| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08016032064128256, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01603206412825651, | |
| "grad_norm": 4.241643905639648, | |
| "learning_rate": 1e-05, | |
| "loss": 17.1, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01603206412825651, | |
| "eval_loss": 1.2148150205612183, | |
| "eval_runtime": 33.124, | |
| "eval_samples_per_second": 3.17, | |
| "eval_steps_per_second": 1.6, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03206412825651302, | |
| "grad_norm": 3.580019235610962, | |
| "learning_rate": 2e-05, | |
| "loss": 19.1669, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03206412825651302, | |
| "eval_loss": 1.222833275794983, | |
| "eval_runtime": 4.7223, | |
| "eval_samples_per_second": 22.235, | |
| "eval_steps_per_second": 11.223, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04809619238476954, | |
| "grad_norm": 3.955512285232544, | |
| "learning_rate": 3e-05, | |
| "loss": 17.9593, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06412825651302605, | |
| "grad_norm": 3.520667314529419, | |
| "learning_rate": 4e-05, | |
| "loss": 18.1645, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06412825651302605, | |
| "eval_loss": 1.218423843383789, | |
| "eval_runtime": 4.7489, | |
| "eval_samples_per_second": 22.11, | |
| "eval_steps_per_second": 11.16, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08016032064128256, | |
| "grad_norm": 3.8611981868743896, | |
| "learning_rate": 5e-05, | |
| "loss": 17.4402, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4764044422545408.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |