| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0017014519056261343, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.2686025408348456e-05, | |
| "grad_norm": 1.8904634714126587, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.855, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.2686025408348456e-05, | |
| "eval_loss": 3.410688638687134, | |
| "eval_runtime": 1237.3059, | |
| "eval_samples_per_second": 30.001, | |
| "eval_steps_per_second": 15.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.537205081669691e-05, | |
| "grad_norm": 1.8866937160491943, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.8678, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 6.805807622504538e-05, | |
| "grad_norm": 1.8513197898864746, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8435, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.074410163339382e-05, | |
| "grad_norm": 1.658372402191162, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 2.6602, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00011343012704174228, | |
| "grad_norm": 2.2875466346740723, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 2.5661, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00013611615245009076, | |
| "grad_norm": 2.1735148429870605, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.4435, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001588021778584392, | |
| "grad_norm": 1.6200734376907349, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.4093, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00018148820326678765, | |
| "grad_norm": 1.4915409088134766, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 2.3486, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00020417422867513612, | |
| "grad_norm": 1.2556705474853516, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.2992, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00022686025408348456, | |
| "grad_norm": 1.3379391431808472, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 2.2776, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000249546279491833, | |
| "grad_norm": 1.745252013206482, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.2814, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0002722323049001815, | |
| "grad_norm": 1.214249849319458, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.2245, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00029491833030852996, | |
| "grad_norm": 0.9381669163703918, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 2.1434, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0003176043557168784, | |
| "grad_norm": 0.9755675196647644, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 2.1348, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00034029038112522685, | |
| "grad_norm": 1.4853951930999756, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.1151, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0003629764065335753, | |
| "grad_norm": 1.8705589771270752, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 2.1256, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0003856624319419238, | |
| "grad_norm": 1.6596029996871948, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 2.121, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00040834845735027224, | |
| "grad_norm": 2.31752347946167, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.1368, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0004310344827586207, | |
| "grad_norm": 3.1325747966766357, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.1559, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00045372050816696913, | |
| "grad_norm": 1.721400260925293, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 2.1241, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00047640653357531763, | |
| "grad_norm": 1.4676975011825562, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.0461, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.000499092558983666, | |
| "grad_norm": 1.8530941009521484, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 2.0458, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0005217785843920145, | |
| "grad_norm": 2.0539281368255615, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 2.054, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.000544464609800363, | |
| "grad_norm": 1.7614209651947021, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.0725, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0005671506352087115, | |
| "grad_norm": 1.2324997186660767, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 2.0791, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0005671506352087115, | |
| "eval_loss": 2.161527633666992, | |
| "eval_runtime": 1239.3508, | |
| "eval_samples_per_second": 29.951, | |
| "eval_steps_per_second": 14.976, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0005898366606170599, | |
| "grad_norm": 1.7302452325820923, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 2.0632, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0006125226860254084, | |
| "grad_norm": 1.7510278224945068, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.1041, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0006352087114337568, | |
| "grad_norm": 1.4340311288833618, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 2.0235, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0006578947368421052, | |
| "grad_norm": 1.4099208116531372, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 2.0296, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0006805807622504537, | |
| "grad_norm": 1.4559657573699951, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.989, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0007032667876588021, | |
| "grad_norm": 1.659051537513733, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 2.0203, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0007259528130671506, | |
| "grad_norm": 2.0444107055664062, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 2.0082, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0007486388384754991, | |
| "grad_norm": 2.0712087154388428, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.9541, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0007713248638838476, | |
| "grad_norm": 1.8016096353530884, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 1.9549, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.000794010889292196, | |
| "grad_norm": 4.192699432373047, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.9673, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0008166969147005445, | |
| "grad_norm": 3.760023355484009, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.9319, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0008393829401088929, | |
| "grad_norm": 2.344935894012451, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 1.9, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0008620689655172414, | |
| "grad_norm": 2.100687026977539, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 1.865, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0008847549909255898, | |
| "grad_norm": 3.1228349208831787, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8805, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0009074410163339383, | |
| "grad_norm": 2.3817391395568848, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 1.8904, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0009301270417422867, | |
| "grad_norm": 2.454270839691162, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 1.9163, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0009528130671506353, | |
| "grad_norm": 2.8007712364196777, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.8889, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0009754990925589837, | |
| "grad_norm": 3.751268148422241, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.7979, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.000998185117967332, | |
| "grad_norm": 2.9384889602661133, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 1.8534, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0010208711433756805, | |
| "grad_norm": 2.206895589828491, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.8246, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.001043557168784029, | |
| "grad_norm": 2.771620512008667, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 1.7729, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0010662431941923776, | |
| "grad_norm": 4.623754978179932, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 1.8095, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.001088929219600726, | |
| "grad_norm": 9.82066822052002, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.8858, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0011116152450090745, | |
| "grad_norm": 15.103967666625977, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 2.0393, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.001134301270417423, | |
| "grad_norm": 14.861157417297363, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 2.1831, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.001134301270417423, | |
| "eval_loss": 2.4072601795196533, | |
| "eval_runtime": 1241.41, | |
| "eval_samples_per_second": 29.901, | |
| "eval_steps_per_second": 14.951, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0011569872958257714, | |
| "grad_norm": 10.760135650634766, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.619, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0011796733212341198, | |
| "grad_norm": 10.61867618560791, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 2.6049, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0012023593466424683, | |
| "grad_norm": 9.48973560333252, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 2.4759, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0012250453720508167, | |
| "grad_norm": 8.987316131591797, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.3972, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0012477313974591652, | |
| "grad_norm": 8.111326217651367, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 2.3231, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0012704174228675136, | |
| "grad_norm": 6.617386817932129, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 2.1985, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.001293103448275862, | |
| "grad_norm": 4.567836761474609, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.1746, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0013157894736842105, | |
| "grad_norm": 2.5743725299835205, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 2.0999, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.001338475499092559, | |
| "grad_norm": 2.6298258304595947, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 2.0759, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0013611615245009074, | |
| "grad_norm": 2.5134525299072266, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.0232, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0013838475499092558, | |
| "grad_norm": 2.05859637260437, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 2.0579, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0014065335753176043, | |
| "grad_norm": 1.8161320686340332, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 2.0462, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0014292196007259527, | |
| "grad_norm": 1.8273543119430542, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.037, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0014519056261343012, | |
| "grad_norm": 1.3664026260375977, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 2.032, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.0014745916515426498, | |
| "grad_norm": 1.3599556684494019, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 2.0063, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0014972776769509983, | |
| "grad_norm": 1.333756446838379, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.9905, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0015199637023593467, | |
| "grad_norm": 1.4712531566619873, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 2.0231, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0015426497277676952, | |
| "grad_norm": 1.438612937927246, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 1.9859, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0015653357531760436, | |
| "grad_norm": 1.5220595598220825, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.9783, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.001588021778584392, | |
| "grad_norm": 1.3201245069503784, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 2.011, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0016107078039927405, | |
| "grad_norm": 1.3130794763565063, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 2.0053, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.001633393829401089, | |
| "grad_norm": 1.6226977109909058, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.978, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0016560798548094374, | |
| "grad_norm": 1.4479483366012573, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 2.0057, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.0016787658802177858, | |
| "grad_norm": 1.4476728439331055, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 2.0159, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.0017014519056261343, | |
| "grad_norm": 1.5175923109054565, | |
| "learning_rate": 0.0, | |
| "loss": 1.9565, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0017014519056261343, | |
| "eval_loss": 1.9482790231704712, | |
| "eval_runtime": 1240.3995, | |
| "eval_samples_per_second": 29.926, | |
| "eval_steps_per_second": 14.963, | |
| "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": 1.46820537778176e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |