| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.3684210526315788, | |
| "eval_steps": 25, | |
| "global_step": 8, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 2.0080935955047607, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.1552, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "eval_loss": 1.8345296382904053, | |
| "eval_runtime": 0.5254, | |
| "eval_samples_per_second": 30.456, | |
| "eval_steps_per_second": 3.807, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 1.2547266483306885, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8496, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 2.0824086666107178, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.7499, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 1.4642688035964966, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5986, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 1.673658013343811, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.4441, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.526315789473684, | |
| "grad_norm": 1.0702685117721558, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.521, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.9473684210526314, | |
| "grad_norm": 1.6451783180236816, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.9002, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 3.3684210526315788, | |
| "grad_norm": 1.3056081533432007, | |
| "learning_rate": 0.0, | |
| "loss": 1.6849, | |
| "step": 8 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 8, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 9.879166951148749e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |