| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 1869, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.6969, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5342960288808665, | |
| "eval_loss": 0.7039318680763245, | |
| "eval_runtime": 9.0213, | |
| "eval_samples_per_second": 30.705, | |
| "eval_steps_per_second": 3.88, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.5903, | |
| "step": 1246 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7184115523465704, | |
| "eval_loss": 0.6461479663848877, | |
| "eval_runtime": 8.9942, | |
| "eval_samples_per_second": 30.798, | |
| "eval_steps_per_second": 3.891, | |
| "step": 1246 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.4557, | |
| "step": 1869 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6642599277978339, | |
| "eval_loss": 1.5187355279922485, | |
| "eval_runtime": 9.0028, | |
| "eval_samples_per_second": 30.768, | |
| "eval_steps_per_second": 3.888, | |
| "step": 1869 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1869, | |
| "total_flos": 6961527284060160.0, | |
| "train_loss": 0.5809510844859801, | |
| "train_runtime": 1072.8997, | |
| "train_samples_per_second": 6.962, | |
| "train_steps_per_second": 1.742 | |
| } | |
| ], | |
| "max_steps": 1869, | |
| "num_train_epochs": 3, | |
| "total_flos": 6961527284060160.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |