| { | |
| "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": 0.16836561262607574, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3729, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "eval_loss": 10.370478630065918, | |
| "eval_runtime": 0.0192, | |
| "eval_samples_per_second": 312.526, | |
| "eval_steps_per_second": 104.175, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.1358407735824585, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3712, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 0.13619433343410492, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3735, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": 0.38317403197288513, | |
| "learning_rate": 4e-05, | |
| "loss": 19.4268, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 0.1365566998720169, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3853, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.8461538461538463, | |
| "grad_norm": 0.13204583525657654, | |
| "learning_rate": 6e-05, | |
| "loss": 10.4453, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.1538461538461537, | |
| "grad_norm": 0.3381084203720093, | |
| "learning_rate": 7e-05, | |
| "loss": 18.4739, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.4615384615384617, | |
| "grad_norm": 0.14508947730064392, | |
| "learning_rate": 8e-05, | |
| "loss": 10.6568, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.769230769230769, | |
| "grad_norm": 0.13342727720737457, | |
| "learning_rate": 9e-05, | |
| "loss": 10.1756, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 0.23672761023044586, | |
| "learning_rate": 0.0001, | |
| "loss": 17.6296, | |
| "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": 1063217233920.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |