| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.998422712933754, | |
| "global_step": 2110, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0003470916966876807, | |
| "loss": 1.587, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 0.2940497398376465, | |
| "eval_runtime": 783.4997, | |
| "eval_samples_per_second": 6.601, | |
| "eval_wer": 0.5440472766257878, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0002163596723446065, | |
| "loss": 0.25, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 0.20464767515659332, | |
| "eval_runtime": 845.5317, | |
| "eval_samples_per_second": 6.117, | |
| "eval_wer": 0.4130690583897707, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 7.697202293654628e-05, | |
| "loss": 0.1538, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "eval_loss": 0.17199403047561646, | |
| "eval_runtime": 847.1175, | |
| "eval_samples_per_second": 6.105, | |
| "eval_wer": 0.3628114949141019, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 2.6763887922288233e-06, | |
| "loss": 0.1143, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "eval_loss": 0.16164630651474, | |
| "eval_runtime": 737.1973, | |
| "eval_samples_per_second": 7.016, | |
| "eval_wer": 0.3482467379651178, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 2110, | |
| "total_flos": 1.0309110757947716e+19, | |
| "train_runtime": 14179.0923, | |
| "train_samples_per_second": 0.149 | |
| } | |
| ], | |
| "max_steps": 2110, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.0309110757947716e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |