| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.076923076923077, | |
| "eval_steps": 50, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 145.8916473388672, | |
| "learning_rate": 1e-05, | |
| "loss": 6.3039, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "eval_loss": 1.207192063331604, | |
| "eval_runtime": 0.5709, | |
| "eval_samples_per_second": 10.509, | |
| "eval_steps_per_second": 3.503, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 152.0794677734375, | |
| "learning_rate": 2e-05, | |
| "loss": 7.072, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 105.73599243164062, | |
| "learning_rate": 3e-05, | |
| "loss": 3.4334, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": 49.147640228271484, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4872, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 32.453651428222656, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9264, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.8461538461538463, | |
| "grad_norm": 19.655824661254883, | |
| "learning_rate": 6e-05, | |
| "loss": 0.8667, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.1538461538461537, | |
| "grad_norm": 15.027318000793457, | |
| "learning_rate": 7e-05, | |
| "loss": 0.5885, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.4615384615384617, | |
| "grad_norm": 9.182798385620117, | |
| "learning_rate": 8e-05, | |
| "loss": 0.4349, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.769230769230769, | |
| "grad_norm": 10.852940559387207, | |
| "learning_rate": 9e-05, | |
| "loss": 0.3853, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 12.851784706115723, | |
| "learning_rate": 0.0001, | |
| "loss": 0.346, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3907511899848704e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |