| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 390, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9e-07, | |
| "loss": 3.1249, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8e-07, | |
| "loss": 2.9372, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7e-07, | |
| "loss": 2.8912, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6e-07, | |
| "loss": 2.8686, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5e-07, | |
| "loss": 2.8503, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4e-07, | |
| "loss": 2.8397, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3e-07, | |
| "loss": 2.8334, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2e-07, | |
| "loss": 2.8271, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1e-07, | |
| "loss": 2.8268, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.82, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 390, | |
| "total_flos": 8711089615388160.0, | |
| "train_loss": 2.881923577724359, | |
| "train_runtime": 3987.6216, | |
| "train_samples_per_second": 38.263, | |
| "train_steps_per_second": 0.098 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 390, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 8711089615388160.0, | |
| "train_batch_size": 384, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |