| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 24.0, |
| "global_step": 1500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.99, |
| "eval_loss": 2.6419124603271484, |
| "eval_runtime": 3.6969, |
| "eval_samples_per_second": 185.289, |
| "eval_steps_per_second": 23.263, |
| "eval_wer": 1.0, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 2.58249568939209, |
| "eval_runtime": 3.6751, |
| "eval_samples_per_second": 186.389, |
| "eval_steps_per_second": 23.401, |
| "eval_wer": 1.0, |
| "step": 125 |
| }, |
| { |
| "epoch": 2.99, |
| "eval_loss": 2.574338436126709, |
| "eval_runtime": 3.7046, |
| "eval_samples_per_second": 184.905, |
| "eval_steps_per_second": 23.214, |
| "eval_wer": 1.0, |
| "step": 187 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 2.5320825576782227, |
| "eval_runtime": 3.7133, |
| "eval_samples_per_second": 184.472, |
| "eval_steps_per_second": 23.16, |
| "eval_wer": 0.9994711792702274, |
| "step": 250 |
| }, |
| { |
| "epoch": 4.99, |
| "eval_loss": 2.2844398021698, |
| "eval_runtime": 3.7345, |
| "eval_samples_per_second": 183.424, |
| "eval_steps_per_second": 23.028, |
| "eval_wer": 1.0, |
| "step": 312 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 1.7816661596298218, |
| "eval_runtime": 3.7402, |
| "eval_samples_per_second": 183.147, |
| "eval_steps_per_second": 22.994, |
| "eval_wer": 0.9640401903754627, |
| "step": 375 |
| }, |
| { |
| "epoch": 6.99, |
| "eval_loss": 1.4727487564086914, |
| "eval_runtime": 3.7405, |
| "eval_samples_per_second": 183.132, |
| "eval_steps_per_second": 22.992, |
| "eval_wer": 0.9299312533051296, |
| "step": 437 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 0.0002193548387096774, |
| "loss": 2.3698, |
| "step": 500 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 1.7388513088226318, |
| "eval_runtime": 3.735, |
| "eval_samples_per_second": 183.399, |
| "eval_steps_per_second": 23.025, |
| "eval_wer": 0.9227921734531994, |
| "step": 500 |
| }, |
| { |
| "epoch": 8.99, |
| "eval_loss": 1.5088895559310913, |
| "eval_runtime": 3.7383, |
| "eval_samples_per_second": 183.241, |
| "eval_steps_per_second": 23.005, |
| "eval_wer": 0.9021681649920676, |
| "step": 562 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 1.6695538759231567, |
| "eval_runtime": 3.7391, |
| "eval_samples_per_second": 183.201, |
| "eval_steps_per_second": 23.0, |
| "eval_wer": 0.8802221047065045, |
| "step": 625 |
| }, |
| { |
| "epoch": 10.99, |
| "eval_loss": 1.8177894353866577, |
| "eval_runtime": 3.7376, |
| "eval_samples_per_second": 183.272, |
| "eval_steps_per_second": 23.009, |
| "eval_wer": 0.9471179270227393, |
| "step": 687 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 1.5107115507125854, |
| "eval_runtime": 3.7409, |
| "eval_samples_per_second": 183.109, |
| "eval_steps_per_second": 22.989, |
| "eval_wer": 0.8791644632469593, |
| "step": 750 |
| }, |
| { |
| "epoch": 12.99, |
| "eval_loss": 1.704025149345398, |
| "eval_runtime": 3.7269, |
| "eval_samples_per_second": 183.796, |
| "eval_steps_per_second": 23.075, |
| "eval_wer": 0.8799576943416182, |
| "step": 812 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 1.6209287643432617, |
| "eval_runtime": 3.73, |
| "eval_samples_per_second": 183.648, |
| "eval_steps_per_second": 23.057, |
| "eval_wer": 0.8860391327340031, |
| "step": 875 |
| }, |
| { |
| "epoch": 14.99, |
| "eval_loss": 1.7103419303894043, |
| "eval_runtime": 3.8137, |
| "eval_samples_per_second": 179.615, |
| "eval_steps_per_second": 22.55, |
| "eval_wer": 0.920676890534109, |
| "step": 937 |
| }, |
| { |
| "epoch": 16.0, |
| "learning_rate": 0.0001387096774193548, |
| "loss": 0.7913, |
| "step": 1000 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 1.8196772336959839, |
| "eval_runtime": 3.7484, |
| "eval_samples_per_second": 182.743, |
| "eval_steps_per_second": 22.943, |
| "eval_wer": 0.891062929666843, |
| "step": 1000 |
| }, |
| { |
| "epoch": 16.99, |
| "eval_loss": 1.871021032333374, |
| "eval_runtime": 3.739, |
| "eval_samples_per_second": 183.206, |
| "eval_steps_per_second": 23.001, |
| "eval_wer": 0.9138022210470651, |
| "step": 1062 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_loss": 2.0114657878875732, |
| "eval_runtime": 3.7597, |
| "eval_samples_per_second": 182.194, |
| "eval_steps_per_second": 22.874, |
| "eval_wer": 0.9138022210470651, |
| "step": 1125 |
| }, |
| { |
| "epoch": 18.99, |
| "eval_loss": 2.164022922515869, |
| "eval_runtime": 3.7353, |
| "eval_samples_per_second": 183.384, |
| "eval_steps_per_second": 23.023, |
| "eval_wer": 0.9180327868852459, |
| "step": 1187 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_loss": 2.1961405277252197, |
| "eval_runtime": 3.7569, |
| "eval_samples_per_second": 182.332, |
| "eval_steps_per_second": 22.891, |
| "eval_wer": 0.9214701216287678, |
| "step": 1250 |
| }, |
| { |
| "epoch": 20.99, |
| "eval_loss": 2.2560768127441406, |
| "eval_runtime": 3.7531, |
| "eval_samples_per_second": 182.517, |
| "eval_steps_per_second": 22.915, |
| "eval_wer": 0.905076679005817, |
| "step": 1312 |
| }, |
| { |
| "epoch": 22.0, |
| "eval_loss": 2.2624008655548096, |
| "eval_runtime": 3.7599, |
| "eval_samples_per_second": 182.187, |
| "eval_steps_per_second": 22.873, |
| "eval_wer": 0.905076679005817, |
| "step": 1375 |
| }, |
| { |
| "epoch": 22.99, |
| "eval_loss": 2.3477489948272705, |
| "eval_runtime": 3.7551, |
| "eval_samples_per_second": 182.418, |
| "eval_steps_per_second": 22.902, |
| "eval_wer": 0.9026969857218403, |
| "step": 1437 |
| }, |
| { |
| "epoch": 24.0, |
| "learning_rate": 5.806451612903225e-05, |
| "loss": 0.284, |
| "step": 1500 |
| } |
| ], |
| "max_steps": 1860, |
| "num_train_epochs": 30, |
| "total_flos": 6.874539672176118e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
