| { | |
| "best_metric": 0.11644134670495987, | |
| "best_model_checkpoint": "GPTNEO\\checkpoint-374", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1122, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.964572192513369, | |
| "eval_f1": 0.9643319350724125, | |
| "eval_loss": 0.11644134670495987, | |
| "eval_runtime": 123.1338, | |
| "eval_samples_per_second": 12.149, | |
| "eval_steps_per_second": 0.763, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.5991360545158386, | |
| "learning_rate": 1.1087344028520499e-05, | |
| "loss": 0.1507, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9705882352941176, | |
| "eval_f1": 0.9702739974269765, | |
| "eval_loss": 0.12776418030261993, | |
| "eval_runtime": 123.7178, | |
| "eval_samples_per_second": 12.092, | |
| "eval_steps_per_second": 0.76, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "grad_norm": 0.041941288858652115, | |
| "learning_rate": 2.1746880570409984e-06, | |
| "loss": 0.0349, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9719251336898396, | |
| "eval_f1": 0.971625179362114, | |
| "eval_loss": 0.13110090792179108, | |
| "eval_runtime": 122.3469, | |
| "eval_samples_per_second": 12.228, | |
| "eval_steps_per_second": 0.768, | |
| "step": 1122 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1122, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 556460755918848.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |