| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.991735537190083, | |
| "global_step": 560, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00016428571428571428, | |
| "loss": 1.4242, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_accuracy": 0.6776859760284424, | |
| "eval_loss": 0.9407395124435425, | |
| "eval_runtime": 15.4142, | |
| "eval_samples_per_second": 7.85, | |
| "eval_steps_per_second": 3.957, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.00012857142857142858, | |
| "loss": 0.884, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_accuracy": 0.6528925895690918, | |
| "eval_loss": 0.8700841665267944, | |
| "eval_runtime": 23.5759, | |
| "eval_samples_per_second": 5.132, | |
| "eval_steps_per_second": 2.587, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 9.357142857142858e-05, | |
| "loss": 0.5967, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "eval_accuracy": 0.8181818127632141, | |
| "eval_loss": 0.7293241620063782, | |
| "eval_runtime": 15.1537, | |
| "eval_samples_per_second": 7.985, | |
| "eval_steps_per_second": 4.025, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 5.785714285714287e-05, | |
| "loss": 0.3024, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.8595041036605835, | |
| "eval_loss": 0.5951272249221802, | |
| "eval_runtime": 23.2801, | |
| "eval_samples_per_second": 5.198, | |
| "eval_steps_per_second": 2.62, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 2.214285714285714e-05, | |
| "loss": 0.1382, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "eval_accuracy": 0.9090909361839294, | |
| "eval_loss": 0.3326501250267029, | |
| "eval_runtime": 23.5413, | |
| "eval_samples_per_second": 5.14, | |
| "eval_steps_per_second": 2.591, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "step": 560, | |
| "total_flos": 5.1637585435657395e+17, | |
| "train_loss": 0.6040960873876299, | |
| "train_runtime": 1484.0947, | |
| "train_samples_per_second": 2.278, | |
| "train_steps_per_second": 0.377 | |
| } | |
| ], | |
| "max_steps": 560, | |
| "num_train_epochs": 7, | |
| "total_flos": 5.1637585435657395e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |