| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 30.76923076923077, |
| "eval_steps": 500, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 15.38, |
| "grad_norm": 2.1158251762390137, |
| "learning_rate": 0.0001, |
| "loss": 1.8108, |
| "step": 100 |
| }, |
| { |
| "epoch": 30.77, |
| "grad_norm": 2.3235597610473633, |
| "learning_rate": 0.0, |
| "loss": 0.9076, |
| "step": 200 |
| }, |
| { |
| "epoch": 30.77, |
| "step": 200, |
| "total_flos": 752998431719424.0, |
| "train_loss": 1.359188232421875, |
| "train_runtime": 123.5443, |
| "train_samples_per_second": 25.902, |
| "train_steps_per_second": 1.619 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 200, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 34, |
| "save_steps": 500, |
| "total_flos": 752998431719424.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
