| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.5934065934065934, |
| "eval_steps": 500, |
| "global_step": 90, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006593406593406593, |
| "grad_norm": 1.1175572872161865, |
| "learning_rate": 0.0, |
| "loss": 3.0744, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.013186813186813187, |
| "grad_norm": 1.2595356702804565, |
| "learning_rate": 4e-05, |
| "loss": 3.3519, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01978021978021978, |
| "grad_norm": 1.1831451654434204, |
| "learning_rate": 8e-05, |
| "loss": 3.4142, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.026373626373626374, |
| "grad_norm": 1.1135042905807495, |
| "learning_rate": 0.00012, |
| "loss": 2.8473, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.03296703296703297, |
| "grad_norm": 1.6986281871795654, |
| "learning_rate": 0.00016, |
| "loss": 3.1145, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03956043956043956, |
| "grad_norm": 1.8996844291687012, |
| "learning_rate": 0.0002, |
| "loss": 2.7206, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.046153846153846156, |
| "grad_norm": 1.654848337173462, |
| "learning_rate": 0.00019955654101995565, |
| "loss": 1.6435, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.05274725274725275, |
| "grad_norm": 1.9960455894470215, |
| "learning_rate": 0.00019911308203991133, |
| "loss": 1.6488, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05934065934065934, |
| "grad_norm": 1.1452784538269043, |
| "learning_rate": 0.00019866962305986697, |
| "loss": 1.2791, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.06593406593406594, |
| "grad_norm": 0.9133374094963074, |
| "learning_rate": 0.00019822616407982261, |
| "loss": 1.0621, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07252747252747253, |
| "grad_norm": 0.7128933668136597, |
| "learning_rate": 0.00019778270509977829, |
| "loss": 0.8729, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07912087912087912, |
| "grad_norm": 0.9738520383834839, |
| "learning_rate": 0.00019733924611973393, |
| "loss": 0.945, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.08571428571428572, |
| "grad_norm": 1.0968796014785767, |
| "learning_rate": 0.0001968957871396896, |
| "loss": 0.9219, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.09230769230769231, |
| "grad_norm": 0.8448852300643921, |
| "learning_rate": 0.00019645232815964525, |
| "loss": 0.7323, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.0989010989010989, |
| "grad_norm": 0.6533470153808594, |
| "learning_rate": 0.00019600886917960092, |
| "loss": 0.7965, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.1054945054945055, |
| "grad_norm": 0.5058298707008362, |
| "learning_rate": 0.00019556541019955653, |
| "loss": 0.7675, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.11208791208791209, |
| "grad_norm": 0.5244030952453613, |
| "learning_rate": 0.0001951219512195122, |
| "loss": 0.6938, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.11868131868131868, |
| "grad_norm": 0.5534260869026184, |
| "learning_rate": 0.00019467849223946785, |
| "loss": 0.7475, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.12527472527472527, |
| "grad_norm": 0.49227115511894226, |
| "learning_rate": 0.00019423503325942352, |
| "loss": 0.7782, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.13186813186813187, |
| "grad_norm": 0.6014466881752014, |
| "learning_rate": 0.00019379157427937917, |
| "loss": 0.6281, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.13846153846153847, |
| "grad_norm": 0.46302980184555054, |
| "learning_rate": 0.00019334811529933484, |
| "loss": 0.6085, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.14505494505494507, |
| "grad_norm": 0.3817231357097626, |
| "learning_rate": 0.00019290465631929045, |
| "loss": 0.4978, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.15164835164835164, |
| "grad_norm": 0.41959288716316223, |
| "learning_rate": 0.00019246119733924613, |
| "loss": 0.7479, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.15824175824175823, |
| "grad_norm": 0.37861549854278564, |
| "learning_rate": 0.00019201773835920177, |
| "loss": 0.5145, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.16483516483516483, |
| "grad_norm": 0.41947174072265625, |
| "learning_rate": 0.00019157427937915744, |
| "loss": 0.6564, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.17142857142857143, |
| "grad_norm": 0.43568453192710876, |
| "learning_rate": 0.00019113082039911309, |
| "loss": 0.7639, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.17802197802197803, |
| "grad_norm": 0.35360434651374817, |
| "learning_rate": 0.00019068736141906876, |
| "loss": 0.7617, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.18461538461538463, |
| "grad_norm": 0.43759599328041077, |
| "learning_rate": 0.0001902439024390244, |
| "loss": 0.6815, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.1912087912087912, |
| "grad_norm": 0.3009309470653534, |
| "learning_rate": 0.00018980044345898005, |
| "loss": 0.5048, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.1978021978021978, |
| "grad_norm": 0.37697890400886536, |
| "learning_rate": 0.00018935698447893572, |
| "loss": 0.5197, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2043956043956044, |
| "grad_norm": 0.36582183837890625, |
| "learning_rate": 0.00018891352549889136, |
| "loss": 0.4953, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.210989010989011, |
| "grad_norm": 0.4371263384819031, |
| "learning_rate": 0.00018847006651884703, |
| "loss": 0.6357, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.2175824175824176, |
| "grad_norm": 0.35323941707611084, |
| "learning_rate": 0.00018802660753880268, |
| "loss": 0.6407, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.22417582417582418, |
| "grad_norm": 0.4218985438346863, |
| "learning_rate": 0.00018758314855875832, |
| "loss": 0.6067, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.23076923076923078, |
| "grad_norm": 0.4576883614063263, |
| "learning_rate": 0.00018713968957871397, |
| "loss": 0.7649, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.23736263736263735, |
| "grad_norm": 0.3939562737941742, |
| "learning_rate": 0.00018669623059866964, |
| "loss": 0.7539, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.24395604395604395, |
| "grad_norm": 0.3907439112663269, |
| "learning_rate": 0.00018625277161862528, |
| "loss": 0.6574, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.25054945054945055, |
| "grad_norm": 0.34653839468955994, |
| "learning_rate": 0.00018580931263858095, |
| "loss": 0.4845, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.2571428571428571, |
| "grad_norm": 0.30807438492774963, |
| "learning_rate": 0.0001853658536585366, |
| "loss": 0.5046, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.26373626373626374, |
| "grad_norm": 0.3422587811946869, |
| "learning_rate": 0.00018492239467849224, |
| "loss": 0.642, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2703296703296703, |
| "grad_norm": 0.4083802103996277, |
| "learning_rate": 0.0001844789356984479, |
| "loss": 0.6177, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.27692307692307694, |
| "grad_norm": 0.3902239203453064, |
| "learning_rate": 0.00018403547671840356, |
| "loss": 0.6883, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.2835164835164835, |
| "grad_norm": 0.413637638092041, |
| "learning_rate": 0.0001835920177383592, |
| "loss": 0.5178, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.29010989010989013, |
| "grad_norm": 0.3305671513080597, |
| "learning_rate": 0.00018314855875831487, |
| "loss": 0.4925, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.2967032967032967, |
| "grad_norm": 0.3556175231933594, |
| "learning_rate": 0.00018270509977827052, |
| "loss": 0.4991, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.3032967032967033, |
| "grad_norm": 0.3833027482032776, |
| "learning_rate": 0.00018226164079822616, |
| "loss": 0.5837, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.3098901098901099, |
| "grad_norm": 0.34828928112983704, |
| "learning_rate": 0.00018181818181818183, |
| "loss": 0.4893, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.31648351648351647, |
| "grad_norm": 0.4020296335220337, |
| "learning_rate": 0.00018137472283813748, |
| "loss": 0.4792, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.3230769230769231, |
| "grad_norm": 0.47377222776412964, |
| "learning_rate": 0.00018093126385809312, |
| "loss": 0.5776, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.32967032967032966, |
| "grad_norm": 0.47716471552848816, |
| "learning_rate": 0.0001804878048780488, |
| "loss": 0.6295, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.3362637362637363, |
| "grad_norm": 0.4160218834877014, |
| "learning_rate": 0.00018004434589800444, |
| "loss": 0.5249, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.34285714285714286, |
| "grad_norm": 0.3925120234489441, |
| "learning_rate": 0.00017960088691796008, |
| "loss": 0.5979, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.34945054945054943, |
| "grad_norm": 0.451288104057312, |
| "learning_rate": 0.00017915742793791575, |
| "loss": 0.7045, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.35604395604395606, |
| "grad_norm": 0.44237250089645386, |
| "learning_rate": 0.0001787139689578714, |
| "loss": 0.6288, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.3626373626373626, |
| "grad_norm": 0.37273454666137695, |
| "learning_rate": 0.00017827050997782707, |
| "loss": 0.5214, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.36923076923076925, |
| "grad_norm": 0.4249885380268097, |
| "learning_rate": 0.00017782705099778271, |
| "loss": 0.6523, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.3758241758241758, |
| "grad_norm": 0.4397568702697754, |
| "learning_rate": 0.00017738359201773839, |
| "loss": 0.7857, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.3824175824175824, |
| "grad_norm": 0.37436991930007935, |
| "learning_rate": 0.000176940133037694, |
| "loss": 0.5266, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.389010989010989, |
| "grad_norm": 0.3295058310031891, |
| "learning_rate": 0.00017649667405764967, |
| "loss": 0.5685, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.3956043956043956, |
| "grad_norm": 0.3959578275680542, |
| "learning_rate": 0.00017605321507760532, |
| "loss": 0.4584, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.4021978021978022, |
| "grad_norm": 0.37387439608573914, |
| "learning_rate": 0.000175609756097561, |
| "loss": 0.5703, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.4087912087912088, |
| "grad_norm": 0.28911006450653076, |
| "learning_rate": 0.00017516629711751663, |
| "loss": 0.4591, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.4153846153846154, |
| "grad_norm": 0.6077892184257507, |
| "learning_rate": 0.0001747228381374723, |
| "loss": 0.7229, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.421978021978022, |
| "grad_norm": 0.44933897256851196, |
| "learning_rate": 0.00017427937915742792, |
| "loss": 0.4895, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 0.4583057463169098, |
| "learning_rate": 0.0001738359201773836, |
| "loss": 0.5422, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.4351648351648352, |
| "grad_norm": 0.441131055355072, |
| "learning_rate": 0.00017339246119733924, |
| "loss": 0.5039, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.44175824175824174, |
| "grad_norm": 0.37214893102645874, |
| "learning_rate": 0.0001729490022172949, |
| "loss": 0.4451, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.44835164835164837, |
| "grad_norm": 0.37915486097335815, |
| "learning_rate": 0.00017250554323725056, |
| "loss": 0.5498, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.45494505494505494, |
| "grad_norm": 0.43058085441589355, |
| "learning_rate": 0.00017206208425720623, |
| "loss": 0.6258, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.46153846153846156, |
| "grad_norm": 0.4087371528148651, |
| "learning_rate": 0.00017161862527716187, |
| "loss": 0.4304, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.46813186813186813, |
| "grad_norm": 0.3702792525291443, |
| "learning_rate": 0.00017117516629711752, |
| "loss": 0.5061, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.4747252747252747, |
| "grad_norm": 0.40271690487861633, |
| "learning_rate": 0.0001707317073170732, |
| "loss": 0.5221, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.48131868131868133, |
| "grad_norm": 0.4654999077320099, |
| "learning_rate": 0.00017028824833702883, |
| "loss": 0.5427, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.4879120879120879, |
| "grad_norm": 0.422850638628006, |
| "learning_rate": 0.0001698447893569845, |
| "loss": 0.5003, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.4945054945054945, |
| "grad_norm": 0.35233739018440247, |
| "learning_rate": 0.00016940133037694015, |
| "loss": 0.5353, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.5010989010989011, |
| "grad_norm": 0.3508605659008026, |
| "learning_rate": 0.00016895787139689582, |
| "loss": 0.5011, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.5076923076923077, |
| "grad_norm": 0.35129278898239136, |
| "learning_rate": 0.00016851441241685144, |
| "loss": 0.5396, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.5142857142857142, |
| "grad_norm": 0.4907684922218323, |
| "learning_rate": 0.0001680709534368071, |
| "loss": 0.5464, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.5208791208791209, |
| "grad_norm": 0.3281923234462738, |
| "learning_rate": 0.00016762749445676275, |
| "loss": 0.5209, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.5274725274725275, |
| "grad_norm": 0.444183349609375, |
| "learning_rate": 0.00016718403547671842, |
| "loss": 0.7176, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.5340659340659341, |
| "grad_norm": 0.5929686427116394, |
| "learning_rate": 0.00016674057649667407, |
| "loss": 0.6389, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.5406593406593406, |
| "grad_norm": 0.40402573347091675, |
| "learning_rate": 0.00016629711751662974, |
| "loss": 0.4612, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.5472527472527473, |
| "grad_norm": 0.4387584626674652, |
| "learning_rate": 0.00016585365853658536, |
| "loss": 0.4967, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.5538461538461539, |
| "grad_norm": 0.3580304682254791, |
| "learning_rate": 0.00016541019955654103, |
| "loss": 0.5834, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.5604395604395604, |
| "grad_norm": 0.5472170114517212, |
| "learning_rate": 0.00016496674057649667, |
| "loss": 0.5454, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.567032967032967, |
| "grad_norm": 0.4298936426639557, |
| "learning_rate": 0.00016452328159645234, |
| "loss": 0.4903, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.5736263736263736, |
| "grad_norm": 0.428013414144516, |
| "learning_rate": 0.000164079822616408, |
| "loss": 0.5407, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.5802197802197803, |
| "grad_norm": 0.4182053506374359, |
| "learning_rate": 0.00016363636363636366, |
| "loss": 0.5558, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.5868131868131868, |
| "grad_norm": 0.3617396652698517, |
| "learning_rate": 0.0001631929046563193, |
| "loss": 0.4448, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.5934065934065934, |
| "grad_norm": 0.35693031549453735, |
| "learning_rate": 0.00016274944567627495, |
| "loss": 0.5425, |
| "step": 90 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 456, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 15, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.692371792990003e+16, |
| "train_batch_size": 22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
