| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 294528, | |
| "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": 0.7012, | |
| "step": 98176 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7716760061130922, | |
| "eval_loss": 0.6348065137863159, | |
| "eval_runtime": 215.1813, | |
| "eval_samples_per_second": 45.613, | |
| "eval_steps_per_second": 5.702, | |
| "step": 98176 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.5672, | |
| "step": 196352 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7882832399388691, | |
| "eval_loss": 0.849821925163269, | |
| "eval_runtime": 214.1745, | |
| "eval_samples_per_second": 45.827, | |
| "eval_steps_per_second": 5.729, | |
| "step": 196352 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.4047, | |
| "step": 294528 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7896077432501274, | |
| "eval_loss": 1.0135771036148071, | |
| "eval_runtime": 214.0372, | |
| "eval_samples_per_second": 45.857, | |
| "eval_steps_per_second": 5.733, | |
| "step": 294528 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 294528, | |
| "total_flos": 7.370457899350856e+17, | |
| "train_loss": 0.5576832624996605, | |
| "train_runtime": 85721.6525, | |
| "train_samples_per_second": 13.743, | |
| "train_steps_per_second": 3.436 | |
| } | |
| ], | |
| "max_steps": 294528, | |
| "num_train_epochs": 3, | |
| "total_flos": 7.370457899350856e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |