| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.716981132075472, | |
| "eval_steps": 500, | |
| "global_step": 1500, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7241935483870968, | |
| "eval_loss": 3.2103216648101807, | |
| "eval_runtime": 2.39, | |
| "eval_samples_per_second": 1297.069, | |
| "eval_steps_per_second": 27.197, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.550763701707098e-05, | |
| "loss": 3.7291, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8529032258064516, | |
| "eval_loss": 1.6777656078338623, | |
| "eval_runtime": 2.436, | |
| "eval_samples_per_second": 1272.578, | |
| "eval_steps_per_second": 26.683, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9058064516129032, | |
| "eval_loss": 0.9034197926521301, | |
| "eval_runtime": 2.544, | |
| "eval_samples_per_second": 1218.553, | |
| "eval_steps_per_second": 25.55, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 1.101527403414196e-05, | |
| "loss": 1.4651, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9283870967741935, | |
| "eval_loss": 0.5764979124069214, | |
| "eval_runtime": 2.477, | |
| "eval_samples_per_second": 1251.514, | |
| "eval_steps_per_second": 26.241, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 6.522911051212939e-06, | |
| "loss": 0.5782, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2226, | |
| "num_train_epochs": 7, | |
| "save_steps": 500, | |
| "total_flos": 472108083521340.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.9093370096712147, | |
| "num_train_epochs": 7, | |
| "temperature": 18 | |
| } | |
| } | |