| { | |
| "best_metric": 0.5470190644264221, | |
| "best_model_checkpoint": "wav2vec2-large-xlsr-coraa-exp-10/checkpoint-1764", | |
| "epoch": 146.0, | |
| "global_step": 2044, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3e-05, | |
| "loss": 37.9224, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_cer": 0.9618198362147407, | |
| "eval_loss": 24.657764434814453, | |
| "eval_runtime": 53.8844, | |
| "eval_samples_per_second": 10.059, | |
| "eval_steps_per_second": 1.262, | |
| "eval_wer": 1.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 7.14532470703125, | |
| "eval_runtime": 53.624, | |
| "eval_samples_per_second": 10.107, | |
| "eval_steps_per_second": 1.268, | |
| "eval_wer": 1.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 4.43905782699585, | |
| "eval_runtime": 53.4498, | |
| "eval_samples_per_second": 10.14, | |
| "eval_steps_per_second": 1.272, | |
| "eval_wer": 1.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.90922474861145, | |
| "eval_runtime": 53.742, | |
| "eval_samples_per_second": 10.085, | |
| "eval_steps_per_second": 1.265, | |
| "eval_wer": 1.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.6834604740142822, | |
| "eval_runtime": 53.6572, | |
| "eval_samples_per_second": 10.101, | |
| "eval_steps_per_second": 1.267, | |
| "eval_wer": 1.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.522313117980957, | |
| "eval_runtime": 53.7448, | |
| "eval_samples_per_second": 10.085, | |
| "eval_steps_per_second": 1.265, | |
| "eval_wer": 1.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.3716423511505127, | |
| "eval_runtime": 53.5358, | |
| "eval_samples_per_second": 10.124, | |
| "eval_steps_per_second": 1.27, | |
| "eval_wer": 1.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 2.8614285714285714e-05, | |
| "loss": 9.0651, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.2723329067230225, | |
| "eval_runtime": 53.6095, | |
| "eval_samples_per_second": 10.11, | |
| "eval_steps_per_second": 1.268, | |
| "eval_wer": 1.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.1859705448150635, | |
| "eval_runtime": 53.5878, | |
| "eval_samples_per_second": 10.114, | |
| "eval_steps_per_second": 1.269, | |
| "eval_wer": 1.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.146104574203491, | |
| "eval_runtime": 53.491, | |
| "eval_samples_per_second": 10.133, | |
| "eval_steps_per_second": 1.271, | |
| "eval_wer": 1.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.1367859840393066, | |
| "eval_runtime": 53.9341, | |
| "eval_samples_per_second": 10.049, | |
| "eval_steps_per_second": 1.261, | |
| "eval_wer": 1.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0960755348205566, | |
| "eval_runtime": 53.5674, | |
| "eval_samples_per_second": 10.118, | |
| "eval_steps_per_second": 1.269, | |
| "eval_wer": 1.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0767099857330322, | |
| "eval_runtime": 53.6269, | |
| "eval_samples_per_second": 10.107, | |
| "eval_steps_per_second": 1.268, | |
| "eval_wer": 1.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0509135723114014, | |
| "eval_runtime": 53.9364, | |
| "eval_samples_per_second": 10.049, | |
| "eval_steps_per_second": 1.261, | |
| "eval_wer": 1.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 2.7185714285714287e-05, | |
| "loss": 3.0601, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.087069511413574, | |
| "eval_runtime": 53.3522, | |
| "eval_samples_per_second": 10.159, | |
| "eval_steps_per_second": 1.275, | |
| "eval_wer": 1.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.041494131088257, | |
| "eval_runtime": 53.2391, | |
| "eval_samples_per_second": 10.18, | |
| "eval_steps_per_second": 1.277, | |
| "eval_wer": 1.0, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0329771041870117, | |
| "eval_runtime": 53.3109, | |
| "eval_samples_per_second": 10.167, | |
| "eval_steps_per_second": 1.276, | |
| "eval_wer": 1.0, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.019200086593628, | |
| "eval_runtime": 53.38, | |
| "eval_samples_per_second": 10.154, | |
| "eval_steps_per_second": 1.274, | |
| "eval_wer": 1.0, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.026556968688965, | |
| "eval_runtime": 53.4357, | |
| "eval_samples_per_second": 10.143, | |
| "eval_steps_per_second": 1.273, | |
| "eval_wer": 1.0, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.024301528930664, | |
| "eval_runtime": 53.5352, | |
| "eval_samples_per_second": 10.124, | |
| "eval_steps_per_second": 1.27, | |
| "eval_wer": 1.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0105724334716797, | |
| "eval_runtime": 53.4874, | |
| "eval_samples_per_second": 10.133, | |
| "eval_steps_per_second": 1.271, | |
| "eval_wer": 1.0, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "learning_rate": 2.5757142857142857e-05, | |
| "loss": 2.9552, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0053164958953857, | |
| "eval_runtime": 53.5107, | |
| "eval_samples_per_second": 10.129, | |
| "eval_steps_per_second": 1.271, | |
| "eval_wer": 1.0, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.9986302852630615, | |
| "eval_runtime": 53.679, | |
| "eval_samples_per_second": 10.097, | |
| "eval_steps_per_second": 1.267, | |
| "eval_wer": 1.0, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0029869079589844, | |
| "eval_runtime": 54.0064, | |
| "eval_samples_per_second": 10.036, | |
| "eval_steps_per_second": 1.259, | |
| "eval_wer": 1.0, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.99497389793396, | |
| "eval_runtime": 53.5494, | |
| "eval_samples_per_second": 10.122, | |
| "eval_steps_per_second": 1.27, | |
| "eval_wer": 1.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0058376789093018, | |
| "eval_runtime": 53.3418, | |
| "eval_samples_per_second": 10.161, | |
| "eval_steps_per_second": 1.275, | |
| "eval_wer": 1.0, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.9943442344665527, | |
| "eval_runtime": 53.5262, | |
| "eval_samples_per_second": 10.126, | |
| "eval_steps_per_second": 1.27, | |
| "eval_wer": 1.0, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.9845216274261475, | |
| "eval_runtime": 53.6167, | |
| "eval_samples_per_second": 10.109, | |
| "eval_steps_per_second": 1.268, | |
| "eval_wer": 1.0, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 2.432857142857143e-05, | |
| "loss": 2.9213, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.971311330795288, | |
| "eval_runtime": 53.7132, | |
| "eval_samples_per_second": 10.091, | |
| "eval_steps_per_second": 1.266, | |
| "eval_wer": 1.0, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.9484527111053467, | |
| "eval_runtime": 53.7813, | |
| "eval_samples_per_second": 10.078, | |
| "eval_steps_per_second": 1.264, | |
| "eval_wer": 1.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.941479206085205, | |
| "eval_runtime": 53.6932, | |
| "eval_samples_per_second": 10.094, | |
| "eval_steps_per_second": 1.266, | |
| "eval_wer": 1.0, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.8912880420684814, | |
| "eval_runtime": 53.8504, | |
| "eval_samples_per_second": 10.065, | |
| "eval_steps_per_second": 1.263, | |
| "eval_wer": 1.0, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_cer": 0.9612010919017289, | |
| "eval_loss": 2.8057382106781006, | |
| "eval_runtime": 54.0302, | |
| "eval_samples_per_second": 10.031, | |
| "eval_steps_per_second": 1.259, | |
| "eval_wer": 1.0, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_cer": 0.9598908098271156, | |
| "eval_loss": 2.698427438735962, | |
| "eval_runtime": 53.7576, | |
| "eval_samples_per_second": 10.082, | |
| "eval_steps_per_second": 1.265, | |
| "eval_wer": 1.0, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_cer": 0.9066787989080982, | |
| "eval_loss": 2.57851243019104, | |
| "eval_runtime": 53.7653, | |
| "eval_samples_per_second": 10.081, | |
| "eval_steps_per_second": 1.265, | |
| "eval_wer": 1.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 35.71, | |
| "learning_rate": 2.29e-05, | |
| "loss": 2.7804, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_cer": 0.7928662420382165, | |
| "eval_loss": 2.3545000553131104, | |
| "eval_runtime": 53.7523, | |
| "eval_samples_per_second": 10.083, | |
| "eval_steps_per_second": 1.265, | |
| "eval_wer": 1.0, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_cer": 0.5933030027297543, | |
| "eval_loss": 2.0432868003845215, | |
| "eval_runtime": 53.6932, | |
| "eval_samples_per_second": 10.094, | |
| "eval_steps_per_second": 1.266, | |
| "eval_wer": 1.0, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_cer": 0.4701000909918107, | |
| "eval_loss": 1.7438023090362549, | |
| "eval_runtime": 53.7889, | |
| "eval_samples_per_second": 10.076, | |
| "eval_steps_per_second": 1.264, | |
| "eval_wer": 1.0, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_cer": 0.4139399454049136, | |
| "eval_loss": 1.4659055471420288, | |
| "eval_runtime": 53.7237, | |
| "eval_samples_per_second": 10.089, | |
| "eval_steps_per_second": 1.266, | |
| "eval_wer": 1.0, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_cer": 0.3840218380345769, | |
| "eval_loss": 1.2873483896255493, | |
| "eval_runtime": 53.8213, | |
| "eval_samples_per_second": 10.07, | |
| "eval_steps_per_second": 1.263, | |
| "eval_wer": 0.9928890694839496, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_cer": 0.3386715195632393, | |
| "eval_loss": 1.1587954759597778, | |
| "eval_runtime": 53.6935, | |
| "eval_samples_per_second": 10.094, | |
| "eval_steps_per_second": 1.266, | |
| "eval_wer": 0.9315318976026006, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_cer": 0.2705732484076433, | |
| "eval_loss": 1.016275405883789, | |
| "eval_runtime": 53.8774, | |
| "eval_samples_per_second": 10.06, | |
| "eval_steps_per_second": 1.262, | |
| "eval_wer": 0.7395367736692402, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 42.86, | |
| "learning_rate": 2.1471428571428574e-05, | |
| "loss": 1.6517, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_cer": 0.22584167424931756, | |
| "eval_loss": 0.9398883581161499, | |
| "eval_runtime": 53.8756, | |
| "eval_samples_per_second": 10.06, | |
| "eval_steps_per_second": 1.262, | |
| "eval_wer": 0.5331166192604633, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_cer": 0.21670609645131939, | |
| "eval_loss": 0.91312175989151, | |
| "eval_runtime": 53.9097, | |
| "eval_samples_per_second": 10.054, | |
| "eval_steps_per_second": 1.261, | |
| "eval_wer": 0.4928890694839496, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_cer": 0.2113557779799818, | |
| "eval_loss": 0.8351526856422424, | |
| "eval_runtime": 54.2652, | |
| "eval_samples_per_second": 9.988, | |
| "eval_steps_per_second": 1.253, | |
| "eval_wer": 0.477041852905323, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_cer": 0.2083712465878071, | |
| "eval_loss": 0.8114636540412903, | |
| "eval_runtime": 53.8109, | |
| "eval_samples_per_second": 10.072, | |
| "eval_steps_per_second": 1.264, | |
| "eval_wer": 0.45550589191385615, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_cer": 0.2037852593266606, | |
| "eval_loss": 0.78495192527771, | |
| "eval_runtime": 53.8458, | |
| "eval_samples_per_second": 10.066, | |
| "eval_steps_per_second": 1.263, | |
| "eval_wer": 0.4402681836651768, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_cer": 0.2018926296633303, | |
| "eval_loss": 0.757414698600769, | |
| "eval_runtime": 53.866, | |
| "eval_samples_per_second": 10.062, | |
| "eval_steps_per_second": 1.262, | |
| "eval_wer": 0.4355952864689151, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_cer": 0.1989080982711556, | |
| "eval_loss": 0.723770022392273, | |
| "eval_runtime": 54.4837, | |
| "eval_samples_per_second": 9.948, | |
| "eval_steps_per_second": 1.248, | |
| "eval_wer": 0.42482730597318163, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 2.004285714285714e-05, | |
| "loss": 0.7966, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_cer": 0.19603275705186532, | |
| "eval_loss": 0.7132200002670288, | |
| "eval_runtime": 53.8591, | |
| "eval_samples_per_second": 10.063, | |
| "eval_steps_per_second": 1.263, | |
| "eval_wer": 0.41304347826086957, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_cer": 0.19628753412192904, | |
| "eval_loss": 0.7053857445716858, | |
| "eval_runtime": 53.8356, | |
| "eval_samples_per_second": 10.068, | |
| "eval_steps_per_second": 1.263, | |
| "eval_wer": 0.41284030881755385, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_cer": 0.19898089171974523, | |
| "eval_loss": 0.7119351029396057, | |
| "eval_runtime": 53.6949, | |
| "eval_samples_per_second": 10.094, | |
| "eval_steps_per_second": 1.266, | |
| "eval_wer": 0.413449817147501, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_cer": 0.19450409463148316, | |
| "eval_loss": 0.6792961955070496, | |
| "eval_runtime": 53.7823, | |
| "eval_samples_per_second": 10.078, | |
| "eval_steps_per_second": 1.264, | |
| "eval_wer": 0.3990247866720845, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_cer": 0.19319381255686988, | |
| "eval_loss": 0.6717870235443115, | |
| "eval_runtime": 53.6919, | |
| "eval_samples_per_second": 10.095, | |
| "eval_steps_per_second": 1.266, | |
| "eval_wer": 0.39435188947582284, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_cer": 0.19494085532302094, | |
| "eval_loss": 0.6717579960823059, | |
| "eval_runtime": 53.8881, | |
| "eval_samples_per_second": 10.058, | |
| "eval_steps_per_second": 1.262, | |
| "eval_wer": 0.4012596505485575, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_cer": 0.19654231119199272, | |
| "eval_loss": 0.6830848455429077, | |
| "eval_runtime": 54.2951, | |
| "eval_samples_per_second": 9.982, | |
| "eval_steps_per_second": 1.252, | |
| "eval_wer": 0.3976026005688744, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_cer": 0.1916287534121929, | |
| "eval_loss": 0.6400262117385864, | |
| "eval_runtime": 53.8725, | |
| "eval_samples_per_second": 10.061, | |
| "eval_steps_per_second": 1.262, | |
| "eval_wer": 0.38703778951645673, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 57.14, | |
| "learning_rate": 1.8614285714285715e-05, | |
| "loss": 0.5799, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_cer": 0.19060964513193812, | |
| "eval_loss": 0.642275869846344, | |
| "eval_runtime": 53.5527, | |
| "eval_samples_per_second": 10.121, | |
| "eval_steps_per_second": 1.27, | |
| "eval_wer": 0.3843965867533523, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_cer": 0.19075523202911737, | |
| "eval_loss": 0.6394357681274414, | |
| "eval_runtime": 54.0972, | |
| "eval_samples_per_second": 10.019, | |
| "eval_steps_per_second": 1.257, | |
| "eval_wer": 0.38338073953677365, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_cer": 0.1924294813466788, | |
| "eval_loss": 0.6573936939239502, | |
| "eval_runtime": 53.9836, | |
| "eval_samples_per_second": 10.04, | |
| "eval_steps_per_second": 1.26, | |
| "eval_wer": 0.37850467289719625, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_cer": 0.19181073703366697, | |
| "eval_loss": 0.6321007013320923, | |
| "eval_runtime": 53.881, | |
| "eval_samples_per_second": 10.059, | |
| "eval_steps_per_second": 1.262, | |
| "eval_wer": 0.38155221454693217, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_cer": 0.19126478616924478, | |
| "eval_loss": 0.63057541847229, | |
| "eval_runtime": 53.9032, | |
| "eval_samples_per_second": 10.055, | |
| "eval_steps_per_second": 1.262, | |
| "eval_wer": 0.38013002844372207, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_cer": 0.1915923566878981, | |
| "eval_loss": 0.6432803869247437, | |
| "eval_runtime": 53.9619, | |
| "eval_samples_per_second": 10.044, | |
| "eval_steps_per_second": 1.26, | |
| "eval_wer": 0.37992685900040635, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_cer": 0.18955414012738853, | |
| "eval_loss": 0.6342417001724243, | |
| "eval_runtime": 53.7595, | |
| "eval_samples_per_second": 10.082, | |
| "eval_steps_per_second": 1.265, | |
| "eval_wer": 0.38114587566030067, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 64.29, | |
| "learning_rate": 1.7185714285714285e-05, | |
| "loss": 0.445, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_cer": 0.19042766151046406, | |
| "eval_loss": 0.6211907267570496, | |
| "eval_runtime": 53.9351, | |
| "eval_samples_per_second": 10.049, | |
| "eval_steps_per_second": 1.261, | |
| "eval_wer": 0.38114587566030067, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_cer": 0.1894813466787989, | |
| "eval_loss": 0.6164088249206543, | |
| "eval_runtime": 53.6257, | |
| "eval_samples_per_second": 10.107, | |
| "eval_steps_per_second": 1.268, | |
| "eval_wer": 0.3789110117838277, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_cer": 0.18715195632393083, | |
| "eval_loss": 0.6005796194076538, | |
| "eval_runtime": 53.6712, | |
| "eval_samples_per_second": 10.099, | |
| "eval_steps_per_second": 1.267, | |
| "eval_wer": 0.3732222673709874, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_cer": 0.18911737943585077, | |
| "eval_loss": 0.6054388880729675, | |
| "eval_runtime": 53.6435, | |
| "eval_samples_per_second": 10.104, | |
| "eval_steps_per_second": 1.268, | |
| "eval_wer": 0.3746444534741975, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_cer": 0.18940855323020928, | |
| "eval_loss": 0.6244754791259766, | |
| "eval_runtime": 53.8541, | |
| "eval_samples_per_second": 10.064, | |
| "eval_steps_per_second": 1.263, | |
| "eval_wer": 0.3722064201544088, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_cer": 0.1878070973612375, | |
| "eval_loss": 0.6090296506881714, | |
| "eval_runtime": 53.9168, | |
| "eval_samples_per_second": 10.053, | |
| "eval_steps_per_second": 1.261, | |
| "eval_wer": 0.36875253961804144, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_cer": 0.18758871701546861, | |
| "eval_loss": 0.6072561144828796, | |
| "eval_runtime": 53.6209, | |
| "eval_samples_per_second": 10.108, | |
| "eval_steps_per_second": 1.268, | |
| "eval_wer": 0.3669240146281999, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 71.43, | |
| "learning_rate": 1.5757142857142858e-05, | |
| "loss": 0.3746, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_cer": 0.18886260236578709, | |
| "eval_loss": 0.5989311337471008, | |
| "eval_runtime": 53.765, | |
| "eval_samples_per_second": 10.081, | |
| "eval_steps_per_second": 1.265, | |
| "eval_wer": 0.3707842340511987, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_cer": 0.18744313011828936, | |
| "eval_loss": 0.5967620611190796, | |
| "eval_runtime": 53.6159, | |
| "eval_samples_per_second": 10.109, | |
| "eval_steps_per_second": 1.268, | |
| "eval_wer": 0.3681430312880943, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_cer": 0.1870427661510464, | |
| "eval_loss": 0.5945658683776855, | |
| "eval_runtime": 53.8501, | |
| "eval_samples_per_second": 10.065, | |
| "eval_steps_per_second": 1.263, | |
| "eval_wer": 0.3659081674116213, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_cer": 0.18638762511373977, | |
| "eval_loss": 0.5873651504516602, | |
| "eval_runtime": 53.5608, | |
| "eval_samples_per_second": 10.119, | |
| "eval_steps_per_second": 1.27, | |
| "eval_wer": 0.3622511174319382, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_cer": 0.1870427661510464, | |
| "eval_loss": 0.5927525758743286, | |
| "eval_runtime": 53.7753, | |
| "eval_samples_per_second": 10.079, | |
| "eval_steps_per_second": 1.265, | |
| "eval_wer": 0.36387647297846404, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_cer": 0.18824385805277524, | |
| "eval_loss": 0.5889000296592712, | |
| "eval_runtime": 53.8481, | |
| "eval_samples_per_second": 10.065, | |
| "eval_steps_per_second": 1.263, | |
| "eval_wer": 0.3681430312880943, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_cer": 0.18635122838944496, | |
| "eval_loss": 0.5722672343254089, | |
| "eval_runtime": 53.9948, | |
| "eval_samples_per_second": 10.038, | |
| "eval_steps_per_second": 1.259, | |
| "eval_wer": 0.36834620073141, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 78.57, | |
| "learning_rate": 1.4328571428571428e-05, | |
| "loss": 0.3543, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_cer": 0.18627843494085533, | |
| "eval_loss": 0.5927807688713074, | |
| "eval_runtime": 53.7175, | |
| "eval_samples_per_second": 10.09, | |
| "eval_steps_per_second": 1.266, | |
| "eval_wer": 0.3657049979683056, | |
| "step": 1106 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_cer": 0.18547770700636942, | |
| "eval_loss": 0.583193838596344, | |
| "eval_runtime": 53.7886, | |
| "eval_samples_per_second": 10.076, | |
| "eval_steps_per_second": 1.264, | |
| "eval_wer": 0.36489232019504264, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_cer": 0.18493175614194723, | |
| "eval_loss": 0.5785495638847351, | |
| "eval_runtime": 53.8447, | |
| "eval_samples_per_second": 10.066, | |
| "eval_steps_per_second": 1.263, | |
| "eval_wer": 0.3644859813084112, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_cer": 0.18424021838034577, | |
| "eval_loss": 0.5877463817596436, | |
| "eval_runtime": 53.7471, | |
| "eval_samples_per_second": 10.084, | |
| "eval_steps_per_second": 1.265, | |
| "eval_wer": 0.35798455912230803, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_cer": 0.18525932666060055, | |
| "eval_loss": 0.5869647860527039, | |
| "eval_runtime": 53.8204, | |
| "eval_samples_per_second": 10.071, | |
| "eval_steps_per_second": 1.263, | |
| "eval_wer": 0.36265745631856966, | |
| "step": 1162 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_cer": 0.18456778889899908, | |
| "eval_loss": 0.5738150477409363, | |
| "eval_runtime": 53.9516, | |
| "eval_samples_per_second": 10.046, | |
| "eval_steps_per_second": 1.26, | |
| "eval_wer": 0.3618447785453068, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_cer": 0.18158325750682439, | |
| "eval_loss": 0.5640825033187866, | |
| "eval_runtime": 53.9077, | |
| "eval_samples_per_second": 10.054, | |
| "eval_steps_per_second": 1.261, | |
| "eval_wer": 0.35757822023567654, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 85.71, | |
| "learning_rate": 1.29e-05, | |
| "loss": 0.3207, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_cer": 0.18209281164695176, | |
| "eval_loss": 0.5727854371070862, | |
| "eval_runtime": 54.0413, | |
| "eval_samples_per_second": 10.029, | |
| "eval_steps_per_second": 1.258, | |
| "eval_wer": 0.35656237301909793, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_cer": 0.18169244767970882, | |
| "eval_loss": 0.5706486105918884, | |
| "eval_runtime": 54.0703, | |
| "eval_samples_per_second": 10.024, | |
| "eval_steps_per_second": 1.258, | |
| "eval_wer": 0.35595286468915077, | |
| "step": 1218 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_cer": 0.1813284804367607, | |
| "eval_loss": 0.5607408881187439, | |
| "eval_runtime": 54.3555, | |
| "eval_samples_per_second": 9.971, | |
| "eval_steps_per_second": 1.251, | |
| "eval_wer": 0.3569687119057294, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_cer": 0.181656050955414, | |
| "eval_loss": 0.56435227394104, | |
| "eval_runtime": 53.7806, | |
| "eval_samples_per_second": 10.078, | |
| "eval_steps_per_second": 1.264, | |
| "eval_wer": 0.35574969524583505, | |
| "step": 1246 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_cer": 0.1824203821656051, | |
| "eval_loss": 0.5659990310668945, | |
| "eval_runtime": 54.3449, | |
| "eval_samples_per_second": 9.973, | |
| "eval_steps_per_second": 1.251, | |
| "eval_wer": 0.35818772856562375, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_cer": 0.18285714285714286, | |
| "eval_loss": 0.5688397884368896, | |
| "eval_runtime": 53.7699, | |
| "eval_samples_per_second": 10.08, | |
| "eval_steps_per_second": 1.265, | |
| "eval_wer": 0.35656237301909793, | |
| "step": 1274 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_cer": 0.18074613284804367, | |
| "eval_loss": 0.563470184803009, | |
| "eval_runtime": 54.0176, | |
| "eval_samples_per_second": 10.034, | |
| "eval_steps_per_second": 1.259, | |
| "eval_wer": 0.35412433969930923, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 92.86, | |
| "learning_rate": 1.1471428571428572e-05, | |
| "loss": 0.2984, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_cer": 0.1813648771610555, | |
| "eval_loss": 0.5662950277328491, | |
| "eval_runtime": 54.0264, | |
| "eval_samples_per_second": 10.032, | |
| "eval_steps_per_second": 1.259, | |
| "eval_wer": 0.35026412027631043, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_cer": 0.18074613284804367, | |
| "eval_loss": 0.5514569282531738, | |
| "eval_runtime": 53.9373, | |
| "eval_samples_per_second": 10.049, | |
| "eval_steps_per_second": 1.261, | |
| "eval_wer": 0.35432750914262495, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_cer": 0.1802729754322111, | |
| "eval_loss": 0.5563488602638245, | |
| "eval_runtime": 54.0134, | |
| "eval_samples_per_second": 10.035, | |
| "eval_steps_per_second": 1.259, | |
| "eval_wer": 0.35168630637952053, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_cer": 0.18089171974522292, | |
| "eval_loss": 0.5617594122886658, | |
| "eval_runtime": 54.0211, | |
| "eval_samples_per_second": 10.033, | |
| "eval_steps_per_second": 1.259, | |
| "eval_wer": 0.3508736286062576, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_cer": 0.18074613284804367, | |
| "eval_loss": 0.5554497838020325, | |
| "eval_runtime": 54.2071, | |
| "eval_samples_per_second": 9.999, | |
| "eval_steps_per_second": 1.254, | |
| "eval_wer": 0.35168630637952053, | |
| "step": 1358 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_cer": 0.18092811646951773, | |
| "eval_loss": 0.5605758428573608, | |
| "eval_runtime": 53.9801, | |
| "eval_samples_per_second": 10.041, | |
| "eval_steps_per_second": 1.26, | |
| "eval_wer": 0.35290532303941485, | |
| "step": 1372 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_cer": 0.1813284804367607, | |
| "eval_loss": 0.5596539974212646, | |
| "eval_runtime": 53.7711, | |
| "eval_samples_per_second": 10.08, | |
| "eval_steps_per_second": 1.265, | |
| "eval_wer": 0.35107679804957337, | |
| "step": 1386 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 1.0042857142857144e-05, | |
| "loss": 0.2622, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_cer": 0.18121929026387626, | |
| "eval_loss": 0.5628100037574768, | |
| "eval_runtime": 53.9102, | |
| "eval_samples_per_second": 10.054, | |
| "eval_steps_per_second": 1.261, | |
| "eval_wer": 0.35046728971962615, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 101.0, | |
| "eval_cer": 0.17990900818926298, | |
| "eval_loss": 0.5564116835594177, | |
| "eval_runtime": 54.03, | |
| "eval_samples_per_second": 10.031, | |
| "eval_steps_per_second": 1.259, | |
| "eval_wer": 0.34945144250304755, | |
| "step": 1414 | |
| }, | |
| { | |
| "epoch": 102.0, | |
| "eval_cer": 0.18114649681528663, | |
| "eval_loss": 0.5625892877578735, | |
| "eval_runtime": 53.8963, | |
| "eval_samples_per_second": 10.056, | |
| "eval_steps_per_second": 1.262, | |
| "eval_wer": 0.3484355952864689, | |
| "step": 1428 | |
| }, | |
| { | |
| "epoch": 103.0, | |
| "eval_cer": 0.1799818016378526, | |
| "eval_loss": 0.5555956959724426, | |
| "eval_runtime": 54.0019, | |
| "eval_samples_per_second": 10.037, | |
| "eval_steps_per_second": 1.259, | |
| "eval_wer": 0.34701340918325885, | |
| "step": 1442 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "eval_cer": 0.1799454049135578, | |
| "eval_loss": 0.5602657198905945, | |
| "eval_runtime": 53.864, | |
| "eval_samples_per_second": 10.062, | |
| "eval_steps_per_second": 1.262, | |
| "eval_wer": 0.3464039008533117, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "eval_cer": 0.17987261146496816, | |
| "eval_loss": 0.5570572018623352, | |
| "eval_runtime": 53.8761, | |
| "eval_samples_per_second": 10.06, | |
| "eval_steps_per_second": 1.262, | |
| "eval_wer": 0.34538805363673303, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 106.0, | |
| "eval_cer": 0.17990900818926298, | |
| "eval_loss": 0.5618259310722351, | |
| "eval_runtime": 53.8537, | |
| "eval_samples_per_second": 10.064, | |
| "eval_steps_per_second": 1.263, | |
| "eval_wer": 0.3466070702966274, | |
| "step": 1484 | |
| }, | |
| { | |
| "epoch": 107.0, | |
| "eval_cer": 0.17867151956323932, | |
| "eval_loss": 0.5518925786018372, | |
| "eval_runtime": 54.2003, | |
| "eval_samples_per_second": 10.0, | |
| "eval_steps_per_second": 1.255, | |
| "eval_wer": 0.343965867533523, | |
| "step": 1498 | |
| }, | |
| { | |
| "epoch": 107.14, | |
| "learning_rate": 8.614285714285714e-06, | |
| "loss": 0.2519, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 108.0, | |
| "eval_cer": 0.17903548680618744, | |
| "eval_loss": 0.5540814399719238, | |
| "eval_runtime": 53.903, | |
| "eval_samples_per_second": 10.055, | |
| "eval_steps_per_second": 1.262, | |
| "eval_wer": 0.343965867533523, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 109.0, | |
| "eval_cer": 0.17939945404913557, | |
| "eval_loss": 0.557438850402832, | |
| "eval_runtime": 54.7258, | |
| "eval_samples_per_second": 9.904, | |
| "eval_steps_per_second": 1.243, | |
| "eval_wer": 0.3464039008533117, | |
| "step": 1526 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "eval_cer": 0.18009099181073704, | |
| "eval_loss": 0.5590262413024902, | |
| "eval_runtime": 54.0902, | |
| "eval_samples_per_second": 10.02, | |
| "eval_steps_per_second": 1.257, | |
| "eval_wer": 0.34538805363673303, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 111.0, | |
| "eval_cer": 0.17958143767060963, | |
| "eval_loss": 0.5529592633247375, | |
| "eval_runtime": 53.9289, | |
| "eval_samples_per_second": 10.05, | |
| "eval_steps_per_second": 1.261, | |
| "eval_wer": 0.34477854530678587, | |
| "step": 1554 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "eval_cer": 0.1791810737033667, | |
| "eval_loss": 0.5500696301460266, | |
| "eval_runtime": 53.992, | |
| "eval_samples_per_second": 10.039, | |
| "eval_steps_per_second": 1.259, | |
| "eval_wer": 0.3437626980902072, | |
| "step": 1568 | |
| }, | |
| { | |
| "epoch": 113.0, | |
| "eval_cer": 0.17990900818926298, | |
| "eval_loss": 0.5595071911811829, | |
| "eval_runtime": 54.515, | |
| "eval_samples_per_second": 9.942, | |
| "eval_steps_per_second": 1.247, | |
| "eval_wer": 0.34477854530678587, | |
| "step": 1582 | |
| }, | |
| { | |
| "epoch": 114.0, | |
| "eval_cer": 0.18005459508644223, | |
| "eval_loss": 0.5535922646522522, | |
| "eval_runtime": 53.9067, | |
| "eval_samples_per_second": 10.054, | |
| "eval_steps_per_second": 1.261, | |
| "eval_wer": 0.34457537586347015, | |
| "step": 1596 | |
| }, | |
| { | |
| "epoch": 114.29, | |
| "learning_rate": 7.185714285714286e-06, | |
| "loss": 0.245, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 115.0, | |
| "eval_cer": 0.1788898999090082, | |
| "eval_loss": 0.5480047464370728, | |
| "eval_runtime": 53.9861, | |
| "eval_samples_per_second": 10.04, | |
| "eval_steps_per_second": 1.26, | |
| "eval_wer": 0.34315318976026005, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 116.0, | |
| "eval_cer": 0.17979981801637854, | |
| "eval_loss": 0.562286913394928, | |
| "eval_runtime": 53.656, | |
| "eval_samples_per_second": 10.101, | |
| "eval_steps_per_second": 1.267, | |
| "eval_wer": 0.34863876472978467, | |
| "step": 1624 | |
| }, | |
| { | |
| "epoch": 117.0, | |
| "eval_cer": 0.17903548680618744, | |
| "eval_loss": 0.549622118473053, | |
| "eval_runtime": 53.5772, | |
| "eval_samples_per_second": 10.116, | |
| "eval_steps_per_second": 1.269, | |
| "eval_wer": 0.3427468508736286, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 118.0, | |
| "eval_cer": 0.17885350318471338, | |
| "eval_loss": 0.5551720857620239, | |
| "eval_runtime": 53.9431, | |
| "eval_samples_per_second": 10.048, | |
| "eval_steps_per_second": 1.261, | |
| "eval_wer": 0.34213734254368144, | |
| "step": 1652 | |
| }, | |
| { | |
| "epoch": 119.0, | |
| "eval_cer": 0.17867151956323932, | |
| "eval_loss": 0.5557767152786255, | |
| "eval_runtime": 54.2974, | |
| "eval_samples_per_second": 9.982, | |
| "eval_steps_per_second": 1.252, | |
| "eval_wer": 0.3437626980902072, | |
| "step": 1666 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "eval_cer": 0.17834394904458598, | |
| "eval_loss": 0.552444338798523, | |
| "eval_runtime": 53.9105, | |
| "eval_samples_per_second": 10.054, | |
| "eval_steps_per_second": 1.261, | |
| "eval_wer": 0.3425436814303129, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 121.0, | |
| "eval_cer": 0.1785987261146497, | |
| "eval_loss": 0.5581905841827393, | |
| "eval_runtime": 53.9834, | |
| "eval_samples_per_second": 10.04, | |
| "eval_steps_per_second": 1.26, | |
| "eval_wer": 0.34213734254368144, | |
| "step": 1694 | |
| }, | |
| { | |
| "epoch": 121.43, | |
| "learning_rate": 5.7571428571428574e-06, | |
| "loss": 0.2322, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 122.0, | |
| "eval_cer": 0.17856232939035488, | |
| "eval_loss": 0.5533866286277771, | |
| "eval_runtime": 54.0755, | |
| "eval_samples_per_second": 10.023, | |
| "eval_steps_per_second": 1.258, | |
| "eval_wer": 0.3425436814303129, | |
| "step": 1708 | |
| }, | |
| { | |
| "epoch": 123.0, | |
| "eval_cer": 0.18012738853503185, | |
| "eval_loss": 0.5595676302909851, | |
| "eval_runtime": 53.7843, | |
| "eval_samples_per_second": 10.077, | |
| "eval_steps_per_second": 1.264, | |
| "eval_wer": 0.3464039008533117, | |
| "step": 1722 | |
| }, | |
| { | |
| "epoch": 124.0, | |
| "eval_cer": 0.17899909008189263, | |
| "eval_loss": 0.5486122369766235, | |
| "eval_runtime": 53.9909, | |
| "eval_samples_per_second": 10.039, | |
| "eval_steps_per_second": 1.259, | |
| "eval_wer": 0.34315318976026005, | |
| "step": 1736 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "eval_cer": 0.1792174704276615, | |
| "eval_loss": 0.5580961108207703, | |
| "eval_runtime": 53.9973, | |
| "eval_samples_per_second": 10.038, | |
| "eval_steps_per_second": 1.259, | |
| "eval_wer": 0.3425436814303129, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 126.0, | |
| "eval_cer": 0.17852593266606007, | |
| "eval_loss": 0.5470190644264221, | |
| "eval_runtime": 53.6657, | |
| "eval_samples_per_second": 10.1, | |
| "eval_steps_per_second": 1.267, | |
| "eval_wer": 0.34173100365705, | |
| "step": 1764 | |
| }, | |
| { | |
| "epoch": 127.0, | |
| "eval_cer": 0.17805277525022747, | |
| "eval_loss": 0.5543853640556335, | |
| "eval_runtime": 53.9507, | |
| "eval_samples_per_second": 10.046, | |
| "eval_steps_per_second": 1.26, | |
| "eval_wer": 0.3413246647704185, | |
| "step": 1778 | |
| }, | |
| { | |
| "epoch": 128.0, | |
| "eval_cer": 0.1780891719745223, | |
| "eval_loss": 0.5500943660736084, | |
| "eval_runtime": 53.7085, | |
| "eval_samples_per_second": 10.092, | |
| "eval_steps_per_second": 1.266, | |
| "eval_wer": 0.3435595286468915, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 128.57, | |
| "learning_rate": 4.328571428571429e-06, | |
| "loss": 0.2324, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 129.0, | |
| "eval_cer": 0.1781619654231119, | |
| "eval_loss": 0.5517907738685608, | |
| "eval_runtime": 54.1553, | |
| "eval_samples_per_second": 10.008, | |
| "eval_steps_per_second": 1.256, | |
| "eval_wer": 0.343965867533523, | |
| "step": 1806 | |
| }, | |
| { | |
| "epoch": 130.0, | |
| "eval_cer": 0.1775432211101001, | |
| "eval_loss": 0.551121711730957, | |
| "eval_runtime": 54.0869, | |
| "eval_samples_per_second": 10.021, | |
| "eval_steps_per_second": 1.257, | |
| "eval_wer": 0.3388866314506298, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 131.0, | |
| "eval_cer": 0.17823475887170154, | |
| "eval_loss": 0.5584121942520142, | |
| "eval_runtime": 54.0126, | |
| "eval_samples_per_second": 10.035, | |
| "eval_steps_per_second": 1.259, | |
| "eval_wer": 0.34173100365705, | |
| "step": 1834 | |
| }, | |
| { | |
| "epoch": 132.0, | |
| "eval_cer": 0.17747042766151047, | |
| "eval_loss": 0.549301028251648, | |
| "eval_runtime": 54.1977, | |
| "eval_samples_per_second": 10.0, | |
| "eval_steps_per_second": 1.255, | |
| "eval_wer": 0.33726127590410404, | |
| "step": 1848 | |
| }, | |
| { | |
| "epoch": 133.0, | |
| "eval_cer": 0.17768880800727935, | |
| "eval_loss": 0.5506242513656616, | |
| "eval_runtime": 54.3838, | |
| "eval_samples_per_second": 9.966, | |
| "eval_steps_per_second": 1.25, | |
| "eval_wer": 0.339496139780577, | |
| "step": 1862 | |
| }, | |
| { | |
| "epoch": 134.0, | |
| "eval_cer": 0.1781619654231119, | |
| "eval_loss": 0.5543136596679688, | |
| "eval_runtime": 53.8876, | |
| "eval_samples_per_second": 10.058, | |
| "eval_steps_per_second": 1.262, | |
| "eval_wer": 0.34091832588378707, | |
| "step": 1876 | |
| }, | |
| { | |
| "epoch": 135.0, | |
| "eval_cer": 0.17805277525022747, | |
| "eval_loss": 0.5588898062705994, | |
| "eval_runtime": 53.8452, | |
| "eval_samples_per_second": 10.066, | |
| "eval_steps_per_second": 1.263, | |
| "eval_wer": 0.33990247866720846, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 135.71, | |
| "learning_rate": 2.9e-06, | |
| "loss": 0.2077, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 136.0, | |
| "eval_cer": 0.17776160145586897, | |
| "eval_loss": 0.5555850267410278, | |
| "eval_runtime": 54.3429, | |
| "eval_samples_per_second": 9.974, | |
| "eval_steps_per_second": 1.251, | |
| "eval_wer": 0.3390898008939455, | |
| "step": 1904 | |
| }, | |
| { | |
| "epoch": 137.0, | |
| "eval_cer": 0.17779799818016379, | |
| "eval_loss": 0.5555258393287659, | |
| "eval_runtime": 53.6523, | |
| "eval_samples_per_second": 10.102, | |
| "eval_steps_per_second": 1.267, | |
| "eval_wer": 0.34071515644047135, | |
| "step": 1918 | |
| }, | |
| { | |
| "epoch": 138.0, | |
| "eval_cer": 0.17739763421292085, | |
| "eval_loss": 0.5501488447189331, | |
| "eval_runtime": 53.6556, | |
| "eval_samples_per_second": 10.101, | |
| "eval_steps_per_second": 1.267, | |
| "eval_wer": 0.3390898008939455, | |
| "step": 1932 | |
| }, | |
| { | |
| "epoch": 139.0, | |
| "eval_cer": 0.17721565059144678, | |
| "eval_loss": 0.5544245839118958, | |
| "eval_runtime": 54.0174, | |
| "eval_samples_per_second": 10.034, | |
| "eval_steps_per_second": 1.259, | |
| "eval_wer": 0.33746444534741976, | |
| "step": 1946 | |
| }, | |
| { | |
| "epoch": 140.0, | |
| "eval_cer": 0.17732484076433122, | |
| "eval_loss": 0.5553618669509888, | |
| "eval_runtime": 54.2475, | |
| "eval_samples_per_second": 9.991, | |
| "eval_steps_per_second": 1.254, | |
| "eval_wer": 0.3386834620073141, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 141.0, | |
| "eval_cer": 0.17721565059144678, | |
| "eval_loss": 0.5504088401794434, | |
| "eval_runtime": 54.07, | |
| "eval_samples_per_second": 10.024, | |
| "eval_steps_per_second": 1.258, | |
| "eval_wer": 0.3380739536773669, | |
| "step": 1974 | |
| }, | |
| { | |
| "epoch": 142.0, | |
| "eval_cer": 0.17699727024567788, | |
| "eval_loss": 0.5484427809715271, | |
| "eval_runtime": 54.0621, | |
| "eval_samples_per_second": 10.026, | |
| "eval_steps_per_second": 1.258, | |
| "eval_wer": 0.33827712312068264, | |
| "step": 1988 | |
| }, | |
| { | |
| "epoch": 142.86, | |
| "learning_rate": 1.4714285714285716e-06, | |
| "loss": 0.2089, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 143.0, | |
| "eval_cer": 0.17721565059144678, | |
| "eval_loss": 0.5519289374351501, | |
| "eval_runtime": 54.2165, | |
| "eval_samples_per_second": 9.997, | |
| "eval_steps_per_second": 1.254, | |
| "eval_wer": 0.33848029256399836, | |
| "step": 2002 | |
| }, | |
| { | |
| "epoch": 144.0, | |
| "eval_cer": 0.17721565059144678, | |
| "eval_loss": 0.5531746745109558, | |
| "eval_runtime": 54.0827, | |
| "eval_samples_per_second": 10.022, | |
| "eval_steps_per_second": 1.257, | |
| "eval_wer": 0.3390898008939455, | |
| "step": 2016 | |
| }, | |
| { | |
| "epoch": 145.0, | |
| "eval_cer": 0.17747042766151047, | |
| "eval_loss": 0.5529664158821106, | |
| "eval_runtime": 54.0306, | |
| "eval_samples_per_second": 10.031, | |
| "eval_steps_per_second": 1.259, | |
| "eval_wer": 0.33969930922389274, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 146.0, | |
| "eval_cer": 0.1775432211101001, | |
| "eval_loss": 0.5551361441612244, | |
| "eval_runtime": 54.0882, | |
| "eval_samples_per_second": 10.021, | |
| "eval_steps_per_second": 1.257, | |
| "eval_wer": 0.33969930922389274, | |
| "step": 2044 | |
| }, | |
| { | |
| "epoch": 146.0, | |
| "step": 2044, | |
| "total_flos": 1.8244410804942518e+19, | |
| "train_loss": 1.3513914437676595, | |
| "train_runtime": 31402.8433, | |
| "train_samples_per_second": 2.14, | |
| "train_steps_per_second": 0.067 | |
| } | |
| ], | |
| "max_steps": 2100, | |
| "num_train_epochs": 150, | |
| "total_flos": 1.8244410804942518e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |