| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 20.0, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 3.1823601722717285, |
| "eval_runtime": 1.8503, |
| "eval_samples_per_second": 126.469, |
| "eval_steps_per_second": 16.214, |
| "eval_wer": 1.0, |
| "step": 25 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 2.933835983276367, |
| "eval_runtime": 1.8259, |
| "eval_samples_per_second": 128.156, |
| "eval_steps_per_second": 16.43, |
| "eval_wer": 1.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 2.8917059898376465, |
| "eval_runtime": 1.8294, |
| "eval_samples_per_second": 127.913, |
| "eval_steps_per_second": 16.399, |
| "eval_wer": 1.0, |
| "step": 75 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 2.9372332096099854, |
| "eval_runtime": 1.8378, |
| "eval_samples_per_second": 127.327, |
| "eval_steps_per_second": 16.324, |
| "eval_wer": 1.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 2.8342607021331787, |
| "eval_runtime": 1.843, |
| "eval_samples_per_second": 126.965, |
| "eval_steps_per_second": 16.278, |
| "eval_wer": 1.0, |
| "step": 125 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 2.8205959796905518, |
| "eval_runtime": 1.8525, |
| "eval_samples_per_second": 126.315, |
| "eval_steps_per_second": 16.194, |
| "eval_wer": 1.0, |
| "step": 150 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 2.7126834392547607, |
| "eval_runtime": 1.8471, |
| "eval_samples_per_second": 126.686, |
| "eval_steps_per_second": 16.242, |
| "eval_wer": 0.9917290271760536, |
| "step": 175 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 2.2903497219085693, |
| "eval_runtime": 1.8549, |
| "eval_samples_per_second": 126.15, |
| "eval_steps_per_second": 16.173, |
| "eval_wer": 0.9279243796770382, |
| "step": 200 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 2.161506414413452, |
| "eval_runtime": 1.8637, |
| "eval_samples_per_second": 125.556, |
| "eval_steps_per_second": 16.097, |
| "eval_wer": 0.9641591177628988, |
| "step": 225 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 1.8126736879348755, |
| "eval_runtime": 1.868, |
| "eval_samples_per_second": 125.265, |
| "eval_steps_per_second": 16.06, |
| "eval_wer": 0.790862544308783, |
| "step": 250 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 1.8635412454605103, |
| "eval_runtime": 1.869, |
| "eval_samples_per_second": 125.203, |
| "eval_steps_per_second": 16.052, |
| "eval_wer": 0.7707758960220559, |
| "step": 275 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 1.9644334316253662, |
| "eval_runtime": 1.8669, |
| "eval_samples_per_second": 125.34, |
| "eval_steps_per_second": 16.069, |
| "eval_wer": 0.7412367073651044, |
| "step": 300 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_loss": 1.9838531017303467, |
| "eval_runtime": 1.8741, |
| "eval_samples_per_second": 124.858, |
| "eval_steps_per_second": 16.007, |
| "eval_wer": 0.7565970854667192, |
| "step": 325 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 2.0554840564727783, |
| "eval_runtime": 1.874, |
| "eval_samples_per_second": 124.864, |
| "eval_steps_per_second": 16.008, |
| "eval_wer": 0.7400551398188263, |
| "step": 350 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_loss": 2.204854965209961, |
| "eval_runtime": 1.8695, |
| "eval_samples_per_second": 125.17, |
| "eval_steps_per_second": 16.047, |
| "eval_wer": 0.7447814100039386, |
| "step": 375 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 2.2302396297454834, |
| "eval_runtime": 1.8667, |
| "eval_samples_per_second": 125.353, |
| "eval_steps_per_second": 16.071, |
| "eval_wer": 0.7443875541551792, |
| "step": 400 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_loss": 2.2742059230804443, |
| "eval_runtime": 1.8774, |
| "eval_samples_per_second": 124.639, |
| "eval_steps_per_second": 15.979, |
| "eval_wer": 0.7581725088617566, |
| "step": 425 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_loss": 2.375885248184204, |
| "eval_runtime": 1.8762, |
| "eval_samples_per_second": 124.719, |
| "eval_steps_per_second": 15.99, |
| "eval_wer": 0.7487199684915321, |
| "step": 450 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_loss": 2.4379167556762695, |
| "eval_runtime": 1.8721, |
| "eval_samples_per_second": 124.99, |
| "eval_steps_per_second": 16.024, |
| "eval_wer": 0.759747932256794, |
| "step": 475 |
| }, |
| { |
| "epoch": 20.0, |
| "learning_rate": 0.0001008, |
| "loss": 1.9367, |
| "step": 500 |
| } |
| ], |
| "max_steps": 750, |
| "num_train_epochs": 30, |
| "total_flos": 2.2993843982800115e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
