| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 25.12562814070352, |
| "global_step": 2500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.99, |
| "eval_loss": 2.7764203548431396, |
| "eval_runtime": 34.2112, |
| "eval_samples_per_second": 24.612, |
| "eval_steps_per_second": 3.098, |
| "eval_wer": 1.0, |
| "step": 99 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 2.762573003768921, |
| "eval_runtime": 33.9987, |
| "eval_samples_per_second": 24.766, |
| "eval_steps_per_second": 3.118, |
| "eval_wer": 1.0, |
| "step": 199 |
| }, |
| { |
| "epoch": 2.99, |
| "eval_loss": 1.5485457181930542, |
| "eval_runtime": 34.1904, |
| "eval_samples_per_second": 24.627, |
| "eval_steps_per_second": 3.1, |
| "eval_wer": 0.9983126781870018, |
| "step": 298 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.4536263048648834, |
| "eval_runtime": 34.3008, |
| "eval_samples_per_second": 24.548, |
| "eval_steps_per_second": 3.09, |
| "eval_wer": 0.6440914644789667, |
| "step": 398 |
| }, |
| { |
| "epoch": 4.99, |
| "eval_loss": 0.32973894476890564, |
| "eval_runtime": 34.0188, |
| "eval_samples_per_second": 24.751, |
| "eval_steps_per_second": 3.116, |
| "eval_wer": 0.5054983417699423, |
| "step": 497 |
| }, |
| { |
| "epoch": 5.03, |
| "learning_rate": 0.0002497979797979798, |
| "loss": 2.1303, |
| "step": 500 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.27073708176612854, |
| "eval_runtime": 33.9387, |
| "eval_samples_per_second": 24.809, |
| "eval_steps_per_second": 3.123, |
| "eval_wer": 0.3777273520684238, |
| "step": 597 |
| }, |
| { |
| "epoch": 6.99, |
| "eval_loss": 0.2596016526222229, |
| "eval_runtime": 33.9444, |
| "eval_samples_per_second": 24.805, |
| "eval_steps_per_second": 3.123, |
| "eval_wer": 0.3815092802699715, |
| "step": 696 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.25216805934906006, |
| "eval_runtime": 33.8461, |
| "eval_samples_per_second": 24.877, |
| "eval_steps_per_second": 3.132, |
| "eval_wer": 0.2978413917495782, |
| "step": 796 |
| }, |
| { |
| "epoch": 8.99, |
| "eval_loss": 0.22613081336021423, |
| "eval_runtime": 33.8906, |
| "eval_samples_per_second": 24.845, |
| "eval_steps_per_second": 3.128, |
| "eval_wer": 0.30965264444056556, |
| "step": 895 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.23950138688087463, |
| "eval_runtime": 33.9858, |
| "eval_samples_per_second": 24.775, |
| "eval_steps_per_second": 3.119, |
| "eval_wer": 0.2646767905975447, |
| "step": 995 |
| }, |
| { |
| "epoch": 10.05, |
| "learning_rate": 0.00019929292929292926, |
| "loss": 0.2057, |
| "step": 1000 |
| }, |
| { |
| "epoch": 10.99, |
| "eval_loss": 0.21791674196720123, |
| "eval_runtime": 33.9224, |
| "eval_samples_per_second": 24.821, |
| "eval_steps_per_second": 3.125, |
| "eval_wer": 0.2613603304823413, |
| "step": 1094 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 0.21110226213932037, |
| "eval_runtime": 33.8358, |
| "eval_samples_per_second": 24.885, |
| "eval_steps_per_second": 3.133, |
| "eval_wer": 0.25903299005061964, |
| "step": 1194 |
| }, |
| { |
| "epoch": 12.99, |
| "eval_loss": 0.22310343384742737, |
| "eval_runtime": 33.7767, |
| "eval_samples_per_second": 24.928, |
| "eval_steps_per_second": 3.138, |
| "eval_wer": 0.25368010705765986, |
| "step": 1293 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 0.2454575151205063, |
| "eval_runtime": 33.8201, |
| "eval_samples_per_second": 24.896, |
| "eval_steps_per_second": 3.134, |
| "eval_wer": 0.2483854075754931, |
| "step": 1393 |
| }, |
| { |
| "epoch": 14.99, |
| "eval_loss": 0.24834834039211273, |
| "eval_runtime": 33.7913, |
| "eval_samples_per_second": 24.918, |
| "eval_steps_per_second": 3.137, |
| "eval_wer": 0.23663233839529876, |
| "step": 1492 |
| }, |
| { |
| "epoch": 15.08, |
| "learning_rate": 0.00014878787878787875, |
| "loss": 0.0945, |
| "step": 1500 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 0.259757936000824, |
| "eval_runtime": 33.8499, |
| "eval_samples_per_second": 24.875, |
| "eval_steps_per_second": 3.131, |
| "eval_wer": 0.22348286495607145, |
| "step": 1592 |
| }, |
| { |
| "epoch": 16.99, |
| "eval_loss": 0.26361608505249023, |
| "eval_runtime": 33.9334, |
| "eval_samples_per_second": 24.813, |
| "eval_steps_per_second": 3.124, |
| "eval_wer": 0.21935183568976552, |
| "step": 1691 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_loss": 0.2598336637020111, |
| "eval_runtime": 33.8712, |
| "eval_samples_per_second": 24.859, |
| "eval_steps_per_second": 3.13, |
| "eval_wer": 0.21964275324373073, |
| "step": 1791 |
| }, |
| { |
| "epoch": 18.99, |
| "eval_loss": 0.24791987240314484, |
| "eval_runtime": 33.8138, |
| "eval_samples_per_second": 24.901, |
| "eval_steps_per_second": 3.135, |
| "eval_wer": 0.20882062023622505, |
| "step": 1890 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_loss": 0.24469724297523499, |
| "eval_runtime": 33.9448, |
| "eval_samples_per_second": 24.805, |
| "eval_steps_per_second": 3.123, |
| "eval_wer": 0.2091697213009833, |
| "step": 1990 |
| }, |
| { |
| "epoch": 20.1, |
| "learning_rate": 9.828282828282828e-05, |
| "loss": 0.0567, |
| "step": 2000 |
| }, |
| { |
| "epoch": 20.99, |
| "eval_loss": 0.25630325078964233, |
| "eval_runtime": 33.677, |
| "eval_samples_per_second": 25.002, |
| "eval_steps_per_second": 3.148, |
| "eval_wer": 0.20463140745912609, |
| "step": 2089 |
| }, |
| { |
| "epoch": 22.0, |
| "eval_loss": 0.2675672173500061, |
| "eval_runtime": 33.7312, |
| "eval_samples_per_second": 24.962, |
| "eval_steps_per_second": 3.142, |
| "eval_wer": 0.198871239890615, |
| "step": 2189 |
| }, |
| { |
| "epoch": 22.99, |
| "eval_loss": 0.25741901993751526, |
| "eval_runtime": 33.6669, |
| "eval_samples_per_second": 25.01, |
| "eval_steps_per_second": 3.148, |
| "eval_wer": 0.19951125850933846, |
| "step": 2288 |
| }, |
| { |
| "epoch": 24.0, |
| "eval_loss": 0.2615770101547241, |
| "eval_runtime": 33.8091, |
| "eval_samples_per_second": 24.905, |
| "eval_steps_per_second": 3.135, |
| "eval_wer": 0.1961947983941351, |
| "step": 2388 |
| }, |
| { |
| "epoch": 24.99, |
| "eval_loss": 0.257935494184494, |
| "eval_runtime": 33.8705, |
| "eval_samples_per_second": 24.859, |
| "eval_steps_per_second": 3.13, |
| "eval_wer": 0.1956129632862047, |
| "step": 2487 |
| }, |
| { |
| "epoch": 25.13, |
| "learning_rate": 4.777777777777778e-05, |
| "loss": 0.0418, |
| "step": 2500 |
| } |
| ], |
| "max_steps": 2970, |
| "num_train_epochs": 30, |
| "total_flos": 6.454758338809764e+19, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
