| { | |
| "best_metric": 1.1196151971817017, | |
| "best_model_checkpoint": "model-bin/checkpoint-1962", | |
| "epoch": 2.0, | |
| "global_step": 3924, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.8374027367856188e-05, | |
| "loss": 3.3707, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.5690904212503355e-05, | |
| "loss": 1.6297, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.3007781057150523e-05, | |
| "loss": 1.3695, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_exact_match": 52.208835341365464, | |
| "eval_f1": 77.43637296399675, | |
| "eval_loss": 1.1196151971817017, | |
| "eval_runtime": 126.4696, | |
| "eval_samples_per_second": 13.782, | |
| "eval_steps_per_second": 1.724, | |
| "step": 1962 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.0324657901797695e-05, | |
| "loss": 1.239, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 7.641534746444862e-06, | |
| "loss": 0.832, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 4.958411591092032e-06, | |
| "loss": 0.8444, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.2752884357392007e-06, | |
| "loss": 0.7784, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_exact_match": 54.44635685599541, | |
| "eval_f1": 78.60432014685901, | |
| "eval_loss": 1.141330599784851, | |
| "eval_runtime": 122.7068, | |
| "eval_samples_per_second": 14.205, | |
| "eval_steps_per_second": 1.777, | |
| "step": 3924 | |
| } | |
| ], | |
| "max_steps": 3924, | |
| "num_train_epochs": 2, | |
| "total_flos": 1.178860206264462e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |