| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.991735537190083, | |
| "global_step": 420, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 7.642857142857143e-05, | |
| "loss": 1.3365, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_accuracy": 0.6363636255264282, | |
| "eval_loss": 0.8412261605262756, | |
| "eval_runtime": 17.1267, | |
| "eval_samples_per_second": 7.065, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 5.285714285714286e-05, | |
| "loss": 0.6421, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_accuracy": 0.8677685856819153, | |
| "eval_loss": 0.4234764575958252, | |
| "eval_runtime": 17.292, | |
| "eval_samples_per_second": 6.997, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 2.9047619047619052e-05, | |
| "loss": 0.3537, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.8429751992225647, | |
| "eval_loss": 0.518673300743103, | |
| "eval_runtime": 17.2657, | |
| "eval_samples_per_second": 7.008, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 5.2380952380952384e-06, | |
| "loss": 0.1469, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "eval_accuracy": 0.9090909361839294, | |
| "eval_loss": 0.3046664297580719, | |
| "eval_runtime": 17.2878, | |
| "eval_samples_per_second": 6.999, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "step": 420, | |
| "total_flos": 2.907298151590248e+16, | |
| "train_runtime": 1331.4211, | |
| "train_samples_per_second": 0.315 | |
| } | |
| ], | |
| "max_steps": 420, | |
| "num_train_epochs": 7, | |
| "total_flos": 2.907298151590248e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |