| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.6, | |
| "eval_steps": 500, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0009866666666666667, | |
| "loss": 3067311560851.456, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 131732.34375, | |
| "eval_runtime": 1192.6725, | |
| "eval_samples_per_second": 16.768, | |
| "eval_steps_per_second": 2.096, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0009733333333333334, | |
| "loss": 130631.296, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 129769.484375, | |
| "eval_runtime": 1199.9356, | |
| "eval_samples_per_second": 16.667, | |
| "eval_steps_per_second": 2.083, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00096, | |
| "loss": 129394.928, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 129025.2265625, | |
| "eval_runtime": 1188.6216, | |
| "eval_samples_per_second": 16.825, | |
| "eval_steps_per_second": 2.103, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0009466666666666667, | |
| "loss": 128776.992, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 128457.265625, | |
| "eval_runtime": 1211.4822, | |
| "eval_samples_per_second": 16.508, | |
| "eval_steps_per_second": 2.064, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 37500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |