| { | |
| "best_metric": 0.5396298170089722, | |
| "best_model_checkpoint": "./results/checkpoint-1642", | |
| "epoch": 3.0, | |
| "global_step": 2463, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.593991067803492e-05, | |
| "loss": 0.6484, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7830104851608317, | |
| "eval_loss": 0.5467866063117981, | |
| "eval_precision": 0.7946395590241245, | |
| "eval_recall": 0.7830104851608317, | |
| "eval_runtime": 207.1913, | |
| "eval_samples_per_second": 27.158, | |
| "step": 821 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.1879821356069834e-05, | |
| "loss": 0.5259, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 7.819732034104752e-06, | |
| "loss": 0.445, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7908299271370179, | |
| "eval_loss": 0.5396298170089722, | |
| "eval_precision": 0.7954586612276937, | |
| "eval_recall": 0.7908299271370179, | |
| "eval_runtime": 206.8656, | |
| "eval_samples_per_second": 27.201, | |
| "step": 1642 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 3.759642712139667e-06, | |
| "loss": 0.3799, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7904744979562822, | |
| "eval_loss": 0.5831448435783386, | |
| "eval_precision": 0.79502140504056, | |
| "eval_recall": 0.7904744979562822, | |
| "eval_runtime": 206.745, | |
| "eval_samples_per_second": 27.217, | |
| "step": 2463 | |
| } | |
| ], | |
| "max_steps": 2463, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.1823337832189616e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |