| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1528, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16361256544502617, | |
| "grad_norm": 27289.80859375, | |
| "learning_rate": 4.18520942408377e-05, | |
| "loss": 0.0008, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.32722513089005234, | |
| "grad_norm": 287.3504638671875, | |
| "learning_rate": 3.367146596858639e-05, | |
| "loss": 0.0006, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4908376963350785, | |
| "grad_norm": 92991.2421875, | |
| "learning_rate": 2.549083769633508e-05, | |
| "loss": 0.0016, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.6544502617801047, | |
| "grad_norm": 2673.955322265625, | |
| "learning_rate": 1.731020942408377e-05, | |
| "loss": 0.0004, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.8180628272251309, | |
| "grad_norm": 0.03750693053007126, | |
| "learning_rate": 9.129581151832461e-06, | |
| "loss": 0.0003, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.981675392670157, | |
| "grad_norm": 0.022292787209153175, | |
| "learning_rate": 9.489528795811518e-07, | |
| "loss": 0.0004, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 250, | |
| "max_steps": 1528, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7452961163182080.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |