| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0010664960273022983, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.265984109209193e-05, | |
| "grad_norm": 0.8950845003128052, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.9575, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.265984109209193e-05, | |
| "eval_loss": 0.8528293371200562, | |
| "eval_runtime": 3346.3891, | |
| "eval_samples_per_second": 5.899, | |
| "eval_steps_per_second": 2.949, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.531968218418386e-05, | |
| "grad_norm": 1.1442168951034546, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 5.2451, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001279795232762758, | |
| "grad_norm": 1.394640564918518, | |
| "learning_rate": 0.0001, | |
| "loss": 5.3981, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00017063936436836772, | |
| "grad_norm": 1.6339935064315796, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 5.5776, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00021329920546045967, | |
| "grad_norm": 2.0181682109832764, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 5.31, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002559590465525516, | |
| "grad_norm": 2.081012487411499, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.69, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002986188876446435, | |
| "grad_norm": 2.091360092163086, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 4.7037, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00034127872873673543, | |
| "grad_norm": 2.663072109222412, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 4.4144, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00038393856982882736, | |
| "grad_norm": 2.2715742588043213, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.8637, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00042659841092091935, | |
| "grad_norm": 4.384383201599121, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 4.0411, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004692582520130113, | |
| "grad_norm": 4.320742607116699, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 3.5344, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0005119180931051031, | |
| "grad_norm": 3.698866844177246, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.3832, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005545779341971951, | |
| "grad_norm": 3.1251349449157715, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 3.359, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.000597237775289287, | |
| "grad_norm": 2.3781769275665283, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 3.002, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0006398976163813789, | |
| "grad_norm": 2.4765355587005615, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.3571, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006825574574734709, | |
| "grad_norm": 2.4396748542785645, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 3.4887, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0007252172985655628, | |
| "grad_norm": 2.1020894050598145, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 3.5473, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0007678771396576547, | |
| "grad_norm": 2.180967330932617, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.5701, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0008105369807497467, | |
| "grad_norm": 2.0794942378997803, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.9633, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0008531968218418387, | |
| "grad_norm": 2.3405985832214355, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 3.264, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008958566629339306, | |
| "grad_norm": 2.1136486530303955, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.1988, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0009385165040260225, | |
| "grad_norm": 2.2635881900787354, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 3.4865, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0009811763451181145, | |
| "grad_norm": 2.510779619216919, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 2.9429, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0010238361862102063, | |
| "grad_norm": 2.3888373374938965, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.348, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0010664960273022983, | |
| "grad_norm": 3.272702932357788, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 3.4122, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0010664960273022983, | |
| "eval_loss": 0.4052564203739166, | |
| "eval_runtime": 3346.521, | |
| "eval_samples_per_second": 5.899, | |
| "eval_steps_per_second": 2.949, | |
| "step": 25 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.303407560635187e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |