084319829940796, |
| "eval_runtime": 101.2745, |
| "eval_samples_per_second": 49.371, |
| "eval_steps_per_second": 12.343, |
| "num_input_tokens_seen": 4456448000, |
| "step": 17000 |
| }, |
| { |
| "epoch": 0.11468680580429588, |
| "grad_norm": 0.17489473521709442, |
| "learning_rate": 0.001, |
| "loss": 3.1781, |
| "num_input_tokens_seen": 4469555200, |
| "step": 17050 |
| }, |
| { |
| "epoch": 0.1150231307480035, |
| "grad_norm": 0.17033468186855316, |
| "learning_rate": 0.001, |
| "loss": 3.1787, |
| "num_input_tokens_seen": 4482662400, |
| "step": 17100 |
| }, |
| { |
| "epoch": 0.1153594556917111, |
| "grad_norm": 0.16838806867599487, |
| "learning_rate": 0.001, |
| "loss": 3.1819, |
| "num_input_tokens_seen": 4495769600, |
| "step": 17150 |
| }, |
| { |
| "epoch": 0.11569578063541872, |
| "grad_norm": 0.18173356354236603, |
| "learning_rate": 0.001, |
| "loss": 3.1663, |
| "num_input_tokens_seen": 4508876800, |
| "step": 17200 |
| }, |
| { |
| "epoch": 0.11603210557912633, |
| "grad_norm": 0.17072565853595734, |
| "learning_rate": 0.001, |
| "loss": 3.1777, |
| "num_input_tokens_seen": 4521984000, |
| "step": 17250 |
| }, |
| { |
| "epoch": 0.11636843052283394, |
| "grad_norm": 0.17745070159435272, |
| "learning_rate": 0.001, |
| "loss": 3.1708, |
| "num_input_tokens_seen": 4535091200, |
| "step": 17300 |
| }, |
| { |
| "epoch": 0.11670475546654155, |
| "grad_norm": 0.16486075520515442, |
| "learning_rate": 0.001, |
| "loss": 3.1698, |
| "num_input_tokens_seen": 4548198400, |
| "step": 17350 |
| }, |
| { |
| "epoch": 0.11704108041024916, |
| "grad_norm": 0.1572778970003128, |
| "learning_rate": 0.001, |
| "loss": 3.1742, |
| "num_input_tokens_seen": 4561305600, |
| "step": 17400 |
| }, |
| { |
| "epoch": 0.11737740535395678, |
| "grad_norm": 0.17188695073127747, |
| "learning_rate": 0.001, |
| "loss": 3.1779, |
| "num_input_tokens_seen": 4574412800, |
| "step": 17450 |
| }, |
| { |
| "epoch": 0.1177137302976644, |
| "grad_norm": 0.16766607761383057, |
| "learning_rate": 0.001, |
| "loss": 3.1717, |
| "num_input_tokens_seen": 4587520000, |
| "step": 17500 |
| }, |
| { |
| "epoch": 0.1177137302976644, |
| "eval_loss": 3.075218677520752, |
| "eval_runtime": 101.5328, |
| "eval_samples_per_second": 49.245, |
| "eval_steps_per_second": 12.311, |
| "num_input_tokens_seen": 4587520000, |
| "step": 17500 |
| }, |
| { |
| "epoch": 0.118050055241372, |
| "grad_norm": 0.16463638842105865, |
| "learning_rate": 0.001, |
| "loss": 3.1698, |
| "num_input_tokens_seen": 4600627200, |
| "step": 17550 |
| }, |
| { |
| "epoch": 0.11838638018507962, |
| "grad_norm": 0.4281676709651947, |
| "learning_rate": 0.001, |
| "loss": 3.169, |
| "num_input_tokens_seen": 4613734400, |
| "step": 17600 |
| }, |
| { |
| "epoch": 0.11872270512878723, |
| "grad_norm": 0.18109829723834991, |
| "learning_rate": 0.001, |
| "loss": 3.166, |
| "num_input_tokens_seen": 4626841600, |
| "step": 17650 |
| }, |
| { |
| "epoch": 0.11905903007249484, |
| "grad_norm": 0.16371768712997437, |
| "learning_rate": 0.001, |
| "loss": 3.1694, |
| "num_input_tokens_seen": 4639948800, |
| "step": 17700 |
| }, |
| { |
| "epoch": 0.11939535501620245, |
| "grad_norm": 0.18475505709648132, |
| "learning_rate": 0.001, |
| "loss": 3.174, |
| "num_input_tokens_seen": 4653056000, |
| "step": 17750 |
| }, |
| { |
| "epoch": 0.11973167995991006, |
| "grad_norm": 0.20489992201328278, |
| "learning_rate": 0.001, |
| "loss": 3.1644, |
| "num_input_tokens_seen": 4666163200, |
| "step": 17800 |
| }, |
| { |
| "epoch": 0.12006800490361767, |
| "grad_norm": 0.1695111244916916, |
| "learning_rate": 0.001, |
| "loss": 3.1699, |
| "num_input_tokens_seen": 4679270400, |
| "step": 17850 |
| }, |
| { |
| "epoch": 0.1204043298473253, |
| "grad_norm": 0.16501003503799438, |
| "learning_rate": 0.001, |
| "loss": 3.1549, |
| "num_input_tokens_seen": 4692377600, |
| "step": 17900 |
| }, |
| { |
| "epoch": 0.12074065479103291, |
| "grad_norm": 0.16232050955295563, |
| "learning_rate": 0.001, |
| "loss": 3.1762, |
| "num_input_tokens_seen": 4705484800, |
| "step": 17950 |
| }, |
| { |
| "epoch": 0.12107697973474052, |
| "grad_norm": 0.17002490162849426, |
| "learning_rate": 0.001, |
| "loss": 3.1597, |
| "num_input_tokens_seen": 4718592000, |
| "step": 18000 |
| }, |
| { |
| "epoch": 0.12107697973474052, |
| "eval_loss": 3.069894552230835, |
| "eval_runtime": 100.7483, |
| "eval_samples_per_second": 49.629, |
| "eval_steps_per_second": 12.407, |
| "num_input_tokens_seen": 4718592000, |
| "step": 18000 |
| }, |
| { |
| "epoch": 0.12141330467844813, |
| "grad_norm": 0.1668955534696579, |
| "learning_rate": 0.001, |
| "loss": 3.1641, |
| "num_input_tokens_seen": 4731699200, |
| "step": 18050 |
| }, |
| { |
| "epoch": 0.12174962962215574, |
| "grad_norm": 0.17743679881095886, |
| "learning_rate": 0.001, |
| "loss": 3.1717, |
| "num_input_tokens_seen": 4744806400, |
| "step": 18100 |
| }, |
| { |
| "epoch": 0.12208595456586335, |
| "grad_norm": 0.17474418878555298, |
| "learning_rate": 0.001, |
| "loss": 3.1745, |
| "num_input_tokens_seen": 4757913600, |
| "step": 18150 |
| }, |
| { |
| "epoch": 0.12242227950957096, |
| "grad_norm": 0.18446923792362213, |
| "learning_rate": 0.001, |
| "loss": 3.1526, |
| "num_input_tokens_seen": 4771020800, |
| "step": 18200 |
| }, |
| { |
| "epoch": 0.12275860445327857, |
| "grad_norm": 0.19560950994491577, |
| "learning_rate": 0.001, |
| "loss": 3.1736, |
| "num_input_tokens_seen": 4784128000, |
| "step": 18250 |
| }, |
| { |
| "epoch": 0.12309492939698619, |
| "grad_norm": 0.17012590169906616, |
| "learning_rate": 0.001, |
| "loss": 3.1743, |
| "num_input_tokens_seen": 4797235200, |
| "step": 18300 |
| }, |
| { |
| "epoch": 0.12343125434069381, |
| "grad_norm": 0.17102253437042236, |
| "learning_rate": 0.001, |
| "loss": 3.169, |
| "num_input_tokens_seen": 4810342400, |
| "step": 18350 |
| }, |
| { |
| "epoch": 0.12376757928440142, |
| "grad_norm": 0.16899776458740234, |
| "learning_rate": 0.001, |
| "loss": 3.1657, |
| "num_input_tokens_seen": 4823449600, |
| "step": 18400 |
| }, |
| { |
| "epoch": 0.12410390422810903, |
| "grad_norm": 0.18831774592399597, |
| "learning_rate": 0.001, |
| "loss": 3.1664, |
| "num_input_tokens_seen": 4836556800, |
| "step": 18450 |
| }, |
| { |
| "epoch": 0.12444022917181664, |
| "grad_norm": 0.2649637460708618, |
| "learning_rate": 0.001, |
| "loss": 3.183, |
| "num_input_tokens_seen": 4849664000, |
| "step": 18500 |
| }, |
| { |
| "epoch": 0.12444022917181664, |
| "eval_loss": 3.088426351547241, |
| "eval_runtime": 100.5331, |
| "eval_samples_per_second": 49.735, |
| "eval_steps_per_second": 12.434, |
| "num_input_tokens_seen": 4849664000, |
| "step": 18500 |
| }, |
| { |
| "epoch": 0.12477655411552425, |
| "grad_norm": 0.2588728368282318, |
| "learning_rate": 0.001, |
| "loss": 3.2022, |
| "num_input_tokens_seen": 4862771200, |
| "step": 18550 |
| }, |
| { |
| "epoch": 0.12511287905923188, |
| "grad_norm": 0.1861683577299118, |
| "learning_rate": 0.001, |
| "loss": 3.1779, |
| "num_input_tokens_seen": 4875878400, |
| "step": 18600 |
| }, |
| { |
| "epoch": 0.1254492040029395, |
| "grad_norm": 0.1803797483444214, |
| "learning_rate": 0.001, |
| "loss": 3.1761, |
| "num_input_tokens_seen": 4888985600, |
| "step": 18650 |
| }, |
| { |
| "epoch": 0.1257855289466471, |
| "grad_norm": 0.20752698183059692, |
| "learning_rate": 0.001, |
| "loss": 3.1867, |
| "num_input_tokens_seen": 4902092800, |
| "step": 18700 |
| }, |
| { |
| "epoch": 0.1261218538903547, |
| "grad_norm": 0.18387116491794586, |
| "learning_rate": 0.001, |
| "loss": 3.1667, |
| "num_input_tokens_seen": 4915200000, |
| "step": 18750 |
| }, |
| { |
| "epoch": 0.12645817883406232, |
| "grad_norm": 0.3406733572483063, |
| "learning_rate": 0.001, |
| "loss": 3.1706, |
| "num_input_tokens_seen": 4928307200, |
| "step": 18800 |
| }, |
| { |
| "epoch": 0.12679450377776993, |
| "grad_norm": 0.17068707942962646, |
| "learning_rate": 0.001, |
| "loss": 3.1715, |
| "num_input_tokens_seen": 4941414400, |
| "step": 18850 |
| }, |
| { |
| "epoch": 0.12713082872147755, |
| "grad_norm": 0.18792368471622467, |
| "learning_rate": 0.001, |
| "loss": 3.1711, |
| "num_input_tokens_seen": 4954521600, |
| "step": 18900 |
| }, |
| { |
| "epoch": 0.12746715366518516, |
| "grad_norm": 0.18366409838199615, |
| "learning_rate": 0.001, |
| "loss": 3.1724, |
| "num_input_tokens_seen": 4967628800, |
| "step": 18950 |
| }, |
| { |
| "epoch": 0.12780347860889277, |
| "grad_norm": 0.15937770903110504, |
| "learning_rate": 0.001, |
| "loss": 3.1541, |
| "num_input_tokens_seen": 4980736000, |
| "step": 19000 |
| }, |
| { |
| "epoch": 0.12780347860889277, |
| "eval_loss": 3.06679630279541, |
| "eval_runtime": 100.9386, |
| "eval_samples_per_second": 49.535, |
| "eval_steps_per_second": 12.384, |
| "num_input_tokens_seen": 4980736000, |
| "step": 19000 |
| }, |
| { |
| "epoch": 0.12813980355260038, |
| "grad_norm": 0.17235547304153442, |
| "learning_rate": 0.001, |
| "loss": 3.1644, |
| "num_input_tokens_seen": 4993843200, |
| "step": 19050 |
| }, |
| { |
| "epoch": 0.128476128496308, |
| "grad_norm": 0.17877432703971863, |
| "learning_rate": 0.001, |
| "loss": 3.1613, |
| "num_input_tokens_seen": 5006950400, |
| "step": 19100 |
| }, |
| { |
| "epoch": 0.1288124534400156, |
| "grad_norm": 0.20647567510604858, |
| "learning_rate": 0.001, |
| "loss": 3.157, |
| "num_input_tokens_seen": 5020057600, |
| "step": 19150 |
| }, |
| { |
| "epoch": 0.1291487783837232, |
| "grad_norm": 0.17320992052555084, |
| "learning_rate": 0.001, |
| "loss": 3.1597, |
| "num_input_tokens_seen": 5033164800, |
| "step": 19200 |
| }, |
| { |
| "epoch": 0.12948510332743082, |
| "grad_norm": 0.1975463479757309, |
| "learning_rate": 0.001, |
| "loss": 3.1588, |
| "num_input_tokens_seen": 5046272000, |
| "step": 19250 |
| }, |
| { |
| "epoch": 0.12982142827113843, |
| "grad_norm": 0.2234167754650116, |
| "learning_rate": 0.001, |
| "loss": 3.1752, |
| "num_input_tokens_seen": 5059379200, |
| "step": 19300 |
| }, |
| { |
| "epoch": 0.13015775321484604, |
| "grad_norm": 0.16287492215633392, |
| "learning_rate": 0.001, |
| "loss": 3.1559, |
| "num_input_tokens_seen": 5072486400, |
| "step": 19350 |
| }, |
| { |
| "epoch": 0.13049407815855366, |
| "grad_norm": 0.21676546335220337, |
| "learning_rate": 0.001, |
| "loss": 3.1556, |
| "num_input_tokens_seen": 5085593600, |
| "step": 19400 |
| }, |
| { |
| "epoch": 0.1308304031022613, |
| "grad_norm": 0.19858922064304352, |
| "learning_rate": 0.001, |
| "loss": 3.1617, |
| "num_input_tokens_seen": 5098700800, |
| "step": 19450 |
| }, |
| { |
| "epoch": 0.1311667280459689, |
| "grad_norm": 0.17459186911582947, |
| "learning_rate": 0.001, |
| "loss": 3.1499, |
| "num_input_tokens_seen": 5111808000, |
| "step": 19500 |
| }, |
| { |
| "epoch": 0.1311667280459689, |
| "eval_loss": 3.0653886795043945, |
| "eval_runtime": 101.0357, |
| "eval_samples_per_second": 49.487, |
| "eval_steps_per_second": 12.372, |
| "num_input_tokens_seen": 5111808000, |
| "step": 19500 |
| }, |
| { |
| "epoch": 0.13150305298967652, |
| "grad_norm": 0.17277012765407562, |
| "learning_rate": 0.001, |
| "loss": 3.1641, |
| "num_input_tokens_seen": 5124915200, |
| "step": 19550 |
| }, |
| { |
| "epoch": 0.13183937793338413, |
| "grad_norm": 0.1894499808549881, |
| "learning_rate": 0.001, |
| "loss": 3.1465, |
| "num_input_tokens_seen": 5138022400, |
| "step": 19600 |
| }, |
| { |
| "epoch": 0.13217570287709174, |
| "grad_norm": 0.17682771384716034, |
| "learning_rate": 0.001, |
| "loss": 3.1573, |
| "num_input_tokens_seen": 5151129600, |
| "step": 19650 |
| }, |
| { |
| "epoch": 0.13251202782079935, |
| "grad_norm": 0.17981217801570892, |
| "learning_rate": 0.001, |
| "loss": 3.1484, |
| "num_input_tokens_seen": 5164236800, |
| "step": 19700 |
| }, |
| { |
| "epoch": 0.13284835276450696, |
| "grad_norm": 0.19152362644672394, |
| "learning_rate": 0.001, |
| "loss": 3.1597, |
| "num_input_tokens_seen": 5177344000, |
| "step": 19750 |
| }, |
| { |
| "epoch": 0.13318467770821457, |
| "grad_norm": 0.17498181760311127, |
| "learning_rate": 0.001, |
| "loss": 3.1604, |
| "num_input_tokens_seen": 5190451200, |
| "step": 19800 |
| }, |
| { |
| "epoch": 0.13352100265192218, |
| "grad_norm": 0.17143672704696655, |
| "learning_rate": 0.001, |
| "loss": 3.1601, |
| "num_input_tokens_seen": 5203558400, |
| "step": 19850 |
| }, |
| { |
| "epoch": 0.1338573275956298, |
| "grad_norm": 0.19592677056789398, |
| "learning_rate": 0.001, |
| "loss": 3.1568, |
| "num_input_tokens_seen": 5216665600, |
| "step": 19900 |
| }, |
| { |
| "epoch": 0.1341936525393374, |
| "grad_norm": 0.1618625670671463, |
| "learning_rate": 0.001, |
| "loss": 3.1584, |
| "num_input_tokens_seen": 5229772800, |
| "step": 19950 |
| }, |
| { |
| "epoch": 0.13452997748304502, |
| "grad_norm": 0.18170061707496643, |
| "learning_rate": 0.001, |
| "loss": 3.1499, |
| "num_input_tokens_seen": 5242880000, |
| "step": 20000 |
| }, |
| { |
| "epoch": 0.13452997748304502, |
| "eval_loss": 3.056318759918213, |
| "eval_runtime": 100.9422, |
| "eval_samples_per_second": 49.533, |
| "eval_steps_per_second": 12.383, |
| "num_input_tokens_seen": 5242880000, |
| "step": 20000 |
| }, |
| { |
| "epoch": 0.13486630242675263, |
| "grad_norm": 0.1726132184267044, |
| "learning_rate": 0.001, |
| "loss": 3.1545, |
| "num_input_tokens_seen": 5255987200, |
| "step": 20050 |
| }, |
| { |
| "epoch": 0.13520262737046024, |
| "grad_norm": 0.17690512537956238, |
| "learning_rate": 0.001, |
| "loss": 3.1526, |
| "num_input_tokens_seen": 5269094400, |
| "step": 20100 |
| }, |
| { |
| "epoch": 0.13553895231416785, |
| "grad_norm": 0.20317280292510986, |
| "learning_rate": 0.001, |
| "loss": 3.15, |
| "num_input_tokens_seen": 5282201600, |
| "step": 20150 |
| }, |
| { |
| "epoch": 0.13587527725787546, |
| "grad_norm": 0.16687753796577454, |
| "learning_rate": 0.001, |
| "loss": 3.144, |
| "num_input_tokens_seen": 5295308800, |
| "step": 20200 |
| }, |
| { |
| "epoch": 0.13621160220158307, |
| "grad_norm": 0.16671325266361237, |
| "learning_rate": 0.001, |
| "loss": 3.1425, |
| "num_input_tokens_seen": 5308416000, |
| "step": 20250 |
| }, |
| { |
| "epoch": 0.13654792714529068, |
| "grad_norm": 0.16259203851222992, |
| "learning_rate": 0.001, |
| "loss": 3.1386, |
| "num_input_tokens_seen": 5321523200, |
| "step": 20300 |
| }, |
| { |
| "epoch": 0.1368842520889983, |
| "grad_norm": 0.15738168358802795, |
| "learning_rate": 0.001, |
| "loss": 3.148, |
| "num_input_tokens_seen": 5334630400, |
| "step": 20350 |
| }, |
| { |
| "epoch": 0.13722057703270593, |
| "grad_norm": 0.17398318648338318, |
| "learning_rate": 0.001, |
| "loss": 3.1484, |
| "num_input_tokens_seen": 5347737600, |
| "step": 20400 |
| }, |
| { |
| "epoch": 0.13755690197641354, |
| "grad_norm": 0.177555114030838, |
| "learning_rate": 0.001, |
| "loss": 3.1507, |
| "num_input_tokens_seen": 5360844800, |
| "step": 20450 |
| }, |
| { |
| "epoch": 0.13789322692012115, |
| "grad_norm": 0.16208910942077637, |
| "learning_rate": 0.001, |
| "loss": 3.1462, |
| "num_input_tokens_seen": 5373952000, |
| "step": 20500 |
| }, |
| { |
| "epoch": 0.13789322692012115, |
| "eval_loss": 3.0525152683258057, |
| "eval_runtime": 101.4785, |
| "eval_samples_per_second": 49.272, |
| "eval_steps_per_second": 12.318, |
| "num_input_tokens_seen": 5373952000, |
| "step": 20500 |
| }, |
| { |
| "epoch": 0.13822955186382876, |
| "grad_norm": 0.1615586280822754, |
| "learning_rate": 0.001, |
| "loss": 3.1469, |
| "num_input_tokens_seen": 5387059200, |
| "step": 20550 |
| }, |
| { |
| "epoch": 0.13856587680753638, |
| "grad_norm": 0.17003317177295685, |
| "learning_rate": 0.001, |
| "loss": 3.15, |
| "num_input_tokens_seen": 5400166400, |
| "step": 20600 |
| }, |
| { |
| "epoch": 0.138902201751244, |
| "grad_norm": 0.16299164295196533, |
| "learning_rate": 0.001, |
| "loss": 3.1522, |
| "num_input_tokens_seen": 5413273600, |
| "step": 20650 |
| }, |
| { |
| "epoch": 0.1392385266949516, |
| "grad_norm": 0.18732890486717224, |
| "learning_rate": 0.001, |
| "loss": 3.1462, |
| "num_input_tokens_seen": 5426380800, |
| "step": 20700 |
| }, |
| { |
| "epoch": 0.1395748516386592, |
| "grad_norm": 0.23970580101013184, |
| "learning_rate": 0.001, |
| "loss": 3.1832, |
| "num_input_tokens_seen": 5439488000, |
| "step": 20750 |
| }, |
| { |
| "epoch": 0.13991117658236682, |
| "grad_norm": 0.1701073795557022, |
| "learning_rate": 0.001, |
| "loss": 3.1713, |
| "num_input_tokens_seen": 5452595200, |
| "step": 20800 |
| }, |
| { |
| "epoch": 0.14024750152607443, |
| "grad_norm": 0.18976852297782898, |
| "learning_rate": 0.001, |
| "loss": 3.1636, |
| "num_input_tokens_seen": 5465702400, |
| "step": 20850 |
| }, |
| { |
| "epoch": 0.14058382646978204, |
| "grad_norm": 0.17788629233837128, |
| "learning_rate": 0.001, |
| "loss": 3.1712, |
| "num_input_tokens_seen": 5478809600, |
| "step": 20900 |
| }, |
| { |
| "epoch": 0.14092015141348965, |
| "grad_norm": 0.20413383841514587, |
| "learning_rate": 0.001, |
| "loss": 3.1604, |
| "num_input_tokens_seen": 5491916800, |
| "step": 20950 |
| }, |
| { |
| "epoch": 0.14125647635719726, |
| "grad_norm": 0.1921602487564087, |
| "learning_rate": 0.001, |
| "loss": 3.15, |
| "num_input_tokens_seen": 5505024000, |
| "step": 21000 |
| }, |
| { |
| "epoch": 0.14125647635719726, |
| "eval_loss": 3.053833484649658, |
| "eval_runtime": 101.2468, |
| "eval_samples_per_second": 49.384, |
| "eval_steps_per_second": 12.346, |
| "num_input_tokens_seen": 5505024000, |
| "step": 21000 |
| }, |
| { |
| "epoch": 0.14159280130090487, |
| "grad_norm": 0.18453796207904816, |
| "learning_rate": 0.001, |
| "loss": 3.1542, |
| "num_input_tokens_seen": 5518131200, |
| "step": 21050 |
| }, |
| { |
| "epoch": 0.14192912624461249, |
| "grad_norm": 0.29931920766830444, |
| "learning_rate": 0.001, |
| "loss": 3.1633, |
| "num_input_tokens_seen": 5531238400, |
| "step": 21100 |
| }, |
| { |
| "epoch": 0.1422654511883201, |
| "grad_norm": 0.19636057317256927, |
| "learning_rate": 0.001, |
| "loss": 3.1544, |
| "num_input_tokens_seen": 5544345600, |
| "step": 21150 |
| }, |
| { |
| "epoch": 0.1426017761320277, |
| "grad_norm": 0.3110333979129791, |
| "learning_rate": 0.001, |
| "loss": 3.186, |
| "num_input_tokens_seen": 5557452800, |
| "step": 21200 |
| }, |
| { |
| "epoch": 0.14293810107573532, |
| "grad_norm": 0.21632343530654907, |
| "learning_rate": 0.001, |
| "loss": 3.1759, |
| "num_input_tokens_seen": 5570560000, |
| "step": 21250 |
| }, |
| { |
| "epoch": 0.14327442601944296, |
| "grad_norm": 0.23088929057121277, |
| "learning_rate": 0.001, |
| "loss": 3.1683, |
| "num_input_tokens_seen": 5583667200, |
| "step": 21300 |
| }, |
| { |
| "epoch": 0.14361075096315057, |
| "grad_norm": 0.19326886534690857, |
| "learning_rate": 0.001, |
| "loss": 3.1535, |
| "num_input_tokens_seen": 5596774400, |
| "step": 21350 |
| }, |
| { |
| "epoch": 0.14394707590685818, |
| "grad_norm": 0.3554578125476837, |
| "learning_rate": 0.001, |
| "loss": 3.1606, |
| "num_input_tokens_seen": 5609881600, |
| "step": 21400 |
| }, |
| { |
| "epoch": 0.1442834008505658, |
| "grad_norm": 0.18607909977436066, |
| "learning_rate": 0.001, |
| "loss": 3.159, |
| "num_input_tokens_seen": 5622988800, |
| "step": 21450 |
| }, |
| { |
| "epoch": 0.1446197257942734, |
| "grad_norm": 0.2276984453201294, |
| "learning_rate": 0.001, |
| "loss": 3.1544, |
| "num_input_tokens_seen": 5636096000, |
| "step": 21500 |
| }, |
| { |
| "epoch": 0.1446197257942734, |
| "eval_loss": 3.051608085632324, |
| "eval_runtime": 101.9015, |
| "eval_samples_per_second": 49.067, |
| "eval_steps_per_second": 12.267, |
| "num_input_tokens_seen": 5636096000, |
| "step": 21500 |
| }, |
| { |
| "epoch": 0.144956050737981, |
| "grad_norm": 0.17796960473060608, |
| "learning_rate": 0.001, |
| "loss": 3.1488, |
| "num_input_tokens_seen": 5649203200, |
| "step": 21550 |
| }, |
| { |
| "epoch": 0.14529237568168862, |
| "grad_norm": 0.1721925139427185, |
| "learning_rate": 0.001, |
| "loss": 3.1465, |
| "num_input_tokens_seen": 5662310400, |
| "step": 21600 |
| }, |
| { |
| "epoch": 0.14562870062539623, |
| "grad_norm": 0.1779259443283081, |
| "learning_rate": 0.001, |
| "loss": 3.1479, |
| "num_input_tokens_seen": 5675417600, |
| "step": 21650 |
| }, |
| { |
| "epoch": 0.14596502556910385, |
| "grad_norm": 0.1955435425043106, |
| "learning_rate": 0.001, |
| "loss": 3.147, |
| "num_input_tokens_seen": 5688524800, |
| "step": 21700 |
| }, |
| { |
| "epoch": 0.14630135051281146, |
| "grad_norm": 0.2717543840408325, |
| "learning_rate": 0.001, |
| "loss": 3.1456, |
| "num_input_tokens_seen": 5701632000, |
| "step": 21750 |
| }, |
| { |
| "epoch": 0.14663767545651907, |
| "grad_norm": 0.22944161295890808, |
| "learning_rate": 0.001, |
| "loss": 3.1596, |
| "num_input_tokens_seen": 5714739200, |
| "step": 21800 |
| }, |
| { |
| "epoch": 0.14697400040022668, |
| "grad_norm": 0.18696273863315582, |
| "learning_rate": 0.001, |
| "loss": 3.1417, |
| "num_input_tokens_seen": 5727846400, |
| "step": 21850 |
| }, |
| { |
| "epoch": 0.1473103253439343, |
| "grad_norm": 0.17678014934062958, |
| "learning_rate": 0.001, |
| "loss": 3.1454, |
| "num_input_tokens_seen": 5740953600, |
| "step": 21900 |
| }, |
| { |
| "epoch": 0.1476466502876419, |
| "grad_norm": 0.16891658306121826, |
| "learning_rate": 0.001, |
| "loss": 3.142, |
| "num_input_tokens_seen": 5754060800, |
| "step": 21950 |
| }, |
| { |
| "epoch": 0.1479829752313495, |
| "grad_norm": 0.20900680124759674, |
| "learning_rate": 0.001, |
| "loss": 3.1475, |
| "num_input_tokens_seen": 5767168000, |
| "step": 22000 |
| }, |
| { |
| "epoch": 0.1479829752313495, |
| "eval_loss": 3.0481514930725098, |
| "eval_runtime": 100.7385, |
| "eval_samples_per_second": 49.633, |
| "eval_steps_per_second": 12.408, |
| "num_input_tokens_seen": 5767168000, |
| "step": 22000 |
| }, |
| { |
| "epoch": 0.14831930017505712, |
| "grad_norm": 0.17889799177646637, |
| "learning_rate": 0.001, |
| "loss": 3.1407, |
| "num_input_tokens_seen": 5780275200, |
| "step": 22050 |
| }, |
| { |
| "epoch": 0.14865562511876473, |
| "grad_norm": 1.7358074188232422, |
| "learning_rate": 0.001, |
| "loss": 3.1454, |
| "num_input_tokens_seen": 5793382400, |
| "step": 22100 |
| }, |
| { |
| "epoch": 0.14899195006247234, |
| "grad_norm": 0.17746248841285706, |
| "learning_rate": 0.001, |
| "loss": 3.154, |
| "num_input_tokens_seen": 5806489600, |
| "step": 22150 |
| }, |
| { |
| "epoch": 0.14932827500617998, |
| "grad_norm": 0.185111865401268, |
| "learning_rate": 0.001, |
| "loss": 3.1522, |
| "num_input_tokens_seen": 5819596800, |
| "step": 22200 |
| }, |
| { |
| "epoch": 0.1496645999498876, |
| "grad_norm": 0.23882286250591278, |
| "learning_rate": 0.001, |
| "loss": 3.1379, |
| "num_input_tokens_seen": 5832704000, |
| "step": 22250 |
| }, |
| { |
| "epoch": 0.1500009248935952, |
| "grad_norm": 0.19389848411083221, |
| "learning_rate": 0.001, |
| "loss": 3.1459, |
| "num_input_tokens_seen": 5845811200, |
| "step": 22300 |
| }, |
| { |
| "epoch": 0.15033724983730282, |
| "grad_norm": 0.18890796601772308, |
| "learning_rate": 0.001, |
| "loss": 3.1401, |
| "num_input_tokens_seen": 5858918400, |
| "step": 22350 |
| }, |
| { |
| "epoch": 0.15067357478101043, |
| "grad_norm": 0.17061029374599457, |
| "learning_rate": 0.001, |
| "loss": 3.1555, |
| "num_input_tokens_seen": 5872025600, |
| "step": 22400 |
| }, |
| { |
| "epoch": 0.15100989972471804, |
| "grad_norm": 0.18124708533287048, |
| "learning_rate": 0.001, |
| "loss": 3.1499, |
| "num_input_tokens_seen": 5885132800, |
| "step": 22450 |
| }, |
| { |
| "epoch": 0.15134622466842565, |
| "grad_norm": 0.21192225813865662, |
| "learning_rate": 0.001, |
| "loss": 3.1364, |
| "num_input_tokens_seen": 5898240000, |
| "step": 22500 |
| }, |
| { |
| "epoch": 0.15134622466842565, |
| "eval_loss": 3.042147636413574, |
| "eval_runtime": 100.7091, |
| "eval_samples_per_second": 49.648, |
| "eval_steps_per_second": 12.412, |
| "num_input_tokens_seen": 5898240000, |
| "step": 22500 |
| }, |
| { |
| "epoch": 0.15168254961213326, |
| "grad_norm": 0.16922616958618164, |
| "learning_rate": 0.001, |
| "loss": 3.149, |
| "num_input_tokens_seen": 5911347200, |
| "step": 22550 |
| }, |
| { |
| "epoch": 0.15201887455584087, |
| "grad_norm": 0.1636754721403122, |
| "learning_rate": 0.001, |
| "loss": 3.1379, |
| "num_input_tokens_seen": 5924454400, |
| "step": 22600 |
| }, |
| { |
| "epoch": 0.15235519949954848, |
| "grad_norm": 0.167410746216774, |
| "learning_rate": 0.001, |
| "loss": 3.1465, |
| "num_input_tokens_seen": 5937561600, |
| "step": 22650 |
| }, |
| { |
| "epoch": 0.1526915244432561, |
| "grad_norm": 0.18413004279136658, |
| "learning_rate": 0.001, |
| "loss": 3.131, |
| "num_input_tokens_seen": 5950668800, |
| "step": 22700 |
| }, |
| { |
| "epoch": 0.1530278493869637, |
| "grad_norm": 0.20482878386974335, |
| "learning_rate": 0.001, |
| "loss": 3.1395, |
| "num_input_tokens_seen": 5963776000, |
| "step": 22750 |
| }, |
| { |
| "epoch": 0.15336417433067132, |
| "grad_norm": 0.19031567871570587, |
| "learning_rate": 0.001, |
| "loss": 3.1369, |
| "num_input_tokens_seen": 5976883200, |
| "step": 22800 |
| }, |
| { |
| "epoch": 0.15370049927437893, |
| "grad_norm": 0.21622490882873535, |
| "learning_rate": 0.001, |
| "loss": 3.1448, |
| "num_input_tokens_seen": 5989990400, |
| "step": 22850 |
| }, |
| { |
| "epoch": 0.15403682421808654, |
| "grad_norm": 0.19105197489261627, |
| "learning_rate": 0.001, |
| "loss": 3.1456, |
| "num_input_tokens_seen": 6003097600, |
| "step": 22900 |
| }, |
| { |
| "epoch": 0.15437314916179415, |
| "grad_norm": 0.26653292775154114, |
| "learning_rate": 0.001, |
| "loss": 3.1405, |
| "num_input_tokens_seen": 6016204800, |
| "step": 22950 |
| }, |
| { |
| "epoch": 0.15470947410550176, |
| "grad_norm": 0.30645105242729187, |
| "learning_rate": 0.001, |
| "loss": 3.1564, |
| "num_input_tokens_seen": 6029312000, |
| "step": 23000 |
| }, |
| { |
| "epoch": 0.15470947410550176, |
| "eval_loss": 3.072319507598877, |
| "eval_runtime": 100.6281, |
| "eval_samples_per_second": 49.688, |
| "eval_steps_per_second": 12.422, |
| "num_input_tokens_seen": 6029312000, |
| "step": 23000 |
| }, |
| { |
| "epoch": 0.15504579904920937, |
| "grad_norm": 0.18146337568759918, |
| "learning_rate": 0.001, |
| "loss": 3.1774, |
| "num_input_tokens_seen": 6042419200, |
| "step": 23050 |
| }, |
| { |
| "epoch": 0.155382123992917, |
| "grad_norm": 0.19545282423496246, |
| "learning_rate": 0.001, |
| "loss": 3.1384, |
| "num_input_tokens_seen": 6055526400, |
| "step": 23100 |
| }, |
| { |
| "epoch": 0.15571844893662462, |
| "grad_norm": 0.17861327528953552, |
| "learning_rate": 0.001, |
| "loss": 3.1459, |
| "num_input_tokens_seen": 6068633600, |
| "step": 23150 |
| }, |
| { |
| "epoch": 0.15605477388033223, |
| "grad_norm": 0.17025263607501984, |
| "learning_rate": 0.001, |
| "loss": 3.1369, |
| "num_input_tokens_seen": 6081740800, |
| "step": 23200 |
| }, |
| { |
| "epoch": 0.15639109882403984, |
| "grad_norm": 0.17162847518920898, |
| "learning_rate": 0.001, |
| "loss": 3.1479, |
| "num_input_tokens_seen": 6094848000, |
| "step": 23250 |
| }, |
| { |
| "epoch": 0.15672742376774745, |
| "grad_norm": 0.19068972766399384, |
| "learning_rate": 0.001, |
| "loss": 3.1418, |
| "num_input_tokens_seen": 6107955200, |
| "step": 23300 |
| }, |
| { |
| "epoch": 0.15706374871145506, |
| "grad_norm": 0.20177774131298065, |
| "learning_rate": 0.001, |
| "loss": 3.1435, |
| "num_input_tokens_seen": 6121062400, |
| "step": 23350 |
| }, |
| { |
| "epoch": 0.15740007365516268, |
| "grad_norm": 0.235867440700531, |
| "learning_rate": 0.001, |
| "loss": 3.1466, |
| "num_input_tokens_seen": 6134169600, |
| "step": 23400 |
| }, |
| { |
| "epoch": 0.1577363985988703, |
| "grad_norm": 0.17313481867313385, |
| "learning_rate": 0.001, |
| "loss": 3.1509, |
| "num_input_tokens_seen": 6147276800, |
| "step": 23450 |
| }, |
| { |
| "epoch": 0.1580727235425779, |
| "grad_norm": 0.20208750665187836, |
| "learning_rate": 0.001, |
| "loss": 3.1312, |
| "num_input_tokens_seen": 6160384000, |
| "step": 23500 |
| }, |
| { |
| "epoch": 0.1580727235425779, |
| "eval_loss": 3.0457797050476074, |
| "eval_runtime": 99.8915, |
| "eval_samples_per_second": 50.054, |
| "eval_steps_per_second": 12.514, |
| "num_input_tokens_seen": 6160384000, |
| "step": 23500 |
| }, |
| { |
| "epoch": 0.1584090484862855, |
| "grad_norm": 0.1771639734506607, |
| "learning_rate": 0.001, |
| "loss": 3.1407, |
| "num_input_tokens_seen": 6173491200, |
| "step": 23550 |
| }, |
| { |
| "epoch": 0.15874537342999312, |
| "grad_norm": 0.20403757691383362, |
| "learning_rate": 0.001, |
| "loss": 3.1404, |
| "num_input_tokens_seen": 6186598400, |
| "step": 23600 |
| }, |
| { |
| "epoch": 0.15908169837370073, |
| "grad_norm": 0.19679167866706848, |
| "learning_rate": 0.001, |
| "loss": 3.1417, |
| "num_input_tokens_seen": 6199705600, |
| "step": 23650 |
| }, |
| { |
| "epoch": 0.15941802331740834, |
| "grad_norm": 0.18299609422683716, |
| "learning_rate": 0.001, |
| "loss": 3.14, |
| "num_input_tokens_seen": 6212812800, |
| "step": 23700 |
| }, |
| { |
| "epoch": 0.15975434826111595, |
| "grad_norm": 0.16773872077465057, |
| "learning_rate": 0.001, |
| "loss": 3.1326, |
| "num_input_tokens_seen": 6225920000, |
| "step": 23750 |
| }, |
| { |
| "epoch": 0.16009067320482356, |
| "grad_norm": 0.18539400398731232, |
| "learning_rate": 0.001, |
| "loss": 3.1294, |
| "num_input_tokens_seen": 6239027200, |
| "step": 23800 |
| }, |
| { |
| "epoch": 0.16042699814853117, |
| "grad_norm": 0.19088850915431976, |
| "learning_rate": 0.001, |
| "loss": 3.1297, |
| "num_input_tokens_seen": 6252134400, |
| "step": 23850 |
| }, |
| { |
| "epoch": 0.16076332309223879, |
| "grad_norm": 0.17390431463718414, |
| "learning_rate": 0.001, |
| "loss": 3.1364, |
| "num_input_tokens_seen": 6265241600, |
| "step": 23900 |
| }, |
| { |
| "epoch": 0.1610996480359464, |
| "grad_norm": 0.35694462060928345, |
| "learning_rate": 0.001, |
| "loss": 3.1519, |
| "num_input_tokens_seen": 6278348800, |
| "step": 23950 |
| }, |
| { |
| "epoch": 0.16143597297965404, |
| "grad_norm": 0.17942555248737335, |
| "learning_rate": 0.001, |
| "loss": 3.132, |
| "num_input_tokens_seen": 6291456000, |
| "step": 24000 |
| }, |
| { |
| "epoch": 0.16143597297965404, |
| "eval_loss": 3.0352118015289307, |
| "eval_runtime": 101.1582, |
| "eval_samples_per_second": 49.428, |
| "eval_steps_per_second": 12.357, |
| "num_input_tokens_seen": 6291456000, |
| "step": 24000 |
| }, |
| { |
| "epoch": 0.16177229792336165, |
| "grad_norm": 0.1748410165309906, |
| "learning_rate": 0.001, |
| "loss": 3.1385, |
| "num_input_tokens_seen": 6304563200, |
| "step": 24050 |
| }, |
| { |
| "epoch": 0.16210862286706926, |
| "grad_norm": 0.19787083566188812, |
| "learning_rate": 0.001, |
| "loss": 3.1241, |
| "num_input_tokens_seen": 6317670400, |
| "step": 24100 |
| }, |
| { |
| "epoch": 0.16244494781077687, |
| "grad_norm": 0.16369663178920746, |
| "learning_rate": 0.001, |
| "loss": 3.1402, |
| "num_input_tokens_seen": 6330777600, |
| "step": 24150 |
| }, |
| { |
| "epoch": 0.16278127275448448, |
| "grad_norm": 0.17019188404083252, |
| "learning_rate": 0.001, |
| "loss": 3.1293, |
| "num_input_tokens_seen": 6343884800, |
| "step": 24200 |
| }, |
| { |
| "epoch": 0.1631175976981921, |
| "grad_norm": 0.1666271686553955, |
| "learning_rate": 0.001, |
| "loss": 3.1218, |
| "num_input_tokens_seen": 6356992000, |
| "step": 24250 |
| }, |
| { |
| "epoch": 0.1634539226418997, |
| "grad_norm": 0.1591423600912094, |
| "learning_rate": 0.001, |
| "loss": 3.1319, |
| "num_input_tokens_seen": 6370099200, |
| "step": 24300 |
| }, |
| { |
| "epoch": 0.1637902475856073, |
| "grad_norm": 0.1642790287733078, |
| "learning_rate": 0.001, |
| "loss": 3.1319, |
| "num_input_tokens_seen": 6383206400, |
| "step": 24350 |
| }, |
| { |
| "epoch": 0.16412657252931492, |
| "grad_norm": 0.17917323112487793, |
| "learning_rate": 0.001, |
| "loss": 3.1204, |
| "num_input_tokens_seen": 6396313600, |
| "step": 24400 |
| }, |
| { |
| "epoch": 0.16446289747302253, |
| "grad_norm": 0.2367531955242157, |
| "learning_rate": 0.001, |
| "loss": 3.125, |
| "num_input_tokens_seen": 6409420800, |
| "step": 24450 |
| }, |
| { |
| "epoch": 0.16479922241673015, |
| "grad_norm": 0.175731360912323, |
| "learning_rate": 0.001, |
| "loss": 3.1358, |
| "num_input_tokens_seen": 6422528000, |
| "step": 24500 |
| }, |
| { |
| "epoch": 0.16479922241673015, |
| "eval_loss": 3.032782793045044, |
| "eval_runtime": 100.7748, |
| "eval_samples_per_second": 49.616, |
| "eval_steps_per_second": 12.404, |
| "num_input_tokens_seen": 6422528000, |
| "step": 24500 |
| }, |
| { |
| "epoch": 0.16513554736043776, |
| "grad_norm": 0.16778303682804108, |
| "learning_rate": 0.001, |
| "loss": 3.1382, |
| "num_input_tokens_seen": 6435635200, |
| "step": 24550 |
| }, |
| { |
| "epoch": 0.16547187230414537, |
| "grad_norm": 0.19019022583961487, |
| "learning_rate": 0.001, |
| "loss": 3.1328, |
| "num_input_tokens_seen": 6448742400, |
| "step": 24600 |
| }, |
| { |
| "epoch": 0.16580819724785298, |
| "grad_norm": 0.18815970420837402, |
| "learning_rate": 0.001, |
| "loss": 3.1274, |
| "num_input_tokens_seen": 6461849600, |
| "step": 24650 |
| }, |
| { |
| "epoch": 0.1661445221915606, |
| "grad_norm": 0.18299463391304016, |
| "learning_rate": 0.001, |
| "loss": 3.1258, |
| "num_input_tokens_seen": 6474956800, |
| "step": 24700 |
| }, |
| { |
| "epoch": 0.1664808471352682, |
| "grad_norm": 0.20152020454406738, |
| "learning_rate": 0.001, |
| "loss": 3.1245, |
| "num_input_tokens_seen": 6488064000, |
| "step": 24750 |
| }, |
| { |
| "epoch": 0.1668171720789758, |
| "grad_norm": 0.1800755113363266, |
| "learning_rate": 0.001, |
| "loss": 3.1332, |
| "num_input_tokens_seen": 6501171200, |
| "step": 24800 |
| }, |
| { |
| "epoch": 0.16715349702268342, |
| "grad_norm": 0.33742496371269226, |
| "learning_rate": 0.001, |
| "loss": 3.1264, |
| "num_input_tokens_seen": 6514278400, |
| "step": 24850 |
| }, |
| { |
| "epoch": 0.16748982196639106, |
| "grad_norm": 0.20022252202033997, |
| "learning_rate": 0.001, |
| "loss": 3.1414, |
| "num_input_tokens_seen": 6527385600, |
| "step": 24900 |
| }, |
| { |
| "epoch": 0.16782614691009867, |
| "grad_norm": 0.19905851781368256, |
| "learning_rate": 0.001, |
| "loss": 3.1327, |
| "num_input_tokens_seen": 6540492800, |
| "step": 24950 |
| }, |
| { |
| "epoch": 0.16816247185380628, |
| "grad_norm": 0.26300039887428284, |
| "learning_rate": 0.001, |
| "loss": 3.1231, |
| "num_input_tokens_seen": 6553600000, |
| "step": 25000 |
| }, |
| { |
| "epoch": 0.16816247185380628, |
| "eval_loss": 3.0353240966796875, |
| "eval_runtime": 100.6, |
| "eval_samples_per_second": 49.702, |
| "eval_steps_per_second": 12.425, |
| "num_input_tokens_seen": 6553600000, |
| "step": 25000 |
| }, |
| { |
| "epoch": 0.1684987967975139, |
| "grad_norm": 1.1301233768463135, |
| "learning_rate": 0.001, |
| "loss": 3.1419, |
| "num_input_tokens_seen": 6566707200, |
| "step": 25050 |
| }, |
| { |
| "epoch": 0.1688351217412215, |
| "grad_norm": 0.18019410967826843, |
| "learning_rate": 0.001, |
| "loss": 3.1514, |
| "num_input_tokens_seen": 6579814400, |
| "step": 25100 |
| }, |
| { |
| "epoch": 0.16917144668492912, |
| "grad_norm": 0.17898766696453094, |
| "learning_rate": 0.001, |
| "loss": 3.1337, |
| "num_input_tokens_seen": 6592921600, |
| "step": 25150 |
| }, |
| { |
| "epoch": 0.16950777162863673, |
| "grad_norm": 0.18393439054489136, |
| "learning_rate": 0.001, |
| "loss": 3.1313, |
| "num_input_tokens_seen": 6606028800, |
| "step": 25200 |
| }, |
| { |
| "epoch": 0.16984409657234434, |
| "grad_norm": 0.16713738441467285, |
| "learning_rate": 0.001, |
| "loss": 3.129, |
| "num_input_tokens_seen": 6619136000, |
| "step": 25250 |
| }, |
| { |
| "epoch": 0.17018042151605195, |
| "grad_norm": 0.17655207216739655, |
| "learning_rate": 0.001, |
| "loss": 3.1245, |
| "num_input_tokens_seen": 6632243200, |
| "step": 25300 |
| }, |
| { |
| "epoch": 0.17051674645975956, |
| "grad_norm": 0.20735637843608856, |
| "learning_rate": 0.001, |
| "loss": 3.1344, |
| "num_input_tokens_seen": 6645350400, |
| "step": 25350 |
| }, |
| { |
| "epoch": 0.17085307140346717, |
| "grad_norm": 0.21318195760250092, |
| "learning_rate": 0.001, |
| "loss": 3.1336, |
| "num_input_tokens_seen": 6658457600, |
| "step": 25400 |
| }, |
| { |
| "epoch": 0.17118939634717478, |
| "grad_norm": 0.1637289971113205, |
| "learning_rate": 0.001, |
| "loss": 3.1306, |
| "num_input_tokens_seen": 6671564800, |
| "step": 25450 |
| }, |
| { |
| "epoch": 0.1715257212908824, |
| "grad_norm": 0.1866239458322525, |
| "learning_rate": 0.001, |
| "loss": 3.1248, |
| "num_input_tokens_seen": 6684672000, |
| "step": 25500 |
| }, |
| { |
| "epoch": 0.1715257212908824, |
| "eval_loss": 3.025984048843384, |
| "eval_runtime": 100.8165, |
| "eval_samples_per_second": 49.595, |
| "eval_steps_per_second": 12.399, |
| "num_input_tokens_seen": 6684672000, |
| "step": 25500 |
| }, |
| { |
| "epoch": 0.17186204623459, |
| "grad_norm": 0.19653931260108948, |
| "learning_rate": 0.001, |
| "loss": 3.1346, |
| "num_input_tokens_seen": 6697779200, |
| "step": 25550 |
| }, |
| { |
| "epoch": 0.17219837117829762, |
| "grad_norm": 0.18339622020721436, |
| "learning_rate": 0.001, |
| "loss": 3.12, |
| "num_input_tokens_seen": 6710886400, |
| "step": 25600 |
| }, |
| { |
| "epoch": 0.17253469612200523, |
| "grad_norm": 0.3683246970176697, |
| "learning_rate": 0.001, |
| "loss": 3.1338, |
| "num_input_tokens_seen": 6723993600, |
| "step": 25650 |
| }, |
| { |
| "epoch": 0.17287102106571284, |
| "grad_norm": 0.17096757888793945, |
| "learning_rate": 0.001, |
| "loss": 3.1283, |
| "num_input_tokens_seen": 6737100800, |
| "step": 25700 |
| }, |
| { |
| "epoch": 0.17320734600942045, |
| "grad_norm": 0.16841623187065125, |
| "learning_rate": 0.001, |
| "loss": 3.1236, |
| "num_input_tokens_seen": 6750208000, |
| "step": 25750 |
| }, |
| { |
| "epoch": 0.1735436709531281, |
| "grad_norm": 0.18569235503673553, |
| "learning_rate": 0.001, |
| "loss": 3.1273, |
| "num_input_tokens_seen": 6763315200, |
| "step": 25800 |
| }, |
| { |
| "epoch": 0.1738799958968357, |
| "grad_norm": 0.18508999049663544, |
| "learning_rate": 0.001, |
| "loss": 3.1246, |
| "num_input_tokens_seen": 6776422400, |
| "step": 25850 |
| }, |
| { |
| "epoch": 0.1742163208405433, |
| "grad_norm": 0.189519464969635, |
| "learning_rate": 0.001, |
| "loss": 3.1239, |
| "num_input_tokens_seen": 6789529600, |
| "step": 25900 |
| }, |
| { |
| "epoch": 0.17455264578425092, |
| "grad_norm": 0.1591208577156067, |
| "learning_rate": 0.001, |
| "loss": 3.1198, |
| "num_input_tokens_seen": 6802636800, |
| "step": 25950 |
| }, |
| { |
| "epoch": 0.17488897072795853, |
| "grad_norm": 0.199269101023674, |
| "learning_rate": 0.001, |
| "loss": 3.118, |
| "num_input_tokens_seen": 6815744000, |
| "step": 26000 |
| }, |
| { |
| "epoch": 0.17488897072795853, |
| "eval_loss": 3.019541025161743, |
| "eval_runtime": 101.0314, |
| "eval_samples_per_second": 49.49, |
| "eval_steps_per_second": 12.372, |
| "num_input_tokens_seen": 6815744000, |
| "step": 26000 |
| }, |
| { |
| "epoch": 0.17522529567166614, |
| "grad_norm": 0.17492325603961945, |
| "learning_rate": 0.001, |
| "loss": 3.1093, |
| "num_input_tokens_seen": 6828851200, |
| "step": 26050 |
| }, |
| { |
| "epoch": 0.17556162061537375, |
| "grad_norm": 0.17826683819293976, |
| "learning_rate": 0.001, |
| "loss": 3.1285, |
| "num_input_tokens_seen": 6841958400, |
| "step": 26100 |
| }, |
| { |
| "epoch": 0.17589794555908136, |
| "grad_norm": 0.17716389894485474, |
| "learning_rate": 0.001, |
| "loss": 3.1141, |
| "num_input_tokens_seen": 6855065600, |
| "step": 26150 |
| }, |
| { |
| "epoch": 0.17623427050278898, |
| "grad_norm": 0.18649104237556458, |
| "learning_rate": 0.001, |
| "loss": 3.1128, |
| "num_input_tokens_seen": 6868172800, |
| "step": 26200 |
| }, |
| { |
| "epoch": 0.1765705954464966, |
| "grad_norm": 0.4175710678100586, |
| "learning_rate": 0.001, |
| "loss": 3.1283, |
| "num_input_tokens_seen": 6881280000, |
| "step": 26250 |
| }, |
| { |
| "epoch": 0.1769069203902042, |
| "grad_norm": 0.2275037169456482, |
| "learning_rate": 0.001, |
| "loss": 3.148, |
| "num_input_tokens_seen": 6894387200, |
| "step": 26300 |
| }, |
| { |
| "epoch": 0.1772432453339118, |
| "grad_norm": 0.42409747838974, |
| "learning_rate": 0.001, |
| "loss": 3.1338, |
| "num_input_tokens_seen": 6907494400, |
| "step": 26350 |
| }, |
| { |
| "epoch": 0.17757957027761942, |
| "grad_norm": 0.23025737702846527, |
| "learning_rate": 0.001, |
| "loss": 3.1451, |
| "num_input_tokens_seen": 6920601600, |
| "step": 26400 |
| }, |
| { |
| "epoch": 0.17791589522132703, |
| "grad_norm": 0.20386695861816406, |
| "learning_rate": 0.001, |
| "loss": 3.1396, |
| "num_input_tokens_seen": 6933708800, |
| "step": 26450 |
| }, |
| { |
| "epoch": 0.17825222016503464, |
| "grad_norm": 0.20394697785377502, |
| "learning_rate": 0.001, |
| "loss": 3.1308, |
| "num_input_tokens_seen": 6946816000, |
| "step": 26500 |
| }, |
| { |
| "epoch": 0.17825222016503464, |
| "eval_loss": 3.02968430519104, |
| "eval_runtime": 100.5354, |
| "eval_samples_per_second": 49.734, |
| "eval_steps_per_second": 12.433, |
| "num_input_tokens_seen": 6946816000, |
| "step": 26500 |
| }, |
| { |
| "epoch": 0.17858854510874225, |
| "grad_norm": 0.19505399465560913, |
| "learning_rate": 0.001, |
| "loss": 3.1229, |
| "num_input_tokens_seen": 6959923200, |
| "step": 26550 |
| }, |
| { |
| "epoch": 0.17892487005244986, |
| "grad_norm": 0.17783001065254211, |
| "learning_rate": 0.001, |
| "loss": 3.108, |
| "num_input_tokens_seen": 6973030400, |
| "step": 26600 |
| }, |
| { |
| "epoch": 0.17926119499615747, |
| "grad_norm": 0.16989105939865112, |
| "learning_rate": 0.001, |
| "loss": 3.1252, |
| "num_input_tokens_seen": 6986137600, |
| "step": 26650 |
| }, |
| { |
| "epoch": 0.1795975199398651, |
| "grad_norm": 0.1939496099948883, |
| "learning_rate": 0.001, |
| "loss": 3.1234, |
| "num_input_tokens_seen": 6999244800, |
| "step": 26700 |
| }, |
| { |
| "epoch": 0.17993384488357272, |
| "grad_norm": 0.1649375557899475, |
| "learning_rate": 0.001, |
| "loss": 3.1156, |
| "num_input_tokens_seen": 7012352000, |
| "step": 26750 |
| }, |
| { |
| "epoch": 0.18027016982728034, |
| "grad_norm": 0.1829315572977066, |
| "learning_rate": 0.001, |
| "loss": 3.1209, |
| "num_input_tokens_seen": 7025459200, |
| "step": 26800 |
| }, |
| { |
| "epoch": 0.18060649477098795, |
| "grad_norm": 0.182273730635643, |
| "learning_rate": 0.001, |
| "loss": 3.1277, |
| "num_input_tokens_seen": 7038566400, |
| "step": 26850 |
| }, |
| { |
| "epoch": 0.18094281971469556, |
| "grad_norm": 0.1677001416683197, |
| "learning_rate": 0.001, |
| "loss": 3.1132, |
| "num_input_tokens_seen": 7051673600, |
| "step": 26900 |
| }, |
| { |
| "epoch": 0.18127914465840317, |
| "grad_norm": 0.2254924178123474, |
| "learning_rate": 0.001, |
| "loss": 3.1254, |
| "num_input_tokens_seen": 7064780800, |
| "step": 26950 |
| }, |
| { |
| "epoch": 0.18161546960211078, |
| "grad_norm": 0.2008505016565323, |
| "learning_rate": 0.001, |
| "loss": 3.1286, |
| "num_input_tokens_seen": 7077888000, |
| "step": 27000 |
| }, |
| { |
| "epoch": 0.18161546960211078, |
| "eval_loss": 3.0181450843811035, |
| "eval_runtime": 100.7921, |
| "eval_samples_per_second": 49.607, |
| "eval_steps_per_second": 12.402, |
| "num_input_tokens_seen": 7077888000, |
| "step": 27000 |
| }, |
| { |
| "epoch": 0.1819517945458184, |
| "grad_norm": 0.172062486410141, |
| "learning_rate": 0.001, |
| "loss": 3.1125, |
| "num_input_tokens_seen": 7090995200, |
| "step": 27050 |
| }, |
| { |
| "epoch": 0.182288119489526, |
| "grad_norm": 0.17802311480045319, |
| "learning_rate": 0.001, |
| "loss": 3.1145, |
| "num_input_tokens_seen": 7104102400, |
| "step": 27100 |
| }, |
| { |
| "epoch": 0.1826244444332336, |
| "grad_norm": 1.872890591621399, |
| "learning_rate": 0.001, |
| "loss": 3.1203, |
| "num_input_tokens_seen": 7117209600, |
| "step": 27150 |
| }, |
| { |
| "epoch": 0.18296076937694122, |
| "grad_norm": 0.1898074597120285, |
| "learning_rate": 0.001, |
| "loss": 3.1246, |
| "num_input_tokens_seen": 7130316800, |
| "step": 27200 |
| }, |
| { |
| "epoch": 0.18329709432064883, |
| "grad_norm": 0.19125746190547943, |
| "learning_rate": 0.001, |
| "loss": 3.1138, |
| "num_input_tokens_seen": 7143424000, |
| "step": 27250 |
| }, |
| { |
| "epoch": 0.18363341926435645, |
| "grad_norm": 0.17721381783485413, |
| "learning_rate": 0.001, |
| "loss": 3.1181, |
| "num_input_tokens_seen": 7156531200, |
| "step": 27300 |
| }, |
| { |
| "epoch": 0.18396974420806406, |
| "grad_norm": 0.26583337783813477, |
| "learning_rate": 0.001, |
| "loss": 3.1067, |
| "num_input_tokens_seen": 7169638400, |
| "step": 27350 |
| }, |
| { |
| "epoch": 0.18430606915177167, |
| "grad_norm": 0.18157972395420074, |
| "learning_rate": 0.001, |
| "loss": 3.1266, |
| "num_input_tokens_seen": 7182745600, |
| "step": 27400 |
| }, |
| { |
| "epoch": 0.18464239409547928, |
| "grad_norm": 0.17585282027721405, |
| "learning_rate": 0.001, |
| "loss": 3.1124, |
| "num_input_tokens_seen": 7195852800, |
| "step": 27450 |
| }, |
| { |
| "epoch": 0.1849787190391869, |
| "grad_norm": 0.23974797129631042, |
| "learning_rate": 0.001, |
| "loss": 3.1231, |
| "num_input_tokens_seen": 7208960000, |
| "step": 27500 |
| }, |
| { |
| "epoch": 0.1849787190391869, |
| "eval_loss": 3.023569345474243, |
| "eval_runtime": 100.613, |
| "eval_samples_per_second": 49.695, |
| "eval_steps_per_second": 12.424, |
| "num_input_tokens_seen": 7208960000, |
| "step": 27500 |
| }, |
| { |
| "epoch": 0.1853150439828945, |
| "grad_norm": 0.2258712202310562, |
| "learning_rate": 0.001, |
| "loss": 3.1415, |
| "num_input_tokens_seen": 7222067200, |
| "step": 27550 |
| }, |
| { |
| "epoch": 0.18565136892660214, |
| "grad_norm": 0.19764864444732666, |
| "learning_rate": 0.001, |
| "loss": 3.1207, |
| "num_input_tokens_seen": 7235174400, |
| "step": 27600 |
| }, |
| { |
| "epoch": 0.18598769387030975, |
| "grad_norm": 0.20053404569625854, |
| "learning_rate": 0.001, |
| "loss": 3.1252, |
| "num_input_tokens_seen": 7248281600, |
| "step": 27650 |
| }, |
| { |
| "epoch": 0.18632401881401736, |
| "grad_norm": 0.20705857872962952, |
| "learning_rate": 0.001, |
| "loss": 3.1296, |
| "num_input_tokens_seen": 7261388800, |
| "step": 27700 |
| }, |
| { |
| "epoch": 0.18666034375772497, |
| "grad_norm": 0.17856301367282867, |
| "learning_rate": 0.001, |
| "loss": 3.1141, |
| "num_input_tokens_seen": 7274496000, |
| "step": 27750 |
| }, |
| { |
| "epoch": 0.18699666870143258, |
| "grad_norm": 0.28354203701019287, |
| "learning_rate": 0.001, |
| "loss": 3.1263, |
| "num_input_tokens_seen": 7287603200, |
| "step": 27800 |
| }, |
| { |
| "epoch": 0.1873329936451402, |
| "grad_norm": 0.25223788619041443, |
| "learning_rate": 0.001, |
| "loss": 3.122, |
| "num_input_tokens_seen": 7300710400, |
| "step": 27850 |
| }, |
| { |
| "epoch": 0.1876693185888478, |
| "grad_norm": 0.6653568148612976, |
| "learning_rate": 0.001, |
| "loss": 3.1434, |
| "num_input_tokens_seen": 7313817600, |
| "step": 27900 |
| }, |
| { |
| "epoch": 0.18800564353255542, |
| "grad_norm": 0.44238439202308655, |
| "learning_rate": 0.001, |
| "loss": 3.1306, |
| "num_input_tokens_seen": 7326924800, |
| "step": 27950 |
| }, |
| { |
| "epoch": 0.18834196847626303, |
| "grad_norm": 0.2601284980773926, |
| "learning_rate": 0.001, |
| "loss": 3.1399, |
| "num_input_tokens_seen": 7340032000, |
| "step": 28000 |
| }, |
| { |
| "epoch": 0.18834196847626303, |
| "eval_loss": 3.0279700756073, |
| "eval_runtime": 101.2218, |
| "eval_samples_per_second": 49.396, |
| "eval_steps_per_second": 12.349, |
| "num_input_tokens_seen": 7340032000, |
| "step": 28000 |
| }, |
| { |
| "epoch": 0.18867829341997064, |
| "grad_norm": 0.22075016796588898, |
| "learning_rate": 0.001, |
| "loss": 3.1316, |
| "num_input_tokens_seen": 7353139200, |
| "step": 28050 |
| }, |
| { |
| "epoch": 0.18901461836367825, |
| "grad_norm": 0.25096815824508667, |
| "learning_rate": 0.001, |
| "loss": 3.1188, |
| "num_input_tokens_seen": 7366246400, |
| "step": 28100 |
| }, |
| { |
| "epoch": 0.18935094330738586, |
| "grad_norm": 0.1836758553981781, |
| "learning_rate": 0.001, |
| "loss": 3.1159, |
| "num_input_tokens_seen": 7379353600, |
| "step": 28150 |
| }, |
| { |
| "epoch": 0.18968726825109347, |
| "grad_norm": 0.24736745655536652, |
| "learning_rate": 0.001, |
| "loss": 3.1068, |
| "num_input_tokens_seen": 7392460800, |
| "step": 28200 |
| }, |
| { |
| "epoch": 0.19002359319480108, |
| "grad_norm": 0.18398351967334747, |
| "learning_rate": 0.001, |
| "loss": 3.1122, |
| "num_input_tokens_seen": 7405568000, |
| "step": 28250 |
| }, |
| { |
| "epoch": 0.1903599181385087, |
| "grad_norm": 0.2027016431093216, |
| "learning_rate": 0.001, |
| "loss": 3.1086, |
| "num_input_tokens_seen": 7418675200, |
| "step": 28300 |
| }, |
| { |
| "epoch": 0.1906962430822163, |
| "grad_norm": 0.18662536144256592, |
| "learning_rate": 0.001, |
| "loss": 3.1165, |
| "num_input_tokens_seen": 7431782400, |
| "step": 28350 |
| }, |
| { |
| "epoch": 0.19103256802592392, |
| "grad_norm": 0.1824251115322113, |
| "learning_rate": 0.001, |
| "loss": 3.1179, |
| "num_input_tokens_seen": 7444889600, |
| "step": 28400 |
| }, |
| { |
| "epoch": 0.19136889296963153, |
| "grad_norm": 0.17664241790771484, |
| "learning_rate": 0.001, |
| "loss": 3.1114, |
| "num_input_tokens_seen": 7457996800, |
| "step": 28450 |
| }, |
| { |
| "epoch": 0.19170521791333917, |
| "grad_norm": 0.17245933413505554, |
| "learning_rate": 0.001, |
| "loss": 3.1113, |
| "num_input_tokens_seen": 7471104000, |
| "step": 28500 |
| }, |
| { |
| "epoch": 0.19170521791333917, |
| "eval_loss": 3.0132832527160645, |
| "eval_runtime": 100.8874, |
| "eval_samples_per_second": 49.56, |
| "eval_steps_per_second": 12.39, |
| "num_input_tokens_seen": 7471104000, |
| "step": 28500 |
| }, |
| { |
| "epoch": 0.19204154285704678, |
| "grad_norm": 0.20906178653240204, |
| "learning_rate": 0.001, |
| "loss": 3.1229, |
| "num_input_tokens_seen": 7484211200, |
| "step": 28550 |
| }, |
| { |
| "epoch": 0.1923778678007544, |
| "grad_norm": 0.19940024614334106, |
| "learning_rate": 0.001, |
| "loss": 3.1214, |
| "num_input_tokens_seen": 7497318400, |
| "step": 28600 |
| }, |
| { |
| "epoch": 0.192714192744462, |
| "grad_norm": 0.20571599900722504, |
| "learning_rate": 0.001, |
| "loss": 3.1124, |
| "num_input_tokens_seen": 7510425600, |
| "step": 28650 |
| }, |
| { |
| "epoch": 0.1930505176881696, |
| "grad_norm": 0.20708389580249786, |
| "learning_rate": 0.001, |
| "loss": 3.1336, |
| "num_input_tokens_seen": 7523532800, |
| "step": 28700 |
| }, |
| { |
| "epoch": 0.19338684263187722, |
| "grad_norm": 0.22445373237133026, |
| "learning_rate": 0.001, |
| "loss": 3.1157, |
| "num_input_tokens_seen": 7536640000, |
| "step": 28750 |
| }, |
| { |
| "epoch": 0.19372316757558483, |
| "grad_norm": 0.19508902728557587, |
| "learning_rate": 0.001, |
| "loss": 3.1248, |
| "num_input_tokens_seen": 7549747200, |
| "step": 28800 |
| }, |
| { |
| "epoch": 0.19405949251929244, |
| "grad_norm": 0.17587284743785858, |
| "learning_rate": 0.001, |
| "loss": 3.126, |
| "num_input_tokens_seen": 7562854400, |
| "step": 28850 |
| }, |
| { |
| "epoch": 0.19439581746300005, |
| "grad_norm": 0.18851327896118164, |
| "learning_rate": 0.001, |
| "loss": 3.1128, |
| "num_input_tokens_seen": 7575961600, |
| "step": 28900 |
| }, |
| { |
| "epoch": 0.19473214240670766, |
| "grad_norm": 0.1922932267189026, |
| "learning_rate": 0.001, |
| "loss": 3.1244, |
| "num_input_tokens_seen": 7589068800, |
| "step": 28950 |
| }, |
| { |
| "epoch": 0.19506846735041528, |
| "grad_norm": 0.21472705900669098, |
| "learning_rate": 0.001, |
| "loss": 3.1287, |
| "num_input_tokens_seen": 7602176000, |
| "step": 29000 |
| }, |
| { |
| "epoch": 0.19506846735041528, |
| "eval_loss": 3.0183699131011963, |
| "eval_runtime": 100.5473, |
| "eval_samples_per_second": 49.728, |
| "eval_steps_per_second": 12.432, |
| "num_input_tokens_seen": 7602176000, |
| "step": 29000 |
| }, |
| { |
| "epoch": 0.1954047922941229, |
| "grad_norm": 0.4608127474784851, |
| "learning_rate": 0.001, |
| "loss": 3.1279, |
| "num_input_tokens_seen": 7615283200, |
| "step": 29050 |
| }, |
| { |
| "epoch": 0.1957411172378305, |
| "grad_norm": 0.19692400097846985, |
| "learning_rate": 0.001, |
| "loss": 3.1227, |
| "num_input_tokens_seen": 7628390400, |
| "step": 29100 |
| }, |
| { |
| "epoch": 0.1960774421815381, |
| "grad_norm": 0.17576786875724792, |
| "learning_rate": 0.001, |
| "loss": 3.1082, |
| "num_input_tokens_seen": 7641497600, |
| "step": 29150 |
| }, |
| { |
| "epoch": 0.19641376712524572, |
| "grad_norm": 0.3715643584728241, |
| "learning_rate": 0.001, |
| "loss": 3.1136, |
| "num_input_tokens_seen": 7654604800, |
| "step": 29200 |
| }, |
| { |
| "epoch": 0.19675009206895333, |
| "grad_norm": 0.19605587422847748, |
| "learning_rate": 0.001, |
| "loss": 3.1233, |
| "num_input_tokens_seen": 7667712000, |
| "step": 29250 |
| }, |
| { |
| "epoch": 0.19708641701266094, |
| "grad_norm": 0.18321235477924347, |
| "learning_rate": 0.001, |
| "loss": 3.1127, |
| "num_input_tokens_seen": 7680819200, |
| "step": 29300 |
| }, |
| { |
| "epoch": 0.19742274195636855, |
| "grad_norm": 0.19760318100452423, |
| "learning_rate": 0.001, |
| "loss": 3.1074, |
| "num_input_tokens_seen": 7693926400, |
| "step": 29350 |
| }, |
| { |
| "epoch": 0.1977590669000762, |
| "grad_norm": 0.2162732481956482, |
| "learning_rate": 0.001, |
| "loss": 3.1126, |
| "num_input_tokens_seen": 7707033600, |
| "step": 29400 |
| }, |
| { |
| "epoch": 0.1980953918437838, |
| "grad_norm": 0.20082025229930878, |
| "learning_rate": 0.001, |
| "loss": 3.1111, |
| "num_input_tokens_seen": 7720140800, |
| "step": 29450 |
| }, |
| { |
| "epoch": 0.1984317167874914, |
| "grad_norm": 0.1623256504535675, |
| "learning_rate": 0.001, |
| "loss": 3.108, |
| "num_input_tokens_seen": 7733248000, |
| "step": 29500 |
| }, |
| { |
| "epoch": 0.1984317167874914, |
| "eval_loss": 3.0064518451690674, |
| "eval_runtime": 101.1359, |
| "eval_samples_per_second": 49.438, |
| "eval_steps_per_second": 12.36, |
| "num_input_tokens_seen": 7733248000, |
| "step": 29500 |
| }, |
| { |
| "epoch": 0.19876804173119902, |
| "grad_norm": 0.22083748877048492, |
| "learning_rate": 0.001, |
| "loss": 3.1171, |
| "num_input_tokens_seen": 7746355200, |
| "step": 29550 |
| }, |
| { |
| "epoch": 0.19910436667490664, |
| "grad_norm": 0.23460319638252258, |
| "learning_rate": 0.001, |
| "loss": 3.1199, |
| "num_input_tokens_seen": 7759462400, |
| "step": 29600 |
| }, |
| { |
| "epoch": 0.19944069161861425, |
| "grad_norm": 0.22132454812526703, |
| "learning_rate": 0.001, |
| "loss": 3.1058, |
| "num_input_tokens_seen": 7772569600, |
| "step": 29650 |
| }, |
| { |
| "epoch": 0.19977701656232186, |
| "grad_norm": 0.18013770878314972, |
| "learning_rate": 0.001, |
| "loss": 3.1193, |
| "num_input_tokens_seen": 7785676800, |
| "step": 29700 |
| }, |
| { |
| "epoch": 0.20011334150602947, |
| "grad_norm": 0.17522746324539185, |
| "learning_rate": 0.001, |
| "loss": 3.1017, |
| "num_input_tokens_seen": 7798784000, |
| "step": 29750 |
| }, |
| { |
| "epoch": 0.20044966644973708, |
| "grad_norm": 0.18989771604537964, |
| "learning_rate": 0.001, |
| "loss": 3.1029, |
| "num_input_tokens_seen": 7811891200, |
| "step": 29800 |
| }, |
| { |
| "epoch": 0.2007859913934447, |
| "grad_norm": 0.38332825899124146, |
| "learning_rate": 0.001, |
| "loss": 3.11, |
| "num_input_tokens_seen": 7824998400, |
| "step": 29850 |
| }, |
| { |
| "epoch": 0.2011223163371523, |
| "grad_norm": 0.1822918802499771, |
| "learning_rate": 0.001, |
| "loss": 3.1018, |
| "num_input_tokens_seen": 7838105600, |
| "step": 29900 |
| }, |
| { |
| "epoch": 0.2014586412808599, |
| "grad_norm": 0.1707374006509781, |
| "learning_rate": 0.001, |
| "loss": 3.1077, |
| "num_input_tokens_seen": 7851212800, |
| "step": 29950 |
| }, |
| { |
| "epoch": 0.20179496622456752, |
| "grad_norm": 0.32529768347740173, |
| "learning_rate": 0.001, |
| "loss": 3.1074, |
| "num_input_tokens_seen": 7864320000, |
| "step": 30000 |
| }, |
| { |
| "epoch": 0.20179496622456752, |
| "eval_loss": 3.0052828788757324, |
| "eval_runtime": 101.5526, |
| "eval_samples_per_second": 49.236, |
| "eval_steps_per_second": 12.309, |
| "num_input_tokens_seen": 7864320000, |
| "step": 30000 |
| }, |
| { |
| "epoch": 0.20213129116827513, |
| "grad_norm": 0.3476233184337616, |
| "learning_rate": 0.001, |
| "loss": 3.1145, |
| "num_input_tokens_seen": 7877427200, |
| "step": 30050 |
| }, |
| { |
| "epoch": 0.20246761611198275, |
| "grad_norm": 0.18626414239406586, |
| "learning_rate": 0.001, |
| "loss": 3.1066, |
| "num_input_tokens_seen": 7890534400, |
| "step": 30100 |
| }, |
| { |
| "epoch": 0.20280394105569036, |
| "grad_norm": 0.254221647977829, |
| "learning_rate": 0.001, |
| "loss": 3.1092, |
| "num_input_tokens_seen": 7903641600, |
| "step": 30150 |
| }, |
| { |
| "epoch": 0.20314026599939797, |
| "grad_norm": 0.22347959876060486, |
| "learning_rate": 0.001, |
| "loss": 3.1168, |
| "num_input_tokens_seen": 7916748800, |
| "step": 30200 |
| }, |
| { |
| "epoch": 0.20347659094310558, |
| "grad_norm": 0.22947949171066284, |
| "learning_rate": 0.001, |
| "loss": 3.1181, |
| "num_input_tokens_seen": 7929856000, |
| "step": 30250 |
| }, |
| { |
| "epoch": 0.2038129158868132, |
| "grad_norm": 0.18353967368602753, |
| "learning_rate": 0.001, |
| "loss": 3.1154, |
| "num_input_tokens_seen": 7942963200, |
| "step": 30300 |
| }, |
| { |
| "epoch": 0.20414924083052083, |
| "grad_norm": 0.1840088963508606, |
| "learning_rate": 0.001, |
| "loss": 3.1145, |
| "num_input_tokens_seen": 7956070400, |
| "step": 30350 |
| }, |
| { |
| "epoch": 0.20448556577422844, |
| "grad_norm": 0.21340833604335785, |
| "learning_rate": 0.001, |
| "loss": 3.1175, |
| "num_input_tokens_seen": 7969177600, |
| "step": 30400 |
| }, |
| { |
| "epoch": 0.20482189071793605, |
| "grad_norm": 0.22054563462734222, |
| "learning_rate": 0.001, |
| "loss": 3.1082, |
| "num_input_tokens_seen": 7982284800, |
| "step": 30450 |
| }, |
| { |
| "epoch": 0.20515821566164366, |
| "grad_norm": 0.23745377361774445, |
| "learning_rate": 0.001, |
| "loss": 3.1155, |
| "num_input_tokens_seen": 7995392000, |
| "step": 30500 |
| }, |
| { |
| "epoch": 0.20515821566164366, |
| "eval_loss": 3.0057761669158936, |
| "eval_runtime": 111.9719, |
| "eval_samples_per_second": 44.654, |
| "eval_steps_per_second": 11.164, |
| "num_input_tokens_seen": 7995392000, |
| "step": 30500 |
| }, |
| { |
| "epoch": 0.20549454060535127, |
| "grad_norm": 0.18189583718776703, |
| "learning_rate": 0.001, |
| "loss": 3.119, |
| "num_input_tokens_seen": 8008499200, |
| "step": 30550 |
| }, |
| { |
| "epoch": 0.20583086554905888, |
| "grad_norm": 0.23735597729682922, |
| "learning_rate": 0.001, |
| "loss": 3.1114, |
| "num_input_tokens_seen": 8021606400, |
| "step": 30600 |
| }, |
| { |
| "epoch": 0.2061671904927665, |
| "grad_norm": 0.6922980546951294, |
| "learning_rate": 0.001, |
| "loss": 3.1155, |
| "num_input_tokens_seen": 8034713600, |
| "step": 30650 |
| }, |
| { |
| "epoch": 0.2065035154364741, |
| "grad_norm": 0.277959406375885, |
| "learning_rate": 0.001, |
| "loss": 3.113, |
| "num_input_tokens_seen": 8047820800, |
| "step": 30700 |
| }, |
| { |
| "epoch": 0.20683984038018172, |
| "grad_norm": 0.20879347622394562, |
| "learning_rate": 0.001, |
| "loss": 3.1052, |
| "num_input_tokens_seen": 8060928000, |
| "step": 30750 |
| }, |
| { |
| "epoch": 0.20717616532388933, |
| "grad_norm": 0.2380591332912445, |
| "learning_rate": 0.001, |
| "loss": 3.0957, |
| "num_input_tokens_seen": 8074035200, |
| "step": 30800 |
| }, |
| { |
| "epoch": 0.20751249026759694, |
| "grad_norm": 0.19781485199928284, |
| "learning_rate": 0.001, |
| "loss": 3.1043, |
| "num_input_tokens_seen": 8087142400, |
| "step": 30850 |
| }, |
| { |
| "epoch": 0.20784881521130455, |
| "grad_norm": 0.20070037245750427, |
| "learning_rate": 0.001, |
| "loss": 3.1064, |
| "num_input_tokens_seen": 8100249600, |
| "step": 30900 |
| }, |
| { |
| "epoch": 0.20818514015501216, |
| "grad_norm": 0.1823301464319229, |
| "learning_rate": 0.001, |
| "loss": 3.0957, |
| "num_input_tokens_seen": 8113356800, |
| "step": 30950 |
| }, |
| { |
| "epoch": 0.20852146509871977, |
| "grad_norm": 0.21749699115753174, |
| "learning_rate": 0.001, |
| "loss": 3.0952, |
| "num_input_tokens_seen": 8126464000, |
| "step": 31000 |
| }, |
| { |
| "epoch": 0.20852146509871977, |
| "eval_loss": 3.003377676010132, |
| "eval_runtime": 101.0747, |
| "eval_samples_per_second": 49.468, |
| "eval_steps_per_second": 12.367, |
| "num_input_tokens_seen": 8126464000, |
| "step": 31000 |
| }, |
| { |
| "epoch": 0.20885779004242738, |
| "grad_norm": 0.189363494515419, |
| "learning_rate": 0.001, |
| "loss": 3.0965, |
| "num_input_tokens_seen": 8139571200, |
| "step": 31050 |
| }, |
| { |
| "epoch": 0.209194114986135, |
| "grad_norm": 0.22209693491458893, |
| "learning_rate": 0.001, |
| "loss": 3.0999, |
| "num_input_tokens_seen": 8152678400, |
| "step": 31100 |
| }, |
| { |
| "epoch": 0.2095304399298426, |
| "grad_norm": 0.2229391485452652, |
| "learning_rate": 0.001, |
| "loss": 3.1051, |
| "num_input_tokens_seen": 8165785600, |
| "step": 31150 |
| }, |
| { |
| "epoch": 0.20986676487355022, |
| "grad_norm": 0.29246941208839417, |
| "learning_rate": 0.001, |
| "loss": 3.1091, |
| "num_input_tokens_seen": 8178892800, |
| "step": 31200 |
| }, |
| { |
| "epoch": 0.21020308981725785, |
| "grad_norm": 0.20801013708114624, |
| "learning_rate": 0.001, |
| "loss": 3.1203, |
| "num_input_tokens_seen": 8192000000, |
| "step": 31250 |
| }, |
| { |
| "epoch": 0.21053941476096547, |
| "grad_norm": 0.20411519706249237, |
| "learning_rate": 0.001, |
| "loss": 3.0988, |
| "num_input_tokens_seen": 8205107200, |
| "step": 31300 |
| }, |
| { |
| "epoch": 0.21087573970467308, |
| "grad_norm": 0.20220200717449188, |
| "learning_rate": 0.001, |
| "loss": 3.0999, |
| "num_input_tokens_seen": 8218214400, |
| "step": 31350 |
| }, |
| { |
| "epoch": 0.2112120646483807, |
| "grad_norm": 0.2107418328523636, |
| "learning_rate": 0.001, |
| "loss": 3.1052, |
| "num_input_tokens_seen": 8231321600, |
| "step": 31400 |
| }, |
| { |
| "epoch": 0.2115483895920883, |
| "grad_norm": 0.2079913169145584, |
| "learning_rate": 0.001, |
| "loss": 3.1095, |
| "num_input_tokens_seen": 8244428800, |
| "step": 31450 |
| }, |
| { |
| "epoch": 0.2118847145357959, |
| "grad_norm": 0.20990462601184845, |
| "learning_rate": 0.001, |
| "loss": 3.1095, |
| "num_input_tokens_seen": 8257536000, |
| "step": 31500 |
| }, |
| { |
| "epoch": 0.2118847145357959, |
| "eval_loss": 3.002542018890381, |
| "eval_runtime": 102.5542, |
| "eval_samples_per_second": 48.755, |
| "eval_steps_per_second": 12.189, |
| "num_input_tokens_seen": 8257536000, |
| "step": 31500 |
| }, |
| { |
| "epoch": 0.21222103947950352, |
| "grad_norm": 0.3199199140071869, |
| "learning_rate": 0.001, |
| "loss": 3.1193, |
| "num_input_tokens_seen": 8270643200, |
| "step": 31550 |
| }, |
| { |
| "epoch": 0.21255736442321113, |
| "grad_norm": 0.3326248824596405, |
| "learning_rate": 0.001, |
| "loss": 3.1398, |
| "num_input_tokens_seen": 8283750400, |
| "step": 31600 |
| }, |
| { |
| "epoch": 0.21289368936691874, |
| "grad_norm": 0.22599756717681885, |
| "learning_rate": 0.001, |
| "loss": 3.1192, |
| "num_input_tokens_seen": 8296857600, |
| "step": 31650 |
| }, |
| { |
| "epoch": 0.21323001431062635, |
| "grad_norm": 0.24016565084457397, |
| "learning_rate": 0.001, |
| "loss": 3.1208, |
| "num_input_tokens_seen": 8309964800, |
| "step": 31700 |
| }, |
| { |
| "epoch": 0.21356633925433396, |
| "grad_norm": 0.2414240539073944, |
| "learning_rate": 0.001, |
| "loss": 3.1188, |
| "num_input_tokens_seen": 8323072000, |
| "step": 31750 |
| }, |
| { |
| "epoch": 0.21390266419804158, |
| "grad_norm": 0.21480241417884827, |
| "learning_rate": 0.001, |
| "loss": 3.1183, |
| "num_input_tokens_seen": 8336179200, |
| "step": 31800 |
| }, |
| { |
| "epoch": 0.2142389891417492, |
| "grad_norm": 0.23109237849712372, |
| "learning_rate": 0.001, |
| "loss": 3.117, |
| "num_input_tokens_seen": 8349286400, |
| "step": 31850 |
| }, |
| { |
| "epoch": 0.2145753140854568, |
| "grad_norm": 1.8171563148498535, |
| "learning_rate": 0.001, |
| "loss": 3.1133, |
| "num_input_tokens_seen": 8362393600, |
| "step": 31900 |
| }, |
| { |
| "epoch": 0.2149116390291644, |
| "grad_norm": 0.19770418107509613, |
| "learning_rate": 0.001, |
| "loss": 3.1004, |
| "num_input_tokens_seen": 8375500800, |
| "step": 31950 |
| }, |
| { |
| "epoch": 0.21524796397287202, |
| "grad_norm": 0.17420834302902222, |
| "learning_rate": 0.001, |
| "loss": 3.1201, |
| "num_input_tokens_seen": 8388608000, |
| "step": 32000 |
| }, |
| { |
| "epoch": 0.21524796397287202, |
| "eval_loss": 2.999030113220215, |
| "eval_runtime": 101.4799, |
| "eval_samples_per_second": 49.271, |
| "eval_steps_per_second": 12.318, |
| "num_input_tokens_seen": 8388608000, |
| "step": 32000 |
| }, |
| { |
| "epoch": 0.21558428891657963, |
| "grad_norm": 0.17642393708229065, |
| "learning_rate": 0.001, |
| "loss": 3.0933, |
| "num_input_tokens_seen": 8401715200, |
| "step": 32050 |
| }, |
| { |
| "epoch": 0.21592061386028724, |
| "grad_norm": 0.17682494223117828, |
| "learning_rate": 0.001, |
| "loss": 3.0944, |
| "num_input_tokens_seen": 8414822400, |
| "step": 32100 |
| }, |
| { |
| "epoch": 0.21625693880399488, |
| "grad_norm": 0.18188636004924774, |
| "learning_rate": 0.001, |
| "loss": 3.0952, |
| "num_input_tokens_seen": 8427929600, |
| "step": 32150 |
| }, |
| { |
| "epoch": 0.2165932637477025, |
| "grad_norm": 0.19842028617858887, |
| "learning_rate": 0.001, |
| "loss": 3.0952, |
| "num_input_tokens_seen": 8441036800, |
| "step": 32200 |
| }, |
| { |
| "epoch": 0.2169295886914101, |
| "grad_norm": 0.5376595854759216, |
| "learning_rate": 0.001, |
| "loss": 3.0995, |
| "num_input_tokens_seen": 8454144000, |
| "step": 32250 |
| }, |
| { |
| "epoch": 0.2172659136351177, |
| "grad_norm": 0.1966828554868698, |
| "learning_rate": 0.001, |
| "loss": 3.0998, |
| "num_input_tokens_seen": 8467251200, |
| "step": 32300 |
| }, |
| { |
| "epoch": 0.21760223857882532, |
| "grad_norm": 0.16826917231082916, |
| "learning_rate": 0.001, |
| "loss": 3.1058, |
| "num_input_tokens_seen": 8480358400, |
| "step": 32350 |
| }, |
| { |
| "epoch": 0.21793856352253294, |
| "grad_norm": 0.17534971237182617, |
| "learning_rate": 0.001, |
| "loss": 3.0989, |
| "num_input_tokens_seen": 8493465600, |
| "step": 32400 |
| }, |
| { |
| "epoch": 0.21827488846624055, |
| "grad_norm": 0.18534857034683228, |
| "learning_rate": 0.001, |
| "loss": 3.1006, |
| "num_input_tokens_seen": 8506572800, |
| "step": 32450 |
| }, |
| { |
| "epoch": 0.21861121340994816, |
| "grad_norm": 0.23653754591941833, |
| "learning_rate": 0.001, |
| "loss": 3.0979, |
| "num_input_tokens_seen": 8519680000, |
| "step": 32500 |
| }, |
| { |
| "epoch": 0.21861121340994816, |
| "eval_loss": 2.9992752075195312, |
| "eval_runtime": 104.1376, |
| "eval_samples_per_second": 48.013, |
| "eval_steps_per_second": 12.003, |
| "num_input_tokens_seen": 8519680000, |
| "step": 32500 |
| }, |
| { |
| "epoch": 0.21894753835365577, |
| "grad_norm": 0.235910564661026, |
| "learning_rate": 0.001, |
| "loss": 3.0965, |
| "num_input_tokens_seen": 8532787200, |
| "step": 32550 |
| }, |
| { |
| "epoch": 0.21928386329736338, |
| "grad_norm": 0.17582012712955475, |
| "learning_rate": 0.001, |
| "loss": 3.0979, |
| "num_input_tokens_seen": 8545894400, |
| "step": 32600 |
| }, |
| { |
| "epoch": 0.219620188241071, |
| "grad_norm": 0.16854169964790344, |
| "learning_rate": 0.001, |
| "loss": 3.0962, |
| "num_input_tokens_seen": 8559001600, |
| "step": 32650 |
| }, |
| { |
| "epoch": 0.2199565131847786, |
| "grad_norm": 0.20170539617538452, |
| "learning_rate": 0.001, |
| "loss": 3.0967, |
| "num_input_tokens_seen": 8572108800, |
| "step": 32700 |
| }, |
| { |
| "epoch": 0.2202928381284862, |
| "grad_norm": 0.15898527204990387, |
| "learning_rate": 0.001, |
| "loss": 3.0846, |
| "num_input_tokens_seen": 8585216000, |
| "step": 32750 |
| }, |
| { |
| "epoch": 0.22062916307219382, |
| "grad_norm": 0.18423962593078613, |
| "learning_rate": 0.001, |
| "loss": 3.0873, |
| "num_input_tokens_seen": 8598323200, |
| "step": 32800 |
| }, |
| { |
| "epoch": 0.22096548801590143, |
| "grad_norm": 0.22025519609451294, |
| "learning_rate": 0.001, |
| "loss": 3.1034, |
| "num_input_tokens_seen": 8611430400, |
| "step": 32850 |
| }, |
| { |
| "epoch": 0.22130181295960905, |
| "grad_norm": 0.22972916066646576, |
| "learning_rate": 0.001, |
| "loss": 3.1018, |
| "num_input_tokens_seen": 8624537600, |
| "step": 32900 |
| }, |
| { |
| "epoch": 0.22163813790331666, |
| "grad_norm": 0.3072693347930908, |
| "learning_rate": 0.001, |
| "loss": 3.1044, |
| "num_input_tokens_seen": 8637644800, |
| "step": 32950 |
| }, |
| { |
| "epoch": 0.22197446284702427, |
| "grad_norm": 0.16734054684638977, |
| "learning_rate": 0.001, |
| "loss": 3.1079, |
| "num_input_tokens_seen": 8650752000, |
| "step": 33000 |
| }, |
| { |
| "epoch": 0.22197446284702427, |
| "eval_loss": 2.9946696758270264, |
| "eval_runtime": 101.2832, |
| "eval_samples_per_second": 49.367, |
| "eval_steps_per_second": 12.342, |
| "num_input_tokens_seen": 8650752000, |
| "step": 33000 |
| }, |
| { |
| "epoch": 0.2223107877907319, |
| "grad_norm": 0.19366054236888885, |
| "learning_rate": 0.001, |
| "loss": 3.1123, |
| "num_input_tokens_seen": 8663859200, |
| "step": 33050 |
| }, |
| { |
| "epoch": 0.22264711273443952, |
| "grad_norm": 0.1908022165298462, |
| "learning_rate": 0.001, |
| "loss": 3.0921, |
| "num_input_tokens_seen": 8676966400, |
| "step": 33100 |
| }, |
| { |
| "epoch": 0.22298343767814713, |
| "grad_norm": 0.1756322979927063, |
| "learning_rate": 0.001, |
| "loss": 3.0898, |
| "num_input_tokens_seen": 8690073600, |
| "step": 33150 |
| }, |
| { |
| "epoch": 0.22331976262185474, |
| "grad_norm": 0.17791526019573212, |
| "learning_rate": 0.001, |
| "loss": 3.099, |
| "num_input_tokens_seen": 8703180800, |
| "step": 33200 |
| }, |
| { |
| "epoch": 0.22365608756556235, |
| "grad_norm": 0.1831691414117813, |
| "learning_rate": 0.001, |
| "loss": 3.0961, |
| "num_input_tokens_seen": 8716288000, |
| "step": 33250 |
| }, |
| { |
| "epoch": 0.22399241250926996, |
| "grad_norm": 0.21115051209926605, |
| "learning_rate": 0.001, |
| "loss": 3.092, |
| "num_input_tokens_seen": 8729395200, |
| "step": 33300 |
| }, |
| { |
| "epoch": 0.22432873745297757, |
| "grad_norm": 0.2059226632118225, |
| "learning_rate": 0.001, |
| "loss": 3.0982, |
| "num_input_tokens_seen": 8742502400, |
| "step": 33350 |
| }, |
| { |
| "epoch": 0.22466506239668518, |
| "grad_norm": 0.18022479116916656, |
| "learning_rate": 0.001, |
| "loss": 3.0853, |
| "num_input_tokens_seen": 8755609600, |
| "step": 33400 |
| }, |
| { |
| "epoch": 0.2250013873403928, |
| "grad_norm": 0.18534015119075775, |
| "learning_rate": 0.001, |
| "loss": 3.0872, |
| "num_input_tokens_seen": 8768716800, |
| "step": 33450 |
| }, |
| { |
| "epoch": 0.2253377122841004, |
| "grad_norm": 0.1856871247291565, |
| "learning_rate": 0.001, |
| "loss": 3.0888, |
| "num_input_tokens_seen": 8781824000, |
| "step": 33500 |
| }, |
| { |
| "epoch": 0.2253377122841004, |
| "eval_loss": 2.989856243133545, |
| "eval_runtime": 100.552, |
| "eval_samples_per_second": 49.725, |
| "eval_steps_per_second": 12.431, |
| "num_input_tokens_seen": 8781824000, |
| "step": 33500 |
| }, |
| { |
| "epoch": 0.22567403722780802, |
| "grad_norm": 0.1858453005552292, |
| "learning_rate": 0.001, |
| "loss": 3.0859, |
| "num_input_tokens_seen": 8794931200, |
| "step": 33550 |
| }, |
| { |
| "epoch": 0.22601036217151563, |
| "grad_norm": 0.15424181520938873, |
| "learning_rate": 0.001, |
| "loss": 3.094, |
| "num_input_tokens_seen": 8808038400, |
| "step": 33600 |
| }, |
| { |
| "epoch": 0.22634668711522324, |
| "grad_norm": 0.1684613823890686, |
| "learning_rate": 0.001, |
| "loss": 3.0924, |
| "num_input_tokens_seen": 8821145600, |
| "step": 33650 |
| }, |
| { |
| "epoch": 0.22668301205893085, |
| "grad_norm": 0.20759907364845276, |
| "learning_rate": 0.001, |
| "loss": 3.0967, |
| "num_input_tokens_seen": 8834252800, |
| "step": 33700 |
| }, |
| { |
| "epoch": 0.22701933700263846, |
| "grad_norm": 0.20460882782936096, |
| "learning_rate": 0.001, |
| "loss": 3.0938, |
| "num_input_tokens_seen": 8847360000, |
| "step": 33750 |
| }, |
| { |
| "epoch": 0.22735566194634607, |
| "grad_norm": 1.1036453247070312, |
| "learning_rate": 0.001, |
| "loss": 3.092, |
| "num_input_tokens_seen": 8860467200, |
| "step": 33800 |
| }, |
| { |
| "epoch": 0.22769198689005368, |
| "grad_norm": 0.23920981585979462, |
| "learning_rate": 0.001, |
| "loss": 3.1014, |
| "num_input_tokens_seen": 8873574400, |
| "step": 33850 |
| }, |
| { |
| "epoch": 0.2280283118337613, |
| "grad_norm": 0.44639232754707336, |
| "learning_rate": 0.001, |
| "loss": 3.0925, |
| "num_input_tokens_seen": 8886681600, |
| "step": 33900 |
| }, |
| { |
| "epoch": 0.22836463677746893, |
| "grad_norm": 0.20524434745311737, |
| "learning_rate": 0.001, |
| "loss": 3.0998, |
| "num_input_tokens_seen": 8899788800, |
| "step": 33950 |
| }, |
| { |
| "epoch": 0.22870096172117654, |
| "grad_norm": 0.3326469957828522, |
| "learning_rate": 0.001, |
| "loss": 3.1028, |
| "num_input_tokens_seen": 8912896000, |
| "step": 34000 |
| }, |
| { |
| "epoch": 0.22870096172117654, |
| "eval_loss": 2.99273681640625, |
| "eval_runtime": 101.3229, |
| "eval_samples_per_second": 49.347, |
| "eval_steps_per_second": 12.337, |
| "num_input_tokens_seen": 8912896000, |
| "step": 34000 |
| }, |
| { |
| "epoch": 0.22903728666488415, |
| "grad_norm": 0.1811443269252777, |
| "learning_rate": 0.001, |
| "loss": 3.0963, |
| "num_input_tokens_seen": 8926003200, |
| "step": 34050 |
| }, |
| { |
| "epoch": 0.22937361160859177, |
| "grad_norm": 0.1995471566915512, |
| "learning_rate": 0.001, |
| "loss": 3.0929, |
| "num_input_tokens_seen": 8939110400, |
| "step": 34100 |
| }, |
| { |
| "epoch": 0.22970993655229938, |
| "grad_norm": 0.18768733739852905, |
| "learning_rate": 0.001, |
| "loss": 3.088, |
| "num_input_tokens_seen": 8952217600, |
| "step": 34150 |
| }, |
| { |
| "epoch": 0.230046261496007, |
| "grad_norm": 0.23258289694786072, |
| "learning_rate": 0.001, |
| "loss": 3.0952, |
| "num_input_tokens_seen": 8965324800, |
| "step": 34200 |
| }, |
| { |
| "epoch": 0.2303825864397146, |
| "grad_norm": 0.2201758772134781, |
| "learning_rate": 0.001, |
| "loss": 3.105, |
| "num_input_tokens_seen": 8978432000, |
| "step": 34250 |
| }, |
| { |
| "epoch": 0.2307189113834222, |
| "grad_norm": 0.3385378420352936, |
| "learning_rate": 0.001, |
| "loss": 3.1242, |
| "num_input_tokens_seen": 8991539200, |
| "step": 34300 |
| }, |
| { |
| "epoch": 0.23105523632712982, |
| "grad_norm": 0.40026524662971497, |
| "learning_rate": 0.001, |
| "loss": 3.1236, |
| "num_input_tokens_seen": 9004646400, |
| "step": 34350 |
| }, |
| { |
| "epoch": 0.23139156127083743, |
| "grad_norm": 0.9256707429885864, |
| "learning_rate": 0.001, |
| "loss": 3.1417, |
| "num_input_tokens_seen": 9017753600, |
| "step": 34400 |
| }, |
| { |
| "epoch": 0.23172788621454504, |
| "grad_norm": 0.2774488627910614, |
| "learning_rate": 0.001, |
| "loss": 3.1258, |
| "num_input_tokens_seen": 9030860800, |
| "step": 34450 |
| }, |
| { |
| "epoch": 0.23206421115825265, |
| "grad_norm": 0.3596802353858948, |
| "learning_rate": 0.001, |
| "loss": 3.1182, |
| "num_input_tokens_seen": 9043968000, |
| "step": 34500 |
| }, |
| { |
| "epoch": 0.23206421115825265, |
| "eval_loss": 3.0026750564575195, |
| "eval_runtime": 101.1458, |
| "eval_samples_per_second": 49.434, |
| "eval_steps_per_second": 12.358, |
| "num_input_tokens_seen": 9043968000, |
| "step": 34500 |
| }, |
| { |
| "epoch": 0.23240053610196026, |
| "grad_norm": 0.23315957188606262, |
| "learning_rate": 0.001, |
| "loss": 3.0983, |
| "num_input_tokens_seen": 9057075200, |
| "step": 34550 |
| }, |
| { |
| "epoch": 0.23273686104566788, |
| "grad_norm": 0.21506045758724213, |
| "learning_rate": 0.001, |
| "loss": 3.1006, |
| "num_input_tokens_seen": 9070182400, |
| "step": 34600 |
| }, |
| { |
| "epoch": 0.2330731859893755, |
| "grad_norm": 0.23909543454647064, |
| "learning_rate": 0.001, |
| "loss": 3.109, |
| "num_input_tokens_seen": 9083289600, |
| "step": 34650 |
| }, |
| { |
| "epoch": 0.2334095109330831, |
| "grad_norm": 0.31270143389701843, |
| "learning_rate": 0.001, |
| "loss": 3.1062, |
| "num_input_tokens_seen": 9096396800, |
| "step": 34700 |
| }, |
| { |
| "epoch": 0.2337458358767907, |
| "grad_norm": 0.2879350483417511, |
| "learning_rate": 0.001, |
| "loss": 3.1065, |
| "num_input_tokens_seen": 9109504000, |
| "step": 34750 |
| }, |
| { |
| "epoch": 0.23408216082049832, |
| "grad_norm": 0.1994767040014267, |
| "learning_rate": 0.001, |
| "loss": 3.0984, |
| "num_input_tokens_seen": 9122611200, |
| "step": 34800 |
| }, |
| { |
| "epoch": 0.23441848576420596, |
| "grad_norm": 0.19194720685482025, |
| "learning_rate": 0.001, |
| "loss": 3.1003, |
| "num_input_tokens_seen": 9135718400, |
| "step": 34850 |
| }, |
| { |
| "epoch": 0.23475481070791357, |
| "grad_norm": 0.22253084182739258, |
| "learning_rate": 0.001, |
| "loss": 3.0969, |
| "num_input_tokens_seen": 9148825600, |
| "step": 34900 |
| }, |
| { |
| "epoch": 0.23509113565162118, |
| "grad_norm": 0.2180721014738083, |
| "learning_rate": 0.001, |
| "loss": 3.0986, |
| "num_input_tokens_seen": 9161932800, |
| "step": 34950 |
| }, |
| { |
| "epoch": 0.2354274605953288, |
| "grad_norm": 0.1867762804031372, |
| "learning_rate": 0.001, |
| "loss": 3.0831, |
| "num_input_tokens_seen": 9175040000, |
| "step": 35000 |
| }, |
| { |
| "epoch": 0.2354274605953288, |
| "eval_loss": 2.987546920776367, |
| "eval_runtime": 100.7704, |
| "eval_samples_per_second": 49.618, |
| "eval_steps_per_second": 12.404, |
| "num_input_tokens_seen": 9175040000, |
| "step": 35000 |
| }, |
| { |
| "epoch": 0.2357637855390364, |
| "grad_norm": 0.22034546732902527, |
| "learning_rate": 0.001, |
| "loss": 3.0963, |
| "num_input_tokens_seen": 9188147200, |
| "step": 35050 |
| }, |
| { |
| "epoch": 0.236100110482744, |
| "grad_norm": 0.20113885402679443, |
| "learning_rate": 0.001, |
| "loss": 3.0948, |
| "num_input_tokens_seen": 9201254400, |
| "step": 35100 |
| }, |
| { |
| "epoch": 0.23643643542645162, |
| "grad_norm": 0.3071548342704773, |
| "learning_rate": 0.001, |
| "loss": 3.0991, |
| "num_input_tokens_seen": 9214361600, |
| "step": 35150 |
| }, |
| { |
| "epoch": 0.23677276037015924, |
| "grad_norm": 0.19438254833221436, |
| "learning_rate": 0.001, |
| "loss": 3.0931, |
| "num_input_tokens_seen": 9227468800, |
| "step": 35200 |
| }, |
| { |
| "epoch": 0.23710908531386685, |
| "grad_norm": 0.19387036561965942, |
| "learning_rate": 0.001, |
| "loss": 3.0945, |
| "num_input_tokens_seen": 9240576000, |
| "step": 35250 |
| }, |
| { |
| "epoch": 0.23744541025757446, |
| "grad_norm": 0.33751723170280457, |
| "learning_rate": 0.001, |
| "loss": 3.0853, |
| "num_input_tokens_seen": 9253683200, |
| "step": 35300 |
| }, |
| { |
| "epoch": 0.23778173520128207, |
| "grad_norm": 0.20809979736804962, |
| "learning_rate": 0.001, |
| "loss": 3.0886, |
| "num_input_tokens_seen": 9266790400, |
| "step": 35350 |
| }, |
| { |
| "epoch": 0.23811806014498968, |
| "grad_norm": 0.22419853508472443, |
| "learning_rate": 0.001, |
| "loss": 3.0903, |
| "num_input_tokens_seen": 9279897600, |
| "step": 35400 |
| }, |
| { |
| "epoch": 0.2384543850886973, |
| "grad_norm": 0.38772207498550415, |
| "learning_rate": 0.001, |
| "loss": 3.0917, |
| "num_input_tokens_seen": 9293004800, |
| "step": 35450 |
| }, |
| { |
| "epoch": 0.2387907100324049, |
| "grad_norm": 0.26076874136924744, |
| "learning_rate": 0.001, |
| "loss": 3.1019, |
| "num_input_tokens_seen": 9306112000, |
| "step": 35500 |
| }, |
| { |
| "epoch": 0.2387907100324049, |
| "eval_loss": 2.9896371364593506, |
| "eval_runtime": 101.1154, |
| "eval_samples_per_second": 49.448, |
| "eval_steps_per_second": 12.362, |
| "num_input_tokens_seen": 9306112000, |
| "step": 35500 |
| }, |
| { |
| "epoch": 0.2391270349761125, |
| "grad_norm": 0.2551634907722473, |
| "learning_rate": 0.001, |
| "loss": 3.0983, |
| "num_input_tokens_seen": 9319219200, |
| "step": 35550 |
| }, |
| { |
| "epoch": 0.23946335991982012, |
| "grad_norm": 0.25666406750679016, |
| "learning_rate": 0.001, |
| "loss": 3.0973, |
| "num_input_tokens_seen": 9332326400, |
| "step": 35600 |
| }, |
| { |
| "epoch": 0.23979968486352773, |
| "grad_norm": 0.21999171376228333, |
| "learning_rate": 0.001, |
| "loss": 3.1023, |
| "num_input_tokens_seen": 9345433600, |
| "step": 35650 |
| }, |
| { |
| "epoch": 0.24013600980723535, |
| "grad_norm": 0.24575746059417725, |
| "learning_rate": 0.001, |
| "loss": 3.0954, |
| "num_input_tokens_seen": 9358540800, |
| "step": 35700 |
| }, |
| { |
| "epoch": 0.24047233475094298, |
| "grad_norm": 0.23686733841896057, |
| "learning_rate": 0.001, |
| "loss": 3.0939, |
| "num_input_tokens_seen": 9371648000, |
| "step": 35750 |
| }, |
| { |
| "epoch": 0.2408086596946506, |
| "grad_norm": 0.2265947312116623, |
| "learning_rate": 0.001, |
| "loss": 3.0972, |
| "num_input_tokens_seen": 9384755200, |
| "step": 35800 |
| }, |
| { |
| "epoch": 0.2411449846383582, |
| "grad_norm": 0.19846303761005402, |
| "learning_rate": 0.001, |
| "loss": 3.0879, |
| "num_input_tokens_seen": 9397862400, |
| "step": 35850 |
| }, |
| { |
| "epoch": 0.24148130958206582, |
| "grad_norm": 0.3813537657260895, |
| "learning_rate": 0.001, |
| "loss": 3.091, |
| "num_input_tokens_seen": 9410969600, |
| "step": 35900 |
| }, |
| { |
| "epoch": 0.24181763452577343, |
| "grad_norm": 0.21791686117649078, |
| "learning_rate": 0.001, |
| "loss": 3.1126, |
| "num_input_tokens_seen": 9424076800, |
| "step": 35950 |
| }, |
| { |
| "epoch": 0.24215395946948104, |
| "grad_norm": 0.1958397924900055, |
| "learning_rate": 0.001, |
| "loss": 3.0993, |
| "num_input_tokens_seen": 9437184000, |
| "step": 36000 |
| }, |
| { |
| "epoch": 0.24215395946948104, |
| "eval_loss": 2.9876413345336914, |
| "eval_runtime": 100.7038, |
| "eval_samples_per_second": 49.651, |
| "eval_steps_per_second": 12.413, |
| "num_input_tokens_seen": 9437184000, |
| "step": 36000 |
| }, |
| { |
| "epoch": 0.24249028441318865, |
| "grad_norm": 0.18913355469703674, |
| "learning_rate": 0.001, |
| "loss": 3.0824, |
| "num_input_tokens_seen": 9450291200, |
| "step": 36050 |
| }, |
| { |
| "epoch": 0.24282660935689626, |
| "grad_norm": 0.17502999305725098, |
| "learning_rate": 0.001, |
| "loss": 3.0947, |
| "num_input_tokens_seen": 9463398400, |
| "step": 36100 |
| }, |
| { |
| "epoch": 0.24316293430060387, |
| "grad_norm": 0.1844000667333603, |
| "learning_rate": 0.001, |
| "loss": 3.1031, |
| "num_input_tokens_seen": 9476505600, |
| "step": 36150 |
| }, |
| { |
| "epoch": 0.24349925924431148, |
| "grad_norm": 0.21123170852661133, |
| "learning_rate": 0.001, |
| "loss": 3.0917, |
| "num_input_tokens_seen": 9489612800, |
| "step": 36200 |
| }, |
| { |
| "epoch": 0.2438355841880191, |
| "grad_norm": 0.20432326197624207, |
| "learning_rate": 0.001, |
| "loss": 3.0777, |
| "num_input_tokens_seen": 9502720000, |
| "step": 36250 |
| }, |
| { |
| "epoch": 0.2441719091317267, |
| "grad_norm": 0.1782015562057495, |
| "learning_rate": 0.001, |
| "loss": 3.0825, |
| "num_input_tokens_seen": 9515827200, |
| "step": 36300 |
| }, |
| { |
| "epoch": 0.24450823407543432, |
| "grad_norm": 0.17421406507492065, |
| "learning_rate": 0.001, |
| "loss": 3.0936, |
| "num_input_tokens_seen": 9528934400, |
| "step": 36350 |
| }, |
| { |
| "epoch": 0.24484455901914193, |
| "grad_norm": 0.20186392962932587, |
| "learning_rate": 0.001, |
| "loss": 3.0873, |
| "num_input_tokens_seen": 9542041600, |
| "step": 36400 |
| }, |
| { |
| "epoch": 0.24518088396284954, |
| "grad_norm": 0.8788098692893982, |
| "learning_rate": 0.001, |
| "loss": 3.0859, |
| "num_input_tokens_seen": 9555148800, |
| "step": 36450 |
| }, |
| { |
| "epoch": 0.24551720890655715, |
| "grad_norm": 0.21201574802398682, |
| "learning_rate": 0.001, |
| "loss": 3.0801, |
| "num_input_tokens_seen": 9568256000, |
| "step": 36500 |
| }, |
| { |
| "epoch": 0.24551720890655715, |
| "eval_loss": 2.9814889430999756, |
| "eval_runtime": 102.1027, |
| "eval_samples_per_second": 48.97, |
| "eval_steps_per_second": 12.243, |
| "num_input_tokens_seen": 9568256000, |
| "step": 36500 |
| }, |
| { |
| "epoch": 0.24585353385026476, |
| "grad_norm": 0.19073808193206787, |
| "learning_rate": 0.001, |
| "loss": 3.0944, |
| "num_input_tokens_seen": 9581363200, |
| "step": 36550 |
| }, |
| { |
| "epoch": 0.24618985879397237, |
| "grad_norm": 0.17367486655712128, |
| "learning_rate": 0.001, |
| "loss": 3.0892, |
| "num_input_tokens_seen": 9594470400, |
| "step": 36600 |
| }, |
| { |
| "epoch": 0.24652618373768, |
| "grad_norm": 0.24065230786800385, |
| "learning_rate": 0.001, |
| "loss": 3.092, |
| "num_input_tokens_seen": 9607577600, |
| "step": 36650 |
| }, |
| { |
| "epoch": 0.24686250868138762, |
| "grad_norm": 0.18443045020103455, |
| "learning_rate": 0.001, |
| "loss": 3.0863, |
| "num_input_tokens_seen": 9620684800, |
| "step": 36700 |
| }, |
| { |
| "epoch": 0.24719883362509523, |
| "grad_norm": 0.2121111899614334, |
| "learning_rate": 0.001, |
| "loss": 3.0902, |
| "num_input_tokens_seen": 9633792000, |
| "step": 36750 |
| }, |
| { |
| "epoch": 0.24753515856880284, |
| "grad_norm": 0.17981579899787903, |
| "learning_rate": 0.001, |
| "loss": 3.0888, |
| "num_input_tokens_seen": 9646899200, |
| "step": 36800 |
| }, |
| { |
| "epoch": 0.24787148351251045, |
| "grad_norm": 0.24683868885040283, |
| "learning_rate": 0.001, |
| "loss": 3.0895, |
| "num_input_tokens_seen": 9660006400, |
| "step": 36850 |
| }, |
| { |
| "epoch": 0.24820780845621807, |
| "grad_norm": 0.17905527353286743, |
| "learning_rate": 0.001, |
| "loss": 3.0771, |
| "num_input_tokens_seen": 9673113600, |
| "step": 36900 |
| }, |
| { |
| "epoch": 0.24854413339992568, |
| "grad_norm": 0.4657650589942932, |
| "learning_rate": 0.001, |
| "loss": 3.093, |
| "num_input_tokens_seen": 9686220800, |
| "step": 36950 |
| }, |
| { |
| "epoch": 0.2488804583436333, |
| "grad_norm": 0.2079911082983017, |
| "learning_rate": 0.001, |
| "loss": 3.0913, |
| "num_input_tokens_seen": 9699328000, |
| "step": 37000 |
| }, |
| { |
| "epoch": 0.2488804583436333, |
| "eval_loss": 2.984112024307251, |
| "eval_runtime": 100.7836, |
| "eval_samples_per_second": 49.611, |
| "eval_steps_per_second": 12.403, |
| "num_input_tokens_seen": 9699328000, |
| "step": 37000 |
| }, |
| { |
| "epoch": 0.2492167832873409, |
| "grad_norm": 0.18588006496429443, |
| "learning_rate": 0.001, |
| "loss": 3.086, |
| "num_input_tokens_seen": 9712435200, |
| "step": 37050 |
| }, |
| { |
| "epoch": 0.2495531082310485, |
| "grad_norm": 0.500970721244812, |
| "learning_rate": 0.001, |
| "loss": 3.0786, |
| "num_input_tokens_seen": 9725542400, |
| "step": 37100 |
| }, |
| { |
| "epoch": 0.24988943317475612, |
| "grad_norm": 0.20005236566066742, |
| "learning_rate": 0.001, |
| "loss": 3.0797, |
| "num_input_tokens_seen": 9738649600, |
| "step": 37150 |
| }, |
| { |
| "epoch": 0.25022575811846376, |
| "grad_norm": 0.1864924281835556, |
| "learning_rate": 0.001, |
| "loss": 3.076, |
| "num_input_tokens_seen": 9751756800, |
| "step": 37200 |
| }, |
| { |
| "epoch": 0.25056208306217137, |
| "grad_norm": 0.19927112758159637, |
| "learning_rate": 0.001, |
| "loss": 3.083, |
| "num_input_tokens_seen": 9764864000, |
| "step": 37250 |
| }, |
| { |
| "epoch": 0.250898408005879, |
| "grad_norm": 0.18902507424354553, |
| "learning_rate": 0.001, |
| "loss": 3.0885, |
| "num_input_tokens_seen": 9777971200, |
| "step": 37300 |
| }, |
| { |
| "epoch": 0.2512347329495866, |
| "grad_norm": 0.19465987384319305, |
| "learning_rate": 0.001, |
| "loss": 3.0826, |
| "num_input_tokens_seen": 9791078400, |
| "step": 37350 |
| }, |
| { |
| "epoch": 0.2515710578932942, |
| "grad_norm": 0.2374599725008011, |
| "learning_rate": 0.001, |
| "loss": 3.0796, |
| "num_input_tokens_seen": 9804185600, |
| "step": 37400 |
| }, |
| { |
| "epoch": 0.2519073828370018, |
| "grad_norm": 0.201645627617836, |
| "learning_rate": 0.001, |
| "loss": 3.0856, |
| "num_input_tokens_seen": 9817292800, |
| "step": 37450 |
| }, |
| { |
| "epoch": 0.2522437077807094, |
| "grad_norm": 0.5505014061927795, |
| "learning_rate": 0.001, |
| "loss": 3.1105, |
| "num_input_tokens_seen": 9830400000, |
| "step": 37500 |
| }, |
| { |
| "epoch": 0.2522437077807094, |
| "eval_loss": 2.9955086708068848, |
| "eval_runtime": 51.2641, |
| "eval_samples_per_second": 97.534, |
| "eval_steps_per_second": 24.384, |
| "num_input_tokens_seen": 9830400000, |
| "step": 37500 |
| }, |
| { |
| "epoch": 0.25258003272441704, |
| "grad_norm": 0.5572711229324341, |
| "learning_rate": 0.001, |
| "loss": 3.0967, |
| "num_input_tokens_seen": 9843507200, |
| "step": 37550 |
| }, |
| { |
| "epoch": 0.25291635766812465, |
| "grad_norm": 0.25361862778663635, |
| "learning_rate": 0.001, |
| "loss": 3.1296, |
| "num_input_tokens_seen": 9856614400, |
| "step": 37600 |
| }, |
| { |
| "epoch": 0.25325268261183226, |
| "grad_norm": 0.24185167253017426, |
| "learning_rate": 0.001, |
| "loss": 3.1003, |
| "num_input_tokens_seen": 9869721600, |
| "step": 37650 |
| }, |
| { |
| "epoch": 0.25358900755553987, |
| "grad_norm": 0.2068016678094864, |
| "learning_rate": 0.001, |
| "loss": 3.088, |
| "num_input_tokens_seen": 9882828800, |
| "step": 37700 |
| }, |
| { |
| "epoch": 0.2539253324992475, |
| "grad_norm": 0.2029482126235962, |
| "learning_rate": 0.001, |
| "loss": 3.0878, |
| "num_input_tokens_seen": 9895936000, |
| "step": 37750 |
| }, |
| { |
| "epoch": 0.2542616574429551, |
| "grad_norm": 0.22508949041366577, |
| "learning_rate": 0.001, |
| "loss": 3.0992, |
| "num_input_tokens_seen": 9909043200, |
| "step": 37800 |
| }, |
| { |
| "epoch": 0.2545979823866627, |
| "grad_norm": 0.19577881693840027, |
| "learning_rate": 0.001, |
| "loss": 3.0866, |
| "num_input_tokens_seen": 9922150400, |
| "step": 37850 |
| }, |
| { |
| "epoch": 0.2549343073303703, |
| "grad_norm": 0.815874457359314, |
| "learning_rate": 0.001, |
| "loss": 3.0858, |
| "num_input_tokens_seen": 9935257600, |
| "step": 37900 |
| }, |
| { |
| "epoch": 0.2552706322740779, |
| "grad_norm": 0.20485574007034302, |
| "learning_rate": 0.001, |
| "loss": 3.0943, |
| "num_input_tokens_seen": 9948364800, |
| "step": 37950 |
| }, |
| { |
| "epoch": 0.25560695721778554, |
| "grad_norm": 0.23158146440982819, |
| "learning_rate": 0.001, |
| "loss": 3.0926, |
| "num_input_tokens_seen": 9961472000, |
| "step": 38000 |
| }, |
| { |
| "epoch": 0.25560695721778554, |
| "eval_loss": 2.9854347705841064, |
| "eval_runtime": 51.4615, |
| "eval_samples_per_second": 97.16, |
| "eval_steps_per_second": 24.29, |
| "num_input_tokens_seen": 9961472000, |
| "step": 38000 |
| }, |
| { |
| "epoch": 0.25594328216149315, |
| "grad_norm": 0.32355332374572754, |
| "learning_rate": 0.001, |
| "loss": 3.0965, |
| "num_input_tokens_seen": 9974579200, |
| "step": 38050 |
| }, |
| { |
| "epoch": 0.25627960710520076, |
| "grad_norm": 0.20291878283023834, |
| "learning_rate": 0.001, |
| "loss": 3.0803, |
| "num_input_tokens_seen": 9987686400, |
| "step": 38100 |
| }, |
| { |
| "epoch": 0.25661593204890837, |
| "grad_norm": 0.17536096274852753, |
| "learning_rate": 0.001, |
| "loss": 3.0765, |
| "num_input_tokens_seen": 10000793600, |
| "step": 38150 |
| }, |
| { |
| "epoch": 0.256952256992616, |
| "grad_norm": 0.17826804518699646, |
| "learning_rate": 0.001, |
| "loss": 3.0735, |
| "num_input_tokens_seen": 10013900800, |
| "step": 38200 |
| }, |
| { |
| "epoch": 0.2572885819363236, |
| "grad_norm": 0.20115964114665985, |
| "learning_rate": 0.001, |
| "loss": 3.0813, |
| "num_input_tokens_seen": 10027008000, |
| "step": 38250 |
| }, |
| { |
| "epoch": 0.2576249068800312, |
| "grad_norm": 0.23634804785251617, |
| "learning_rate": 0.001, |
| "loss": 3.0821, |
| "num_input_tokens_seen": 10040115200, |
| "step": 38300 |
| }, |
| { |
| "epoch": 0.2579612318237388, |
| "grad_norm": 0.31893596053123474, |
| "learning_rate": 0.001, |
| "loss": 3.096, |
| "num_input_tokens_seen": 10053222400, |
| "step": 38350 |
| }, |
| { |
| "epoch": 0.2582975567674464, |
| "grad_norm": 0.21891412138938904, |
| "learning_rate": 0.001, |
| "loss": 3.0904, |
| "num_input_tokens_seen": 10066329600, |
| "step": 38400 |
| }, |
| { |
| "epoch": 0.25863388171115403, |
| "grad_norm": 0.21848681569099426, |
| "learning_rate": 0.001, |
| "loss": 3.0793, |
| "num_input_tokens_seen": 10079436800, |
| "step": 38450 |
| }, |
| { |
| "epoch": 0.25897020665486165, |
| "grad_norm": 0.2052360624074936, |
| "learning_rate": 0.001, |
| "loss": 3.0802, |
| "num_input_tokens_seen": 10092544000, |
| "step": 38500 |
| }, |
| { |
| "epoch": 0.25897020665486165, |
| "eval_loss": 2.9803249835968018, |
| "eval_runtime": 51.5379, |
| "eval_samples_per_second": 97.016, |
| "eval_steps_per_second": 24.254, |
| "num_input_tokens_seen": 10092544000, |
| "step": 38500 |
| }, |
| { |
| "epoch": 0.25930653159856926, |
| "grad_norm": 0.23162005841732025, |
| "learning_rate": 0.001, |
| "loss": 3.0876, |
| "num_input_tokens_seen": 10105651200, |
| "step": 38550 |
| }, |
| { |
| "epoch": 0.25964285654227687, |
| "grad_norm": 0.23110276460647583, |
| "learning_rate": 0.001, |
| "loss": 3.0745, |
| "num_input_tokens_seen": 10118758400, |
| "step": 38600 |
| }, |
| { |
| "epoch": 0.2599791814859845, |
| "grad_norm": 0.22557710111141205, |
| "learning_rate": 0.001, |
| "loss": 3.0716, |
| "num_input_tokens_seen": 10131865600, |
| "step": 38650 |
| }, |
| { |
| "epoch": 0.2603155064296921, |
| "grad_norm": 0.19009199738502502, |
| "learning_rate": 0.001, |
| "loss": 3.0765, |
| "num_input_tokens_seen": 10144972800, |
| "step": 38700 |
| }, |
| { |
| "epoch": 0.2606518313733997, |
| "grad_norm": 0.2352983057498932, |
| "learning_rate": 0.001, |
| "loss": 3.0834, |
| "num_input_tokens_seen": 10158080000, |
| "step": 38750 |
| }, |
| { |
| "epoch": 0.2609881563171073, |
| "grad_norm": 0.1986854076385498, |
| "learning_rate": 0.001, |
| "loss": 3.084, |
| "num_input_tokens_seen": 10171187200, |
| "step": 38800 |
| }, |
| { |
| "epoch": 0.2613244812608149, |
| "grad_norm": 1.6988344192504883, |
| "learning_rate": 0.001, |
| "loss": 3.0994, |
| "num_input_tokens_seen": 10184294400, |
| "step": 38850 |
| }, |
| { |
| "epoch": 0.2616608062045226, |
| "grad_norm": 0.2794356346130371, |
| "learning_rate": 0.001, |
| "loss": 3.1265, |
| "num_input_tokens_seen": 10197401600, |
| "step": 38900 |
| }, |
| { |
| "epoch": 0.2619971311482302, |
| "grad_norm": 0.2307969629764557, |
| "learning_rate": 0.001, |
| "loss": 3.1015, |
| "num_input_tokens_seen": 10210508800, |
| "step": 38950 |
| }, |
| { |
| "epoch": 0.2623334560919378, |
| "grad_norm": 0.29501858353614807, |
| "learning_rate": 0.001, |
| "loss": 3.0881, |
| "num_input_tokens_seen": 10223616000, |
| "step": 39000 |
| }, |
| { |
| "epoch": 0.2623334560919378, |
| "eval_loss": 2.9856879711151123, |
| "eval_runtime": 51.7163, |
| "eval_samples_per_second": 96.681, |
| "eval_steps_per_second": 24.17, |
| "num_input_tokens_seen": 10223616000, |
| "step": 39000 |
| }, |
| { |
| "epoch": 0.2626697810356454, |
| "grad_norm": 0.288418710231781, |
| "learning_rate": 0.001, |
| "loss": 3.0901, |
| "num_input_tokens_seen": 10236723200, |
| "step": 39050 |
| }, |
| { |
| "epoch": 0.26300610597935303, |
| "grad_norm": 0.2238176465034485, |
| "learning_rate": 0.001, |
| "loss": 3.0869, |
| "num_input_tokens_seen": 10249830400, |
| "step": 39100 |
| }, |
| { |
| "epoch": 0.26334243092306064, |
| "grad_norm": 0.21013687551021576, |
| "learning_rate": 0.001, |
| "loss": 3.0821, |
| "num_input_tokens_seen": 10262937600, |
| "step": 39150 |
| }, |
| { |
| "epoch": 0.26367875586676826, |
| "grad_norm": 0.20650598406791687, |
| "learning_rate": 0.001, |
| "loss": 3.0924, |
| "num_input_tokens_seen": 10276044800, |
| "step": 39200 |
| }, |
| { |
| "epoch": 0.26401508081047587, |
| "grad_norm": 1.1471627950668335, |
| "learning_rate": 0.001, |
| "loss": 3.0719, |
| "num_input_tokens_seen": 10289152000, |
| "step": 39250 |
| }, |
| { |
| "epoch": 0.2643514057541835, |
| "grad_norm": 0.2899995446205139, |
| "learning_rate": 0.001, |
| "loss": 3.0901, |
| "num_input_tokens_seen": 10302259200, |
| "step": 39300 |
| }, |
| { |
| "epoch": 0.2646877306978911, |
| "grad_norm": 0.25812703371047974, |
| "learning_rate": 0.001, |
| "loss": 3.088, |
| "num_input_tokens_seen": 10315366400, |
| "step": 39350 |
| }, |
| { |
| "epoch": 0.2650240556415987, |
| "grad_norm": 0.36547353863716125, |
| "learning_rate": 0.001, |
| "loss": 3.0782, |
| "num_input_tokens_seen": 10328473600, |
| "step": 39400 |
| }, |
| { |
| "epoch": 0.2653603805853063, |
| "grad_norm": 0.41187551617622375, |
| "learning_rate": 0.001, |
| "loss": 3.0991, |
| "num_input_tokens_seen": 10341580800, |
| "step": 39450 |
| }, |
| { |
| "epoch": 0.2656967055290139, |
| "grad_norm": 0.2279098927974701, |
| "learning_rate": 0.001, |
| "loss": 3.083, |
| "num_input_tokens_seen": 10354688000, |
| "step": 39500 |
| }, |
| { |
| "epoch": 0.2656967055290139, |
| "eval_loss": 2.9809067249298096, |
| "eval_runtime": 51.2151, |
| "eval_samples_per_second": 97.627, |
| "eval_steps_per_second": 24.407, |
| "num_input_tokens_seen": 10354688000, |
| "step": 39500 |
| }, |
| { |
| "epoch": 0.26603303047272153, |
| "grad_norm": 0.2444402426481247, |
| "learning_rate": 0.001, |
| "loss": 3.0887, |
| "num_input_tokens_seen": 10367795200, |
| "step": 39550 |
| }, |
| { |
| "epoch": 0.26636935541642914, |
| "grad_norm": 0.24601753056049347, |
| "learning_rate": 0.001, |
| "loss": 3.0802, |
| "num_input_tokens_seen": 10380902400, |
| "step": 39600 |
| }, |
| { |
| "epoch": 0.26670568036013675, |
| "grad_norm": 0.21487103402614594, |
| "learning_rate": 0.001, |
| "loss": 3.0777, |
| "num_input_tokens_seen": 10394009600, |
| "step": 39650 |
| }, |
| { |
| "epoch": 0.26704200530384437, |
| "grad_norm": 0.21092857420444489, |
| "learning_rate": 0.001, |
| "loss": 3.083, |
| "num_input_tokens_seen": 10407116800, |
| "step": 39700 |
| }, |
| { |
| "epoch": 0.267378330247552, |
| "grad_norm": 0.21346789598464966, |
| "learning_rate": 0.001, |
| "loss": 3.0946, |
| "num_input_tokens_seen": 10420224000, |
| "step": 39750 |
| }, |
| { |
| "epoch": 0.2677146551912596, |
| "grad_norm": 0.3449369966983795, |
| "learning_rate": 0.001, |
| "loss": 3.0827, |
| "num_input_tokens_seen": 10433331200, |
| "step": 39800 |
| }, |
| { |
| "epoch": 0.2680509801349672, |
| "grad_norm": 0.33765944838523865, |
| "learning_rate": 0.001, |
| "loss": 3.0886, |
| "num_input_tokens_seen": 10446438400, |
| "step": 39850 |
| }, |
| { |
| "epoch": 0.2683873050786748, |
| "grad_norm": 0.2361810952425003, |
| "learning_rate": 0.001, |
| "loss": 3.0902, |
| "num_input_tokens_seen": 10459545600, |
| "step": 39900 |
| }, |
| { |
| "epoch": 0.2687236300223824, |
| "grad_norm": 0.2562389373779297, |
| "learning_rate": 0.001, |
| "loss": 3.0958, |
| "num_input_tokens_seen": 10472652800, |
| "step": 39950 |
| }, |
| { |
| "epoch": 0.26905995496609003, |
| "grad_norm": 0.20619696378707886, |
| "learning_rate": 0.001, |
| "loss": 3.0904, |
| "num_input_tokens_seen": 10485760000, |
| "step": 40000 |
| }, |
| { |
| "epoch": 0.26905995496609003, |
| "eval_loss": 2.9785397052764893, |
| "eval_runtime": 51.4486, |
| "eval_samples_per_second": 97.184, |
| "eval_steps_per_second": 24.296, |
| "num_input_tokens_seen": 10485760000, |
| "step": 40000 |
| }, |
| { |
| "epoch": 0.26939627990979764, |
| "grad_norm": 0.775861382484436, |
| "learning_rate": 0.001, |
| "loss": 3.0856, |
| "num_input_tokens_seen": 10498867200, |
| "step": 40050 |
| }, |
| { |
| "epoch": 0.26973260485350525, |
| "grad_norm": 0.2422339916229248, |
| "learning_rate": 0.001, |
| "loss": 3.0831, |
| "num_input_tokens_seen": 10511974400, |
| "step": 40100 |
| }, |
| { |
| "epoch": 0.27006892979721286, |
| "grad_norm": 0.21582826972007751, |
| "learning_rate": 0.001, |
| "loss": 3.0735, |
| "num_input_tokens_seen": 10525081600, |
| "step": 40150 |
| }, |
| { |
| "epoch": 0.2704052547409205, |
| "grad_norm": 0.17632398009300232, |
| "learning_rate": 0.001, |
| "loss": 3.0878, |
| "num_input_tokens_seen": 10538188800, |
| "step": 40200 |
| }, |
| { |
| "epoch": 0.2707415796846281, |
| "grad_norm": 0.2152569591999054, |
| "learning_rate": 0.001, |
| "loss": 3.0766, |
| "num_input_tokens_seen": 10551296000, |
| "step": 40250 |
| }, |
| { |
| "epoch": 0.2710779046283357, |
| "grad_norm": 0.19657547771930695, |
| "learning_rate": 0.001, |
| "loss": 3.0674, |
| "num_input_tokens_seen": 10564403200, |
| "step": 40300 |
| }, |
| { |
| "epoch": 0.2714142295720433, |
| "grad_norm": 0.21468690037727356, |
| "learning_rate": 0.001, |
| "loss": 3.0746, |
| "num_input_tokens_seen": 10577510400, |
| "step": 40350 |
| }, |
| { |
| "epoch": 0.2717505545157509, |
| "grad_norm": 0.19693616032600403, |
| "learning_rate": 0.001, |
| "loss": 3.0795, |
| "num_input_tokens_seen": 10590617600, |
| "step": 40400 |
| }, |
| { |
| "epoch": 0.27208687945945853, |
| "grad_norm": 0.21241678297519684, |
| "learning_rate": 0.001, |
| "loss": 3.0843, |
| "num_input_tokens_seen": 10603724800, |
| "step": 40450 |
| }, |
| { |
| "epoch": 0.27242320440316614, |
| "grad_norm": 0.2053707093000412, |
| "learning_rate": 0.001, |
| "loss": 3.0857, |
| "num_input_tokens_seen": 10616832000, |
| "step": 40500 |
| }, |
| { |
| "epoch": 0.27242320440316614, |
| "eval_loss": 2.9741692543029785, |
| "eval_runtime": 51.4287, |
| "eval_samples_per_second": 97.222, |
| "eval_steps_per_second": 24.305, |
| "num_input_tokens_seen": 10616832000, |
| "step": 40500 |
| }, |
| { |
| "epoch": 0.27275952934687375, |
| "grad_norm": 0.18715134263038635, |
| "learning_rate": 0.001, |
| "loss": 3.0699, |
| "num_input_tokens_seen": 10629939200, |
| "step": 40550 |
| }, |
| { |
| "epoch": 0.27309585429058136, |
| "grad_norm": 0.20241226255893707, |
| "learning_rate": 0.001, |
| "loss": 3.0794, |
| "num_input_tokens_seen": 10643046400, |
| "step": 40600 |
| }, |
| { |
| "epoch": 0.273432179234289, |
| "grad_norm": 0.19430743157863617, |
| "learning_rate": 0.001, |
| "loss": 3.0768, |
| "num_input_tokens_seen": 10656153600, |
| "step": 40650 |
| }, |
| { |
| "epoch": 0.2737685041779966, |
| "grad_norm": 0.18806929886341095, |
| "learning_rate": 0.001, |
| "loss": 3.0778, |
| "num_input_tokens_seen": 10669260800, |
| "step": 40700 |
| }, |
| { |
| "epoch": 0.27410482912170425, |
| "grad_norm": 0.20148856937885284, |
| "learning_rate": 0.001, |
| "loss": 3.0768, |
| "num_input_tokens_seen": 10682368000, |
| "step": 40750 |
| }, |
| { |
| "epoch": 0.27444115406541186, |
| "grad_norm": 0.17226669192314148, |
| "learning_rate": 0.001, |
| "loss": 3.0621, |
| "num_input_tokens_seen": 10695475200, |
| "step": 40800 |
| }, |
| { |
| "epoch": 0.2747774790091195, |
| "grad_norm": 0.18090015649795532, |
| "learning_rate": 0.001, |
| "loss": 3.0693, |
| "num_input_tokens_seen": 10708582400, |
| "step": 40850 |
| }, |
| { |
| "epoch": 0.2751138039528271, |
| "grad_norm": 0.177758127450943, |
| "learning_rate": 0.001, |
| "loss": 3.0719, |
| "num_input_tokens_seen": 10721689600, |
| "step": 40900 |
| }, |
| { |
| "epoch": 0.2754501288965347, |
| "grad_norm": 0.18323731422424316, |
| "learning_rate": 0.001, |
| "loss": 3.0662, |
| "num_input_tokens_seen": 10734796800, |
| "step": 40950 |
| }, |
| { |
| "epoch": 0.2757864538402423, |
| "grad_norm": 0.1883731186389923, |
| "learning_rate": 0.001, |
| "loss": 3.0675, |
| "num_input_tokens_seen": 10747904000, |
| "step": 41000 |
| }, |
| { |
| "epoch": 0.2757864538402423, |
| "eval_loss": 2.9687845706939697, |
| "eval_runtime": 51.0712, |
| "eval_samples_per_second": 97.902, |
| "eval_steps_per_second": 24.476, |
| "num_input_tokens_seen": 10747904000, |
| "step": 41000 |
| }, |
| { |
| "epoch": 0.2761227787839499, |
| "grad_norm": 0.26252472400665283, |
| "learning_rate": 0.001, |
| "loss": 3.0668, |
| "num_input_tokens_seen": 10761011200, |
| "step": 41050 |
| }, |
| { |
| "epoch": 0.27645910372765753, |
| "grad_norm": 0.2921096086502075, |
| "learning_rate": 0.001, |
| "loss": 3.0817, |
| "num_input_tokens_seen": 10774118400, |
| "step": 41100 |
| }, |
| { |
| "epoch": 0.27679542867136514, |
| "grad_norm": 0.2732321619987488, |
| "learning_rate": 0.001, |
| "loss": 3.0918, |
| "num_input_tokens_seen": 10787225600, |
| "step": 41150 |
| }, |
| { |
| "epoch": 0.27713175361507275, |
| "grad_norm": 0.23650842905044556, |
| "learning_rate": 0.001, |
| "loss": 3.0767, |
| "num_input_tokens_seen": 10800332800, |
| "step": 41200 |
| }, |
| { |
| "epoch": 0.27746807855878036, |
| "grad_norm": 0.36582860350608826, |
| "learning_rate": 0.001, |
| "loss": 3.097, |
| "num_input_tokens_seen": 10813440000, |
| "step": 41250 |
| }, |
| { |
| "epoch": 0.277804403502488, |
| "grad_norm": 0.20505377650260925, |
| "learning_rate": 0.001, |
| "loss": 3.0776, |
| "num_input_tokens_seen": 10826547200, |
| "step": 41300 |
| }, |
| { |
| "epoch": 0.2781407284461956, |
| "grad_norm": 0.22332334518432617, |
| "learning_rate": 0.001, |
| "loss": 3.0822, |
| "num_input_tokens_seen": 10839654400, |
| "step": 41350 |
| }, |
| { |
| "epoch": 0.2784770533899032, |
| "grad_norm": 0.20054738223552704, |
| "learning_rate": 0.001, |
| "loss": 3.0756, |
| "num_input_tokens_seen": 10852761600, |
| "step": 41400 |
| }, |
| { |
| "epoch": 0.2788133783336108, |
| "grad_norm": 0.1935984194278717, |
| "learning_rate": 0.001, |
| "loss": 3.0772, |
| "num_input_tokens_seen": 10865868800, |
| "step": 41450 |
| }, |
| { |
| "epoch": 0.2791497032773184, |
| "grad_norm": 0.21076564490795135, |
| "learning_rate": 0.001, |
| "loss": 3.0733, |
| "num_input_tokens_seen": 10878976000, |
| "step": 41500 |
| }, |
| { |
| "epoch": 0.2791497032773184, |
| "eval_loss": 2.969437837600708, |
| "eval_runtime": 51.3634, |
| "eval_samples_per_second": 97.346, |
| "eval_steps_per_second": 24.336, |
| "num_input_tokens_seen": 10878976000, |
| "step": 41500 |
| }, |
| { |
| "epoch": 0.27948602822102603, |
| "grad_norm": 0.19656164944171906, |
| "learning_rate": 0.001, |
| "loss": 3.0705, |
| "num_input_tokens_seen": 10892083200, |
| "step": 41550 |
| }, |
| { |
| "epoch": 0.27982235316473364, |
| "grad_norm": 0.20582802593708038, |
| "learning_rate": 0.001, |
| "loss": 3.0847, |
| "num_input_tokens_seen": 10905190400, |
| "step": 41600 |
| }, |
| { |
| "epoch": 0.28015867810844125, |
| "grad_norm": 0.1748686581850052, |
| "learning_rate": 0.001, |
| "loss": 3.0612, |
| "num_input_tokens_seen": 10918297600, |
| "step": 41650 |
| }, |
| { |
| "epoch": 0.28049500305214886, |
| "grad_norm": 0.1908082365989685, |
| "learning_rate": 0.001, |
| "loss": 3.0673, |
| "num_input_tokens_seen": 10931404800, |
| "step": 41700 |
| }, |
| { |
| "epoch": 0.2808313279958565, |
| "grad_norm": 0.20851461589336395, |
| "learning_rate": 0.001, |
| "loss": 3.0724, |
| "num_input_tokens_seen": 10944512000, |
| "step": 41750 |
| }, |
| { |
| "epoch": 0.2811676529395641, |
| "grad_norm": 0.18114647269248962, |
| "learning_rate": 0.001, |
| "loss": 3.069, |
| "num_input_tokens_seen": 10957619200, |
| "step": 41800 |
| }, |
| { |
| "epoch": 0.2815039778832717, |
| "grad_norm": 0.19079278409481049, |
| "learning_rate": 0.001, |
| "loss": 3.0658, |
| "num_input_tokens_seen": 10970726400, |
| "step": 41850 |
| }, |
| { |
| "epoch": 0.2818403028269793, |
| "grad_norm": 0.16630959510803223, |
| "learning_rate": 0.001, |
| "loss": 3.0589, |
| "num_input_tokens_seen": 10983833600, |
| "step": 41900 |
| }, |
| { |
| "epoch": 0.2821766277706869, |
| "grad_norm": 0.1777983158826828, |
| "learning_rate": 0.001, |
| "loss": 3.0642, |
| "num_input_tokens_seen": 10996940800, |
| "step": 41950 |
| }, |
| { |
| "epoch": 0.2825129527143945, |
| "grad_norm": 0.36513733863830566, |
| "learning_rate": 0.001, |
| "loss": 3.0685, |
| "num_input_tokens_seen": 11010048000, |
| "step": 42000 |
| }, |
| { |
| "epoch": 0.2825129527143945, |
| "eval_loss": 2.9688751697540283, |
| "eval_runtime": 51.3924, |
| "eval_samples_per_second": 97.291, |
| "eval_steps_per_second": 24.323, |
| "num_input_tokens_seen": 11010048000, |
| "step": 42000 |
| }, |
| { |
| "epoch": 0.28284927765810214, |
| "grad_norm": 0.36728134751319885, |
| "learning_rate": 0.001, |
| "loss": 3.1317, |
| "num_input_tokens_seen": 11023155200, |
| "step": 42050 |
| }, |
| { |
| "epoch": 0.28318560260180975, |
| "grad_norm": 0.27042749524116516, |
| "learning_rate": 0.001, |
| "loss": 3.0815, |
| "num_input_tokens_seen": 11036262400, |
| "step": 42100 |
| }, |
| { |
| "epoch": 0.28352192754551736, |
| "grad_norm": 0.18322569131851196, |
| "learning_rate": 0.001, |
| "loss": 3.1027, |
| "num_input_tokens_seen": 11049369600, |
| "step": 42150 |
| }, |
| { |
| "epoch": 0.28385825248922497, |
| "grad_norm": 0.21849602460861206, |
| "learning_rate": 0.001, |
| "loss": 3.071, |
| "num_input_tokens_seen": 11062476800, |
| "step": 42200 |
| }, |
| { |
| "epoch": 0.2841945774329326, |
| "grad_norm": 0.38253432512283325, |
| "learning_rate": 0.001, |
| "loss": 3.0898, |
| "num_input_tokens_seen": 11075584000, |
| "step": 42250 |
| }, |
| { |
| "epoch": 0.2845309023766402, |
| "grad_norm": 0.21137705445289612, |
| "learning_rate": 0.001, |
| "loss": 3.0813, |
| "num_input_tokens_seen": 11088691200, |
| "step": 42300 |
| }, |
| { |
| "epoch": 0.2848672273203478, |
| "grad_norm": 1.2625150680541992, |
| "learning_rate": 0.001, |
| "loss": 3.0799, |
| "num_input_tokens_seen": 11101798400, |
| "step": 42350 |
| }, |
| { |
| "epoch": 0.2852035522640554, |
| "grad_norm": 0.2312895804643631, |
| "learning_rate": 0.001, |
| "loss": 3.0877, |
| "num_input_tokens_seen": 11114905600, |
| "step": 42400 |
| }, |
| { |
| "epoch": 0.285539877207763, |
| "grad_norm": 0.2823241353034973, |
| "learning_rate": 0.001, |
| "loss": 3.0733, |
| "num_input_tokens_seen": 11128012800, |
| "step": 42450 |
| }, |
| { |
| "epoch": 0.28587620215147064, |
| "grad_norm": 0.21215762197971344, |
| "learning_rate": 0.001, |
| "loss": 3.0798, |
| "num_input_tokens_seen": 11141120000, |
| "step": 42500 |
| }, |
| { |
| "epoch": 0.28587620215147064, |
| "eval_loss": 2.9728448390960693, |
| "eval_runtime": 51.3574, |
| "eval_samples_per_second": 97.357, |
| "eval_steps_per_second": 24.339, |
| "num_input_tokens_seen": 11141120000, |
| "step": 42500 |
| }, |
| { |
| "epoch": 0.2862125270951783, |
| "grad_norm": 0.216337651014328, |
| "learning_rate": 0.001, |
| "loss": 3.0786, |
| "num_input_tokens_seen": 11154227200, |
| "step": 42550 |
| }, |
| { |
| "epoch": 0.2865488520388859, |
| "grad_norm": 0.2741137444972992, |
| "learning_rate": 0.001, |
| "loss": 3.0814, |
| "num_input_tokens_seen": 11167334400, |
| "step": 42600 |
| }, |
| { |
| "epoch": 0.2868851769825935, |
| "grad_norm": 0.22545816004276276, |
| "learning_rate": 0.001, |
| "loss": 3.0808, |
| "num_input_tokens_seen": 11180441600, |
| "step": 42650 |
| }, |
| { |
| "epoch": 0.28722150192630114, |
| "grad_norm": 0.2085258960723877, |
| "learning_rate": 0.001, |
| "loss": 3.0696, |
| "num_input_tokens_seen": 11193548800, |
| "step": 42700 |
| }, |
| { |
| "epoch": 0.28755782687000875, |
| "grad_norm": 0.25214484333992004, |
| "learning_rate": 0.001, |
| "loss": 3.0787, |
| "num_input_tokens_seen": 11206656000, |
| "step": 42750 |
| }, |
| { |
| "epoch": 0.28789415181371636, |
| "grad_norm": 0.23247800767421722, |
| "learning_rate": 0.001, |
| "loss": 3.0718, |
| "num_input_tokens_seen": 11219763200, |
| "step": 42800 |
| }, |
| { |
| "epoch": 0.28823047675742397, |
| "grad_norm": 0.22879773378372192, |
| "learning_rate": 0.001, |
| "loss": 3.0709, |
| "num_input_tokens_seen": 11232870400, |
| "step": 42850 |
| }, |
| { |
| "epoch": 0.2885668017011316, |
| "grad_norm": 0.19782567024230957, |
| "learning_rate": 0.001, |
| "loss": 3.07, |
| "num_input_tokens_seen": 11245977600, |
| "step": 42900 |
| }, |
| { |
| "epoch": 0.2889031266448392, |
| "grad_norm": 0.2164357751607895, |
| "learning_rate": 0.001, |
| "loss": 3.0614, |
| "num_input_tokens_seen": 11259084800, |
| "step": 42950 |
| }, |
| { |
| "epoch": 0.2892394515885468, |
| "grad_norm": 0.2364019900560379, |
| "learning_rate": 0.001, |
| "loss": 3.071, |
| "num_input_tokens_seen": 11272192000, |
| "step": 43000 |
| }, |
| { |
| "epoch": 0.2892394515885468, |
| "eval_loss": 2.969633102416992, |
| "eval_runtime": 51.5112, |
| "eval_samples_per_second": 97.066, |
| "eval_steps_per_second": 24.267, |
| "num_input_tokens_seen": 11272192000, |
| "step": 43000 |
| }, |
| { |
| "epoch": 0.2895757765322544, |
| "grad_norm": 0.2350464016199112, |
| "learning_rate": 0.001, |
| "loss": 3.0636, |
| "num_input_tokens_seen": 11285299200, |
| "step": 43050 |
| }, |
| { |
| "epoch": 0.289912101475962, |
| "grad_norm": 0.2345239371061325, |
| "learning_rate": 0.001, |
| "loss": 3.0764, |
| "num_input_tokens_seen": 11298406400, |
| "step": 43100 |
| }, |
| { |
| "epoch": 0.29024842641966964, |
| "grad_norm": 0.2316889762878418, |
| "learning_rate": 0.001, |
| "loss": 3.0799, |
| "num_input_tokens_seen": 11311513600, |
| "step": 43150 |
| }, |
| { |
| "epoch": 0.29058475136337725, |
| "grad_norm": 0.17912918329238892, |
| "learning_rate": 0.001, |
| "loss": 3.0822, |
| "num_input_tokens_seen": 11324620800, |
| "step": 43200 |
| }, |
| { |
| "epoch": 0.29092107630708486, |
| "grad_norm": 0.18596945703029633, |
| "learning_rate": 0.001, |
| "loss": 3.0599, |
| "num_input_tokens_seen": 11337728000, |
| "step": 43250 |
| }, |
| { |
| "epoch": 0.29125740125079247, |
| "grad_norm": 0.20373962819576263, |
| "learning_rate": 0.001, |
| "loss": 3.0668, |
| "num_input_tokens_seen": 11350835200, |
| "step": 43300 |
| }, |
| { |
| "epoch": 0.2915937261945001, |
| "grad_norm": 0.17628611624240875, |
| "learning_rate": 0.001, |
| "loss": 3.0642, |
| "num_input_tokens_seen": 11363942400, |
| "step": 43350 |
| }, |
| { |
| "epoch": 0.2919300511382077, |
| "grad_norm": 0.17134816944599152, |
| "learning_rate": 0.001, |
| "loss": 3.0711, |
| "num_input_tokens_seen": 11377049600, |
| "step": 43400 |
| }, |
| { |
| "epoch": 0.2922663760819153, |
| "grad_norm": 0.18842625617980957, |
| "learning_rate": 0.001, |
| "loss": 3.0656, |
| "num_input_tokens_seen": 11390156800, |
| "step": 43450 |
| }, |
| { |
| "epoch": 0.2926027010256229, |
| "grad_norm": 0.20406392216682434, |
| "learning_rate": 0.001, |
| "loss": 3.0664, |
| "num_input_tokens_seen": 11403264000, |
| "step": 43500 |
| }, |
| { |
| "epoch": 0.2926027010256229, |
| "eval_loss": 2.967707872390747, |
| "eval_runtime": 50.7844, |
| "eval_samples_per_second": 98.455, |
| "eval_steps_per_second": 24.614, |
| "num_input_tokens_seen": 11403264000, |
| "step": 43500 |
| }, |
| { |
| "epoch": 0.2929390259693305, |
| "grad_norm": 0.1807146519422531, |
| "learning_rate": 0.001, |
| "loss": 3.0722, |
| "num_input_tokens_seen": 11416371200, |
| "step": 43550 |
| }, |
| { |
| "epoch": 0.29327535091303814, |
| "grad_norm": 0.18754515051841736, |
| "learning_rate": 0.001, |
| "loss": 3.0705, |
| "num_input_tokens_seen": 11429478400, |
| "step": 43600 |
| }, |
| { |
| "epoch": 0.29361167585674575, |
| "grad_norm": 0.21045394241809845, |
| "learning_rate": 0.001, |
| "loss": 3.0727, |
| "num_input_tokens_seen": 11442585600, |
| "step": 43650 |
| }, |
| { |
| "epoch": 0.29394800080045336, |
| "grad_norm": 0.2657870054244995, |
| "learning_rate": 0.001, |
| "loss": 3.0692, |
| "num_input_tokens_seen": 11455692800, |
| "step": 43700 |
| }, |
| { |
| "epoch": 0.29428432574416097, |
| "grad_norm": 0.18931645154953003, |
| "learning_rate": 0.001, |
| "loss": 3.0773, |
| "num_input_tokens_seen": 11468800000, |
| "step": 43750 |
| }, |
| { |
| "epoch": 0.2946206506878686, |
| "grad_norm": 0.18956629931926727, |
| "learning_rate": 0.001, |
| "loss": 3.0638, |
| "num_input_tokens_seen": 11481907200, |
| "step": 43800 |
| }, |
| { |
| "epoch": 0.2949569756315762, |
| "grad_norm": 0.18412917852401733, |
| "learning_rate": 0.001, |
| "loss": 3.0673, |
| "num_input_tokens_seen": 11495014400, |
| "step": 43850 |
| }, |
| { |
| "epoch": 0.2952933005752838, |
| "grad_norm": 0.18386723101139069, |
| "learning_rate": 0.001, |
| "loss": 3.0532, |
| "num_input_tokens_seen": 11508121600, |
| "step": 43900 |
| }, |
| { |
| "epoch": 0.2956296255189914, |
| "grad_norm": 1.7288094758987427, |
| "learning_rate": 0.001, |
| "loss": 3.0686, |
| "num_input_tokens_seen": 11521228800, |
| "step": 43950 |
| }, |
| { |
| "epoch": 0.295965950462699, |
| "grad_norm": 1.273023009300232, |
| "learning_rate": 0.001, |
| "loss": 3.0844, |
| "num_input_tokens_seen": 11534336000, |
| "step": 44000 |
| }, |
| { |
| "epoch": 0.295965950462699, |
| "eval_loss": 2.988032102584839, |
| "eval_runtime": 51.218, |
| "eval_samples_per_second": 97.622, |
| "eval_steps_per_second": 24.405, |
| "num_input_tokens_seen": 11534336000, |
| "step": 44000 |
| }, |
| { |
| "epoch": 0.29630227540640663, |
| "grad_norm": 0.22384904325008392, |
| "learning_rate": 0.001, |
| "loss": 3.0741, |
| "num_input_tokens_seen": 11547443200, |
| "step": 44050 |
| }, |
| { |
| "epoch": 0.29663860035011425, |
| "grad_norm": 0.2000838816165924, |
| "learning_rate": 0.001, |
| "loss": 3.0681, |
| "num_input_tokens_seen": 11560550400, |
| "step": 44100 |
| }, |
| { |
| "epoch": 0.29697492529382186, |
| "grad_norm": 0.5984578728675842, |
| "learning_rate": 0.001, |
| "loss": 3.0652, |
| "num_input_tokens_seen": 11573657600, |
| "step": 44150 |
| }, |
| { |
| "epoch": 0.29731125023752947, |
| "grad_norm": 0.20970633625984192, |
| "learning_rate": 0.001, |
| "loss": 3.0799, |
| "num_input_tokens_seen": 11586764800, |
| "step": 44200 |
| }, |
| { |
| "epoch": 0.2976475751812371, |
| "grad_norm": 0.18818268179893494, |
| "learning_rate": 0.001, |
| "loss": 3.0719, |
| "num_input_tokens_seen": 11599872000, |
| "step": 44250 |
| }, |
| { |
| "epoch": 0.2979839001249447, |
| "grad_norm": 0.2058591991662979, |
| "learning_rate": 0.001, |
| "loss": 3.074, |
| "num_input_tokens_seen": 11612979200, |
| "step": 44300 |
| }, |
| { |
| "epoch": 0.29832022506865236, |
| "grad_norm": 0.40354540944099426, |
| "learning_rate": 0.001, |
| "loss": 3.0809, |
| "num_input_tokens_seen": 11626086400, |
| "step": 44350 |
| }, |
| { |
| "epoch": 0.29865655001235997, |
| "grad_norm": 0.1923748105764389, |
| "learning_rate": 0.001, |
| "loss": 3.0769, |
| "num_input_tokens_seen": 11639193600, |
| "step": 44400 |
| }, |
| { |
| "epoch": 0.2989928749560676, |
| "grad_norm": 0.24034352600574493, |
| "learning_rate": 0.001, |
| "loss": 3.0648, |
| "num_input_tokens_seen": 11652300800, |
| "step": 44450 |
| }, |
| { |
| "epoch": 0.2993291998997752, |
| "grad_norm": 0.2124001830816269, |
| "learning_rate": 0.001, |
| "loss": 3.0591, |
| "num_input_tokens_seen": 11665408000, |
| "step": 44500 |
| }, |
| { |
| "epoch": 0.2993291998997752, |
| "eval_loss": 2.9622106552124023, |
| "eval_runtime": 51.3129, |
| "eval_samples_per_second": 97.441, |
| "eval_steps_per_second": 24.36, |
| "num_input_tokens_seen": 11665408000, |
| "step": 44500 |
| }, |
| { |
| "epoch": 0.2996655248434828, |
| "grad_norm": 0.2701764702796936, |
| "learning_rate": 0.001, |
| "loss": 3.0739, |
| "num_input_tokens_seen": 11678515200, |
| "step": 44550 |
| }, |
| { |
| "epoch": 0.3000018497871904, |
| "grad_norm": 0.20468254387378693, |
| "learning_rate": 0.001, |
| "loss": 3.0724, |
| "num_input_tokens_seen": 11691622400, |
| "step": 44600 |
| }, |
| { |
| "epoch": 0.300338174730898, |
| "grad_norm": 0.18791192770004272, |
| "learning_rate": 0.001, |
| "loss": 3.0705, |
| "num_input_tokens_seen": 11704729600, |
| "step": 44650 |
| }, |
| { |
| "epoch": 0.30067449967460563, |
| "grad_norm": 0.21384365856647491, |
| "learning_rate": 0.001, |
| "loss": 3.0719, |
| "num_input_tokens_seen": 11717836800, |
| "step": 44700 |
| }, |
| { |
| "epoch": 0.30101082461831324, |
| "grad_norm": 0.20965896546840668, |
| "learning_rate": 0.001, |
| "loss": 3.0575, |
| "num_input_tokens_seen": 11730944000, |
| "step": 44750 |
| }, |
| { |
| "epoch": 0.30134714956202086, |
| "grad_norm": 0.4128492772579193, |
| "learning_rate": 0.001, |
| "loss": 3.0948, |
| "num_input_tokens_seen": 11744051200, |
| "step": 44800 |
| }, |
| { |
| "epoch": 0.30168347450572847, |
| "grad_norm": 0.27056023478507996, |
| "learning_rate": 0.001, |
| "loss": 3.0807, |
| "num_input_tokens_seen": 11757158400, |
| "step": 44850 |
| }, |
| { |
| "epoch": 0.3020197994494361, |
| "grad_norm": 0.1866568773984909, |
| "learning_rate": 0.001, |
| "loss": 3.0737, |
| "num_input_tokens_seen": 11770265600, |
| "step": 44900 |
| }, |
| { |
| "epoch": 0.3023561243931437, |
| "grad_norm": 0.21440774202346802, |
| "learning_rate": 0.001, |
| "loss": 3.0804, |
| "num_input_tokens_seen": 11783372800, |
| "step": 44950 |
| }, |
| { |
| "epoch": 0.3026924493368513, |
| "grad_norm": 0.30685120820999146, |
| "learning_rate": 0.001, |
| "loss": 3.0603, |
| "num_input_tokens_seen": 11796480000, |
| "step": 45000 |
| }, |
| { |
| "epoch": 0.3026924493368513, |
| "eval_loss": 2.966905355453491, |
| "eval_runtime": 51.6659, |
| "eval_samples_per_second": 96.776, |
| "eval_steps_per_second": 24.194, |
| "num_input_tokens_seen": 11796480000, |
| "step": 45000 |
| }, |
| { |
| "epoch": 0.3030287742805589, |
| "grad_norm": 0.22337579727172852, |
| "learning_rate": 0.001, |
| "loss": 3.0839, |
| "num_input_tokens_seen": 11809587200, |
| "step": 45050 |
| }, |
| { |
| "epoch": 0.3033650992242665, |
| "grad_norm": 0.23798304796218872, |
| "learning_rate": 0.001, |
| "loss": 3.0729, |
| "num_input_tokens_seen": 11822694400, |
| "step": 45100 |
| }, |
| { |
| "epoch": 0.30370142416797413, |
| "grad_norm": 0.1956755667924881, |
| "learning_rate": 0.001, |
| "loss": 3.071, |
| "num_input_tokens_seen": 11835801600, |
| "step": 45150 |
| }, |
| { |
| "epoch": 0.30403774911168174, |
| "grad_norm": 0.20110267400741577, |
| "learning_rate": 0.001, |
| "loss": 3.0662, |
| "num_input_tokens_seen": 11848908800, |
| "step": 45200 |
| }, |
| { |
| "epoch": 0.30437407405538935, |
| "grad_norm": 0.20845186710357666, |
| "learning_rate": 0.001, |
| "loss": 3.0627, |
| "num_input_tokens_seen": 11862016000, |
| "step": 45250 |
| }, |
| { |
| "epoch": 0.30471039899909697, |
| "grad_norm": 0.17928333580493927, |
| "learning_rate": 0.001, |
| "loss": 3.0543, |
| "num_input_tokens_seen": 11875123200, |
| "step": 45300 |
| }, |
| { |
| "epoch": 0.3050467239428046, |
| "grad_norm": 0.17617329955101013, |
| "learning_rate": 0.001, |
| "loss": 3.0614, |
| "num_input_tokens_seen": 11888230400, |
| "step": 45350 |
| }, |
| { |
| "epoch": 0.3053830488865122, |
| "grad_norm": 0.2610914409160614, |
| "learning_rate": 0.001, |
| "loss": 3.069, |
| "num_input_tokens_seen": 11901337600, |
| "step": 45400 |
| }, |
| { |
| "epoch": 0.3057193738302198, |
| "grad_norm": 0.3862092196941376, |
| "learning_rate": 0.001, |
| "loss": 3.0944, |
| "num_input_tokens_seen": 11914444800, |
| "step": 45450 |
| }, |
| { |
| "epoch": 0.3060556987739274, |
| "grad_norm": 0.40467047691345215, |
| "learning_rate": 0.001, |
| "loss": 3.0714, |
| "num_input_tokens_seen": 11927552000, |
| "step": 45500 |
| }, |
| { |
| "epoch": 0.3060556987739274, |
| "eval_loss": 2.965502977371216, |
| "eval_runtime": 51.4918, |
| "eval_samples_per_second": 97.103, |
| "eval_steps_per_second": 24.276, |
| "num_input_tokens_seen": 11927552000, |
| "step": 45500 |
| }, |
| { |
| "epoch": 0.306392023717635, |
| "grad_norm": 0.19686584174633026, |
| "learning_rate": 0.001, |
| "loss": 3.0673, |
| "num_input_tokens_seen": 11940659200, |
| "step": 45550 |
| }, |
| { |
| "epoch": 0.30672834866134263, |
| "grad_norm": 0.24866420030593872, |
| "learning_rate": 0.001, |
| "loss": 3.0773, |
| "num_input_tokens_seen": 11953766400, |
| "step": 45600 |
| }, |
| { |
| "epoch": 0.30706467360505024, |
| "grad_norm": 0.208501935005188, |
| "learning_rate": 0.001, |
| "loss": 3.0751, |
| "num_input_tokens_seen": 11966873600, |
| "step": 45650 |
| }, |
| { |
| "epoch": 0.30740099854875785, |
| "grad_norm": 0.20565010607242584, |
| "learning_rate": 0.001, |
| "loss": 3.0709, |
| "num_input_tokens_seen": 11979980800, |
| "step": 45700 |
| }, |
| { |
| "epoch": 0.30773732349246546, |
| "grad_norm": 0.21517585217952728, |
| "learning_rate": 0.001, |
| "loss": 3.0765, |
| "num_input_tokens_seen": 11993088000, |
| "step": 45750 |
| }, |
| { |
| "epoch": 0.3080736484361731, |
| "grad_norm": 0.2618497610092163, |
| "learning_rate": 0.001, |
| "loss": 3.0549, |
| "num_input_tokens_seen": 12006195200, |
| "step": 45800 |
| }, |
| { |
| "epoch": 0.3084099733798807, |
| "grad_norm": 0.24163542687892914, |
| "learning_rate": 0.001, |
| "loss": 3.0704, |
| "num_input_tokens_seen": 12019302400, |
| "step": 45850 |
| }, |
| { |
| "epoch": 0.3087462983235883, |
| "grad_norm": 0.2038656324148178, |
| "learning_rate": 0.001, |
| "loss": 3.0631, |
| "num_input_tokens_seen": 12032409600, |
| "step": 45900 |
| }, |
| { |
| "epoch": 0.3090826232672959, |
| "grad_norm": 0.20691357553005219, |
| "learning_rate": 0.001, |
| "loss": 3.0723, |
| "num_input_tokens_seen": 12045516800, |
| "step": 45950 |
| }, |
| { |
| "epoch": 0.3094189482110035, |
| "grad_norm": 0.18757498264312744, |
| "learning_rate": 0.001, |
| "loss": 3.0602, |
| "num_input_tokens_seen": 12058624000, |
| "step": 46000 |
| }, |
| { |
| "epoch": 0.3094189482110035, |
| "eval_loss": 2.9599878787994385, |
| "eval_runtime": 53.3376, |
| "eval_samples_per_second": 93.742, |
| "eval_steps_per_second": 23.436, |
| "num_input_tokens_seen": 12058624000, |
| "step": 46000 |
| }, |
| { |
| "epoch": 0.30975527315471113, |
| "grad_norm": 0.1939045637845993, |
| "learning_rate": 0.001, |
| "loss": 3.0701, |
| "num_input_tokens_seen": 12071731200, |
| "step": 46050 |
| }, |
| { |
| "epoch": 0.31009159809841874, |
| "grad_norm": 0.22705882787704468, |
| "learning_rate": 0.001, |
| "loss": 3.0574, |
| "num_input_tokens_seen": 12084838400, |
| "step": 46100 |
| }, |
| { |
| "epoch": 0.3104279230421264, |
| "grad_norm": 0.2075151801109314, |
| "learning_rate": 0.001, |
| "loss": 3.067, |
| "num_input_tokens_seen": 12097945600, |
| "step": 46150 |
| }, |
| { |
| "epoch": 0.310764247985834, |
| "grad_norm": 0.4686187207698822, |
| "learning_rate": 0.001, |
| "loss": 3.0656, |
| "num_input_tokens_seen": 12111052800, |
| "step": 46200 |
| }, |
| { |
| "epoch": 0.31110057292954163, |
| "grad_norm": 0.1929931640625, |
| "learning_rate": 0.001, |
| "loss": 3.0631, |
| "num_input_tokens_seen": 12124160000, |
| "step": 46250 |
| }, |
| { |
| "epoch": 0.31143689787324924, |
| "grad_norm": 0.18403789401054382, |
| "learning_rate": 0.001, |
| "loss": 3.0579, |
| "num_input_tokens_seen": 12137267200, |
| "step": 46300 |
| }, |
| { |
| "epoch": 0.31177322281695685, |
| "grad_norm": 0.18552987277507782, |
| "learning_rate": 0.001, |
| "loss": 3.0625, |
| "num_input_tokens_seen": 12150374400, |
| "step": 46350 |
| }, |
| { |
| "epoch": 0.31210954776066446, |
| "grad_norm": 0.24002918601036072, |
| "learning_rate": 0.001, |
| "loss": 3.0629, |
| "num_input_tokens_seen": 12163481600, |
| "step": 46400 |
| }, |
| { |
| "epoch": 0.3124458727043721, |
| "grad_norm": 0.17444545030593872, |
| "learning_rate": 0.001, |
| "loss": 3.055, |
| "num_input_tokens_seen": 12176588800, |
| "step": 46450 |
| }, |
| { |
| "epoch": 0.3127821976480797, |
| "grad_norm": 0.1911567747592926, |
| "learning_rate": 0.001, |
| "loss": 3.067, |
| "num_input_tokens_seen": 12189696000, |
| "step": 46500 |
| }, |
| { |
| "epoch": 0.3127821976480797, |
| "eval_loss": 2.9570987224578857, |
| "eval_runtime": 52.5377, |
| "eval_samples_per_second": 95.17, |
| "eval_steps_per_second": 23.792, |
| "num_input_tokens_seen": 12189696000, |
| "step": 46500 |
| }, |
| { |
| "epoch": 0.3131185225917873, |
| "grad_norm": 0.18903926014900208, |
| "learning_rate": 0.001, |
| "loss": 3.0499, |
| "num_input_tokens_seen": 12202803200, |
| "step": 46550 |
| }, |
| { |
| "epoch": 0.3134548475354949, |
| "grad_norm": 0.35490429401397705, |
| "learning_rate": 0.001, |
| "loss": 3.0573, |
| "num_input_tokens_seen": 12215910400, |
| "step": 46600 |
| }, |
| { |
| "epoch": 0.3137911724792025, |
| "grad_norm": 0.2066306322813034, |
| "learning_rate": 0.001, |
| "loss": 3.0613, |
| "num_input_tokens_seen": 12229017600, |
| "step": 46650 |
| }, |
| { |
| "epoch": 0.31412749742291013, |
| "grad_norm": 0.3016819357872009, |
| "learning_rate": 0.001, |
| "loss": 3.068, |
| "num_input_tokens_seen": 12242124800, |
| "step": 46700 |
| }, |
| { |
| "epoch": 0.31446382236661774, |
| "grad_norm": 0.22070977091789246, |
| "learning_rate": 0.001, |
| "loss": 3.0929, |
| "num_input_tokens_seen": 12255232000, |
| "step": 46750 |
| }, |
| { |
| "epoch": 0.31480014731032535, |
| "grad_norm": 0.21311117708683014, |
| "learning_rate": 0.001, |
| "loss": 3.0739, |
| "num_input_tokens_seen": 12268339200, |
| "step": 46800 |
| }, |
| { |
| "epoch": 0.31513647225403296, |
| "grad_norm": 0.22895431518554688, |
| "learning_rate": 0.001, |
| "loss": 3.0726, |
| "num_input_tokens_seen": 12281446400, |
| "step": 46850 |
| }, |
| { |
| "epoch": 0.3154727971977406, |
| "grad_norm": 0.304040789604187, |
| "learning_rate": 0.001, |
| "loss": 3.0561, |
| "num_input_tokens_seen": 12294553600, |
| "step": 46900 |
| }, |
| { |
| "epoch": 0.3158091221414482, |
| "grad_norm": 0.18291215598583221, |
| "learning_rate": 0.001, |
| "loss": 3.0671, |
| "num_input_tokens_seen": 12307660800, |
| "step": 46950 |
| }, |
| { |
| "epoch": 0.3161454470851558, |
| "grad_norm": 0.19144318997859955, |
| "learning_rate": 0.001, |
| "loss": 3.0676, |
| "num_input_tokens_seen": 12320768000, |
| "step": 47000 |
| }, |
| { |
| "epoch": 0.3161454470851558, |
| "eval_loss": 2.9561285972595215, |
| "eval_runtime": 53.2725, |
| "eval_samples_per_second": 93.857, |
| "eval_steps_per_second": 23.464, |
| "num_input_tokens_seen": 12320768000, |
| "step": 47000 |
| }, |
| { |
| "epoch": 0.3164817720288634, |
| "grad_norm": 0.1988057643175125, |
| "learning_rate": 0.001, |
| "loss": 3.0652, |
| "num_input_tokens_seen": 12333875200, |
| "step": 47050 |
| }, |
| { |
| "epoch": 0.316818096972571, |
| "grad_norm": 0.19520634412765503, |
| "learning_rate": 0.001, |
| "loss": 3.0641, |
| "num_input_tokens_seen": 12346982400, |
| "step": 47100 |
| }, |
| { |
| "epoch": 0.31715442191627863, |
| "grad_norm": 0.21420574188232422, |
| "learning_rate": 0.001, |
| "loss": 3.0665, |
| "num_input_tokens_seen": 12360089600, |
| "step": 47150 |
| }, |
| { |
| "epoch": 0.31749074685998624, |
| "grad_norm": 0.18173083662986755, |
| "learning_rate": 0.001, |
| "loss": 3.0565, |
| "num_input_tokens_seen": 12373196800, |
| "step": 47200 |
| }, |
| { |
| "epoch": 0.31782707180369385, |
| "grad_norm": 0.1746867150068283, |
| "learning_rate": 0.001, |
| "loss": 3.0739, |
| "num_input_tokens_seen": 12386304000, |
| "step": 47250 |
| }, |
| { |
| "epoch": 0.31816339674740146, |
| "grad_norm": 0.16941632330417633, |
| "learning_rate": 0.001, |
| "loss": 3.0514, |
| "num_input_tokens_seen": 12399411200, |
| "step": 47300 |
| }, |
| { |
| "epoch": 0.3184997216911091, |
| "grad_norm": 0.19572339951992035, |
| "learning_rate": 0.001, |
| "loss": 3.0512, |
| "num_input_tokens_seen": 12412518400, |
| "step": 47350 |
| }, |
| { |
| "epoch": 0.3188360466348167, |
| "grad_norm": 0.19083815813064575, |
| "learning_rate": 0.001, |
| "loss": 3.0482, |
| "num_input_tokens_seen": 12425625600, |
| "step": 47400 |
| }, |
| { |
| "epoch": 0.3191723715785243, |
| "grad_norm": 0.1741664558649063, |
| "learning_rate": 0.001, |
| "loss": 3.0544, |
| "num_input_tokens_seen": 12438732800, |
| "step": 47450 |
| }, |
| { |
| "epoch": 0.3195086965222319, |
| "grad_norm": 0.1787065714597702, |
| "learning_rate": 0.001, |
| "loss": 3.0544, |
| "num_input_tokens_seen": 12451840000, |
| "step": 47500 |
| }, |
| { |
| "epoch": 0.3195086965222319, |
| "eval_loss": 2.953366756439209, |
| "eval_runtime": 53.4179, |
| "eval_samples_per_second": 93.602, |
| "eval_steps_per_second": 23.4, |
| "num_input_tokens_seen": 12451840000, |
| "step": 47500 |
| }, |
| { |
| "epoch": 0.3198450214659395, |
| "grad_norm": 0.1822129189968109, |
| "learning_rate": 0.001, |
| "loss": 3.0606, |
| "num_input_tokens_seen": 12464947200, |
| "step": 47550 |
| }, |
| { |
| "epoch": 0.3201813464096471, |
| "grad_norm": 0.20426377654075623, |
| "learning_rate": 0.001, |
| "loss": 3.0586, |
| "num_input_tokens_seen": 12478054400, |
| "step": 47600 |
| }, |
| { |
| "epoch": 0.32051767135335474, |
| "grad_norm": 0.2057754248380661, |
| "learning_rate": 0.001, |
| "loss": 3.0604, |
| "num_input_tokens_seen": 12491161600, |
| "step": 47650 |
| }, |
| { |
| "epoch": 0.32085399629706235, |
| "grad_norm": 0.19302618503570557, |
| "learning_rate": 0.001, |
| "loss": 3.0578, |
| "num_input_tokens_seen": 12504268800, |
| "step": 47700 |
| }, |
| { |
| "epoch": 0.32119032124076996, |
| "grad_norm": 0.4289242625236511, |
| "learning_rate": 0.001, |
| "loss": 3.0563, |
| "num_input_tokens_seen": 12517376000, |
| "step": 47750 |
| }, |
| { |
| "epoch": 0.32152664618447757, |
| "grad_norm": 0.6544061899185181, |
| "learning_rate": 0.001, |
| "loss": 3.072, |
| "num_input_tokens_seen": 12530483200, |
| "step": 47800 |
| }, |
| { |
| "epoch": 0.3218629711281852, |
| "grad_norm": 0.27349674701690674, |
| "learning_rate": 0.001, |
| "loss": 3.077, |
| "num_input_tokens_seen": 12543590400, |
| "step": 47850 |
| }, |
| { |
| "epoch": 0.3221992960718928, |
| "grad_norm": 0.21640093624591827, |
| "learning_rate": 0.001, |
| "loss": 3.0665, |
| "num_input_tokens_seen": 12556697600, |
| "step": 47900 |
| }, |
| { |
| "epoch": 0.32253562101560046, |
| "grad_norm": 0.19193384051322937, |
| "learning_rate": 0.001, |
| "loss": 3.0542, |
| "num_input_tokens_seen": 12569804800, |
| "step": 47950 |
| }, |
| { |
| "epoch": 0.32287194595930807, |
| "grad_norm": 0.21732182800769806, |
| "learning_rate": 0.001, |
| "loss": 3.0489, |
| "num_input_tokens_seen": 12582912000, |
| "step": 48000 |
| }, |
| { |
| "epoch": 0.32287194595930807, |
| "eval_loss": 2.95477294921875, |
| "eval_runtime": 53.2298, |
| "eval_samples_per_second": 93.932, |
| "eval_steps_per_second": 23.483, |
| "num_input_tokens_seen": 12582912000, |
| "step": 48000 |
| }, |
| { |
| "epoch": 0.3232082709030157, |
| "grad_norm": 0.1941204071044922, |
| "learning_rate": 0.001, |
| "loss": 3.0582, |
| "num_input_tokens_seen": 12596019200, |
| "step": 48050 |
| }, |
| { |
| "epoch": 0.3235445958467233, |
| "grad_norm": 4.390545845031738, |
| "learning_rate": 0.001, |
| "loss": 3.0713, |
| "num_input_tokens_seen": 12609126400, |
| "step": 48100 |
| }, |
| { |
| "epoch": 0.3238809207904309, |
| "grad_norm": 0.2377273291349411, |
| "learning_rate": 0.001, |
| "loss": 3.0792, |
| "num_input_tokens_seen": 12622233600, |
| "step": 48150 |
| }, |
| { |
| "epoch": 0.3242172457341385, |
| "grad_norm": 0.20397226512432098, |
| "learning_rate": 0.001, |
| "loss": 3.0718, |
| "num_input_tokens_seen": 12635340800, |
| "step": 48200 |
| }, |
| { |
| "epoch": 0.3245535706778461, |
| "grad_norm": 0.21039831638336182, |
| "learning_rate": 0.001, |
| "loss": 3.0669, |
| "num_input_tokens_seen": 12648448000, |
| "step": 48250 |
| }, |
| { |
| "epoch": 0.32488989562155374, |
| "grad_norm": 0.18443848192691803, |
| "learning_rate": 0.001, |
| "loss": 3.0723, |
| "num_input_tokens_seen": 12661555200, |
| "step": 48300 |
| }, |
| { |
| "epoch": 0.32522622056526135, |
| "grad_norm": 0.1816088706254959, |
| "learning_rate": 0.001, |
| "loss": 3.0516, |
| "num_input_tokens_seen": 12674662400, |
| "step": 48350 |
| }, |
| { |
| "epoch": 0.32556254550896896, |
| "grad_norm": 0.17938339710235596, |
| "learning_rate": 0.001, |
| "loss": 3.0567, |
| "num_input_tokens_seen": 12687769600, |
| "step": 48400 |
| }, |
| { |
| "epoch": 0.32589887045267657, |
| "grad_norm": 0.2365075796842575, |
| "learning_rate": 0.001, |
| "loss": 3.0673, |
| "num_input_tokens_seen": 12700876800, |
| "step": 48450 |
| }, |
| { |
| "epoch": 0.3262351953963842, |
| "grad_norm": 0.24168556928634644, |
| "learning_rate": 0.001, |
| "loss": 3.072, |
| "num_input_tokens_seen": 12713984000, |
| "step": 48500 |
| }, |
| { |
| "epoch": 0.3262351953963842, |
| "eval_loss": 2.967775583267212, |
| "eval_runtime": 53.2002, |
| "eval_samples_per_second": 93.985, |
| "eval_steps_per_second": 23.496, |
| "num_input_tokens_seen": 12713984000, |
| "step": 48500 |
| }, |
| { |
| "epoch": 0.3265715203400918, |
| "grad_norm": 0.3560108542442322, |
| "learning_rate": 0.001, |
| "loss": 3.0714, |
| "num_input_tokens_seen": 12727091200, |
| "step": 48550 |
| }, |
| { |
| "epoch": 0.3269078452837994, |
| "grad_norm": 2.40458345413208, |
| "learning_rate": 0.001, |
| "loss": 3.0729, |
| "num_input_tokens_seen": 12740198400, |
| "step": 48600 |
| }, |
| { |
| "epoch": 0.327244170227507, |
| "grad_norm": 0.3201708495616913, |
| "learning_rate": 0.001, |
| "loss": 3.0719, |
| "num_input_tokens_seen": 12753305600, |
| "step": 48650 |
| }, |
| { |
| "epoch": 0.3275804951712146, |
| "grad_norm": 0.2094539850950241, |
| "learning_rate": 0.001, |
| "loss": 3.0559, |
| "num_input_tokens_seen": 12766412800, |
| "step": 48700 |
| }, |
| { |
| "epoch": 0.32791682011492224, |
| "grad_norm": 0.2323814332485199, |
| "learning_rate": 0.001, |
| "loss": 3.0652, |
| "num_input_tokens_seen": 12779520000, |
| "step": 48750 |
| }, |
| { |
| "epoch": 0.32825314505862985, |
| "grad_norm": 0.20684729516506195, |
| "learning_rate": 0.001, |
| "loss": 3.0631, |
| "num_input_tokens_seen": 12792627200, |
| "step": 48800 |
| }, |
| { |
| "epoch": 0.32858947000233746, |
| "grad_norm": 0.19242416322231293, |
| "learning_rate": 0.001, |
| "loss": 3.0578, |
| "num_input_tokens_seen": 12805734400, |
| "step": 48850 |
| }, |
| { |
| "epoch": 0.32892579494604507, |
| "grad_norm": 0.1994556188583374, |
| "learning_rate": 0.001, |
| "loss": 3.0615, |
| "num_input_tokens_seen": 12818841600, |
| "step": 48900 |
| }, |
| { |
| "epoch": 0.3292621198897527, |
| "grad_norm": 0.19869546592235565, |
| "learning_rate": 0.001, |
| "loss": 3.0647, |
| "num_input_tokens_seen": 12831948800, |
| "step": 48950 |
| }, |
| { |
| "epoch": 0.3295984448334603, |
| "grad_norm": 0.21512825787067413, |
| "learning_rate": 0.001, |
| "loss": 3.0473, |
| "num_input_tokens_seen": 12845056000, |
| "step": 49000 |
| }, |
| { |
| "epoch": 0.3295984448334603, |
| "eval_loss": 2.952073335647583, |
| "eval_runtime": 52.8116, |
| "eval_samples_per_second": 94.676, |
| "eval_steps_per_second": 23.669, |
| "num_input_tokens_seen": 12845056000, |
| "step": 49000 |
| }, |
| { |
| "epoch": 0.3299347697771679, |
| "grad_norm": 0.22994808852672577, |
| "learning_rate": 0.001, |
| "loss": 3.0594, |
| "num_input_tokens_seen": 12858163200, |
| "step": 49050 |
| }, |
| { |
| "epoch": 0.3302710947208755, |
| "grad_norm": 0.45408371090888977, |
| "learning_rate": 0.001, |
| "loss": 3.0777, |
| "num_input_tokens_seen": 12871270400, |
| "step": 49100 |
| }, |
| { |
| "epoch": 0.3306074196645831, |
| "grad_norm": 0.2698614001274109, |
| "learning_rate": 0.001, |
| "loss": 3.0689, |
| "num_input_tokens_seen": 12884377600, |
| "step": 49150 |
| }, |
| { |
| "epoch": 0.33094374460829074, |
| "grad_norm": 0.22741588950157166, |
| "learning_rate": 0.001, |
| "loss": 3.0746, |
| "num_input_tokens_seen": 12897484800, |
| "step": 49200 |
| }, |
| { |
| "epoch": 0.33128006955199835, |
| "grad_norm": 0.3616434335708618, |
| "learning_rate": 0.001, |
| "loss": 3.0813, |
| "num_input_tokens_seen": 12910592000, |
| "step": 49250 |
| }, |
| { |
| "epoch": 0.33161639449570596, |
| "grad_norm": 0.2551349401473999, |
| "learning_rate": 0.001, |
| "loss": 3.0749, |
| "num_input_tokens_seen": 12923699200, |
| "step": 49300 |
| }, |
| { |
| "epoch": 0.33195271943941357, |
| "grad_norm": 0.24054627120494843, |
| "learning_rate": 0.001, |
| "loss": 3.0664, |
| "num_input_tokens_seen": 12936806400, |
| "step": 49350 |
| }, |
| { |
| "epoch": 0.3322890443831212, |
| "grad_norm": 0.25859707593917847, |
| "learning_rate": 0.001, |
| "loss": 3.0673, |
| "num_input_tokens_seen": 12949913600, |
| "step": 49400 |
| }, |
| { |
| "epoch": 0.3326253693268288, |
| "grad_norm": 0.2500990629196167, |
| "learning_rate": 0.001, |
| "loss": 3.0575, |
| "num_input_tokens_seen": 12963020800, |
| "step": 49450 |
| }, |
| { |
| "epoch": 0.3329616942705364, |
| "grad_norm": 1.1027246713638306, |
| "learning_rate": 0.001, |
| "loss": 3.0573, |
| "num_input_tokens_seen": 12976128000, |
| "step": 49500 |
| }, |
| { |
| "epoch": 0.3329616942705364, |
| "eval_loss": 2.976292133331299, |
| "eval_runtime": 53.0133, |
| "eval_samples_per_second": 94.316, |
| "eval_steps_per_second": 23.579, |
| "num_input_tokens_seen": 12976128000, |
| "step": 49500 |
| }, |
| { |
| "epoch": 0.333298019214244, |
| "grad_norm": 0.3605392873287201, |
| "learning_rate": 0.001, |
| "loss": 3.0741, |
| "num_input_tokens_seen": 12989235200, |
| "step": 49550 |
| }, |
| { |
| "epoch": 0.3336343441579516, |
| "grad_norm": 0.3265780210494995, |
| "learning_rate": 0.001, |
| "loss": 3.0707, |
| "num_input_tokens_seen": 13002342400, |
| "step": 49600 |
| }, |
| { |
| "epoch": 0.33397066910165923, |
| "grad_norm": 0.4178712069988251, |
| "learning_rate": 0.001, |
| "loss": 3.0681, |
| "num_input_tokens_seen": 13015449600, |
| "step": 49650 |
| }, |
| { |
| "epoch": 0.33430699404536685, |
| "grad_norm": 0.2647295892238617, |
| "learning_rate": 0.001, |
| "loss": 3.0684, |
| "num_input_tokens_seen": 13028556800, |
| "step": 49700 |
| }, |
| { |
| "epoch": 0.3346433189890745, |
| "grad_norm": 0.20664212107658386, |
| "learning_rate": 0.001, |
| "loss": 3.0649, |
| "num_input_tokens_seen": 13041664000, |
| "step": 49750 |
| }, |
| { |
| "epoch": 0.3349796439327821, |
| "grad_norm": 0.45491111278533936, |
| "learning_rate": 0.001, |
| "loss": 3.0667, |
| "num_input_tokens_seen": 13054771200, |
| "step": 49800 |
| }, |
| { |
| "epoch": 0.33531596887648973, |
| "grad_norm": 0.27275514602661133, |
| "learning_rate": 0.001, |
| "loss": 3.0717, |
| "num_input_tokens_seen": 13067878400, |
| "step": 49850 |
| }, |
| { |
| "epoch": 0.33565229382019734, |
| "grad_norm": 0.24294881522655487, |
| "learning_rate": 0.001, |
| "loss": 3.0717, |
| "num_input_tokens_seen": 13080985600, |
| "step": 49900 |
| }, |
| { |
| "epoch": 0.33598861876390496, |
| "grad_norm": 0.2790290415287018, |
| "learning_rate": 0.001, |
| "loss": 3.0687, |
| "num_input_tokens_seen": 13094092800, |
| "step": 49950 |
| }, |
| { |
| "epoch": 0.33632494370761257, |
| "grad_norm": 0.32556888461112976, |
| "learning_rate": 0.001, |
| "loss": 3.0805, |
| "num_input_tokens_seen": 13107200000, |
| "step": 50000 |
| }, |
| { |
| "epoch": 0.33632494370761257, |
| "eval_loss": 2.958136796951294, |
| "eval_runtime": 53.5587, |
| "eval_samples_per_second": 93.355, |
| "eval_steps_per_second": 23.339, |
| "num_input_tokens_seen": 13107200000, |
| "step": 50000 |
| }, |
| { |
| "epoch": 0.3366612686513202, |
| "grad_norm": 0.2707626223564148, |
| "learning_rate": 0.001, |
| "loss": 3.0719, |
| "num_input_tokens_seen": 13120307200, |
| "step": 50050 |
| }, |
| { |
| "epoch": 0.3369975935950278, |
| "grad_norm": 0.28657791018486023, |
| "learning_rate": 0.001, |
| "loss": 3.0713, |
| "num_input_tokens_seen": 13133414400, |
| "step": 50100 |
| }, |
| { |
| "epoch": 0.3373339185387354, |
| "grad_norm": 0.22508807480335236, |
| "learning_rate": 0.001, |
| "loss": 3.0626, |
| "num_input_tokens_seen": 13146521600, |
| "step": 50150 |
| }, |
| { |
| "epoch": 0.337670243482443, |
| "grad_norm": 0.3013211786746979, |
| "learning_rate": 0.001, |
| "loss": 3.0871, |
| "num_input_tokens_seen": 13159628800, |
| "step": 50200 |
| }, |
| { |
| "epoch": 0.3380065684261506, |
| "grad_norm": 0.4010023772716522, |
| "learning_rate": 0.001, |
| "loss": 3.0624, |
| "num_input_tokens_seen": 13172736000, |
| "step": 50250 |
| }, |
| { |
| "epoch": 0.33834289336985823, |
| "grad_norm": 0.23215509951114655, |
| "learning_rate": 0.001, |
| "loss": 3.058, |
| "num_input_tokens_seen": 13185843200, |
| "step": 50300 |
| }, |
| { |
| "epoch": 0.33867921831356584, |
| "grad_norm": 0.3135644495487213, |
| "learning_rate": 0.001, |
| "loss": 3.0668, |
| "num_input_tokens_seen": 13198950400, |
| "step": 50350 |
| }, |
| { |
| "epoch": 0.33901554325727346, |
| "grad_norm": 0.8496716618537903, |
| "learning_rate": 0.001, |
| "loss": 3.0558, |
| "num_input_tokens_seen": 13212057600, |
| "step": 50400 |
| }, |
| { |
| "epoch": 0.33935186820098107, |
| "grad_norm": 0.2706848084926605, |
| "learning_rate": 0.001, |
| "loss": 3.0656, |
| "num_input_tokens_seen": 13225164800, |
| "step": 50450 |
| }, |
| { |
| "epoch": 0.3396881931446887, |
| "grad_norm": 0.24779066443443298, |
| "learning_rate": 0.001, |
| "loss": 3.073, |
| "num_input_tokens_seen": 13238272000, |
| "step": 50500 |
| }, |
| { |
| "epoch": 0.3396881931446887, |
| "eval_loss": 2.9553372859954834, |
| "eval_runtime": 53.3111, |
| "eval_samples_per_second": 93.789, |
| "eval_steps_per_second": 23.447, |
| "num_input_tokens_seen": 13238272000, |
| "step": 50500 |
| }, |
| { |
| "epoch": 0.3400245180883963, |
| "grad_norm": 0.2277699112892151, |
| "learning_rate": 0.001, |
| "loss": 3.0516, |
| "num_input_tokens_seen": 13251379200, |
| "step": 50550 |
| }, |
| { |
| "epoch": 0.3403608430321039, |
| "grad_norm": 0.2331630438566208, |
| "learning_rate": 0.001, |
| "loss": 3.0685, |
| "num_input_tokens_seen": 13264486400, |
| "step": 50600 |
| }, |
| { |
| "epoch": 0.3406971679758115, |
| "grad_norm": 0.2572009563446045, |
| "learning_rate": 0.001, |
| "loss": 3.0628, |
| "num_input_tokens_seen": 13277593600, |
| "step": 50650 |
| }, |
| { |
| "epoch": 0.3410334929195191, |
| "grad_norm": 0.35386911034584045, |
| "learning_rate": 0.001, |
| "loss": 3.0554, |
| "num_input_tokens_seen": 13290700800, |
| "step": 50700 |
| }, |
| { |
| "epoch": 0.34136981786322673, |
| "grad_norm": 0.19923870265483856, |
| "learning_rate": 0.001, |
| "loss": 3.0579, |
| "num_input_tokens_seen": 13303808000, |
| "step": 50750 |
| }, |
| { |
| "epoch": 0.34170614280693434, |
| "grad_norm": 0.22291727364063263, |
| "learning_rate": 0.001, |
| "loss": 3.0653, |
| "num_input_tokens_seen": 13316915200, |
| "step": 50800 |
| }, |
| { |
| "epoch": 0.34204246775064195, |
| "grad_norm": 0.2049180120229721, |
| "learning_rate": 0.001, |
| "loss": 3.0511, |
| "num_input_tokens_seen": 13330022400, |
| "step": 50850 |
| }, |
| { |
| "epoch": 0.34237879269434957, |
| "grad_norm": 0.2586233615875244, |
| "learning_rate": 0.001, |
| "loss": 3.0589, |
| "num_input_tokens_seen": 13343129600, |
| "step": 50900 |
| }, |
| { |
| "epoch": 0.3427151176380572, |
| "grad_norm": 0.2137664556503296, |
| "learning_rate": 0.001, |
| "loss": 3.0522, |
| "num_input_tokens_seen": 13356236800, |
| "step": 50950 |
| }, |
| { |
| "epoch": 0.3430514425817648, |
| "grad_norm": 0.21726618707180023, |
| "learning_rate": 0.001, |
| "loss": 3.054, |
| "num_input_tokens_seen": 13369344000, |
| "step": 51000 |
| }, |
| { |
| "epoch": 0.3430514425817648, |
| "eval_loss": 2.948333740234375, |
| "eval_runtime": 53.0951, |
| "eval_samples_per_second": 94.171, |
| "eval_steps_per_second": 23.543, |
| "num_input_tokens_seen": 13369344000, |
| "step": 51000 |
| }, |
| { |
| "epoch": 0.3433877675254724, |
| "grad_norm": 0.19399498403072357, |
| "learning_rate": 0.001, |
| "loss": 3.0583, |
| "num_input_tokens_seen": 13382451200, |
| "step": 51050 |
| }, |
| { |
| "epoch": 0.34372409246918, |
| "grad_norm": 0.19893072545528412, |
| "learning_rate": 0.001, |
| "loss": 3.0505, |
| "num_input_tokens_seen": 13395558400, |
| "step": 51100 |
| }, |
| { |
| "epoch": 0.3440604174128876, |
| "grad_norm": 0.17791305482387543, |
| "learning_rate": 0.001, |
| "loss": 3.0504, |
| "num_input_tokens_seen": 13408665600, |
| "step": 51150 |
| }, |
| { |
| "epoch": 0.34439674235659523, |
| "grad_norm": 0.7631425261497498, |
| "learning_rate": 0.001, |
| "loss": 3.0483, |
| "num_input_tokens_seen": 13421772800, |
| "step": 51200 |
| }, |
| { |
| "epoch": 0.34473306730030284, |
| "grad_norm": 0.22620978951454163, |
| "learning_rate": 0.001, |
| "loss": 3.0512, |
| "num_input_tokens_seen": 13434880000, |
| "step": 51250 |
| }, |
| { |
| "epoch": 0.34506939224401045, |
| "grad_norm": 0.219919815659523, |
| "learning_rate": 0.001, |
| "loss": 3.0415, |
| "num_input_tokens_seen": 13447987200, |
| "step": 51300 |
| }, |
| { |
| "epoch": 0.34540571718771806, |
| "grad_norm": 0.21654649078845978, |
| "learning_rate": 0.001, |
| "loss": 3.062, |
| "num_input_tokens_seen": 13461094400, |
| "step": 51350 |
| }, |
| { |
| "epoch": 0.3457420421314257, |
| "grad_norm": 0.2439095377922058, |
| "learning_rate": 0.001, |
| "loss": 3.0478, |
| "num_input_tokens_seen": 13474201600, |
| "step": 51400 |
| }, |
| { |
| "epoch": 0.3460783670751333, |
| "grad_norm": 0.19535380601882935, |
| "learning_rate": 0.001, |
| "loss": 3.0444, |
| "num_input_tokens_seen": 13487308800, |
| "step": 51450 |
| }, |
| { |
| "epoch": 0.3464146920188409, |
| "grad_norm": 0.1964534968137741, |
| "learning_rate": 0.001, |
| "loss": 3.049, |
| "num_input_tokens_seen": 13500416000, |
| "step": 51500 |
| }, |
| { |
| "epoch": 0.3464146920188409, |
| "eval_loss": 2.945749044418335, |
| "eval_runtime": 53.0447, |
| "eval_samples_per_second": 94.26, |
| "eval_steps_per_second": 23.565, |
| "num_input_tokens_seen": 13500416000, |
| "step": 51500 |
| }, |
| { |
| "epoch": 0.3467510169625485, |
| "grad_norm": 0.2085062563419342, |
| "learning_rate": 0.001, |
| "loss": 3.0582, |
| "num_input_tokens_seen": 13513523200, |
| "step": 51550 |
| }, |
| { |
| "epoch": 0.3470873419062562, |
| "grad_norm": 0.1903097778558731, |
| "learning_rate": 0.001, |
| "loss": 3.0488, |
| "num_input_tokens_seen": 13526630400, |
| "step": 51600 |
| }, |
| { |
| "epoch": 0.3474236668499638, |
| "grad_norm": 0.20101405680179596, |
| "learning_rate": 0.001, |
| "loss": 3.0573, |
| "num_input_tokens_seen": 13539737600, |
| "step": 51650 |
| }, |
| { |
| "epoch": 0.3477599917936714, |
| "grad_norm": 0.6418889164924622, |
| "learning_rate": 0.001, |
| "loss": 3.0513, |
| "num_input_tokens_seen": 13552844800, |
| "step": 51700 |
| }, |
| { |
| "epoch": 0.348096316737379, |
| "grad_norm": 0.22524093091487885, |
| "learning_rate": 0.001, |
| "loss": 3.0567, |
| "num_input_tokens_seen": 13565952000, |
| "step": 51750 |
| }, |
| { |
| "epoch": 0.3484326416810866, |
| "grad_norm": 0.21830599009990692, |
| "learning_rate": 0.001, |
| "loss": 3.0538, |
| "num_input_tokens_seen": 13579059200, |
| "step": 51800 |
| }, |
| { |
| "epoch": 0.34876896662479423, |
| "grad_norm": 0.6111611127853394, |
| "learning_rate": 0.001, |
| "loss": 3.0581, |
| "num_input_tokens_seen": 13592166400, |
| "step": 51850 |
| }, |
| { |
| "epoch": 0.34910529156850184, |
| "grad_norm": 0.3782864511013031, |
| "learning_rate": 0.001, |
| "loss": 3.0694, |
| "num_input_tokens_seen": 13605273600, |
| "step": 51900 |
| }, |
| { |
| "epoch": 0.34944161651220945, |
| "grad_norm": 0.23944802582263947, |
| "learning_rate": 0.001, |
| "loss": 3.0683, |
| "num_input_tokens_seen": 13618380800, |
| "step": 51950 |
| }, |
| { |
| "epoch": 0.34977794145591706, |
| "grad_norm": 0.20257577300071716, |
| "learning_rate": 0.001, |
| "loss": 3.0509, |
| "num_input_tokens_seen": 13631488000, |
| "step": 52000 |
| }, |
| { |
| "epoch": 0.34977794145591706, |
| "eval_loss": 2.94769287109375, |
| "eval_runtime": 53.1351, |
| "eval_samples_per_second": 94.1, |
| "eval_steps_per_second": 23.525, |
| "num_input_tokens_seen": 13631488000, |
| "step": 52000 |
| }, |
| { |
| "epoch": 0.3501142663996247, |
| "grad_norm": 0.22132734954357147, |
| "learning_rate": 0.001, |
| "loss": 3.0564, |
| "num_input_tokens_seen": 13644595200, |
| "step": 52050 |
| }, |
| { |
| "epoch": 0.3504505913433323, |
| "grad_norm": 0.19554653763771057, |
| "learning_rate": 0.001, |
| "loss": 3.0457, |
| "num_input_tokens_seen": 13657702400, |
| "step": 52100 |
| }, |
| { |
| "epoch": 0.3507869162870399, |
| "grad_norm": 0.23935073614120483, |
| "learning_rate": 0.001, |
| "loss": 3.0465, |
| "num_input_tokens_seen": 13670809600, |
| "step": 52150 |
| }, |
| { |
| "epoch": 0.3511232412307475, |
| "grad_norm": 0.2895826995372772, |
| "learning_rate": 0.001, |
| "loss": 3.0509, |
| "num_input_tokens_seen": 13683916800, |
| "step": 52200 |
| }, |
| { |
| "epoch": 0.3514595661744551, |
| "grad_norm": 0.24599236249923706, |
| "learning_rate": 0.001, |
| "loss": 3.0385, |
| "num_input_tokens_seen": 13697024000, |
| "step": 52250 |
| }, |
| { |
| "epoch": 0.35179589111816273, |
| "grad_norm": 0.19500850141048431, |
| "learning_rate": 0.001, |
| "loss": 3.0523, |
| "num_input_tokens_seen": 13710131200, |
| "step": 52300 |
| }, |
| { |
| "epoch": 0.35213221606187034, |
| "grad_norm": 0.20790818333625793, |
| "learning_rate": 0.001, |
| "loss": 3.0547, |
| "num_input_tokens_seen": 13723238400, |
| "step": 52350 |
| }, |
| { |
| "epoch": 0.35246854100557795, |
| "grad_norm": 0.18653196096420288, |
| "learning_rate": 0.001, |
| "loss": 3.0545, |
| "num_input_tokens_seen": 13736345600, |
| "step": 52400 |
| }, |
| { |
| "epoch": 0.35280486594928556, |
| "grad_norm": 0.22097791731357574, |
| "learning_rate": 0.001, |
| "loss": 3.0573, |
| "num_input_tokens_seen": 13749452800, |
| "step": 52450 |
| }, |
| { |
| "epoch": 0.3531411908929932, |
| "grad_norm": 0.22931267321109772, |
| "learning_rate": 0.001, |
| "loss": 3.0478, |
| "num_input_tokens_seen": 13762560000, |
| "step": 52500 |
| }, |
| { |
| "epoch": 0.3531411908929932, |
| "eval_loss": 2.9459915161132812, |
| "eval_runtime": 52.6495, |
| "eval_samples_per_second": 94.968, |
| "eval_steps_per_second": 23.742, |
| "num_input_tokens_seen": 13762560000, |
| "step": 52500 |
| }, |
| { |
| "epoch": 0.3534775158367008, |
| "grad_norm": 0.31109049916267395, |
| "learning_rate": 0.001, |
| "loss": 3.0462, |
| "num_input_tokens_seen": 13775667200, |
| "step": 52550 |
| }, |
| { |
| "epoch": 0.3538138407804084, |
| "grad_norm": 1.7297276258468628, |
| "learning_rate": 0.001, |
| "loss": 3.0629, |
| "num_input_tokens_seen": 13788774400, |
| "step": 52600 |
| }, |
| { |
| "epoch": 0.354150165724116, |
| "grad_norm": 0.4056268334388733, |
| "learning_rate": 0.001, |
| "loss": 3.0763, |
| "num_input_tokens_seen": 13801881600, |
| "step": 52650 |
| }, |
| { |
| "epoch": 0.3544864906678236, |
| "grad_norm": 0.3694227635860443, |
| "learning_rate": 0.001, |
| "loss": 3.099, |
| "num_input_tokens_seen": 13814988800, |
| "step": 52700 |
| }, |
| { |
| "epoch": 0.35482281561153123, |
| "grad_norm": 0.2708556056022644, |
| "learning_rate": 0.001, |
| "loss": 3.0985, |
| "num_input_tokens_seen": 13828096000, |
| "step": 52750 |
| }, |
| { |
| "epoch": 0.35515914055523884, |
| "grad_norm": 0.27150145173072815, |
| "learning_rate": 0.001, |
| "loss": 3.0694, |
| "num_input_tokens_seen": 13841203200, |
| "step": 52800 |
| }, |
| { |
| "epoch": 0.35549546549894645, |
| "grad_norm": 0.2626855969429016, |
| "learning_rate": 0.001, |
| "loss": 3.0642, |
| "num_input_tokens_seen": 13854310400, |
| "step": 52850 |
| }, |
| { |
| "epoch": 0.35583179044265406, |
| "grad_norm": 0.20539118349552155, |
| "learning_rate": 0.001, |
| "loss": 3.059, |
| "num_input_tokens_seen": 13867417600, |
| "step": 52900 |
| }, |
| { |
| "epoch": 0.35616811538636167, |
| "grad_norm": 0.21489828824996948, |
| "learning_rate": 0.001, |
| "loss": 3.054, |
| "num_input_tokens_seen": 13880524800, |
| "step": 52950 |
| }, |
| { |
| "epoch": 0.3565044403300693, |
| "grad_norm": 0.263488233089447, |
| "learning_rate": 0.001, |
| "loss": 3.044, |
| "num_input_tokens_seen": 13893632000, |
| "step": 53000 |
| }, |
| { |
| "epoch": 0.3565044403300693, |
| "eval_loss": 2.9570043087005615, |
| "eval_runtime": 53.2194, |
| "eval_samples_per_second": 93.951, |
| "eval_steps_per_second": 23.488, |
| "num_input_tokens_seen": 13893632000, |
| "step": 53000 |
| }, |
| { |
| "epoch": 0.3568407652737769, |
| "grad_norm": 0.3147699236869812, |
| "learning_rate": 0.001, |
| "loss": 3.0557, |
| "num_input_tokens_seen": 13906739200, |
| "step": 53050 |
| }, |
| { |
| "epoch": 0.3571770902174845, |
| "grad_norm": 0.22110533714294434, |
| "learning_rate": 0.001, |
| "loss": 3.0515, |
| "num_input_tokens_seen": 13919846400, |
| "step": 53100 |
| }, |
| { |
| "epoch": 0.3575134151611921, |
| "grad_norm": 0.23334212601184845, |
| "learning_rate": 0.001, |
| "loss": 3.0523, |
| "num_input_tokens_seen": 13932953600, |
| "step": 53150 |
| }, |
| { |
| "epoch": 0.3578497401048997, |
| "grad_norm": 0.200640469789505, |
| "learning_rate": 0.001, |
| "loss": 3.0621, |
| "num_input_tokens_seen": 13946060800, |
| "step": 53200 |
| }, |
| { |
| "epoch": 0.35818606504860734, |
| "grad_norm": 0.20875929296016693, |
| "learning_rate": 0.001, |
| "loss": 3.0591, |
| "num_input_tokens_seen": 13959168000, |
| "step": 53250 |
| }, |
| { |
| "epoch": 0.35852238999231495, |
| "grad_norm": 0.19065573811531067, |
| "learning_rate": 0.001, |
| "loss": 3.0591, |
| "num_input_tokens_seen": 13972275200, |
| "step": 53300 |
| }, |
| { |
| "epoch": 0.35885871493602256, |
| "grad_norm": 0.18688392639160156, |
| "learning_rate": 0.001, |
| "loss": 3.0475, |
| "num_input_tokens_seen": 13985382400, |
| "step": 53350 |
| }, |
| { |
| "epoch": 0.3591950398797302, |
| "grad_norm": 0.1864282786846161, |
| "learning_rate": 0.001, |
| "loss": 3.0485, |
| "num_input_tokens_seen": 13998489600, |
| "step": 53400 |
| }, |
| { |
| "epoch": 0.35953136482343784, |
| "grad_norm": 0.20456114411354065, |
| "learning_rate": 0.001, |
| "loss": 3.0529, |
| "num_input_tokens_seen": 14011596800, |
| "step": 53450 |
| }, |
| { |
| "epoch": 0.35986768976714545, |
| "grad_norm": 0.24362069368362427, |
| "learning_rate": 0.001, |
| "loss": 3.0444, |
| "num_input_tokens_seen": 14024704000, |
| "step": 53500 |
| }, |
| { |
| "epoch": 0.35986768976714545, |
| "eval_loss": 2.943416118621826, |
| "eval_runtime": 53.1574, |
| "eval_samples_per_second": 94.06, |
| "eval_steps_per_second": 23.515, |
| "num_input_tokens_seen": 14024704000, |
| "step": 53500 |
| }, |
| { |
| "epoch": 0.36020401471085306, |
| "grad_norm": 0.19701169431209564, |
| "learning_rate": 0.001, |
| "loss": 3.0513, |
| "num_input_tokens_seen": 14037811200, |
| "step": 53550 |
| }, |
| { |
| "epoch": 0.36054033965456067, |
| "grad_norm": 0.1785692274570465, |
| "learning_rate": 0.001, |
| "loss": 3.0541, |
| "num_input_tokens_seen": 14050918400, |
| "step": 53600 |
| }, |
| { |
| "epoch": 0.3608766645982683, |
| "grad_norm": 0.1865462064743042, |
| "learning_rate": 0.001, |
| "loss": 3.0367, |
| "num_input_tokens_seen": 14064025600, |
| "step": 53650 |
| }, |
| { |
| "epoch": 0.3612129895419759, |
| "grad_norm": 0.4129047095775604, |
| "learning_rate": 0.001, |
| "loss": 3.043, |
| "num_input_tokens_seen": 14077132800, |
| "step": 53700 |
| }, |
| { |
| "epoch": 0.3615493144856835, |
| "grad_norm": 0.21066440641880035, |
| "learning_rate": 0.001, |
| "loss": 3.0585, |
| "num_input_tokens_seen": 14090240000, |
| "step": 53750 |
| }, |
| { |
| "epoch": 0.3618856394293911, |
| "grad_norm": 0.6820788383483887, |
| "learning_rate": 0.001, |
| "loss": 3.0534, |
| "num_input_tokens_seen": 14103347200, |
| "step": 53800 |
| }, |
| { |
| "epoch": 0.3622219643730987, |
| "grad_norm": 0.9664424657821655, |
| "learning_rate": 0.001, |
| "loss": 3.069, |
| "num_input_tokens_seen": 14116454400, |
| "step": 53850 |
| }, |
| { |
| "epoch": 0.36255828931680634, |
| "grad_norm": 0.35416921973228455, |
| "learning_rate": 0.001, |
| "loss": 3.0629, |
| "num_input_tokens_seen": 14129561600, |
| "step": 53900 |
| }, |
| { |
| "epoch": 0.36289461426051395, |
| "grad_norm": 0.3159606158733368, |
| "learning_rate": 0.001, |
| "loss": 3.0722, |
| "num_input_tokens_seen": 14142668800, |
| "step": 53950 |
| }, |
| { |
| "epoch": 0.36323093920422156, |
| "grad_norm": 0.2518790662288666, |
| "learning_rate": 0.001, |
| "loss": 3.071, |
| "num_input_tokens_seen": 14155776000, |
| "step": 54000 |
| }, |
| { |
| "epoch": 0.36323093920422156, |
| "eval_loss": 2.9483964443206787, |
| "eval_runtime": 53.2042, |
| "eval_samples_per_second": 93.978, |
| "eval_steps_per_second": 23.494, |
| "num_input_tokens_seen": 14155776000, |
| "step": 54000 |
| }, |
| { |
| "epoch": 0.36356726414792917, |
| "grad_norm": 0.2197147160768509, |
| "learning_rate": 0.0009998286624877785, |
| "loss": 3.0502, |
| "num_input_tokens_seen": 14168883200, |
| "step": 54050 |
| }, |
| { |
| "epoch": 0.3639035890916368, |
| "grad_norm": 0.22259306907653809, |
| "learning_rate": 0.0009993147673772868, |
| "loss": 3.0433, |
| "num_input_tokens_seen": 14181990400, |
| "step": 54100 |
| }, |
| { |
| "epoch": 0.3642399140353444, |
| "grad_norm": 0.19341766834259033, |
| "learning_rate": 0.000998458666866564, |
| "loss": 3.0486, |
| "num_input_tokens_seen": 14195097600, |
| "step": 54150 |
| }, |
| { |
| "epoch": 0.364576238979052, |
| "grad_norm": 0.2313617616891861, |
| "learning_rate": 0.0009972609476841367, |
| "loss": 3.0446, |
| "num_input_tokens_seen": 14208204800, |
| "step": 54200 |
| }, |
| { |
| "epoch": 0.3649125639227596, |
| "grad_norm": 0.1925128698348999, |
| "learning_rate": 0.0009957224306869053, |
| "loss": 3.0528, |
| "num_input_tokens_seen": 14221312000, |
| "step": 54250 |
| }, |
| { |
| "epoch": 0.3652488888664672, |
| "grad_norm": 0.2100643515586853, |
| "learning_rate": 0.0009938441702975688, |
| "loss": 3.0453, |
| "num_input_tokens_seen": 14234419200, |
| "step": 54300 |
| }, |
| { |
| "epoch": 0.36558521381017484, |
| "grad_norm": 0.46658360958099365, |
| "learning_rate": 0.0009916274537819774, |
| "loss": 3.0464, |
| "num_input_tokens_seen": 14247526400, |
| "step": 54350 |
| }, |
| { |
| "epoch": 0.36592153875388245, |
| "grad_norm": 0.19623732566833496, |
| "learning_rate": 0.0009890738003669028, |
| "loss": 3.0427, |
| "num_input_tokens_seen": 14260633600, |
| "step": 54400 |
| }, |
| { |
| "epoch": 0.36625786369759006, |
| "grad_norm": 0.24941138923168182, |
| "learning_rate": 0.0009861849601988384, |
| "loss": 3.0528, |
| "num_input_tokens_seen": 14273740800, |
| "step": 54450 |
| }, |
| { |
| "epoch": 0.36659418864129767, |
| "grad_norm": 0.22141198813915253, |
| "learning_rate": 0.0009829629131445341, |
| "loss": 3.0523, |
| "num_input_tokens_seen": 14286848000, |
| "step": 54500 |
| }, |
| { |
| "epoch": 0.36659418864129767, |
| "eval_loss": 2.9419288635253906, |
| "eval_runtime": 53.6937, |
| "eval_samples_per_second": 93.121, |
| "eval_steps_per_second": 23.28, |
| "num_input_tokens_seen": 14286848000, |
| "step": 54500 |
| }, |
| { |
| "epoch": 0.3669305135850053, |
| "grad_norm": 0.2028401494026184, |
| "learning_rate": 0.0009794098674340967, |
| "loss": 3.0403, |
| "num_input_tokens_seen": 14299955200, |
| "step": 54550 |
| }, |
| { |
| "epoch": 0.3672668385287129, |
| "grad_norm": 0.20509253442287445, |
| "learning_rate": 0.0009755282581475768, |
| "loss": 3.0543, |
| "num_input_tokens_seen": 14313062400, |
| "step": 54600 |
| }, |
| { |
| "epoch": 0.3676031634724205, |
| "grad_norm": 1.2793521881103516, |
| "learning_rate": 0.0009713207455460893, |
| "loss": 3.0718, |
| "num_input_tokens_seen": 14326169600, |
| "step": 54650 |
| }, |
| { |
| "epoch": 0.3679394884161281, |
| "grad_norm": 1.1210218667984009, |
| "learning_rate": 0.0009667902132486009, |
| "loss": 3.0706, |
| "num_input_tokens_seen": 14339276800, |
| "step": 54700 |
| }, |
| { |
| "epoch": 0.3682758133598357, |
| "grad_norm": 0.5492864847183228, |
| "learning_rate": 0.0009619397662556434, |
| "loss": 3.0793, |
| "num_input_tokens_seen": 14352384000, |
| "step": 54750 |
| }, |
| { |
| "epoch": 0.36861213830354334, |
| "grad_norm": 0.34732338786125183, |
| "learning_rate": 0.0009567727288213005, |
| "loss": 3.0662, |
| "num_input_tokens_seen": 14365491200, |
| "step": 54800 |
| }, |
| { |
| "epoch": 0.36894846324725095, |
| "grad_norm": 0.2698073983192444, |
| "learning_rate": 0.0009512926421749304, |
| "loss": 3.0682, |
| "num_input_tokens_seen": 14378598400, |
| "step": 54850 |
| }, |
| { |
| "epoch": 0.36928478819095856, |
| "grad_norm": 0.593543529510498, |
| "learning_rate": 0.0009455032620941839, |
| "loss": 3.0507, |
| "num_input_tokens_seen": 14391705600, |
| "step": 54900 |
| }, |
| { |
| "epoch": 0.36962111313466617, |
| "grad_norm": 0.28389155864715576, |
| "learning_rate": 0.0009394085563309827, |
| "loss": 3.0593, |
| "num_input_tokens_seen": 14404812800, |
| "step": 54950 |
| }, |
| { |
| "epoch": 0.3699574380783738, |
| "grad_norm": 0.2569947838783264, |
| "learning_rate": 0.0009330127018922195, |
| "loss": 3.0524, |
| "num_input_tokens_seen": 14417920000, |
| "step": 55000 |
| }, |
| { |
| "epoch": 0.3699574380783738, |
| "eval_loss": 2.9468750953674316, |
| "eval_runtime": 52.9661, |
| "eval_samples_per_second": 94.4, |
| "eval_steps_per_second": 23.6, |
| "num_input_tokens_seen": 14417920000, |
| "step": 55000 |
| }, |
| { |
| "epoch": 0.3702937630220814, |
| "grad_norm": 0.2545956075191498, |
| "learning_rate": 0.0009263200821770461, |
| "loss": 3.0397, |
| "num_input_tokens_seen": 14431027200, |
| "step": 55050 |
| }, |
| { |
| "epoch": 0.370630087965789, |
| "grad_norm": 0.26363736391067505, |
| "learning_rate": 0.0009193352839727121, |
| "loss": 3.0554, |
| "num_input_tokens_seen": 14444134400, |
| "step": 55100 |
| }, |
| { |
| "epoch": 0.3709664129094966, |
| "grad_norm": 0.2228112667798996, |
| "learning_rate": 0.0009120630943110077, |
| "loss": 3.0482, |
| "num_input_tokens_seen": 14457241600, |
| "step": 55150 |
| }, |
| { |
| "epoch": 0.3713027378532043, |
| "grad_norm": 0.2184106856584549, |
| "learning_rate": 0.0009045084971874737, |
| "loss": 3.0368, |
| "num_input_tokens_seen": 14470348800, |
| "step": 55200 |
| }, |
| { |
| "epoch": 0.3716390627969119, |
| "grad_norm": 0.5658212900161743, |
| "learning_rate": 0.0008966766701456176, |
| "loss": 3.0541, |
| "num_input_tokens_seen": 14483456000, |
| "step": 55250 |
| }, |
| { |
| "epoch": 0.3719753877406195, |
| "grad_norm": 0.31839439272880554, |
| "learning_rate": 0.0008885729807284854, |
| "loss": 3.0516, |
| "num_input_tokens_seen": 14496563200, |
| "step": 55300 |
| }, |
| { |
| "epoch": 0.3723117126843271, |
| "grad_norm": 0.2521055042743683, |
| "learning_rate": 0.0008802029828000156, |
| "loss": 3.049, |
| "num_input_tokens_seen": 14509670400, |
| "step": 55350 |
| }, |
| { |
| "epoch": 0.3726480376280347, |
| "grad_norm": 0.23797062039375305, |
| "learning_rate": 0.0008715724127386971, |
| "loss": 3.0393, |
| "num_input_tokens_seen": 14522777600, |
| "step": 55400 |
| }, |
| { |
| "epoch": 0.37298436257174233, |
| "grad_norm": 0.26673102378845215, |
| "learning_rate": 0.0008626871855061438, |
| "loss": 3.0535, |
| "num_input_tokens_seen": 14535884800, |
| "step": 55450 |
| }, |
| { |
| "epoch": 0.37332068751544994, |
| "grad_norm": 0.37754055857658386, |
| "learning_rate": 0.0008535533905932737, |
| "loss": 3.0432, |
| "num_input_tokens_seen": 14548992000, |
| "step": 55500 |
| }, |
| { |
| "epoch": 0.37332068751544994, |
| "eval_loss": 2.9362170696258545, |
| "eval_runtime": 53.4795, |
| "eval_samples_per_second": 93.494, |
| "eval_steps_per_second": 23.373, |
| "num_input_tokens_seen": 14548992000, |
| "step": 55500 |
| }, |
| { |
| "epoch": 0.37365701245915756, |
| "grad_norm": 0.2160724252462387, |
| "learning_rate": 0.000844177287846877, |
| "loss": 3.0378, |
| "num_input_tokens_seen": 14562099200, |
| "step": 55550 |
| }, |
| { |
| "epoch": 0.37399333740286517, |
| "grad_norm": 0.22323860228061676, |
| "learning_rate": 0.0008345653031794292, |
| "loss": 3.0419, |
| "num_input_tokens_seen": 14575206400, |
| "step": 55600 |
| }, |
| { |
| "epoch": 0.3743296623465728, |
| "grad_norm": 0.19688346982002258, |
| "learning_rate": 0.0008247240241650918, |
| "loss": 3.0297, |
| "num_input_tokens_seen": 14588313600, |
| "step": 55650 |
| }, |
| { |
| "epoch": 0.3746659872902804, |
| "grad_norm": 0.1972673088312149, |
| "learning_rate": 0.0008146601955249188, |
| "loss": 3.0405, |
| "num_input_tokens_seen": 14601420800, |
| "step": 55700 |
| }, |
| { |
| "epoch": 0.375002312233988, |
| "grad_norm": 0.44073277711868286, |
| "learning_rate": 0.0008043807145043603, |
| "loss": 3.0343, |
| "num_input_tokens_seen": 14614528000, |
| "step": 55750 |
| }, |
| { |
| "epoch": 0.3753386371776956, |
| "grad_norm": 0.22042399644851685, |
| "learning_rate": 0.0007938926261462366, |
| "loss": 3.0337, |
| "num_input_tokens_seen": 14627635200, |
| "step": 55800 |
| }, |
| { |
| "epoch": 0.3756749621214032, |
| "grad_norm": 0.2954588234424591, |
| "learning_rate": 0.0007832031184624164, |
| "loss": 3.0334, |
| "num_input_tokens_seen": 14640742400, |
| "step": 55850 |
| }, |
| { |
| "epoch": 0.37601128706511083, |
| "grad_norm": 0.5062097907066345, |
| "learning_rate": 0.0007723195175075137, |
| "loss": 3.0385, |
| "num_input_tokens_seen": 14653849600, |
| "step": 55900 |
| }, |
| { |
| "epoch": 0.37634761200881844, |
| "grad_norm": 0.30344095826148987, |
| "learning_rate": 0.0007612492823579744, |
| "loss": 3.04, |
| "num_input_tokens_seen": 14666956800, |
| "step": 55950 |
| }, |
| { |
| "epoch": 0.37668393695252606, |
| "grad_norm": 0.21088473498821259, |
| "learning_rate": 0.00075, |
| "loss": 3.0364, |
| "num_input_tokens_seen": 14680064000, |
| "step": 56000 |
| }, |
| { |
| "epoch": 0.37668393695252606, |
| "eval_loss": 2.9313743114471436, |
| "eval_runtime": 53.142, |
| "eval_samples_per_second": 94.088, |
| "eval_steps_per_second": 23.522, |
| "num_input_tokens_seen": 14680064000, |
| "step": 56000 |
| }, |
| { |
| "epoch": 0.37702026189623367, |
| "grad_norm": 0.2067674696445465, |
| "learning_rate": 0.0007385793801298042, |
| "loss": 3.05, |
| "num_input_tokens_seen": 14693171200, |
| "step": 56050 |
| }, |
| { |
| "epoch": 0.3773565868399413, |
| "grad_norm": 0.20803235471248627, |
| "learning_rate": 0.0007269952498697733, |
| "loss": 3.0451, |
| "num_input_tokens_seen": 14706278400, |
| "step": 56100 |
| }, |
| { |
| "epoch": 0.3776929117836489, |
| "grad_norm": 0.2035783976316452, |
| "learning_rate": 0.0007152555484041476, |
| "loss": 3.0281, |
| "num_input_tokens_seen": 14719385600, |
| "step": 56150 |
| }, |
| { |
| "epoch": 0.3780292367273565, |
| "grad_norm": 0.21911849081516266, |
| "learning_rate": 0.0007033683215379002, |
| "loss": 3.0312, |
| "num_input_tokens_seen": 14732492800, |
| "step": 56200 |
| }, |
| { |
| "epoch": 0.3783655616710641, |
| "grad_norm": 0.2263978123664856, |
| "learning_rate": 0.000691341716182545, |
| "loss": 3.0237, |
| "num_input_tokens_seen": 14745600000, |
| "step": 56250 |
| }, |
| { |
| "epoch": 0.3787018866147717, |
| "grad_norm": 0.20394045114517212, |
| "learning_rate": 0.0006791839747726501, |
| "loss": 3.0271, |
| "num_input_tokens_seen": 14758707200, |
| "step": 56300 |
| }, |
| { |
| "epoch": 0.37903821155847933, |
| "grad_norm": 0.1954122930765152, |
| "learning_rate": 0.0006669034296168854, |
| "loss": 3.0368, |
| "num_input_tokens_seen": 14771814400, |
| "step": 56350 |
| }, |
| { |
| "epoch": 0.37937453650218694, |
| "grad_norm": 0.2434541881084442, |
| "learning_rate": 0.0006545084971874737, |
| "loss": 3.0268, |
| "num_input_tokens_seen": 14784921600, |
| "step": 56400 |
| }, |
| { |
| "epoch": 0.37971086144589455, |
| "grad_norm": 0.19820261001586914, |
| "learning_rate": 0.0006420076723519614, |
| "loss": 3.0193, |
| "num_input_tokens_seen": 14798028800, |
| "step": 56450 |
| }, |
| { |
| "epoch": 0.38004718638960217, |
| "grad_norm": 0.18117697536945343, |
| "learning_rate": 0.0006294095225512603, |
| "loss": 3.0241, |
| "num_input_tokens_seen": 14811136000, |
| "step": 56500 |
| }, |
| { |
| "epoch": 0.38004718638960217, |
| "eval_loss": 2.920185089111328, |
| "eval_runtime": 53.8805, |
| "eval_samples_per_second": 92.798, |
| "eval_steps_per_second": 23.199, |
| "num_input_tokens_seen": 14811136000, |
| "step": 56500 |
| }, |
| { |
| "epoch": 0.3803835113333098, |
| "grad_norm": 0.20303522050380707, |
| "learning_rate": 0.0006167226819279528, |
| "loss": 3.0133, |
| "num_input_tokens_seen": 14824243200, |
| "step": 56550 |
| }, |
| { |
| "epoch": 0.3807198362770174, |
| "grad_norm": 0.19498929381370544, |
| "learning_rate": 0.0006039558454088796, |
| "loss": 3.0241, |
| "num_input_tokens_seen": 14837350400, |
| "step": 56600 |
| }, |
| { |
| "epoch": 0.381056161220725, |
| "grad_norm": 0.21773076057434082, |
| "learning_rate": 0.0005911177627460738, |
| "loss": 3.0235, |
| "num_input_tokens_seen": 14850457600, |
| "step": 56650 |
| }, |
| { |
| "epoch": 0.3813924861644326, |
| "grad_norm": 0.19796748459339142, |
| "learning_rate": 0.0005782172325201155, |
| "loss": 3.019, |
| "num_input_tokens_seen": 14863564800, |
| "step": 56700 |
| }, |
| { |
| "epoch": 0.3817288111081402, |
| "grad_norm": 0.18569409847259521, |
| "learning_rate": 0.000565263096110026, |
| "loss": 3.0189, |
| "num_input_tokens_seen": 14876672000, |
| "step": 56750 |
| }, |
| { |
| "epoch": 0.38206513605184783, |
| "grad_norm": 0.27358362078666687, |
| "learning_rate": 0.0005522642316338268, |
| "loss": 3.0107, |
| "num_input_tokens_seen": 14889779200, |
| "step": 56800 |
| }, |
| { |
| "epoch": 0.38240146099555544, |
| "grad_norm": 0.2143600583076477, |
| "learning_rate": 0.0005392295478639225, |
| "loss": 3.0139, |
| "num_input_tokens_seen": 14902886400, |
| "step": 56850 |
| }, |
| { |
| "epoch": 0.38273778593926305, |
| "grad_norm": 0.18786349892616272, |
| "learning_rate": 0.000526167978121472, |
| "loss": 3.0187, |
| "num_input_tokens_seen": 14915993600, |
| "step": 56900 |
| }, |
| { |
| "epoch": 0.38307411088297066, |
| "grad_norm": 0.1809261441230774, |
| "learning_rate": 0.0005130884741539367, |
| "loss": 3.0197, |
| "num_input_tokens_seen": 14929100800, |
| "step": 56950 |
| }, |
| { |
| "epoch": 0.38341043582667833, |
| "grad_norm": 0.1926116794347763, |
| "learning_rate": 0.0005, |
| "loss": 3.0101, |
| "num_input_tokens_seen": 14942208000, |
| "step": 57000 |
| }, |
| { |
| "epoch": 0.38341043582667833, |
| "eval_loss": 2.912503242492676, |
| "eval_runtime": 52.7455, |
| "eval_samples_per_second": 94.795, |
| "eval_steps_per_second": 23.699, |
| "num_input_tokens_seen": 14942208000, |
| "step": 57000 |
| }, |
| { |
| "epoch": 0.38374676077038594, |
| "grad_norm": 0.255500853061676, |
| "learning_rate": 0.0004869115258460635, |
| "loss": 3.0102, |
| "num_input_tokens_seen": 14955315200, |
| "step": 57050 |
| }, |
| { |
| "epoch": 0.38408308571409355, |
| "grad_norm": 0.18287675082683563, |
| "learning_rate": 0.0004738320218785281, |
| "loss": 3.0074, |
| "num_input_tokens_seen": 14968422400, |
| "step": 57100 |
| }, |
| { |
| "epoch": 0.38441941065780116, |
| "grad_norm": 0.1864452064037323, |
| "learning_rate": 0.0004607704521360776, |
| "loss": 3.0181, |
| "num_input_tokens_seen": 14981529600, |
| "step": 57150 |
| }, |
| { |
| "epoch": 0.3847557356015088, |
| "grad_norm": 0.17273065447807312, |
| "learning_rate": 0.00044773576836617336, |
| "loss": 3.0077, |
| "num_input_tokens_seen": 14994636800, |
| "step": 57200 |
| }, |
| { |
| "epoch": 0.3850920605452164, |
| "grad_norm": 0.17590677738189697, |
| "learning_rate": 0.00043473690388997434, |
| "loss": 3.0118, |
| "num_input_tokens_seen": 15007744000, |
| "step": 57250 |
| }, |
| { |
| "epoch": 0.385428385488924, |
| "grad_norm": 0.16380582749843597, |
| "learning_rate": 0.0004217827674798845, |
| "loss": 3.0074, |
| "num_input_tokens_seen": 15020851200, |
| "step": 57300 |
| }, |
| { |
| "epoch": 0.3857647104326316, |
| "grad_norm": 0.19464251399040222, |
| "learning_rate": 0.00040888223725392626, |
| "loss": 3.0126, |
| "num_input_tokens_seen": 15033958400, |
| "step": 57350 |
| }, |
| { |
| "epoch": 0.3861010353763392, |
| "grad_norm": 0.17150136828422546, |
| "learning_rate": 0.0003960441545911204, |
| "loss": 3.0049, |
| "num_input_tokens_seen": 15047065600, |
| "step": 57400 |
| }, |
| { |
| "epoch": 0.38643736032004683, |
| "grad_norm": 0.1877928376197815, |
| "learning_rate": 0.00038327731807204744, |
| "loss": 3.0089, |
| "num_input_tokens_seen": 15060172800, |
| "step": 57450 |
| }, |
| { |
| "epoch": 0.38677368526375444, |
| "grad_norm": 0.2605326771736145, |
| "learning_rate": 0.0003705904774487396, |
| "loss": 3.0115, |
| "num_input_tokens_seen": 15073280000, |
| "step": 57500 |
| }, |
| { |
| "epoch": 0.38677368526375444, |
| "eval_loss": 2.9029135704040527, |
| "eval_runtime": 53.9097, |
| "eval_samples_per_second": 92.748, |
| "eval_steps_per_second": 23.187, |
| "num_input_tokens_seen": 15073280000, |
| "step": 57500 |
| }, |
| { |
| "epoch": 0.38711001020746205, |
| "grad_norm": 0.21006393432617188, |
| "learning_rate": 0.0003579923276480387, |
| "loss": 3.0044, |
| "num_input_tokens_seen": 15086387200, |
| "step": 57550 |
| }, |
| { |
| "epoch": 0.38744633515116966, |
| "grad_norm": 0.1743878722190857, |
| "learning_rate": 0.00034549150281252633, |
| "loss": 3.0114, |
| "num_input_tokens_seen": 15099494400, |
| "step": 57600 |
| }, |
| { |
| "epoch": 0.3877826600948773, |
| "grad_norm": 0.16699257493019104, |
| "learning_rate": 0.00033309657038311456, |
| "loss": 3.0041, |
| "num_input_tokens_seen": 15112601600, |
| "step": 57650 |
| }, |
| { |
| "epoch": 0.3881189850385849, |
| "grad_norm": 0.17115868628025055, |
| "learning_rate": 0.00032081602522734986, |
| "loss": 3.0051, |
| "num_input_tokens_seen": 15125708800, |
| "step": 57700 |
| }, |
| { |
| "epoch": 0.3884553099822925, |
| "grad_norm": 0.16885310411453247, |
| "learning_rate": 0.0003086582838174551, |
| "loss": 2.9969, |
| "num_input_tokens_seen": 15138816000, |
| "step": 57750 |
| }, |
| { |
| "epoch": 0.3887916349260001, |
| "grad_norm": 0.17101123929023743, |
| "learning_rate": 0.0002966316784621, |
| "loss": 2.9947, |
| "num_input_tokens_seen": 15151923200, |
| "step": 57800 |
| }, |
| { |
| "epoch": 0.3891279598697077, |
| "grad_norm": 0.1529199331998825, |
| "learning_rate": 0.0002847444515958523, |
| "loss": 3.0019, |
| "num_input_tokens_seen": 15165030400, |
| "step": 57850 |
| }, |
| { |
| "epoch": 0.38946428481341533, |
| "grad_norm": 0.16087768971920013, |
| "learning_rate": 0.00027300475013022663, |
| "loss": 2.9947, |
| "num_input_tokens_seen": 15178137600, |
| "step": 57900 |
| }, |
| { |
| "epoch": 0.38980060975712294, |
| "grad_norm": 0.16023555397987366, |
| "learning_rate": 0.00026142061987019576, |
| "loss": 3.0022, |
| "num_input_tokens_seen": 15191244800, |
| "step": 57950 |
| }, |
| { |
| "epoch": 0.39013693470083055, |
| "grad_norm": 0.16161410510540009, |
| "learning_rate": 0.0002500000000000001, |
| "loss": 2.9931, |
| "num_input_tokens_seen": 15204352000, |
| "step": 58000 |
| }, |
| { |
| "epoch": 0.39013693470083055, |
| "eval_loss": 2.8950610160827637, |
| "eval_runtime": 53.5434, |
| "eval_samples_per_second": 93.382, |
| "eval_steps_per_second": 23.346, |
| "num_input_tokens_seen": 15204352000, |
| "step": 58000 |
| }, |
| { |
| "epoch": 0.39047325964453816, |
| "grad_norm": 0.1577194780111313, |
| "learning_rate": 0.00023875071764202561, |
| "loss": 2.9866, |
| "num_input_tokens_seen": 15217459200, |
| "step": 58050 |
| }, |
| { |
| "epoch": 0.3908095845882458, |
| "grad_norm": 0.1869671791791916, |
| "learning_rate": 0.00022768048249248646, |
| "loss": 2.9973, |
| "num_input_tokens_seen": 15230566400, |
| "step": 58100 |
| }, |
| { |
| "epoch": 0.3911459095319534, |
| "grad_norm": 0.1568073183298111, |
| "learning_rate": 0.0002167968815375837, |
| "loss": 3.0012, |
| "num_input_tokens_seen": 15243673600, |
| "step": 58150 |
| }, |
| { |
| "epoch": 0.391482234475661, |
| "grad_norm": 0.15343065559864044, |
| "learning_rate": 0.00020610737385376348, |
| "loss": 2.988, |
| "num_input_tokens_seen": 15256780800, |
| "step": 58200 |
| }, |
| { |
| "epoch": 0.3918185594193686, |
| "grad_norm": 0.22413235902786255, |
| "learning_rate": 0.00019561928549563967, |
| "loss": 2.993, |
| "num_input_tokens_seen": 15269888000, |
| "step": 58250 |
| }, |
| { |
| "epoch": 0.3921548843630762, |
| "grad_norm": 0.1807044893503189, |
| "learning_rate": 0.00018533980447508135, |
| "loss": 2.9905, |
| "num_input_tokens_seen": 15282995200, |
| "step": 58300 |
| }, |
| { |
| "epoch": 0.39249120930678383, |
| "grad_norm": 0.1571112871170044, |
| "learning_rate": 0.00017527597583490823, |
| "loss": 2.9983, |
| "num_input_tokens_seen": 15296102400, |
| "step": 58350 |
| }, |
| { |
| "epoch": 0.39282753425049144, |
| "grad_norm": 0.16821637749671936, |
| "learning_rate": 0.00016543469682057105, |
| "loss": 2.9966, |
| "num_input_tokens_seen": 15309209600, |
| "step": 58400 |
| }, |
| { |
| "epoch": 0.39316385919419905, |
| "grad_norm": 0.1497010737657547, |
| "learning_rate": 0.00015582271215312294, |
| "loss": 2.9814, |
| "num_input_tokens_seen": 15322316800, |
| "step": 58450 |
| }, |
| { |
| "epoch": 0.39350018413790666, |
| "grad_norm": 0.15679225325584412, |
| "learning_rate": 0.00014644660940672628, |
| "loss": 2.9876, |
| "num_input_tokens_seen": 15335424000, |
| "step": 58500 |
| }, |
| { |
| "epoch": 0.39350018413790666, |
| "eval_loss": 2.8887994289398193, |
| "eval_runtime": 53.8449, |
| "eval_samples_per_second": 92.859, |
| "eval_steps_per_second": 23.215, |
| "num_input_tokens_seen": 15335424000, |
| "step": 58500 |
| }, |
| { |
| "epoch": 0.39383650908161427, |
| "grad_norm": 0.15169823169708252, |
| "learning_rate": 0.0001373128144938563, |
| "loss": 2.9875, |
| "num_input_tokens_seen": 15348531200, |
| "step": 58550 |
| }, |
| { |
| "epoch": 0.3941728340253219, |
| "grad_norm": 0.1635347604751587, |
| "learning_rate": 0.00012842758726130281, |
| "loss": 2.9898, |
| "num_input_tokens_seen": 15361638400, |
| "step": 58600 |
| }, |
| { |
| "epoch": 0.3945091589690295, |
| "grad_norm": 0.15156348049640656, |
| "learning_rate": 0.00011979701719998454, |
| "loss": 2.9977, |
| "num_input_tokens_seen": 15374745600, |
| "step": 58650 |
| }, |
| { |
| "epoch": 0.3948454839127371, |
| "grad_norm": 0.15710316598415375, |
| "learning_rate": 0.00011142701927151455, |
| "loss": 2.981, |
| "num_input_tokens_seen": 15387852800, |
| "step": 58700 |
| }, |
| { |
| "epoch": 0.3951818088564447, |
| "grad_norm": 0.2838917374610901, |
| "learning_rate": 0.00010332332985438247, |
| "loss": 2.9909, |
| "num_input_tokens_seen": 15400960000, |
| "step": 58750 |
| }, |
| { |
| "epoch": 0.3955181338001524, |
| "grad_norm": 0.1509639173746109, |
| "learning_rate": 9.549150281252633e-05, |
| "loss": 2.9851, |
| "num_input_tokens_seen": 15414067200, |
| "step": 58800 |
| }, |
| { |
| "epoch": 0.39585445874386, |
| "grad_norm": 0.1501421183347702, |
| "learning_rate": 8.793690568899215e-05, |
| "loss": 2.9931, |
| "num_input_tokens_seen": 15427174400, |
| "step": 58850 |
| }, |
| { |
| "epoch": 0.3961907836875676, |
| "grad_norm": 0.14904147386550903, |
| "learning_rate": 8.066471602728804e-05, |
| "loss": 2.9862, |
| "num_input_tokens_seen": 15440281600, |
| "step": 58900 |
| }, |
| { |
| "epoch": 0.3965271086312752, |
| "grad_norm": 0.15182824432849884, |
| "learning_rate": 7.367991782295391e-05, |
| "loss": 2.9882, |
| "num_input_tokens_seen": 15453388800, |
| "step": 58950 |
| }, |
| { |
| "epoch": 0.3968634335749828, |
| "grad_norm": 0.14710576832294464, |
| "learning_rate": 6.698729810778065e-05, |
| "loss": 2.9856, |
| "num_input_tokens_seen": 15466496000, |
| "step": 59000 |
| }, |
| { |
| "epoch": 0.3968634335749828, |
| "eval_loss": 2.8845956325531006, |
| "eval_runtime": 53.5429, |
| "eval_samples_per_second": 93.383, |
| "eval_steps_per_second": 23.346, |
| "num_input_tokens_seen": 15466496000, |
| "step": 59000 |
| }, |
| { |
| "epoch": 0.39719975851869044, |
| "grad_norm": 0.14572475850582123, |
| "learning_rate": 6.059144366901737e-05, |
| "loss": 2.9861, |
| "num_input_tokens_seen": 15479603200, |
| "step": 59050 |
| }, |
| { |
| "epoch": 0.39753608346239805, |
| "grad_norm": 0.5027282238006592, |
| "learning_rate": 5.449673790581611e-05, |
| "loss": 2.9773, |
| "num_input_tokens_seen": 15492710400, |
| "step": 59100 |
| }, |
| { |
| "epoch": 0.39787240840610566, |
| "grad_norm": 0.192597895860672, |
| "learning_rate": 4.87073578250698e-05, |
| "loss": 2.9874, |
| "num_input_tokens_seen": 15505817600, |
| "step": 59150 |
| }, |
| { |
| "epoch": 0.39820873334981327, |
| "grad_norm": 0.15083667635917664, |
| "learning_rate": 4.322727117869951e-05, |
| "loss": 2.987, |
| "num_input_tokens_seen": 15518924800, |
| "step": 59200 |
| }, |
| { |
| "epoch": 0.3985450582935209, |
| "grad_norm": 0.14701534807682037, |
| "learning_rate": 3.806023374435663e-05, |
| "loss": 2.9858, |
| "num_input_tokens_seen": 15532032000, |
| "step": 59250 |
| }, |
| { |
| "epoch": 0.3988813832372285, |
| "grad_norm": 0.145115464925766, |
| "learning_rate": 3.3209786751399184e-05, |
| "loss": 2.9926, |
| "num_input_tokens_seen": 15545139200, |
| "step": 59300 |
| }, |
| { |
| "epoch": 0.3992177081809361, |
| "grad_norm": 0.15828457474708557, |
| "learning_rate": 2.8679254453910786e-05, |
| "loss": 2.9803, |
| "num_input_tokens_seen": 15558246400, |
| "step": 59350 |
| }, |
| { |
| "epoch": 0.3995540331246437, |
| "grad_norm": 0.14400678873062134, |
| "learning_rate": 2.4471741852423235e-05, |
| "loss": 2.9701, |
| "num_input_tokens_seen": 15571353600, |
| "step": 59400 |
| }, |
| { |
| "epoch": 0.3998903580683513, |
| "grad_norm": 0.14925344288349152, |
| "learning_rate": 2.0590132565903473e-05, |
| "loss": 2.989, |
| "num_input_tokens_seen": 15584460800, |
| "step": 59450 |
| }, |
| { |
| "epoch": 0.40022668301205894, |
| "grad_norm": 0.14081260561943054, |
| "learning_rate": 1.70370868554659e-05, |
| "loss": 2.9824, |
| "num_input_tokens_seen": 15597568000, |
| "step": 59500 |
| }, |
| { |
| "epoch": 0.40022668301205894, |
| "eval_loss": 2.882228136062622, |
| "eval_runtime": 53.7595, |
| "eval_samples_per_second": 93.007, |
| "eval_steps_per_second": 23.252, |
| "num_input_tokens_seen": 15597568000, |
| "step": 59500 |
| }, |
| { |
| "epoch": 0.40056300795576655, |
| "grad_norm": 0.13585136830806732, |
| "learning_rate": 1.3815039801161721e-05, |
| "loss": 2.9883, |
| "num_input_tokens_seen": 15610675200, |
| "step": 59550 |
| }, |
| { |
| "epoch": 0.40089933289947416, |
| "grad_norm": 0.1438748985528946, |
| "learning_rate": 1.0926199633097156e-05, |
| "loss": 2.9781, |
| "num_input_tokens_seen": 15623782400, |
| "step": 59600 |
| }, |
| { |
| "epoch": 0.40123565784318177, |
| "grad_norm": 0.3345394730567932, |
| "learning_rate": 8.372546218022748e-06, |
| "loss": 2.9869, |
| "num_input_tokens_seen": 15636889600, |
| "step": 59650 |
| }, |
| { |
| "epoch": 0.4015719827868894, |
| "grad_norm": 0.14581316709518433, |
| "learning_rate": 6.15582970243117e-06, |
| "loss": 2.9882, |
| "num_input_tokens_seen": 15649996800, |
| "step": 59700 |
| }, |
| { |
| "epoch": 0.401908307730597, |
| "grad_norm": 0.1409323662519455, |
| "learning_rate": 4.277569313094809e-06, |
| "loss": 2.9833, |
| "num_input_tokens_seen": 15663104000, |
| "step": 59750 |
| }, |
| { |
| "epoch": 0.4022446326743046, |
| "grad_norm": 0.1412041187286377, |
| "learning_rate": 2.739052315863355e-06, |
| "loss": 2.9835, |
| "num_input_tokens_seen": 15676211200, |
| "step": 59800 |
| }, |
| { |
| "epoch": 0.4025809576180122, |
| "grad_norm": 0.14011850953102112, |
| "learning_rate": 1.541333133436018e-06, |
| "loss": 2.9819, |
| "num_input_tokens_seen": 15689318400, |
| "step": 59850 |
| }, |
| { |
| "epoch": 0.4029172825617198, |
| "grad_norm": 0.14772015810012817, |
| "learning_rate": 6.852326227130834e-07, |
| "loss": 2.9855, |
| "num_input_tokens_seen": 15702425600, |
| "step": 59900 |
| }, |
| { |
| "epoch": 0.40325360750542744, |
| "grad_norm": 0.14281156659126282, |
| "learning_rate": 1.7133751222137007e-07, |
| "loss": 2.978, |
| "num_input_tokens_seen": 15715532800, |
| "step": 59950 |
| }, |
| { |
| "epoch": 0.40358993244913505, |
| "grad_norm": 0.14420129358768463, |
| "learning_rate": 0.0, |
| "loss": 2.9789, |
| "num_input_tokens_seen": 15728640000, |
| "step": 60000 |
| }, |
| { |
| "epoch": 0.40358993244913505, |
| "eval_loss": 2.8818726539611816, |
| "eval_runtime": 53.5982, |
| "eval_samples_per_second": 93.287, |
| "eval_steps_per_second": 23.322, |
| "num_input_tokens_seen": 15728640000, |
| "step": 60000 |
| }, |
| { |
| "epoch": 0.40392625739284266, |
| "grad_norm": 0.2130047082901001, |
| "learning_rate": 0.0006867974850262581, |
| "loss": 3.0074, |
| "num_input_tokens_seen": 15741747200, |
| "step": 60050 |
| }, |
| { |
| "epoch": 0.40426258233655027, |
| "grad_norm": 0.18596570193767548, |
| "learning_rate": 0.000682235249939575, |
| "loss": 2.9981, |
| "num_input_tokens_seen": 15754854400, |
| "step": 60100 |
| }, |
| { |
| "epoch": 0.4045989072802579, |
| "grad_norm": 0.2774942219257355, |
| "learning_rate": 0.0006776554506402081, |
| "loss": 3.0024, |
| "num_input_tokens_seen": 15767961600, |
| "step": 60150 |
| }, |
| { |
| "epoch": 0.4049352322239655, |
| "grad_norm": 0.19329522550106049, |
| "learning_rate": 0.0006730585285387465, |
| "loss": 3.0101, |
| "num_input_tokens_seen": 15781068800, |
| "step": 60200 |
| }, |
| { |
| "epoch": 0.4052715571676731, |
| "grad_norm": 0.21384254097938538, |
| "learning_rate": 0.0006684449266961101, |
| "loss": 3.0095, |
| "num_input_tokens_seen": 15794176000, |
| "step": 60250 |
| }, |
| { |
| "epoch": 0.4056078821113807, |
| "grad_norm": 0.3892166018486023, |
| "learning_rate": 0.0006638150897808468, |
| "loss": 3.0101, |
| "num_input_tokens_seen": 15807283200, |
| "step": 60300 |
| }, |
| { |
| "epoch": 0.4059442070550883, |
| "grad_norm": 0.27356287837028503, |
| "learning_rate": 0.0006591694640262749, |
| "loss": 3.0322, |
| "num_input_tokens_seen": 15820390400, |
| "step": 60350 |
| }, |
| { |
| "epoch": 0.40628053199879594, |
| "grad_norm": 0.20498153567314148, |
| "learning_rate": 0.0006545084971874737, |
| "loss": 3.0064, |
| "num_input_tokens_seen": 15833497600, |
| "step": 60400 |
| }, |
| { |
| "epoch": 0.40661685694250355, |
| "grad_norm": 0.19939659535884857, |
| "learning_rate": 0.0006498326384981283, |
| "loss": 3.0158, |
| "num_input_tokens_seen": 15846604800, |
| "step": 60450 |
| }, |
| { |
| "epoch": 0.40695318188621116, |
| "grad_norm": 0.24545226991176605, |
| "learning_rate": 0.0006451423386272311, |
| "loss": 3.0132, |
| "num_input_tokens_seen": 15859712000, |
| "step": 60500 |
| }, |
| { |
| "epoch": 0.40695318188621116, |
| "eval_loss": 2.914865255355835, |
| "eval_runtime": 51.2039, |
| "eval_samples_per_second": 97.649, |
| "eval_steps_per_second": 24.412, |
| "num_input_tokens_seen": 15859712000, |
| "step": 60500 |
| }, |
| { |
| "epoch": 0.40728950682991877, |
| "grad_norm": 0.2364359349012375, |
| "learning_rate": 0.0006404380496356461, |
| "loss": 3.0102, |
| "num_input_tokens_seen": 15872819200, |
| "step": 60550 |
| }, |
| { |
| "epoch": 0.4076258317736264, |
| "grad_norm": 0.19283762574195862, |
| "learning_rate": 0.0006357202249325371, |
| "loss": 3.0132, |
| "num_input_tokens_seen": 15885926400, |
| "step": 60600 |
| }, |
| { |
| "epoch": 0.40796215671733405, |
| "grad_norm": 0.19770501554012299, |
| "learning_rate": 0.0006309893192316686, |
| "loss": 3.0106, |
| "num_input_tokens_seen": 15899033600, |
| "step": 60650 |
| }, |
| { |
| "epoch": 0.40829848166104166, |
| "grad_norm": 0.18395134806632996, |
| "learning_rate": 0.000626245788507579, |
| "loss": 3.005, |
| "num_input_tokens_seen": 15912140800, |
| "step": 60700 |
| }, |
| { |
| "epoch": 0.40863480660474927, |
| "grad_norm": 0.21380823850631714, |
| "learning_rate": 0.000621490089951632, |
| "loss": 3.0106, |
| "num_input_tokens_seen": 15925248000, |
| "step": 60750 |
| }, |
| { |
| "epoch": 0.4089711315484569, |
| "grad_norm": 0.17995478212833405, |
| "learning_rate": 0.0006167226819279528, |
| "loss": 3.0237, |
| "num_input_tokens_seen": 15938355200, |
| "step": 60800 |
| }, |
| { |
| "epoch": 0.4093074564921645, |
| "grad_norm": 0.31993716955184937, |
| "learning_rate": 0.0006119440239292493, |
| "loss": 3.0158, |
| "num_input_tokens_seen": 15951462400, |
| "step": 60850 |
| }, |
| { |
| "epoch": 0.4096437814358721, |
| "grad_norm": 0.19210565090179443, |
| "learning_rate": 0.0006071545765325253, |
| "loss": 3.0121, |
| "num_input_tokens_seen": 15964569600, |
| "step": 60900 |
| }, |
| { |
| "epoch": 0.4099801063795797, |
| "grad_norm": 0.4126472771167755, |
| "learning_rate": 0.0006023548013546899, |
| "loss": 3.0215, |
| "num_input_tokens_seen": 15977676800, |
| "step": 60950 |
| }, |
| { |
| "epoch": 0.4103164313232873, |
| "grad_norm": 0.26418012380599976, |
| "learning_rate": 0.0005975451610080642, |
| "loss": 3.0125, |
| "num_input_tokens_seen": 15990784000, |
| "step": 61000 |
| }, |
| { |
| "epoch": 0.4103164313232873, |
| "eval_loss": 2.913696765899658, |
| "eval_runtime": 52.0924, |
| "eval_samples_per_second": 95.983, |
| "eval_steps_per_second": 23.996, |
| "num_input_tokens_seen": 15990784000, |
| "step": 61000 |
| }, |
| { |
| "epoch": 0.41065275626699493, |
| "grad_norm": 0.3535885810852051, |
| "learning_rate": 0.0005927261190557954, |
| "loss": 3.0102, |
| "num_input_tokens_seen": 16003891200, |
| "step": 61050 |
| }, |
| { |
| "epoch": 0.41098908121070254, |
| "grad_norm": 0.2633107304573059, |
| "learning_rate": 0.0005878981399671774, |
| "loss": 3.0424, |
| "num_input_tokens_seen": 16016998400, |
| "step": 61100 |
| }, |
| { |
| "epoch": 0.41132540615441016, |
| "grad_norm": 0.3054018020629883, |
| "learning_rate": 0.0005830616890728827, |
| "loss": 3.0233, |
| "num_input_tokens_seen": 16030105600, |
| "step": 61150 |
| }, |
| { |
| "epoch": 0.41166173109811777, |
| "grad_norm": 0.21453993022441864, |
| "learning_rate": 0.0005782172325201155, |
| "loss": 3.018, |
| "num_input_tokens_seen": 16043212800, |
| "step": 61200 |
| }, |
| { |
| "epoch": 0.4119980560418254, |
| "grad_norm": 0.27815598249435425, |
| "learning_rate": 0.0005733652372276809, |
| "loss": 3.0254, |
| "num_input_tokens_seen": 16056320000, |
| "step": 61250 |
| }, |
| { |
| "epoch": 0.412334380985533, |
| "grad_norm": 0.20687313377857208, |
| "learning_rate": 0.0005685061708409841, |
| "loss": 3.0165, |
| "num_input_tokens_seen": 16069427200, |
| "step": 61300 |
| }, |
| { |
| "epoch": 0.4126707059292406, |
| "grad_norm": 0.1985252946615219, |
| "learning_rate": 0.0005636405016869566, |
| "loss": 3.0164, |
| "num_input_tokens_seen": 16082534400, |
| "step": 61350 |
| }, |
| { |
| "epoch": 0.4130070308729482, |
| "grad_norm": 0.26703181862831116, |
| "learning_rate": 0.0005587686987289189, |
| "loss": 3.0001, |
| "num_input_tokens_seen": 16095641600, |
| "step": 61400 |
| }, |
| { |
| "epoch": 0.4133433558166558, |
| "grad_norm": 0.1948036104440689, |
| "learning_rate": 0.0005538912315213797, |
| "loss": 3.0058, |
| "num_input_tokens_seen": 16108748800, |
| "step": 61450 |
| }, |
| { |
| "epoch": 0.41367968076036343, |
| "grad_norm": 0.20653308928012848, |
| "learning_rate": 0.0005490085701647804, |
| "loss": 3.0115, |
| "num_input_tokens_seen": 16121856000, |
| "step": 61500 |
| }, |
| { |
| "epoch": 0.41367968076036343, |
| "eval_loss": 2.9048781394958496, |
| "eval_runtime": 53.8207, |
| "eval_samples_per_second": 92.901, |
| "eval_steps_per_second": 23.225, |
| "num_input_tokens_seen": 16121856000, |
| "step": 61500 |
| }, |
| { |
| "epoch": 0.41401600570407104, |
| "grad_norm": 0.19605295360088348, |
| "learning_rate": 0.0005441211852601849, |
| "loss": 3.0225, |
| "num_input_tokens_seen": 16134963200, |
| "step": 61550 |
| }, |
| { |
| "epoch": 0.41435233064777865, |
| "grad_norm": 0.17526155710220337, |
| "learning_rate": 0.0005392295478639225, |
| "loss": 3.0117, |
| "num_input_tokens_seen": 16148070400, |
| "step": 61600 |
| }, |
| { |
| "epoch": 0.41468865559148627, |
| "grad_norm": 0.17657403647899628, |
| "learning_rate": 0.0005343341294421868, |
| "loss": 3.0107, |
| "num_input_tokens_seen": 16161177600, |
| "step": 61650 |
| }, |
| { |
| "epoch": 0.4150249805351939, |
| "grad_norm": 0.18658681213855743, |
| "learning_rate": 0.0005294354018255945, |
| "loss": 3.0085, |
| "num_input_tokens_seen": 16174284800, |
| "step": 61700 |
| }, |
| { |
| "epoch": 0.4153613054789015, |
| "grad_norm": 0.24781519174575806, |
| "learning_rate": 0.0005245338371637091, |
| "loss": 2.9939, |
| "num_input_tokens_seen": 16187392000, |
| "step": 61750 |
| }, |
| { |
| "epoch": 0.4156976304226091, |
| "grad_norm": 0.20824941992759705, |
| "learning_rate": 0.0005196299078795343, |
| "loss": 3.0038, |
| "num_input_tokens_seen": 16200499200, |
| "step": 61800 |
| }, |
| { |
| "epoch": 0.4160339553663167, |
| "grad_norm": 0.38262441754341125, |
| "learning_rate": 0.0005147240866239817, |
| "loss": 3.0141, |
| "num_input_tokens_seen": 16213606400, |
| "step": 61850 |
| }, |
| { |
| "epoch": 0.4163702803100243, |
| "grad_norm": 0.200628861784935, |
| "learning_rate": 0.0005098168462303141, |
| "loss": 3.0187, |
| "num_input_tokens_seen": 16226713600, |
| "step": 61900 |
| }, |
| { |
| "epoch": 0.41670660525373193, |
| "grad_norm": 0.18858259916305542, |
| "learning_rate": 0.000504908659668575, |
| "loss": 3.0049, |
| "num_input_tokens_seen": 16239820800, |
| "step": 61950 |
| }, |
| { |
| "epoch": 0.41704293019743954, |
| "grad_norm": 0.19025108218193054, |
| "learning_rate": 0.0005, |
| "loss": 3.0079, |
| "num_input_tokens_seen": 16252928000, |
| "step": 62000 |
| }, |
| { |
| "epoch": 0.41704293019743954, |
| "eval_loss": 2.9012608528137207, |
| "eval_runtime": 52.7052, |
| "eval_samples_per_second": 94.867, |
| "eval_steps_per_second": 23.717, |
| "num_input_tokens_seen": 16252928000, |
| "step": 62000 |
| }, |
| { |
| "epoch": 0.41737925514114715, |
| "grad_norm": 0.19505389034748077, |
| "learning_rate": 0.0004950913403314252, |
| "loss": 2.9995, |
| "num_input_tokens_seen": 16266035200, |
| "step": 62050 |
| }, |
| { |
| "epoch": 0.41771558008485477, |
| "grad_norm": 0.18988089263439178, |
| "learning_rate": 0.0004901831537696859, |
| "loss": 3.0041, |
| "num_input_tokens_seen": 16279142400, |
| "step": 62100 |
| }, |
| { |
| "epoch": 0.4180519050285624, |
| "grad_norm": 0.19544407725334167, |
| "learning_rate": 0.0004852759133760184, |
| "loss": 3.0073, |
| "num_input_tokens_seen": 16292249600, |
| "step": 62150 |
| }, |
| { |
| "epoch": 0.41838822997227, |
| "grad_norm": 0.1884351521730423, |
| "learning_rate": 0.00048037009212046586, |
| "loss": 3.0035, |
| "num_input_tokens_seen": 16305356800, |
| "step": 62200 |
| }, |
| { |
| "epoch": 0.4187245549159776, |
| "grad_norm": 0.17927390336990356, |
| "learning_rate": 0.000475466162836291, |
| "loss": 2.9921, |
| "num_input_tokens_seen": 16318464000, |
| "step": 62250 |
| }, |
| { |
| "epoch": 0.4190608798596852, |
| "grad_norm": 0.18687283992767334, |
| "learning_rate": 0.00047056459817440544, |
| "loss": 3.0042, |
| "num_input_tokens_seen": 16331571200, |
| "step": 62300 |
| }, |
| { |
| "epoch": 0.4193972048033928, |
| "grad_norm": 0.18783149123191833, |
| "learning_rate": 0.00046566587055781316, |
| "loss": 3.0003, |
| "num_input_tokens_seen": 16344678400, |
| "step": 62350 |
| }, |
| { |
| "epoch": 0.41973352974710043, |
| "grad_norm": 0.18625770509243011, |
| "learning_rate": 0.0004607704521360776, |
| "loss": 3.0061, |
| "num_input_tokens_seen": 16357785600, |
| "step": 62400 |
| }, |
| { |
| "epoch": 0.4200698546908081, |
| "grad_norm": 0.20189669728279114, |
| "learning_rate": 0.00045587881473981533, |
| "loss": 2.9976, |
| "num_input_tokens_seen": 16370892800, |
| "step": 62450 |
| }, |
| { |
| "epoch": 0.4204061796345157, |
| "grad_norm": 0.19049198925495148, |
| "learning_rate": 0.0004509914298352197, |
| "loss": 3.0055, |
| "num_input_tokens_seen": 16384000000, |
| "step": 62500 |
| }, |
| { |
| "epoch": 0.4204061796345157, |
| "eval_loss": 2.896798849105835, |
| "eval_runtime": 52.8908, |
| "eval_samples_per_second": 94.534, |
| "eval_steps_per_second": 23.634, |
| "num_input_tokens_seen": 16384000000, |
| "step": 62500 |
| }, |
| { |
| "epoch": 0.4207425045782233, |
| "grad_norm": 0.1667575091123581, |
| "learning_rate": 0.00044610876847862033, |
| "loss": 2.9929, |
| "num_input_tokens_seen": 16397107200, |
| "step": 62550 |
| }, |
| { |
| "epoch": 0.42107882952193093, |
| "grad_norm": 0.7176526188850403, |
| "learning_rate": 0.00044123130127108126, |
| "loss": 2.9918, |
| "num_input_tokens_seen": 16410214400, |
| "step": 62600 |
| }, |
| { |
| "epoch": 0.42141515446563854, |
| "grad_norm": 0.20578069984912872, |
| "learning_rate": 0.00043635949831304343, |
| "loss": 3.0037, |
| "num_input_tokens_seen": 16423321600, |
| "step": 62650 |
| }, |
| { |
| "epoch": 0.42175147940934615, |
| "grad_norm": 0.19712655246257782, |
| "learning_rate": 0.0004314938291590161, |
| "loss": 3.0142, |
| "num_input_tokens_seen": 16436428800, |
| "step": 62700 |
| }, |
| { |
| "epoch": 0.42208780435305376, |
| "grad_norm": 0.20189446210861206, |
| "learning_rate": 0.00042663476277231917, |
| "loss": 2.9983, |
| "num_input_tokens_seen": 16449536000, |
| "step": 62750 |
| }, |
| { |
| "epoch": 0.4224241292967614, |
| "grad_norm": 0.18463867902755737, |
| "learning_rate": 0.0004217827674798845, |
| "loss": 2.9971, |
| "num_input_tokens_seen": 16462643200, |
| "step": 62800 |
| }, |
| { |
| "epoch": 0.422760454240469, |
| "grad_norm": 0.17639389634132385, |
| "learning_rate": 0.0004169383109271174, |
| "loss": 3.0032, |
| "num_input_tokens_seen": 16475750400, |
| "step": 62850 |
| }, |
| { |
| "epoch": 0.4230967791841766, |
| "grad_norm": 0.1733781099319458, |
| "learning_rate": 0.00041210186003282274, |
| "loss": 2.9932, |
| "num_input_tokens_seen": 16488857600, |
| "step": 62900 |
| }, |
| { |
| "epoch": 0.4234331041278842, |
| "grad_norm": 0.17753124237060547, |
| "learning_rate": 0.00040727388094420456, |
| "loss": 3.0012, |
| "num_input_tokens_seen": 16501964800, |
| "step": 62950 |
| }, |
| { |
| "epoch": 0.4237694290715918, |
| "grad_norm": 0.180925652384758, |
| "learning_rate": 0.00040245483899193594, |
| "loss": 2.9823, |
| "num_input_tokens_seen": 16515072000, |
| "step": 63000 |
| }, |
| { |
| "epoch": 0.4237694290715918, |
| "eval_loss": 2.8929545879364014, |
| "eval_runtime": 53.37, |
| "eval_samples_per_second": 93.686, |
| "eval_steps_per_second": 23.421, |
| "num_input_tokens_seen": 16515072000, |
| "step": 63000 |
| }, |
| { |
| "epoch": 0.42410575401529943, |
| "grad_norm": 0.15995506942272186, |
| "learning_rate": 0.00039764519864531023, |
| "loss": 2.9898, |
| "num_input_tokens_seen": 16528179200, |
| "step": 63050 |
| }, |
| { |
| "epoch": 0.42444207895900704, |
| "grad_norm": 0.16034817695617676, |
| "learning_rate": 0.0003928454234674747, |
| "loss": 2.9884, |
| "num_input_tokens_seen": 16541286400, |
| "step": 63100 |
| }, |
| { |
| "epoch": 0.42477840390271465, |
| "grad_norm": 0.17681469023227692, |
| "learning_rate": 0.00038805597607075075, |
| "loss": 2.9952, |
| "num_input_tokens_seen": 16554393600, |
| "step": 63150 |
| }, |
| { |
| "epoch": 0.42511472884642226, |
| "grad_norm": 0.18527273833751678, |
| "learning_rate": 0.00038327731807204744, |
| "loss": 2.9947, |
| "num_input_tokens_seen": 16567500800, |
| "step": 63200 |
| }, |
| { |
| "epoch": 0.4254510537901299, |
| "grad_norm": 0.16262546181678772, |
| "learning_rate": 0.0003785099100483681, |
| "loss": 2.9972, |
| "num_input_tokens_seen": 16580608000, |
| "step": 63250 |
| }, |
| { |
| "epoch": 0.4257873787338375, |
| "grad_norm": 0.1709870994091034, |
| "learning_rate": 0.00037375421149242103, |
| "loss": 2.999, |
| "num_input_tokens_seen": 16593715200, |
| "step": 63300 |
| }, |
| { |
| "epoch": 0.4261237036775451, |
| "grad_norm": 0.1716383844614029, |
| "learning_rate": 0.0003690106807683313, |
| "loss": 2.9964, |
| "num_input_tokens_seen": 16606822400, |
| "step": 63350 |
| }, |
| { |
| "epoch": 0.4264600286212527, |
| "grad_norm": 0.18682868778705597, |
| "learning_rate": 0.0003642797750674629, |
| "loss": 3.0037, |
| "num_input_tokens_seen": 16619929600, |
| "step": 63400 |
| }, |
| { |
| "epoch": 0.4267963535649603, |
| "grad_norm": 0.16003596782684326, |
| "learning_rate": 0.00035956195036435405, |
| "loss": 2.9893, |
| "num_input_tokens_seen": 16633036800, |
| "step": 63450 |
| }, |
| { |
| "epoch": 0.42713267850866793, |
| "grad_norm": 0.17876048386096954, |
| "learning_rate": 0.0003548576613727689, |
| "loss": 3.0004, |
| "num_input_tokens_seen": 16646144000, |
| "step": 63500 |
| }, |
| { |
| "epoch": 0.42713267850866793, |
| "eval_loss": 2.8903579711914062, |
| "eval_runtime": 53.0482, |
| "eval_samples_per_second": 94.254, |
| "eval_steps_per_second": 23.563, |
| "num_input_tokens_seen": 16646144000, |
| "step": 63500 |
| }, |
| { |
| "epoch": 0.42746900345237554, |
| "grad_norm": 0.21229425072669983, |
| "learning_rate": 0.00035016736150187165, |
| "loss": 2.9925, |
| "num_input_tokens_seen": 16659251200, |
| "step": 63550 |
| }, |
| { |
| "epoch": 0.42780532839608315, |
| "grad_norm": 0.19477584958076477, |
| "learning_rate": 0.00034549150281252633, |
| "loss": 2.9892, |
| "num_input_tokens_seen": 16672358400, |
| "step": 63600 |
| }, |
| { |
| "epoch": 0.42814165333979076, |
| "grad_norm": 0.1866609901189804, |
| "learning_rate": 0.0003408305359737252, |
| "loss": 2.9913, |
| "num_input_tokens_seen": 16685465600, |
| "step": 63650 |
| }, |
| { |
| "epoch": 0.4284779782834984, |
| "grad_norm": 0.19487887620925903, |
| "learning_rate": 0.0003361849102191533, |
| "loss": 2.9875, |
| "num_input_tokens_seen": 16698572800, |
| "step": 63700 |
| }, |
| { |
| "epoch": 0.428814303227206, |
| "grad_norm": 0.15979841351509094, |
| "learning_rate": 0.00033155507330389, |
| "loss": 2.9894, |
| "num_input_tokens_seen": 16711680000, |
| "step": 63750 |
| }, |
| { |
| "epoch": 0.4291506281709136, |
| "grad_norm": 0.1749998778104782, |
| "learning_rate": 0.0003269414714612534, |
| "loss": 2.9945, |
| "num_input_tokens_seen": 16724787200, |
| "step": 63800 |
| }, |
| { |
| "epoch": 0.4294869531146212, |
| "grad_norm": 0.16839075088500977, |
| "learning_rate": 0.00032234454935979205, |
| "loss": 2.9989, |
| "num_input_tokens_seen": 16737894400, |
| "step": 63850 |
| }, |
| { |
| "epoch": 0.4298232780583288, |
| "grad_norm": 0.19226372241973877, |
| "learning_rate": 0.0003177647500604252, |
| "loss": 2.9854, |
| "num_input_tokens_seen": 16751001600, |
| "step": 63900 |
| }, |
| { |
| "epoch": 0.43015960300203643, |
| "grad_norm": 0.15530380606651306, |
| "learning_rate": 0.0003132025149737419, |
| "loss": 2.9903, |
| "num_input_tokens_seen": 16764108800, |
| "step": 63950 |
| }, |
| { |
| "epoch": 0.43049592794574404, |
| "grad_norm": 0.17773845791816711, |
| "learning_rate": 0.0003086582838174551, |
| "loss": 2.9839, |
| "num_input_tokens_seen": 16777216000, |
| "step": 64000 |
| }, |
| { |
| "epoch": 0.43049592794574404, |
| "eval_loss": 2.8860437870025635, |
| "eval_runtime": 53.1514, |
| "eval_samples_per_second": 94.071, |
| "eval_steps_per_second": 23.518, |
| "num_input_tokens_seen": 16777216000, |
| "step": 64000 |
| }, |
| { |
| "epoch": 0.43083225288945165, |
| "grad_norm": 0.15883377194404602, |
| "learning_rate": 0.000304132494574022, |
| "loss": 2.9851, |
| "num_input_tokens_seen": 16790323200, |
| "step": 64050 |
| }, |
| { |
| "epoch": 0.43116857783315926, |
| "grad_norm": 0.176467627286911, |
| "learning_rate": 0.00029962558344842963, |
| "loss": 2.9865, |
| "num_input_tokens_seen": 16803430400, |
| "step": 64100 |
| }, |
| { |
| "epoch": 0.43150490277686687, |
| "grad_norm": 0.16392388939857483, |
| "learning_rate": 0.00029513798482615227, |
| "loss": 2.9788, |
| "num_input_tokens_seen": 16816537600, |
| "step": 64150 |
| }, |
| { |
| "epoch": 0.4318412277205745, |
| "grad_norm": 0.15614169836044312, |
| "learning_rate": 0.0002906701312312861, |
| "loss": 2.9769, |
| "num_input_tokens_seen": 16829644800, |
| "step": 64200 |
| }, |
| { |
| "epoch": 0.43217755266428215, |
| "grad_norm": 0.16225555539131165, |
| "learning_rate": 0.00028622245328485907, |
| "loss": 2.9881, |
| "num_input_tokens_seen": 16842752000, |
| "step": 64250 |
| }, |
| { |
| "epoch": 0.43251387760798976, |
| "grad_norm": 0.16419048607349396, |
| "learning_rate": 0.0002817953796633289, |
| "loss": 2.99, |
| "num_input_tokens_seen": 16855859200, |
| "step": 64300 |
| }, |
| { |
| "epoch": 0.43285020255169737, |
| "grad_norm": 0.16654469072818756, |
| "learning_rate": 0.000277389337057266, |
| "loss": 2.9919, |
| "num_input_tokens_seen": 16868966400, |
| "step": 64350 |
| }, |
| { |
| "epoch": 0.433186527495405, |
| "grad_norm": 0.1688661277294159, |
| "learning_rate": 0.00027300475013022663, |
| "loss": 2.9844, |
| "num_input_tokens_seen": 16882073600, |
| "step": 64400 |
| }, |
| { |
| "epoch": 0.4335228524391126, |
| "grad_norm": 0.162180095911026, |
| "learning_rate": 0.000268642041477825, |
| "loss": 2.9847, |
| "num_input_tokens_seen": 16895180800, |
| "step": 64450 |
| }, |
| { |
| "epoch": 0.4338591773828202, |
| "grad_norm": 0.18244421482086182, |
| "learning_rate": 0.00026430163158700117, |
| "loss": 2.9789, |
| "num_input_tokens_seen": 16908288000, |
| "step": 64500 |
| }, |
| { |
| "epoch": 0.4338591773828202, |
| "eval_loss": 2.8813860416412354, |
| "eval_runtime": 53.1806, |
| "eval_samples_per_second": 94.019, |
| "eval_steps_per_second": 23.505, |
| "num_input_tokens_seen": 16908288000, |
| "step": 64500 |
| }, |
| { |
| "epoch": 0.4341955023265278, |
| "grad_norm": 0.15887753665447235, |
| "learning_rate": 0.00025998393879549445, |
| "loss": 2.9723, |
| "num_input_tokens_seen": 16921395200, |
| "step": 64550 |
| }, |
| { |
| "epoch": 0.4345318272702354, |
| "grad_norm": 0.17573221027851105, |
| "learning_rate": 0.0002556893792515227, |
| "loss": 2.99, |
| "num_input_tokens_seen": 16934502400, |
| "step": 64600 |
| }, |
| { |
| "epoch": 0.43486815221394304, |
| "grad_norm": 0.1790430247783661, |
| "learning_rate": 0.0002514183668736727, |
| "loss": 2.9887, |
| "num_input_tokens_seen": 16947609600, |
| "step": 64650 |
| }, |
| { |
| "epoch": 0.43520447715765065, |
| "grad_norm": 0.16031622886657715, |
| "learning_rate": 0.0002471713133110078, |
| "loss": 2.9835, |
| "num_input_tokens_seen": 16960716800, |
| "step": 64700 |
| }, |
| { |
| "epoch": 0.43554080210135826, |
| "grad_norm": 0.1702345311641693, |
| "learning_rate": 0.0002429486279033892, |
| "loss": 2.9862, |
| "num_input_tokens_seen": 16973824000, |
| "step": 64750 |
| }, |
| { |
| "epoch": 0.43587712704506587, |
| "grad_norm": 0.16080138087272644, |
| "learning_rate": 0.00023875071764202561, |
| "loss": 2.9785, |
| "num_input_tokens_seen": 16986931200, |
| "step": 64800 |
| }, |
| { |
| "epoch": 0.4362134519887735, |
| "grad_norm": 0.17694465816020966, |
| "learning_rate": 0.0002345779871302453, |
| "loss": 2.9962, |
| "num_input_tokens_seen": 17000038400, |
| "step": 64850 |
| }, |
| { |
| "epoch": 0.4365497769324811, |
| "grad_norm": 0.15310978889465332, |
| "learning_rate": 0.00023043083854449987, |
| "loss": 2.98, |
| "num_input_tokens_seen": 17013145600, |
| "step": 64900 |
| }, |
| { |
| "epoch": 0.4368861018761887, |
| "grad_norm": 0.15505504608154297, |
| "learning_rate": 0.0002263096715956019, |
| "loss": 2.9825, |
| "num_input_tokens_seen": 17026252800, |
| "step": 64950 |
| }, |
| { |
| "epoch": 0.4372224268198963, |
| "grad_norm": 0.15211448073387146, |
| "learning_rate": 0.00022221488349019903, |
| "loss": 2.9876, |
| "num_input_tokens_seen": 17039360000, |
| "step": 65000 |
| }, |
| { |
| "epoch": 0.4372224268198963, |
| "eval_loss": 2.8792829513549805, |
| "eval_runtime": 53.0249, |
| "eval_samples_per_second": 94.295, |
| "eval_steps_per_second": 23.574, |
| "num_input_tokens_seen": 17039360000, |
| "step": 65000 |
| }, |
| { |
| "epoch": 0.4375587517636039, |
| "grad_norm": 0.16188842058181763, |
| "learning_rate": 0.00021814686889249158, |
| "loss": 2.9812, |
| "num_input_tokens_seen": 17052467200, |
| "step": 65050 |
| }, |
| { |
| "epoch": 0.43789507670731154, |
| "grad_norm": 0.14550812542438507, |
| "learning_rate": 0.00021410601988619394, |
| "loss": 2.9856, |
| "num_input_tokens_seen": 17065574400, |
| "step": 65100 |
| }, |
| { |
| "epoch": 0.43823140165101915, |
| "grad_norm": 0.1500539779663086, |
| "learning_rate": 0.00021009272593674322, |
| "loss": 2.9827, |
| "num_input_tokens_seen": 17078681600, |
| "step": 65150 |
| }, |
| { |
| "epoch": 0.43856772659472676, |
| "grad_norm": 0.1571357101202011, |
| "learning_rate": 0.00020610737385376348, |
| "loss": 2.9788, |
| "num_input_tokens_seen": 17091788800, |
| "step": 65200 |
| }, |
| { |
| "epoch": 0.43890405153843437, |
| "grad_norm": 0.1671544760465622, |
| "learning_rate": 0.00020215034775378332, |
| "loss": 2.9758, |
| "num_input_tokens_seen": 17104896000, |
| "step": 65250 |
| }, |
| { |
| "epoch": 0.439240376482142, |
| "grad_norm": 0.15525776147842407, |
| "learning_rate": 0.0001982220290232143, |
| "loss": 2.9823, |
| "num_input_tokens_seen": 17118003200, |
| "step": 65300 |
| }, |
| { |
| "epoch": 0.4395767014258496, |
| "grad_norm": 0.14799903333187103, |
| "learning_rate": 0.00019432279628159188, |
| "loss": 2.9781, |
| "num_input_tokens_seen": 17131110400, |
| "step": 65350 |
| }, |
| { |
| "epoch": 0.4399130263695572, |
| "grad_norm": 0.16087676584720612, |
| "learning_rate": 0.00019045302534508295, |
| "loss": 2.9805, |
| "num_input_tokens_seen": 17144217600, |
| "step": 65400 |
| }, |
| { |
| "epoch": 0.4402493513132648, |
| "grad_norm": 0.15892113745212555, |
| "learning_rate": 0.0001866130891902653, |
| "loss": 2.9823, |
| "num_input_tokens_seen": 17157324800, |
| "step": 65450 |
| }, |
| { |
| "epoch": 0.4405856762569724, |
| "grad_norm": 0.187602236866951, |
| "learning_rate": 0.00018280335791817732, |
| "loss": 2.9804, |
| "num_input_tokens_seen": 17170432000, |
| "step": 65500 |
| }, |
| { |
| "epoch": 0.4405856762569724, |
| "eval_loss": 2.875824451446533, |
| "eval_runtime": 53.0867, |
| "eval_samples_per_second": 94.186, |
| "eval_steps_per_second": 23.546, |
| "num_input_tokens_seen": 17170432000, |
| "step": 65500 |
| }, |
| { |
| "epoch": 0.44092200120068004, |
| "grad_norm": 0.15579210221767426, |
| "learning_rate": 0.0001790241987186485, |
| "loss": 2.9734, |
| "num_input_tokens_seen": 17183539200, |
| "step": 65550 |
| }, |
| { |
| "epoch": 0.44125832614438765, |
| "grad_norm": 0.15250550210475922, |
| "learning_rate": 0.00017527597583490823, |
| "loss": 2.9787, |
| "num_input_tokens_seen": 17196646400, |
| "step": 65600 |
| }, |
| { |
| "epoch": 0.44159465108809526, |
| "grad_norm": 0.15954890847206116, |
| "learning_rate": 0.00017155905052847938, |
| "loss": 2.978, |
| "num_input_tokens_seen": 17209753600, |
| "step": 65650 |
| }, |
| { |
| "epoch": 0.44193097603180287, |
| "grad_norm": 0.15598754584789276, |
| "learning_rate": 0.00016787378104435928, |
| "loss": 2.9809, |
| "num_input_tokens_seen": 17222860800, |
| "step": 65700 |
| }, |
| { |
| "epoch": 0.4422673009755105, |
| "grad_norm": 0.14709477126598358, |
| "learning_rate": 0.00016422052257649078, |
| "loss": 2.9793, |
| "num_input_tokens_seen": 17235968000, |
| "step": 65750 |
| }, |
| { |
| "epoch": 0.4426036259192181, |
| "grad_norm": 0.15505217015743256, |
| "learning_rate": 0.0001605996272335291, |
| "loss": 2.9763, |
| "num_input_tokens_seen": 17249075200, |
| "step": 65800 |
| }, |
| { |
| "epoch": 0.4429399508629257, |
| "grad_norm": 0.14491549134254456, |
| "learning_rate": 0.0001570114440049037, |
| "loss": 2.9756, |
| "num_input_tokens_seen": 17262182400, |
| "step": 65850 |
| }, |
| { |
| "epoch": 0.4432762758066333, |
| "grad_norm": 0.1571652740240097, |
| "learning_rate": 0.00015345631872718213, |
| "loss": 2.977, |
| "num_input_tokens_seen": 17275289600, |
| "step": 65900 |
| }, |
| { |
| "epoch": 0.4436126007503409, |
| "grad_norm": 0.18299035727977753, |
| "learning_rate": 0.00014993459405073824, |
| "loss": 2.9788, |
| "num_input_tokens_seen": 17288396800, |
| "step": 65950 |
| }, |
| { |
| "epoch": 0.44394892569404854, |
| "grad_norm": 0.14829285442829132, |
| "learning_rate": 0.00014644660940672628, |
| "loss": 2.9851, |
| "num_input_tokens_seen": 17301504000, |
| "step": 66000 |
| }, |
| { |
| "epoch": 0.44394892569404854, |
| "eval_loss": 2.8729286193847656, |
| "eval_runtime": 53.2839, |
| "eval_samples_per_second": 93.837, |
| "eval_steps_per_second": 23.459, |
| "num_input_tokens_seen": 17301504000, |
| "step": 66000 |
| }, |
| { |
| "epoch": 0.4442852506377562, |
| "grad_norm": 0.14435406029224396, |
| "learning_rate": 0.0001429927009743659, |
| "loss": 2.9718, |
| "num_input_tokens_seen": 17314611200, |
| "step": 66050 |
| }, |
| { |
| "epoch": 0.4446215755814638, |
| "grad_norm": 0.1603071242570877, |
| "learning_rate": 0.0001395732016485406, |
| "loss": 2.9731, |
| "num_input_tokens_seen": 17327718400, |
| "step": 66100 |
| }, |
| { |
| "epoch": 0.4449579005251714, |
| "grad_norm": 0.14310726523399353, |
| "learning_rate": 0.00013618844100771256, |
| "loss": 2.9665, |
| "num_input_tokens_seen": 17340825600, |
| "step": 66150 |
| }, |
| { |
| "epoch": 0.44529422546887903, |
| "grad_norm": 0.276594340801239, |
| "learning_rate": 0.00013283874528215734, |
| "loss": 2.9711, |
| "num_input_tokens_seen": 17353932800, |
| "step": 66200 |
| }, |
| { |
| "epoch": 0.44563055041258665, |
| "grad_norm": 0.1535540074110031, |
| "learning_rate": 0.00012952443732252057, |
| "loss": 2.9693, |
| "num_input_tokens_seen": 17367040000, |
| "step": 66250 |
| }, |
| { |
| "epoch": 0.44596687535629426, |
| "grad_norm": 0.15807458758354187, |
| "learning_rate": 0.00012624583656870153, |
| "loss": 2.9754, |
| "num_input_tokens_seen": 17380147200, |
| "step": 66300 |
| }, |
| { |
| "epoch": 0.44630320030000187, |
| "grad_norm": 0.14477893710136414, |
| "learning_rate": 0.00012300325901906528, |
| "loss": 2.9735, |
| "num_input_tokens_seen": 17393254400, |
| "step": 66350 |
| }, |
| { |
| "epoch": 0.4466395252437095, |
| "grad_norm": 0.14505073428153992, |
| "learning_rate": 0.00011979701719998454, |
| "loss": 2.9783, |
| "num_input_tokens_seen": 17406361600, |
| "step": 66400 |
| }, |
| { |
| "epoch": 0.4469758501874171, |
| "grad_norm": 0.15850161015987396, |
| "learning_rate": 0.00011662742013571926, |
| "loss": 2.967, |
| "num_input_tokens_seen": 17419468800, |
| "step": 66450 |
| }, |
| { |
| "epoch": 0.4473121751311247, |
| "grad_norm": 0.14653578400611877, |
| "learning_rate": 0.00011349477331863151, |
| "loss": 2.9651, |
| "num_input_tokens_seen": 17432576000, |
| "step": 66500 |
| }, |
| { |
| "epoch": 0.4473121751311247, |
| "eval_loss": 2.8710148334503174, |
| "eval_runtime": 53.2889, |
| "eval_samples_per_second": 93.828, |
| "eval_steps_per_second": 23.457, |
| "num_input_tokens_seen": 17432576000, |
| "step": 66500 |
| }, |
| { |
| "epoch": 0.4476485000748323, |
| "grad_norm": 0.15636616945266724, |
| "learning_rate": 0.00011039937867974164, |
| "loss": 2.9758, |
| "num_input_tokens_seen": 17445683200, |
| "step": 66550 |
| }, |
| { |
| "epoch": 0.4479848250185399, |
| "grad_norm": 0.14427579939365387, |
| "learning_rate": 0.00010734153455962764, |
| "loss": 2.9594, |
| "num_input_tokens_seen": 17458790400, |
| "step": 66600 |
| }, |
| { |
| "epoch": 0.44832114996224753, |
| "grad_norm": 0.15148353576660156, |
| "learning_rate": 0.00010432153567966984, |
| "loss": 2.9684, |
| "num_input_tokens_seen": 17471897600, |
| "step": 66650 |
| }, |
| { |
| "epoch": 0.44865747490595514, |
| "grad_norm": 0.1541094332933426, |
| "learning_rate": 0.0001013396731136465, |
| "loss": 2.9685, |
| "num_input_tokens_seen": 17485004800, |
| "step": 66700 |
| }, |
| { |
| "epoch": 0.44899379984966276, |
| "grad_norm": 0.14267295598983765, |
| "learning_rate": 9.839623425967759e-05, |
| "loss": 2.9728, |
| "num_input_tokens_seen": 17498112000, |
| "step": 66750 |
| }, |
| { |
| "epoch": 0.44933012479337037, |
| "grad_norm": 0.1437918245792389, |
| "learning_rate": 9.549150281252633e-05, |
| "loss": 2.9752, |
| "num_input_tokens_seen": 17511219200, |
| "step": 66800 |
| }, |
| { |
| "epoch": 0.449666449737078, |
| "grad_norm": 0.1517232209444046, |
| "learning_rate": 9.262575873625529e-05, |
| "loss": 2.9729, |
| "num_input_tokens_seen": 17524326400, |
| "step": 66850 |
| }, |
| { |
| "epoch": 0.4500027746807856, |
| "grad_norm": 0.15286608040332794, |
| "learning_rate": 8.979927823724321e-05, |
| "loss": 2.9687, |
| "num_input_tokens_seen": 17537433600, |
| "step": 66900 |
| }, |
| { |
| "epoch": 0.4503390996244932, |
| "grad_norm": 0.14875057339668274, |
| "learning_rate": 8.70123337375635e-05, |
| "loss": 2.9758, |
| "num_input_tokens_seen": 17550540800, |
| "step": 66950 |
| }, |
| { |
| "epoch": 0.4506754245682008, |
| "grad_norm": 0.1493612825870514, |
| "learning_rate": 8.426519384872733e-05, |
| "loss": 2.9704, |
| "num_input_tokens_seen": 17563648000, |
| "step": 67000 |
| }, |
| { |
| "epoch": 0.4506754245682008, |
| "eval_loss": 2.869231939315796, |
| "eval_runtime": 53.2491, |
| "eval_samples_per_second": 93.898, |
| "eval_steps_per_second": 23.475, |
| "num_input_tokens_seen": 17563648000, |
| "step": 67000 |
| }, |
| { |
| "epoch": 0.4510117495119084, |
| "grad_norm": 0.14675357937812805, |
| "learning_rate": 8.155812334579532e-05, |
| "loss": 2.9682, |
| "num_input_tokens_seen": 17576755200, |
| "step": 67050 |
| }, |
| { |
| "epoch": 0.45134807445561603, |
| "grad_norm": 0.14341385662555695, |
| "learning_rate": 7.889138314185678e-05, |
| "loss": 2.9749, |
| "num_input_tokens_seen": 17589862400, |
| "step": 67100 |
| }, |
| { |
| "epoch": 0.45168439939932364, |
| "grad_norm": 0.1442009061574936, |
| "learning_rate": 7.626523026288279e-05, |
| "loss": 2.9637, |
| "num_input_tokens_seen": 17602969600, |
| "step": 67150 |
| }, |
| { |
| "epoch": 0.45202072434303125, |
| "grad_norm": 0.14580078423023224, |
| "learning_rate": 7.367991782295391e-05, |
| "loss": 2.9636, |
| "num_input_tokens_seen": 17616076800, |
| "step": 67200 |
| }, |
| { |
| "epoch": 0.45235704928673887, |
| "grad_norm": 0.13888555765151978, |
| "learning_rate": 7.1135694999864e-05, |
| "loss": 2.9737, |
| "num_input_tokens_seen": 17629184000, |
| "step": 67250 |
| }, |
| { |
| "epoch": 0.4526933742304465, |
| "grad_norm": 0.14820803701877594, |
| "learning_rate": 6.863280701110408e-05, |
| "loss": 2.9778, |
| "num_input_tokens_seen": 17642291200, |
| "step": 67300 |
| }, |
| { |
| "epoch": 0.4530296991741541, |
| "grad_norm": 0.14933691918849945, |
| "learning_rate": 6.617149509022808e-05, |
| "loss": 2.9667, |
| "num_input_tokens_seen": 17655398400, |
| "step": 67350 |
| }, |
| { |
| "epoch": 0.4533660241178617, |
| "grad_norm": 0.14829853177070618, |
| "learning_rate": 6.375199646360142e-05, |
| "loss": 2.9691, |
| "num_input_tokens_seen": 17668505600, |
| "step": 67400 |
| }, |
| { |
| "epoch": 0.4537023490615693, |
| "grad_norm": 0.14731477200984955, |
| "learning_rate": 6.137454432753797e-05, |
| "loss": 2.9731, |
| "num_input_tokens_seen": 17681612800, |
| "step": 67450 |
| }, |
| { |
| "epoch": 0.4540386740052769, |
| "grad_norm": 0.14357906579971313, |
| "learning_rate": 5.903936782582253e-05, |
| "loss": 2.9785, |
| "num_input_tokens_seen": 17694720000, |
| "step": 67500 |
| }, |
| { |
| "epoch": 0.4540386740052769, |
| "eval_loss": 2.867840528488159, |
| "eval_runtime": 53.8197, |
| "eval_samples_per_second": 92.903, |
| "eval_steps_per_second": 23.226, |
| "num_input_tokens_seen": 17694720000, |
| "step": 67500 |
| }, |
| { |
| "epoch": 0.45437499894898453, |
| "grad_norm": 0.1438903659582138, |
| "learning_rate": 5.6746692027626835e-05, |
| "loss": 2.9733, |
| "num_input_tokens_seen": 17707827200, |
| "step": 67550 |
| }, |
| { |
| "epoch": 0.45471132389269214, |
| "grad_norm": 0.14171506464481354, |
| "learning_rate": 5.449673790581611e-05, |
| "loss": 2.9637, |
| "num_input_tokens_seen": 17720934400, |
| "step": 67600 |
| }, |
| { |
| "epoch": 0.45504764883639975, |
| "grad_norm": 0.1645549088716507, |
| "learning_rate": 5.2289722315651546e-05, |
| "loss": 2.9668, |
| "num_input_tokens_seen": 17734041600, |
| "step": 67650 |
| }, |
| { |
| "epoch": 0.45538397378010737, |
| "grad_norm": 0.1390199065208435, |
| "learning_rate": 5.0125857973889355e-05, |
| "loss": 2.9762, |
| "num_input_tokens_seen": 17747148800, |
| "step": 67700 |
| }, |
| { |
| "epoch": 0.455720298723815, |
| "grad_norm": 0.14667369425296783, |
| "learning_rate": 4.800535343827833e-05, |
| "loss": 2.9724, |
| "num_input_tokens_seen": 17760256000, |
| "step": 67750 |
| }, |
| { |
| "epoch": 0.4560566236675226, |
| "grad_norm": 0.14203302562236786, |
| "learning_rate": 4.592841308745932e-05, |
| "loss": 2.9679, |
| "num_input_tokens_seen": 17773363200, |
| "step": 67800 |
| }, |
| { |
| "epoch": 0.45639294861123025, |
| "grad_norm": 0.1517883837223053, |
| "learning_rate": 4.389523710126619e-05, |
| "loss": 2.9723, |
| "num_input_tokens_seen": 17786470400, |
| "step": 67850 |
| }, |
| { |
| "epoch": 0.45672927355493786, |
| "grad_norm": 0.1438019722700119, |
| "learning_rate": 4.190602144143207e-05, |
| "loss": 2.973, |
| "num_input_tokens_seen": 17799577600, |
| "step": 67900 |
| }, |
| { |
| "epoch": 0.4570655984986455, |
| "grad_norm": 0.14281606674194336, |
| "learning_rate": 3.9960957832702595e-05, |
| "loss": 2.9733, |
| "num_input_tokens_seen": 17812684800, |
| "step": 67950 |
| }, |
| { |
| "epoch": 0.4574019234423531, |
| "grad_norm": 0.14911025762557983, |
| "learning_rate": 3.806023374435663e-05, |
| "loss": 2.9724, |
| "num_input_tokens_seen": 17825792000, |
| "step": 68000 |
| }, |
| { |
| "epoch": 0.4574019234423531, |
| "eval_loss": 2.8663442134857178, |
| "eval_runtime": 53.8853, |
| "eval_samples_per_second": 92.79, |
| "eval_steps_per_second": 23.197, |
| "num_input_tokens_seen": 17825792000, |
| "step": 68000 |
| }, |
| { |
| "epoch": 0.4577382483860607, |
| "grad_norm": 0.14517797529697418, |
| "learning_rate": 3.6204032372137984e-05, |
| "loss": 2.9674, |
| "num_input_tokens_seen": 17838899200, |
| "step": 68050 |
| }, |
| { |
| "epoch": 0.4580745733297683, |
| "grad_norm": 0.14154207706451416, |
| "learning_rate": 3.439253262059822e-05, |
| "loss": 2.9627, |
| "num_input_tokens_seen": 17852006400, |
| "step": 68100 |
| }, |
| { |
| "epoch": 0.4584108982734759, |
| "grad_norm": 0.14251314103603363, |
| "learning_rate": 3.2625909085853776e-05, |
| "loss": 2.9681, |
| "num_input_tokens_seen": 17865113600, |
| "step": 68150 |
| }, |
| { |
| "epoch": 0.45874722321718353, |
| "grad_norm": 0.15670983493328094, |
| "learning_rate": 3.0904332038757974e-05, |
| "loss": 2.9708, |
| "num_input_tokens_seen": 17878220800, |
| "step": 68200 |
| }, |
| { |
| "epoch": 0.45908354816089114, |
| "grad_norm": 0.1453925371170044, |
| "learning_rate": 2.9227967408489654e-05, |
| "loss": 2.9686, |
| "num_input_tokens_seen": 17891328000, |
| "step": 68250 |
| }, |
| { |
| "epoch": 0.45941987310459875, |
| "grad_norm": 0.13307476043701172, |
| "learning_rate": 2.7596976766560976e-05, |
| "loss": 2.9595, |
| "num_input_tokens_seen": 17904435200, |
| "step": 68300 |
| }, |
| { |
| "epoch": 0.45975619804830636, |
| "grad_norm": 0.14958307147026062, |
| "learning_rate": 2.6011517311244848e-05, |
| "loss": 2.9661, |
| "num_input_tokens_seen": 17917542400, |
| "step": 68350 |
| }, |
| { |
| "epoch": 0.460092522992014, |
| "grad_norm": 0.14210085570812225, |
| "learning_rate": 2.4471741852423235e-05, |
| "loss": 2.9737, |
| "num_input_tokens_seen": 17930649600, |
| "step": 68400 |
| }, |
| { |
| "epoch": 0.4604288479357216, |
| "grad_norm": 0.15127155184745789, |
| "learning_rate": 2.2977798796859794e-05, |
| "loss": 2.9627, |
| "num_input_tokens_seen": 17943756800, |
| "step": 68450 |
| }, |
| { |
| "epoch": 0.4607651728794292, |
| "grad_norm": 0.14184921979904175, |
| "learning_rate": 2.152983213389559e-05, |
| "loss": 2.9732, |
| "num_input_tokens_seen": 17956864000, |
| "step": 68500 |
| }, |
| { |
| "epoch": 0.4607651728794292, |
| "eval_loss": 2.865307331085205, |
| "eval_runtime": 53.2908, |
| "eval_samples_per_second": 93.825, |
| "eval_steps_per_second": 23.456, |
| "num_input_tokens_seen": 17956864000, |
| "step": 68500 |
| }, |
| { |
| "epoch": 0.4611014978231368, |
| "grad_norm": 0.14755961298942566, |
| "learning_rate": 2.0127981421571295e-05, |
| "loss": 2.9687, |
| "num_input_tokens_seen": 17969971200, |
| "step": 68550 |
| }, |
| { |
| "epoch": 0.4614378227668444, |
| "grad_norm": 0.1370965540409088, |
| "learning_rate": 1.8772381773176416e-05, |
| "loss": 2.9711, |
| "num_input_tokens_seen": 17983078400, |
| "step": 68600 |
| }, |
| { |
| "epoch": 0.46177414771055203, |
| "grad_norm": 0.14454130828380585, |
| "learning_rate": 1.7463163844226305e-05, |
| "loss": 2.9633, |
| "num_input_tokens_seen": 17996185600, |
| "step": 68650 |
| }, |
| { |
| "epoch": 0.46211047265425964, |
| "grad_norm": 0.13908445835113525, |
| "learning_rate": 1.620045381987012e-05, |
| "loss": 2.9662, |
| "num_input_tokens_seen": 18009292800, |
| "step": 68700 |
| }, |
| { |
| "epoch": 0.46244679759796725, |
| "grad_norm": 0.2359876185655594, |
| "learning_rate": 1.4984373402728013e-05, |
| "loss": 2.9671, |
| "num_input_tokens_seen": 18022400000, |
| "step": 68750 |
| }, |
| { |
| "epoch": 0.46278312254167486, |
| "grad_norm": 0.13809122145175934, |
| "learning_rate": 1.3815039801161721e-05, |
| "loss": 2.9684, |
| "num_input_tokens_seen": 18035507200, |
| "step": 68800 |
| }, |
| { |
| "epoch": 0.4631194474853825, |
| "grad_norm": 0.14375115931034088, |
| "learning_rate": 1.26925657179775e-05, |
| "loss": 2.9677, |
| "num_input_tokens_seen": 18048614400, |
| "step": 68850 |
| }, |
| { |
| "epoch": 0.4634557724290901, |
| "grad_norm": 0.14648525416851044, |
| "learning_rate": 1.1617059339563806e-05, |
| "loss": 2.9625, |
| "num_input_tokens_seen": 18061721600, |
| "step": 68900 |
| }, |
| { |
| "epoch": 0.4637920973727977, |
| "grad_norm": 0.1428016871213913, |
| "learning_rate": 1.058862432546387e-05, |
| "loss": 2.9717, |
| "num_input_tokens_seen": 18074828800, |
| "step": 68950 |
| }, |
| { |
| "epoch": 0.4641284223165053, |
| "grad_norm": 0.14518927037715912, |
| "learning_rate": 9.607359798384786e-06, |
| "loss": 2.9622, |
| "num_input_tokens_seen": 18087936000, |
| "step": 69000 |
| }, |
| { |
| "epoch": 0.4641284223165053, |
| "eval_loss": 2.8647797107696533, |
| "eval_runtime": 53.1259, |
| "eval_samples_per_second": 94.116, |
| "eval_steps_per_second": 23.529, |
| "num_input_tokens_seen": 18087936000, |
| "step": 69000 |
| }, |
| { |
| "epoch": 0.4644647472602129, |
| "grad_norm": 0.1424110382795334, |
| "learning_rate": 8.67336033464411e-06, |
| "loss": 2.9591, |
| "num_input_tokens_seen": 18101043200, |
| "step": 69050 |
| }, |
| { |
| "epoch": 0.46480107220392053, |
| "grad_norm": 0.14686723053455353, |
| "learning_rate": 7.786715955054202e-06, |
| "loss": 2.9561, |
| "num_input_tokens_seen": 18114150400, |
| "step": 69100 |
| }, |
| { |
| "epoch": 0.46513739714762814, |
| "grad_norm": 0.13719068467617035, |
| "learning_rate": 6.947512116245669e-06, |
| "loss": 2.9629, |
| "num_input_tokens_seen": 18127257600, |
| "step": 69150 |
| }, |
| { |
| "epoch": 0.46547372209133575, |
| "grad_norm": 0.14337210357189178, |
| "learning_rate": 6.15582970243117e-06, |
| "loss": 2.9713, |
| "num_input_tokens_seen": 18140364800, |
| "step": 69200 |
| }, |
| { |
| "epoch": 0.46581004703504336, |
| "grad_norm": 0.18305008113384247, |
| "learning_rate": 5.411745017609493e-06, |
| "loss": 2.9659, |
| "num_input_tokens_seen": 18153472000, |
| "step": 69250 |
| }, |
| { |
| "epoch": 0.466146371978751, |
| "grad_norm": 0.137322798371315, |
| "learning_rate": 4.715329778211374e-06, |
| "loss": 2.9678, |
| "num_input_tokens_seen": 18166579200, |
| "step": 69300 |
| }, |
| { |
| "epoch": 0.4664826969224586, |
| "grad_norm": 0.13300293684005737, |
| "learning_rate": 4.066651106186981e-06, |
| "loss": 2.9647, |
| "num_input_tokens_seen": 18179686400, |
| "step": 69350 |
| }, |
| { |
| "epoch": 0.4668190218661662, |
| "grad_norm": 0.13357709348201752, |
| "learning_rate": 3.4657715225368535e-06, |
| "loss": 2.965, |
| "num_input_tokens_seen": 18192793600, |
| "step": 69400 |
| }, |
| { |
| "epoch": 0.4671553468098738, |
| "grad_norm": 0.13399702310562134, |
| "learning_rate": 2.9127489412859033e-06, |
| "loss": 2.9614, |
| "num_input_tokens_seen": 18205900800, |
| "step": 69450 |
| }, |
| { |
| "epoch": 0.4674916717535814, |
| "grad_norm": 0.13703274726867676, |
| "learning_rate": 2.4076366639015913e-06, |
| "loss": 2.964, |
| "num_input_tokens_seen": 18219008000, |
| "step": 69500 |
| }, |
| { |
| "epoch": 0.4674916717535814, |
| "eval_loss": 2.8645894527435303, |
| "eval_runtime": 53.3524, |
| "eval_samples_per_second": 93.716, |
| "eval_steps_per_second": 23.429, |
| "num_input_tokens_seen": 18219008000, |
| "step": 69500 |
| }, |
| { |
| "epoch": 0.46782799669728903, |
| "grad_norm": 0.3837803900241852, |
| "learning_rate": 1.950483374156431e-06, |
| "loss": 2.9665, |
| "num_input_tokens_seen": 18232115200, |
| "step": 69550 |
| }, |
| { |
| "epoch": 0.46816432164099664, |
| "grad_norm": 0.13585589826107025, |
| "learning_rate": 1.541333133436018e-06, |
| "loss": 2.9579, |
| "num_input_tokens_seen": 18245222400, |
| "step": 69600 |
| }, |
| { |
| "epoch": 0.4685006465847043, |
| "grad_norm": 0.13347585499286652, |
| "learning_rate": 1.18022537649215e-06, |
| "loss": 2.9636, |
| "num_input_tokens_seen": 18258329600, |
| "step": 69650 |
| }, |
| { |
| "epoch": 0.4688369715284119, |
| "grad_norm": 0.13726544380187988, |
| "learning_rate": 8.671949076420882e-07, |
| "loss": 2.9626, |
| "num_input_tokens_seen": 18271436800, |
| "step": 69700 |
| }, |
| { |
| "epoch": 0.4691732964721195, |
| "grad_norm": 0.14254987239837646, |
| "learning_rate": 6.022718974137975e-07, |
| "loss": 2.9698, |
| "num_input_tokens_seen": 18284544000, |
| "step": 69750 |
| }, |
| { |
| "epoch": 0.46950962141582714, |
| "grad_norm": 0.1329219937324524, |
| "learning_rate": 3.854818796385495e-07, |
| "loss": 2.96, |
| "num_input_tokens_seen": 18297651200, |
| "step": 69800 |
| }, |
| { |
| "epoch": 0.46984594635953475, |
| "grad_norm": 0.1384582668542862, |
| "learning_rate": 2.1684574898939157e-07, |
| "loss": 2.9693, |
| "num_input_tokens_seen": 18310758400, |
| "step": 69850 |
| }, |
| { |
| "epoch": 0.47018227130324236, |
| "grad_norm": 0.14365264773368835, |
| "learning_rate": 9.637975896759077e-08, |
| "loss": 2.9686, |
| "num_input_tokens_seen": 18323865600, |
| "step": 69900 |
| }, |
| { |
| "epoch": 0.47051859624694997, |
| "grad_norm": 0.13613733649253845, |
| "learning_rate": 2.4095520335998265e-08, |
| "loss": 2.9607, |
| "num_input_tokens_seen": 18336972800, |
| "step": 69950 |
| }, |
| { |
| "epoch": 0.4708549211906576, |
| "grad_norm": 0.14377959072589874, |
| "learning_rate": 0.0, |
| "loss": 2.9684, |
| "num_input_tokens_seen": 18350080000, |
| "step": 70000 |
| }, |
| { |
| "epoch": 0.4708549211906576, |
| "eval_loss": 2.8644959926605225, |
| "eval_runtime": 54.0337, |
| "eval_samples_per_second": 92.535, |
| "eval_steps_per_second": 23.134, |
| "num_input_tokens_seen": 18350080000, |
| "step": 70000 |
| }, |
| { |
| "epoch": 0.4708549211906576, |
| "num_input_tokens_seen": 18350080000, |
| "step": 70000, |
| "total_flos": 4.9088254967808e+18, |
| "train_loss": 0.4265073311941964, |
| "train_runtime": 14322.5496, |
| "train_samples_per_second": 1251.174, |
| "train_steps_per_second": 4.887, |
| "train_tokens_per_second": 1281202.057 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 70000, |
| "num_input_tokens_seen": 18350080000, |
| "num_train_epochs": 1, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.9088254967808e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
