| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 50, | |
| "global_step": 450, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.044444444444444446, | |
| "grad_norm": 0.17305362224578857, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.2942, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 0.042544737458229065, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.0024, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "eval_loss": 0.0013170767342671752, | |
| "eval_runtime": 232.8005, | |
| "eval_samples_per_second": 4.296, | |
| "eval_steps_per_second": 0.215, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13333333333333333, | |
| "grad_norm": 0.03146813064813614, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.0012, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 0.03375430032610893, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.0012, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.0878819078207016, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0011, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "eval_loss": 0.000957556301727891, | |
| "eval_runtime": 232.4585, | |
| "eval_samples_per_second": 4.302, | |
| "eval_steps_per_second": 0.215, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 0.03542569652199745, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.0012, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3111111111111111, | |
| "grad_norm": 0.015578300692141056, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.0009, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "eval_loss": 0.0007864935323596001, | |
| "eval_runtime": 232.695, | |
| "eval_samples_per_second": 4.297, | |
| "eval_steps_per_second": 0.215, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.029168328270316124, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.001, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.05920561030507088, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.001, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.03357287123799324, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.001, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "eval_loss": 0.0008135823300108314, | |
| "eval_runtime": 232.395, | |
| "eval_samples_per_second": 4.303, | |
| "eval_steps_per_second": 0.215, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4888888888888889, | |
| "grad_norm": 0.019826048985123634, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.0011, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.025309834629297256, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.0009, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "eval_loss": 0.0007757659768685699, | |
| "eval_runtime": 232.3457, | |
| "eval_samples_per_second": 4.304, | |
| "eval_steps_per_second": 0.215, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5777777777777777, | |
| "grad_norm": 0.016265789046883583, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.0011, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 0.0712108463048935, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.0008, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.04358217492699623, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0006, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "eval_loss": 0.000731022737454623, | |
| "eval_runtime": 232.45, | |
| "eval_samples_per_second": 4.302, | |
| "eval_steps_per_second": 0.215, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.02700887806713581, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.0008, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7555555555555555, | |
| "grad_norm": 0.02106143906712532, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.0007, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7777777777777778, | |
| "eval_loss": 0.0006801169947721064, | |
| "eval_runtime": 232.1532, | |
| "eval_samples_per_second": 4.307, | |
| "eval_steps_per_second": 0.215, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.020221324637532234, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0007, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8444444444444444, | |
| "grad_norm": 0.020666765049099922, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.0008, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.00924940500408411, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.0007, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "eval_loss": 0.0006416882388293743, | |
| "eval_runtime": 232.5441, | |
| "eval_samples_per_second": 4.3, | |
| "eval_steps_per_second": 0.215, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9333333333333333, | |
| "grad_norm": 0.028802907094359398, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.0007, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": 0.035981908440589905, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.0009, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.0006301100365817547, | |
| "eval_runtime": 232.5439, | |
| "eval_samples_per_second": 4.3, | |
| "eval_steps_per_second": 0.215, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 450, | |
| "total_flos": 9.625596140737004e+17, | |
| "train_loss": 0.014024514413128297, | |
| "train_runtime": 8823.7876, | |
| "train_samples_per_second": 1.02, | |
| "train_steps_per_second": 0.051 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 450, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.625596140737004e+17, | |
| "train_batch_size": 10, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |