| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 1.0298, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.3583333194255829, | |
| "eval_loss": 1.027502417564392, | |
| "eval_runtime": 13.2982, | |
| "eval_samples_per_second": 9.024, | |
| "eval_steps_per_second": 2.256, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.9216, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_accuracy": 0.6583333611488342, | |
| "eval_loss": 0.9037414789199829, | |
| "eval_runtime": 13.3332, | |
| "eval_samples_per_second": 9.0, | |
| "eval_steps_per_second": 2.25, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9802, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.34166666865348816, | |
| "eval_loss": 0.9806223511695862, | |
| "eval_runtime": 13.2424, | |
| "eval_samples_per_second": 9.062, | |
| "eval_steps_per_second": 2.265, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.8864, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_accuracy": 0.699999988079071, | |
| "eval_loss": 0.8415695428848267, | |
| "eval_runtime": 13.0866, | |
| "eval_samples_per_second": 9.17, | |
| "eval_steps_per_second": 2.292, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.753, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.7083333134651184, | |
| "eval_loss": 0.7226903438568115, | |
| "eval_runtime": 13.037, | |
| "eval_samples_per_second": 9.205, | |
| "eval_steps_per_second": 2.301, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.7567, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7083333134651184, | |
| "eval_loss": 0.7225412726402283, | |
| "eval_runtime": 13.0892, | |
| "eval_samples_per_second": 9.168, | |
| "eval_steps_per_second": 2.292, | |
| "step": 60 | |
| } | |
| ], | |
| "max_steps": 60, | |
| "num_train_epochs": 1, | |
| "total_flos": 6.56395391232e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |