| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016047178705393859, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00032094357410787714, | |
| "grad_norm": 78.40737915039062, | |
| "learning_rate": 1e-05, | |
| "loss": 63.0326, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00032094357410787714, | |
| "eval_loss": 3.9700841903686523, | |
| "eval_runtime": 198.0404, | |
| "eval_samples_per_second": 26.5, | |
| "eval_steps_per_second": 13.25, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006418871482157543, | |
| "grad_norm": 74.18360137939453, | |
| "learning_rate": 2e-05, | |
| "loss": 63.7609, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006418871482157543, | |
| "eval_loss": 3.7709908485412598, | |
| "eval_runtime": 185.4547, | |
| "eval_samples_per_second": 28.298, | |
| "eval_steps_per_second": 14.149, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009628307223236315, | |
| "grad_norm": 79.35127258300781, | |
| "learning_rate": 3e-05, | |
| "loss": 62.5642, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012837742964315086, | |
| "grad_norm": 77.93685150146484, | |
| "learning_rate": 4e-05, | |
| "loss": 66.6364, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012837742964315086, | |
| "eval_loss": 3.5823817253112793, | |
| "eval_runtime": 186.0493, | |
| "eval_samples_per_second": 28.208, | |
| "eval_steps_per_second": 14.104, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0016047178705393859, | |
| "grad_norm": 85.34315490722656, | |
| "learning_rate": 5e-05, | |
| "loss": 58.3853, | |
| "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": 3257466271825920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |