| { | |
| "best_metric": 5.696169637752716, | |
| "best_model_checkpoint": "./checkpoint-500", | |
| "epoch": 1.03, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3.4043195900439816e-07, | |
| "loss": 0.0907, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.203103093438967e-07, | |
| "loss": 0.0802, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.6583071503011386e-07, | |
| "loss": 0.0774, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.978065189231237e-07, | |
| "loss": 0.0746, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0834, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0775, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0784, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0756, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0744, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0801, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0768, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0795, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0837, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0827, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0858, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 5e-07, | |
| "loss": 0.088, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0865, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0911, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0976, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5e-07, | |
| "loss": 0.1665, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 0.1700439453125, | |
| "eval_runtime": 3050.6887, | |
| "eval_samples_per_second": 5.087, | |
| "eval_steps_per_second": 0.159, | |
| "eval_wer": 5.696169637752716, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "step": 500, | |
| "total_flos": 3.2659357379539763e+19, | |
| "train_loss": 0.0865213623046875, | |
| "train_runtime": 8011.6489, | |
| "train_samples_per_second": 3.994, | |
| "train_steps_per_second": 0.062 | |
| } | |
| ], | |
| "max_steps": 500, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 3.2659357379539763e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |