| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 15.0, | |
| "eval_steps": 500, | |
| "global_step": 18390, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8156606851549756, | |
| "grad_norm": 2.7835583686828613, | |
| "learning_rate": 0.00019968889417401253, | |
| "loss": 0.6438, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.631321370309951, | |
| "grad_norm": 0.3261709213256836, | |
| "learning_rate": 0.00019676585418772425, | |
| "loss": 0.2388, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.4469820554649266, | |
| "grad_norm": 2.9635205268859863, | |
| "learning_rate": 0.00019084912501825553, | |
| "loss": 0.2032, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.262642740619902, | |
| "grad_norm": 2.162414312362671, | |
| "learning_rate": 0.00018212175520336934, | |
| "loss": 0.163, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.078303425774878, | |
| "grad_norm": 3.4721012115478516, | |
| "learning_rate": 0.00017085374734710157, | |
| "loss": 0.1519, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.893964110929853, | |
| "grad_norm": 1.8501887321472168, | |
| "learning_rate": 0.0001573937049265616, | |
| "loss": 0.13, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 5.709624796084829, | |
| "grad_norm": 3.3048102855682373, | |
| "learning_rate": 0.00014215804738782126, | |
| "loss": 0.1186, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 6.525285481239804, | |
| "grad_norm": 2.223738193511963, | |
| "learning_rate": 0.00012561812718836913, | |
| "loss": 0.1046, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 7.3409461663947795, | |
| "grad_norm": 0.2893391251564026, | |
| "learning_rate": 0.00010828564735203954, | |
| "loss": 0.0957, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 8.156606851549755, | |
| "grad_norm": 0.24986231327056885, | |
| "learning_rate": 9.069683068014265e-05, | |
| "loss": 0.0912, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 8.97226753670473, | |
| "grad_norm": 0.6728571653366089, | |
| "learning_rate": 7.339583038310173e-05, | |
| "loss": 0.08, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 9.787928221859707, | |
| "grad_norm": 0.3318624794483185, | |
| "learning_rate": 5.69178953654216e-05, | |
| "loss": 0.0722, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 10.603588907014682, | |
| "grad_norm": 0.1652187556028366, | |
| "learning_rate": 4.177281098721372e-05, | |
| "loss": 0.07, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 11.419249592169658, | |
| "grad_norm": 0.13997943699359894, | |
| "learning_rate": 2.8429127602959905e-05, | |
| "loss": 0.0635, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 12.234910277324634, | |
| "grad_norm": 0.17078348994255066, | |
| "learning_rate": 1.729966480637476e-05, | |
| "loss": 0.0607, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 13.05057096247961, | |
| "grad_norm": 0.10830472409725189, | |
| "learning_rate": 8.728739843127509e-06, | |
| "loss": 0.0599, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 13.866231647634583, | |
| "grad_norm": 0.13888326287269592, | |
| "learning_rate": 2.9815153118197825e-06, | |
| "loss": 0.0566, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 14.681892332789559, | |
| "grad_norm": 0.138445645570755, | |
| "learning_rate": 2.3579570823278885e-07, | |
| "loss": 0.0556, | |
| "step": 18000 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 18390, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 6000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.5627004461372e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |