| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.0, | |
| "global_step": 1650, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3e-05, | |
| "loss": 1.8786, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_exact_match": 50.891920251836304, | |
| "eval_f1": 59.77181589273692, | |
| "eval_runtime": 3.5228, | |
| "eval_samples_per_second": 2434.745, | |
| "eval_steps_per_second": 7.664, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0114, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_exact_match": 50.099102250204034, | |
| "eval_f1": 59.27801305634267, | |
| "eval_runtime": 3.0825, | |
| "eval_samples_per_second": 2782.451, | |
| "eval_steps_per_second": 8.759, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.8056, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_exact_match": 51.34662469394893, | |
| "eval_f1": 60.15916465244632, | |
| "eval_runtime": 3.0645, | |
| "eval_samples_per_second": 2798.83, | |
| "eval_steps_per_second": 8.811, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.6596, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_exact_match": 51.77801095954296, | |
| "eval_f1": 60.60172829136609, | |
| "eval_runtime": 3.0043, | |
| "eval_samples_per_second": 2854.95, | |
| "eval_steps_per_second": 8.987, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.5419, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_exact_match": 51.509851929579106, | |
| "eval_f1": 59.942123676155056, | |
| "eval_runtime": 3.0268, | |
| "eval_samples_per_second": 2833.667, | |
| "eval_steps_per_second": 8.92, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4463, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_exact_match": 52.44257899032296, | |
| "eval_f1": 60.93207881355018, | |
| "eval_runtime": 2.9996, | |
| "eval_samples_per_second": 2859.411, | |
| "eval_steps_per_second": 9.001, | |
| "step": 1650 | |
| } | |
| ], | |
| "max_steps": 2750, | |
| "num_train_epochs": 10, | |
| "total_flos": 198652180037632.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |