| { | |
| "best_metric": 1.0035810470581055, | |
| "best_model_checkpoint": "ckpt_base/checkpoint-1740", | |
| "epoch": 4.0, | |
| "global_step": 1740, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.1327471733093262, | |
| "eval_runtime": 5108.4501, | |
| "eval_samples_per_second": 0.623, | |
| "eval_steps_per_second": 0.311, | |
| "eval_wer": 1053.8786428269746, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 2.47e-06, | |
| "loss": 1.8361, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.05120849609375, | |
| "eval_runtime": 3561.6255, | |
| "eval_samples_per_second": 0.893, | |
| "eval_steps_per_second": 0.447, | |
| "eval_wer": 648.7118119104604, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 4.970000000000001e-06, | |
| "loss": 1.0706, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.0082696676254272, | |
| "eval_runtime": 3000.1391, | |
| "eval_samples_per_second": 1.061, | |
| "eval_steps_per_second": 0.53, | |
| "eval_wer": 531.1980853160636, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 4.679220779220779e-06, | |
| "loss": 0.953, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.0035810470581055, | |
| "eval_runtime": 2833.412, | |
| "eval_samples_per_second": 1.123, | |
| "eval_steps_per_second": 0.562, | |
| "eval_wer": 529.7761509221456, | |
| "step": 1740 | |
| } | |
| ], | |
| "max_steps": 8700, | |
| "num_train_epochs": 20, | |
| "total_flos": 5.902415445120726e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |