| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.025236593059936908, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005047318611987382, | |
| "grad_norm": 371.6877746582031, | |
| "learning_rate": 1e-05, | |
| "loss": 60.2657, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005047318611987382, | |
| "eval_loss": 4.164096355438232, | |
| "eval_runtime": 80.4901, | |
| "eval_samples_per_second": 4.15, | |
| "eval_steps_per_second": 2.075, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010094637223974764, | |
| "grad_norm": 411.6836853027344, | |
| "learning_rate": 2e-05, | |
| "loss": 66.2732, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010094637223974764, | |
| "eval_loss": 3.80216646194458, | |
| "eval_runtime": 30.5795, | |
| "eval_samples_per_second": 10.922, | |
| "eval_steps_per_second": 5.461, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.015141955835962145, | |
| "grad_norm": 357.18817138671875, | |
| "learning_rate": 3e-05, | |
| "loss": 55.8286, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02018927444794953, | |
| "grad_norm": 424.9853820800781, | |
| "learning_rate": 4e-05, | |
| "loss": 54.9917, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02018927444794953, | |
| "eval_loss": 2.4038145542144775, | |
| "eval_runtime": 53.1902, | |
| "eval_samples_per_second": 6.279, | |
| "eval_steps_per_second": 3.14, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.025236593059936908, | |
| "grad_norm": 230.79364013671875, | |
| "learning_rate": 5e-05, | |
| "loss": 33.0761, | |
| "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": 3505343598428160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |