| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.2849002849002849, |
| "eval_steps": 25, |
| "global_step": 75, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.003798670465337132, |
| "grad_norm": 5.763856410980225, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 1.3805, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.003798670465337132, |
| "eval_loss": 1.6539767980575562, |
| "eval_runtime": 46.0435, |
| "eval_samples_per_second": 4.822, |
| "eval_steps_per_second": 2.411, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.007597340930674264, |
| "grad_norm": 10.064556121826172, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 1.3331, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.011396011396011397, |
| "grad_norm": 4.493223190307617, |
| "learning_rate": 0.0001, |
| "loss": 1.2743, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.015194681861348529, |
| "grad_norm": 2.946624755859375, |
| "learning_rate": 9.99524110790929e-05, |
| "loss": 0.8182, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.01899335232668566, |
| "grad_norm": 2.3877036571502686, |
| "learning_rate": 9.980973490458728e-05, |
| "loss": 0.4942, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.022792022792022793, |
| "grad_norm": 2.079784631729126, |
| "learning_rate": 9.957224306869053e-05, |
| "loss": 0.3639, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.026590693257359924, |
| "grad_norm": 2.2234725952148438, |
| "learning_rate": 9.924038765061042e-05, |
| "loss": 0.2986, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.030389363722697058, |
| "grad_norm": 2.4654929637908936, |
| "learning_rate": 9.881480035599667e-05, |
| "loss": 0.3149, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.03418803418803419, |
| "grad_norm": 1.5854908227920532, |
| "learning_rate": 9.829629131445342e-05, |
| "loss": 0.2439, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.03798670465337132, |
| "grad_norm": 1.5591164827346802, |
| "learning_rate": 9.768584753741134e-05, |
| "loss": 0.2072, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.04178537511870845, |
| "grad_norm": 1.7570960521697998, |
| "learning_rate": 9.698463103929542e-05, |
| "loss": 0.2455, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.045584045584045586, |
| "grad_norm": 1.3588300943374634, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.2317, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.04938271604938271, |
| "grad_norm": 1.2992509603500366, |
| "learning_rate": 9.53153893518325e-05, |
| "loss": 0.2435, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.05318138651471985, |
| "grad_norm": 1.2096527814865112, |
| "learning_rate": 9.435054165891109e-05, |
| "loss": 0.1905, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.05698005698005698, |
| "grad_norm": 1.542781114578247, |
| "learning_rate": 9.330127018922194e-05, |
| "loss": 0.2319, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.060778727445394115, |
| "grad_norm": 1.497053861618042, |
| "learning_rate": 9.21695722906443e-05, |
| "loss": 0.2579, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.06457739791073125, |
| "grad_norm": 0.8226407766342163, |
| "learning_rate": 9.09576022144496e-05, |
| "loss": 0.1359, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.06837606837606838, |
| "grad_norm": 1.5668431520462036, |
| "learning_rate": 8.966766701456177e-05, |
| "loss": 0.196, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.0721747388414055, |
| "grad_norm": 0.9736147522926331, |
| "learning_rate": 8.83022221559489e-05, |
| "loss": 0.147, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.07597340930674264, |
| "grad_norm": 1.0604015588760376, |
| "learning_rate": 8.68638668405062e-05, |
| "loss": 0.157, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.07977207977207977, |
| "grad_norm": 1.4285651445388794, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.1586, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.0835707502374169, |
| "grad_norm": 1.30019211769104, |
| "learning_rate": 8.377951038078302e-05, |
| "loss": 0.1612, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.08736942070275404, |
| "grad_norm": 1.120355248451233, |
| "learning_rate": 8.213938048432697e-05, |
| "loss": 0.1544, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.09116809116809117, |
| "grad_norm": 1.0541555881500244, |
| "learning_rate": 8.043807145043604e-05, |
| "loss": 0.177, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.0949667616334283, |
| "grad_norm": 4.731549263000488, |
| "learning_rate": 7.86788218175523e-05, |
| "loss": 0.1304, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0949667616334283, |
| "eval_loss": 0.13617277145385742, |
| "eval_runtime": 46.0992, |
| "eval_samples_per_second": 4.816, |
| "eval_steps_per_second": 2.408, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.09876543209876543, |
| "grad_norm": 1.1956746578216553, |
| "learning_rate": 7.68649804173412e-05, |
| "loss": 0.1458, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.10256410256410256, |
| "grad_norm": 1.324112057685852, |
| "learning_rate": 7.500000000000001e-05, |
| "loss": 0.163, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.1063627730294397, |
| "grad_norm": 0.8233721256256104, |
| "learning_rate": 7.308743066175172e-05, |
| "loss": 0.1269, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.11016144349477683, |
| "grad_norm": 1.525368332862854, |
| "learning_rate": 7.113091308703498e-05, |
| "loss": 0.1434, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.11396011396011396, |
| "grad_norm": 0.9574621319770813, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.1332, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.1177587844254511, |
| "grad_norm": 1.4583760499954224, |
| "learning_rate": 6.710100716628344e-05, |
| "loss": 0.1763, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.12155745489078823, |
| "grad_norm": 1.0511687994003296, |
| "learning_rate": 6.503528997521366e-05, |
| "loss": 0.1497, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.12535612535612536, |
| "grad_norm": 1.6222001314163208, |
| "learning_rate": 6.294095225512603e-05, |
| "loss": 0.1879, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.1291547958214625, |
| "grad_norm": 0.9461656212806702, |
| "learning_rate": 6.0821980696905146e-05, |
| "loss": 0.1369, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.13295346628679963, |
| "grad_norm": 1.5839506387710571, |
| "learning_rate": 5.868240888334653e-05, |
| "loss": 0.1875, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.13675213675213677, |
| "grad_norm": 0.9987668395042419, |
| "learning_rate": 5.6526309611002594e-05, |
| "loss": 0.1665, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.14055080721747387, |
| "grad_norm": 1.055713176727295, |
| "learning_rate": 5.435778713738292e-05, |
| "loss": 0.1277, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.144349477682811, |
| "grad_norm": 1.4075400829315186, |
| "learning_rate": 5.218096936826681e-05, |
| "loss": 0.1546, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.14814814814814814, |
| "grad_norm": 1.492407202720642, |
| "learning_rate": 5e-05, |
| "loss": 0.1452, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.15194681861348527, |
| "grad_norm": 1.1356338262557983, |
| "learning_rate": 4.781903063173321e-05, |
| "loss": 0.2063, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.1557454890788224, |
| "grad_norm": 0.7817217707633972, |
| "learning_rate": 4.564221286261709e-05, |
| "loss": 0.1271, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.15954415954415954, |
| "grad_norm": 1.0964385271072388, |
| "learning_rate": 4.347369038899744e-05, |
| "loss": 0.1298, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.16334283000949668, |
| "grad_norm": 0.8101369738578796, |
| "learning_rate": 4.131759111665349e-05, |
| "loss": 0.1566, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.1671415004748338, |
| "grad_norm": 0.8687131404876709, |
| "learning_rate": 3.917801930309486e-05, |
| "loss": 0.1348, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.17094017094017094, |
| "grad_norm": 1.1124910116195679, |
| "learning_rate": 3.705904774487396e-05, |
| "loss": 0.1794, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.17473884140550808, |
| "grad_norm": 0.9842135310173035, |
| "learning_rate": 3.4964710024786354e-05, |
| "loss": 0.1326, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.1785375118708452, |
| "grad_norm": 0.8552569150924683, |
| "learning_rate": 3.289899283371657e-05, |
| "loss": 0.1088, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.18233618233618235, |
| "grad_norm": 0.7058787941932678, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.1296, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.18613485280151948, |
| "grad_norm": 0.9564892053604126, |
| "learning_rate": 2.886908691296504e-05, |
| "loss": 0.1502, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.1899335232668566, |
| "grad_norm": 0.9216586351394653, |
| "learning_rate": 2.6912569338248315e-05, |
| "loss": 0.1617, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.1899335232668566, |
| "eval_loss": 0.11469363421201706, |
| "eval_runtime": 46.0987, |
| "eval_samples_per_second": 4.816, |
| "eval_steps_per_second": 2.408, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.19373219373219372, |
| "grad_norm": 1.5434670448303223, |
| "learning_rate": 2.500000000000001e-05, |
| "loss": 0.1701, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 0.7094946503639221, |
| "learning_rate": 2.3135019582658802e-05, |
| "loss": 0.106, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.201329534662868, |
| "grad_norm": 0.6739745140075684, |
| "learning_rate": 2.132117818244771e-05, |
| "loss": 0.0905, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.20512820512820512, |
| "grad_norm": 1.323537826538086, |
| "learning_rate": 1.9561928549563968e-05, |
| "loss": 0.1193, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.20892687559354226, |
| "grad_norm": 0.6400057673454285, |
| "learning_rate": 1.7860619515673033e-05, |
| "loss": 0.0969, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.2127255460588794, |
| "grad_norm": 0.5726168155670166, |
| "learning_rate": 1.622048961921699e-05, |
| "loss": 0.1037, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.21652421652421652, |
| "grad_norm": 0.9324626326560974, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.086, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.22032288698955366, |
| "grad_norm": 0.8309210538864136, |
| "learning_rate": 1.3136133159493802e-05, |
| "loss": 0.1208, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.2241215574548908, |
| "grad_norm": 0.8675907850265503, |
| "learning_rate": 1.1697777844051105e-05, |
| "loss": 0.1326, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.22792022792022792, |
| "grad_norm": 0.6248118877410889, |
| "learning_rate": 1.0332332985438248e-05, |
| "loss": 0.1048, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.23171889838556506, |
| "grad_norm": 0.7150914072990417, |
| "learning_rate": 9.042397785550405e-06, |
| "loss": 0.1132, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.2355175688509022, |
| "grad_norm": 0.5807145833969116, |
| "learning_rate": 7.830427709355725e-06, |
| "loss": 0.1046, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.23931623931623933, |
| "grad_norm": 0.7972524762153625, |
| "learning_rate": 6.698729810778065e-06, |
| "loss": 0.1191, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.24311490978157646, |
| "grad_norm": 0.5663894414901733, |
| "learning_rate": 5.649458341088915e-06, |
| "loss": 0.1081, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.24691358024691357, |
| "grad_norm": 1.2583680152893066, |
| "learning_rate": 4.684610648167503e-06, |
| "loss": 0.1063, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.25071225071225073, |
| "grad_norm": 0.5461013317108154, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.1087, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.25451092117758783, |
| "grad_norm": 0.8133847117424011, |
| "learning_rate": 3.0153689607045845e-06, |
| "loss": 0.1474, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.258309591642925, |
| "grad_norm": 0.7079008221626282, |
| "learning_rate": 2.314152462588659e-06, |
| "loss": 0.141, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.2621082621082621, |
| "grad_norm": 0.49465906620025635, |
| "learning_rate": 1.70370868554659e-06, |
| "loss": 0.0914, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.26590693257359926, |
| "grad_norm": 0.7780298590660095, |
| "learning_rate": 1.1851996440033319e-06, |
| "loss": 0.1402, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.26970560303893637, |
| "grad_norm": 1.1167643070220947, |
| "learning_rate": 7.596123493895991e-07, |
| "loss": 0.1814, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.27350427350427353, |
| "grad_norm": 0.5520243048667908, |
| "learning_rate": 4.277569313094809e-07, |
| "loss": 0.092, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.27730294396961064, |
| "grad_norm": 0.5053026676177979, |
| "learning_rate": 1.9026509541272275e-07, |
| "loss": 0.0918, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.28110161443494774, |
| "grad_norm": 0.7503936290740967, |
| "learning_rate": 4.7588920907110094e-08, |
| "loss": 0.1032, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.2849002849002849, |
| "grad_norm": 0.8561326265335083, |
| "learning_rate": 0.0, |
| "loss": 0.1271, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.2849002849002849, |
| "eval_loss": 0.10664498805999756, |
| "eval_runtime": 46.0966, |
| "eval_samples_per_second": 4.816, |
| "eval_steps_per_second": 2.408, |
| "step": 75 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 75, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 25, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.24338409832448e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
