| { |
| "best_metric": 51.37028014616322, |
| "best_model_checkpoint": "./checkpoint-2000", |
| "epoch": 1.0, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1, |
| "learning_rate": 2.9850000000000002e-06, |
| "loss": 2.4574, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.1, |
| "eval_loss": 1.4662598371505737, |
| "eval_runtime": 21.5397, |
| "eval_samples_per_second": 7.475, |
| "eval_steps_per_second": 0.279, |
| "eval_wer": 71.65042630937882, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 3e-06, |
| "loss": 1.9587, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_loss": 1.2580980062484741, |
| "eval_runtime": 16.6116, |
| "eval_samples_per_second": 9.692, |
| "eval_steps_per_second": 0.361, |
| "eval_wer": 64.73812423873325, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 3e-06, |
| "loss": 1.816, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.3, |
| "eval_loss": 1.1671593189239502, |
| "eval_runtime": 17.1526, |
| "eval_samples_per_second": 9.386, |
| "eval_steps_per_second": 0.35, |
| "eval_wer": 60.93179049939099, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 3e-06, |
| "loss": 1.7199, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_loss": 1.100619912147522, |
| "eval_runtime": 15.3573, |
| "eval_samples_per_second": 10.484, |
| "eval_steps_per_second": 0.391, |
| "eval_wer": 57.673568818514006, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 3e-06, |
| "loss": 1.6686, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.5, |
| "eval_loss": 1.0630302429199219, |
| "eval_runtime": 16.3877, |
| "eval_samples_per_second": 9.824, |
| "eval_steps_per_second": 0.366, |
| "eval_wer": 56.18148599269184, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 3e-06, |
| "loss": 1.621, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.6, |
| "eval_loss": 1.0273046493530273, |
| "eval_runtime": 16.6903, |
| "eval_samples_per_second": 9.646, |
| "eval_steps_per_second": 0.359, |
| "eval_wer": 55.481120584652864, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 3e-06, |
| "loss": 1.5846, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.7, |
| "eval_loss": 1.0016604661941528, |
| "eval_runtime": 16.3415, |
| "eval_samples_per_second": 9.852, |
| "eval_steps_per_second": 0.367, |
| "eval_wer": 53.98903775883069, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 3e-06, |
| "loss": 1.5482, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_loss": 0.9773023128509521, |
| "eval_runtime": 16.9737, |
| "eval_samples_per_second": 9.485, |
| "eval_steps_per_second": 0.353, |
| "eval_wer": 53.014616321559075, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 3e-06, |
| "loss": 1.521, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.9, |
| "eval_loss": 0.9574936628341675, |
| "eval_runtime": 18.1323, |
| "eval_samples_per_second": 8.879, |
| "eval_steps_per_second": 0.331, |
| "eval_wer": 52.10109622411693, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 3e-06, |
| "loss": 1.4932, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.9374914765357971, |
| "eval_runtime": 15.2056, |
| "eval_samples_per_second": 10.588, |
| "eval_steps_per_second": 0.395, |
| "eval_wer": 51.37028014616322, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 2000, |
| "total_flos": 6.30243459072e+18, |
| "train_loss": 1.7388742218017579, |
| "train_runtime": 29801.9401, |
| "train_samples_per_second": 8.59, |
| "train_steps_per_second": 0.067 |
| } |
| ], |
| "max_steps": 2000, |
| "num_train_epochs": 9223372036854775807, |
| "total_flos": 6.30243459072e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
