| { | |
| "best_metric": 0.5485906004905701, | |
| "best_model_checkpoint": "wav2vec2-large-xlsr-coraa-exp-17/checkpoint-1358", | |
| "epoch": 117.0, | |
| "global_step": 1638, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0, | |
| "loss": 38.4208, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_cer": 1.2145950864422201, | |
| "eval_loss": 41.80952453613281, | |
| "eval_per": 1.0056887444128404, | |
| "eval_runtime": 16.4211, | |
| "eval_samples_per_second": 33.006, | |
| "eval_steps_per_second": 4.141, | |
| "eval_wer": 1.0056887444128404, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 12.287281036376953, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.3942, | |
| "eval_samples_per_second": 33.06, | |
| "eval_steps_per_second": 4.148, | |
| "eval_wer": 1.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 4.809342861175537, | |
| "eval_per": 1.0, | |
| "eval_runtime": 17.8009, | |
| "eval_samples_per_second": 30.448, | |
| "eval_steps_per_second": 3.82, | |
| "eval_wer": 1.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.9737813472747803, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.1587, | |
| "eval_samples_per_second": 33.542, | |
| "eval_steps_per_second": 4.208, | |
| "eval_wer": 1.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.6683900356292725, | |
| "eval_per": 1.0, | |
| "eval_runtime": 17.3608, | |
| "eval_samples_per_second": 31.22, | |
| "eval_steps_per_second": 3.917, | |
| "eval_wer": 1.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.5007262229919434, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.8377, | |
| "eval_samples_per_second": 32.19, | |
| "eval_steps_per_second": 4.039, | |
| "eval_wer": 1.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.3854148387908936, | |
| "eval_per": 1.0, | |
| "eval_runtime": 15.8896, | |
| "eval_samples_per_second": 34.11, | |
| "eval_steps_per_second": 4.28, | |
| "eval_wer": 1.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 3.853775853775854e-05, | |
| "loss": 11.8009, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.450645923614502, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.3597, | |
| "eval_samples_per_second": 33.13, | |
| "eval_steps_per_second": 4.157, | |
| "eval_wer": 1.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.178906202316284, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.1702, | |
| "eval_samples_per_second": 33.519, | |
| "eval_steps_per_second": 4.205, | |
| "eval_wer": 1.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.1274373531341553, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.9804, | |
| "eval_samples_per_second": 31.919, | |
| "eval_steps_per_second": 4.005, | |
| "eval_wer": 1.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.1624248027801514, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.0626, | |
| "eval_samples_per_second": 33.743, | |
| "eval_steps_per_second": 4.233, | |
| "eval_wer": 1.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.1065869331359863, | |
| "eval_per": 1.0, | |
| "eval_runtime": 15.7377, | |
| "eval_samples_per_second": 34.44, | |
| "eval_steps_per_second": 4.321, | |
| "eval_wer": 1.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0579798221588135, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.1086, | |
| "eval_samples_per_second": 33.647, | |
| "eval_steps_per_second": 4.221, | |
| "eval_wer": 1.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0477194786071777, | |
| "eval_per": 1.0, | |
| "eval_runtime": 17.7392, | |
| "eval_samples_per_second": 30.554, | |
| "eval_steps_per_second": 3.833, | |
| "eval_wer": 1.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 3.6613756613756616e-05, | |
| "loss": 3.0395, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.051933526992798, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.5102, | |
| "eval_samples_per_second": 32.828, | |
| "eval_steps_per_second": 4.119, | |
| "eval_wer": 1.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0363881587982178, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.6774, | |
| "eval_samples_per_second": 32.499, | |
| "eval_steps_per_second": 4.077, | |
| "eval_wer": 1.0, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.015160083770752, | |
| "eval_per": 1.0, | |
| "eval_runtime": 17.0522, | |
| "eval_samples_per_second": 31.785, | |
| "eval_steps_per_second": 3.988, | |
| "eval_wer": 1.0, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0166876316070557, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.1958, | |
| "eval_samples_per_second": 33.465, | |
| "eval_steps_per_second": 4.199, | |
| "eval_wer": 1.0, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0129683017730713, | |
| "eval_per": 1.0, | |
| "eval_runtime": 17.0594, | |
| "eval_samples_per_second": 31.771, | |
| "eval_steps_per_second": 3.986, | |
| "eval_wer": 1.0, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0103399753570557, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.6483, | |
| "eval_samples_per_second": 32.556, | |
| "eval_steps_per_second": 4.084, | |
| "eval_wer": 1.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.9993834495544434, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.1419, | |
| "eval_samples_per_second": 33.577, | |
| "eval_steps_per_second": 4.213, | |
| "eval_wer": 1.0, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "learning_rate": 3.468975468975469e-05, | |
| "loss": 2.9424, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.999858856201172, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.4633, | |
| "eval_samples_per_second": 32.922, | |
| "eval_steps_per_second": 4.13, | |
| "eval_wer": 1.0, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.000885486602783, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.4157, | |
| "eval_samples_per_second": 33.017, | |
| "eval_steps_per_second": 4.142, | |
| "eval_wer": 1.0, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.002438545227051, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.3396, | |
| "eval_samples_per_second": 33.171, | |
| "eval_steps_per_second": 4.162, | |
| "eval_wer": 1.0, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.000091552734375, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.2524, | |
| "eval_samples_per_second": 33.349, | |
| "eval_steps_per_second": 4.184, | |
| "eval_wer": 1.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.989057779312134, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.9129, | |
| "eval_samples_per_second": 32.047, | |
| "eval_steps_per_second": 4.021, | |
| "eval_wer": 1.0, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.988072633743286, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.8979, | |
| "eval_samples_per_second": 32.075, | |
| "eval_steps_per_second": 4.024, | |
| "eval_wer": 1.0, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.97031569480896, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.5706, | |
| "eval_samples_per_second": 32.708, | |
| "eval_steps_per_second": 4.104, | |
| "eval_wer": 1.0, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 3.276575276575277e-05, | |
| "loss": 2.9154, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.9531471729278564, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.0162, | |
| "eval_samples_per_second": 33.841, | |
| "eval_steps_per_second": 4.246, | |
| "eval_wer": 1.0, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.920755624771118, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.2922, | |
| "eval_samples_per_second": 33.267, | |
| "eval_steps_per_second": 4.174, | |
| "eval_wer": 1.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.898137331008911, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.1037, | |
| "eval_samples_per_second": 33.657, | |
| "eval_steps_per_second": 4.223, | |
| "eval_wer": 1.0, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.8320581912994385, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.1007, | |
| "eval_samples_per_second": 33.663, | |
| "eval_steps_per_second": 4.223, | |
| "eval_wer": 1.0, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.7583184242248535, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.3232, | |
| "eval_samples_per_second": 33.204, | |
| "eval_steps_per_second": 4.166, | |
| "eval_wer": 1.0, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_cer": 0.9616014558689718, | |
| "eval_loss": 2.6405322551727295, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.4064, | |
| "eval_samples_per_second": 33.036, | |
| "eval_steps_per_second": 4.145, | |
| "eval_wer": 1.0, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_cer": 0.8832029117379436, | |
| "eval_loss": 2.5071756839752197, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.3137, | |
| "eval_samples_per_second": 33.224, | |
| "eval_steps_per_second": 4.168, | |
| "eval_wer": 1.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 35.71, | |
| "learning_rate": 3.0841750841750846e-05, | |
| "loss": 2.7552, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_cer": 0.6144131028207461, | |
| "eval_loss": 2.1546847820281982, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.1444, | |
| "eval_samples_per_second": 33.572, | |
| "eval_steps_per_second": 4.212, | |
| "eval_wer": 1.0, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_cer": 0.49958143767060964, | |
| "eval_loss": 1.7564772367477417, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.6494, | |
| "eval_samples_per_second": 32.554, | |
| "eval_steps_per_second": 4.084, | |
| "eval_wer": 1.0, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_cer": 0.40651501364877163, | |
| "eval_loss": 1.460233211517334, | |
| "eval_per": 1.0, | |
| "eval_runtime": 16.6864, | |
| "eval_samples_per_second": 32.482, | |
| "eval_steps_per_second": 4.075, | |
| "eval_wer": 1.0, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_cer": 0.36578707916287534, | |
| "eval_loss": 1.2268937826156616, | |
| "eval_per": 0.9892320195042665, | |
| "eval_runtime": 16.8505, | |
| "eval_samples_per_second": 32.165, | |
| "eval_steps_per_second": 4.035, | |
| "eval_wer": 0.989638358390898, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_cer": 0.3204731574158326, | |
| "eval_loss": 1.0905884504318237, | |
| "eval_per": 0.8833807395367737, | |
| "eval_runtime": 16.8204, | |
| "eval_samples_per_second": 32.223, | |
| "eval_steps_per_second": 4.043, | |
| "eval_wer": 0.8880536367330354, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_cer": 0.26314831665150135, | |
| "eval_loss": 0.9941390752792358, | |
| "eval_per": 0.6603006907761073, | |
| "eval_runtime": 16.4361, | |
| "eval_samples_per_second": 32.976, | |
| "eval_steps_per_second": 4.137, | |
| "eval_wer": 0.6771637545713125, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_cer": 0.23221110100090991, | |
| "eval_loss": 0.9132717847824097, | |
| "eval_per": 0.5154408776919951, | |
| "eval_runtime": 16.9668, | |
| "eval_samples_per_second": 31.945, | |
| "eval_steps_per_second": 4.008, | |
| "eval_wer": 0.5422592442096709, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 42.86, | |
| "learning_rate": 2.8917748917748916e-05, | |
| "loss": 1.4599, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_cer": 0.22413102820746134, | |
| "eval_loss": 0.8487069010734558, | |
| "eval_per": 0.48821617228768793, | |
| "eval_runtime": 16.6557, | |
| "eval_samples_per_second": 32.541, | |
| "eval_steps_per_second": 4.083, | |
| "eval_wer": 0.5142218610321008, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_cer": 0.22074613284804367, | |
| "eval_loss": 0.8211185336112976, | |
| "eval_per": 0.46261682242990654, | |
| "eval_runtime": 16.0355, | |
| "eval_samples_per_second": 33.8, | |
| "eval_steps_per_second": 4.241, | |
| "eval_wer": 0.48984152783421375, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_cer": 0.214049135577798, | |
| "eval_loss": 0.7671909332275391, | |
| "eval_per": 0.4518488419341731, | |
| "eval_runtime": 16.1929, | |
| "eval_samples_per_second": 33.471, | |
| "eval_steps_per_second": 4.199, | |
| "eval_wer": 0.48029256399837467, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_cer": 0.2092083712465878, | |
| "eval_loss": 0.7431579828262329, | |
| "eval_per": 0.44453474197480697, | |
| "eval_runtime": 16.359, | |
| "eval_samples_per_second": 33.132, | |
| "eval_steps_per_second": 4.157, | |
| "eval_wer": 0.4707436001625356, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_cer": 0.2059326660600546, | |
| "eval_loss": 0.7389556765556335, | |
| "eval_per": 0.42624949207639173, | |
| "eval_runtime": 16.6785, | |
| "eval_samples_per_second": 32.497, | |
| "eval_steps_per_second": 4.077, | |
| "eval_wer": 0.44920763917106865, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_cer": 0.2011282984531392, | |
| "eval_loss": 0.699397087097168, | |
| "eval_per": 0.41060544494108087, | |
| "eval_runtime": 16.5887, | |
| "eval_samples_per_second": 32.673, | |
| "eval_steps_per_second": 4.099, | |
| "eval_wer": 0.43478260869565216, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_cer": 0.19909008189262967, | |
| "eval_loss": 0.6998735070228577, | |
| "eval_per": 0.3998374644453474, | |
| "eval_runtime": 16.3728, | |
| "eval_samples_per_second": 33.104, | |
| "eval_steps_per_second": 4.153, | |
| "eval_wer": 0.4229987809833401, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 2.6993746993746993e-05, | |
| "loss": 0.7585, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_cer": 0.19588717015468607, | |
| "eval_loss": 0.6737520098686218, | |
| "eval_per": 0.38825680617635105, | |
| "eval_runtime": 16.7385, | |
| "eval_samples_per_second": 32.38, | |
| "eval_steps_per_second": 4.062, | |
| "eval_wer": 0.4122308004876067, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_cer": 0.19628753412192904, | |
| "eval_loss": 0.6696569919586182, | |
| "eval_per": 0.38581877285656235, | |
| "eval_runtime": 16.5913, | |
| "eval_samples_per_second": 32.668, | |
| "eval_steps_per_second": 4.099, | |
| "eval_wer": 0.4093864282811865, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_cer": 0.19963603275705186, | |
| "eval_loss": 0.6706883907318115, | |
| "eval_per": 0.39536773669240144, | |
| "eval_runtime": 18.473, | |
| "eval_samples_per_second": 29.34, | |
| "eval_steps_per_second": 3.681, | |
| "eval_wer": 0.41629418935392115, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_cer": 0.19417652411282985, | |
| "eval_loss": 0.6397454738616943, | |
| "eval_per": 0.38317757009345793, | |
| "eval_runtime": 16.3057, | |
| "eval_samples_per_second": 33.24, | |
| "eval_steps_per_second": 4.17, | |
| "eval_wer": 0.40308817553839904, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_cer": 0.19388535031847134, | |
| "eval_loss": 0.6293218731880188, | |
| "eval_per": 0.38358390898008937, | |
| "eval_runtime": 16.6245, | |
| "eval_samples_per_second": 32.603, | |
| "eval_steps_per_second": 4.09, | |
| "eval_wer": 0.4039008533116619, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_cer": 0.19457688808007279, | |
| "eval_loss": 0.6479354500770569, | |
| "eval_per": 0.3852092645266152, | |
| "eval_runtime": 17.0356, | |
| "eval_samples_per_second": 31.816, | |
| "eval_steps_per_second": 3.992, | |
| "eval_wer": 0.4026818366517676, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_cer": 0.19344858962693356, | |
| "eval_loss": 0.6307466626167297, | |
| "eval_per": 0.38216172287687933, | |
| "eval_runtime": 15.9943, | |
| "eval_samples_per_second": 33.887, | |
| "eval_steps_per_second": 4.252, | |
| "eval_wer": 0.39821210889882164, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_cer": 0.190828025477707, | |
| "eval_loss": 0.6166068911552429, | |
| "eval_per": 0.36733035351483134, | |
| "eval_runtime": 18.3763, | |
| "eval_samples_per_second": 29.495, | |
| "eval_steps_per_second": 3.7, | |
| "eval_wer": 0.3843965867533523, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 57.14, | |
| "learning_rate": 2.506974506974507e-05, | |
| "loss": 0.5473, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_cer": 0.19064604185623293, | |
| "eval_loss": 0.6098698377609253, | |
| "eval_per": 0.3707842340511987, | |
| "eval_runtime": 17.7821, | |
| "eval_samples_per_second": 30.48, | |
| "eval_steps_per_second": 3.824, | |
| "eval_wer": 0.3860219422998781, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_cer": 0.19039126478616925, | |
| "eval_loss": 0.6007358431816101, | |
| "eval_per": 0.3730190979276717, | |
| "eval_runtime": 17.0728, | |
| "eval_samples_per_second": 31.746, | |
| "eval_steps_per_second": 3.983, | |
| "eval_wer": 0.386834620073141, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_cer": 0.19275705186533212, | |
| "eval_loss": 0.6191249489784241, | |
| "eval_per": 0.3744412840308818, | |
| "eval_runtime": 16.4977, | |
| "eval_samples_per_second": 32.853, | |
| "eval_steps_per_second": 4.122, | |
| "eval_wer": 0.3884599756196668, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_cer": 0.1891901728844404, | |
| "eval_loss": 0.6014622449874878, | |
| "eval_per": 0.3732222673709874, | |
| "eval_runtime": 16.6101, | |
| "eval_samples_per_second": 32.631, | |
| "eval_steps_per_second": 4.094, | |
| "eval_wer": 0.3884599756196668, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_cer": 0.19017288444040037, | |
| "eval_loss": 0.5964884757995605, | |
| "eval_per": 0.36875253961804144, | |
| "eval_runtime": 17.8493, | |
| "eval_samples_per_second": 30.365, | |
| "eval_steps_per_second": 3.81, | |
| "eval_wer": 0.3837870784234051, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_cer": 0.19042766151046406, | |
| "eval_loss": 0.5926450490951538, | |
| "eval_per": 0.3667208451848842, | |
| "eval_runtime": 17.884, | |
| "eval_samples_per_second": 30.306, | |
| "eval_steps_per_second": 3.802, | |
| "eval_wer": 0.38256806176351077, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_cer": 0.19210191082802547, | |
| "eval_loss": 0.6187658905982971, | |
| "eval_per": 0.376472978464039, | |
| "eval_runtime": 17.0859, | |
| "eval_samples_per_second": 31.722, | |
| "eval_steps_per_second": 3.98, | |
| "eval_wer": 0.39211702559934986, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 64.29, | |
| "learning_rate": 2.3145743145743147e-05, | |
| "loss": 0.443, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_cer": 0.1891537761601456, | |
| "eval_loss": 0.5834715366363525, | |
| "eval_per": 0.36895570906135716, | |
| "eval_runtime": 16.6058, | |
| "eval_samples_per_second": 32.639, | |
| "eval_steps_per_second": 4.095, | |
| "eval_wer": 0.3829744006501422, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_cer": 0.1902820746132848, | |
| "eval_loss": 0.5914222598075867, | |
| "eval_per": 0.3722064201544088, | |
| "eval_runtime": 17.2325, | |
| "eval_samples_per_second": 31.452, | |
| "eval_steps_per_second": 3.946, | |
| "eval_wer": 0.38703778951645673, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_cer": 0.1875523202911738, | |
| "eval_loss": 0.582801878452301, | |
| "eval_per": 0.36265745631856966, | |
| "eval_runtime": 16.3441, | |
| "eval_samples_per_second": 33.162, | |
| "eval_steps_per_second": 4.161, | |
| "eval_wer": 0.3778951645672491, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_cer": 0.1857324840764331, | |
| "eval_loss": 0.5744664072990417, | |
| "eval_per": 0.35757822023567654, | |
| "eval_runtime": 17.4764, | |
| "eval_samples_per_second": 31.013, | |
| "eval_steps_per_second": 3.891, | |
| "eval_wer": 0.3722064201544088, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_cer": 0.18817106460418562, | |
| "eval_loss": 0.5785911083221436, | |
| "eval_per": 0.3632669646485169, | |
| "eval_runtime": 16.8602, | |
| "eval_samples_per_second": 32.147, | |
| "eval_steps_per_second": 4.033, | |
| "eval_wer": 0.3795205201137749, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_cer": 0.1884258416742493, | |
| "eval_loss": 0.5868948698043823, | |
| "eval_per": 0.36042259244209673, | |
| "eval_runtime": 16.384, | |
| "eval_samples_per_second": 33.081, | |
| "eval_steps_per_second": 4.15, | |
| "eval_wer": 0.37505079236082894, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_cer": 0.18878980891719746, | |
| "eval_loss": 0.592288076877594, | |
| "eval_per": 0.3596099146688338, | |
| "eval_runtime": 16.4263, | |
| "eval_samples_per_second": 32.996, | |
| "eval_steps_per_second": 4.14, | |
| "eval_wer": 0.37525396180414466, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 71.43, | |
| "learning_rate": 2.1221741221741224e-05, | |
| "loss": 0.3564, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_cer": 0.18587807097361236, | |
| "eval_loss": 0.5706638097763062, | |
| "eval_per": 0.35778138967899226, | |
| "eval_runtime": 16.3727, | |
| "eval_samples_per_second": 33.104, | |
| "eval_steps_per_second": 4.153, | |
| "eval_wer": 0.37139374238114586, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_cer": 0.1856960873521383, | |
| "eval_loss": 0.5733203887939453, | |
| "eval_per": 0.35514018691588783, | |
| "eval_runtime": 16.1456, | |
| "eval_samples_per_second": 33.569, | |
| "eval_steps_per_second": 4.212, | |
| "eval_wer": 0.3699715562779358, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_cer": 0.1854413102820746, | |
| "eval_loss": 0.5731407403945923, | |
| "eval_per": 0.35656237301909793, | |
| "eval_runtime": 16.2817, | |
| "eval_samples_per_second": 33.289, | |
| "eval_steps_per_second": 4.176, | |
| "eval_wer": 0.370581064607883, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_cer": 0.18467697907188352, | |
| "eval_loss": 0.5643908381462097, | |
| "eval_per": 0.3531084924827306, | |
| "eval_runtime": 16.6661, | |
| "eval_samples_per_second": 32.521, | |
| "eval_steps_per_second": 4.08, | |
| "eval_wer": 0.3669240146281999, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_cer": 0.18522292993630574, | |
| "eval_loss": 0.5660921335220337, | |
| "eval_per": 0.3555465258025193, | |
| "eval_runtime": 16.5118, | |
| "eval_samples_per_second": 32.825, | |
| "eval_steps_per_second": 4.118, | |
| "eval_wer": 0.37017472572125154, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_cer": 0.18474977252047317, | |
| "eval_loss": 0.5705360174179077, | |
| "eval_per": 0.3512799674928891, | |
| "eval_runtime": 17.1186, | |
| "eval_samples_per_second": 31.661, | |
| "eval_steps_per_second": 3.972, | |
| "eval_wer": 0.3675335229581471, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_cer": 0.1835122838944495, | |
| "eval_loss": 0.5630640983581543, | |
| "eval_per": 0.35270215359609913, | |
| "eval_runtime": 17.2728, | |
| "eval_samples_per_second": 31.379, | |
| "eval_steps_per_second": 3.937, | |
| "eval_wer": 0.3671271840715156, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 78.57, | |
| "learning_rate": 1.92977392977393e-05, | |
| "loss": 0.3456, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_cer": 0.18311191992720655, | |
| "eval_loss": 0.5674863457679749, | |
| "eval_per": 0.35026412027631043, | |
| "eval_runtime": 16.31, | |
| "eval_samples_per_second": 33.231, | |
| "eval_steps_per_second": 4.169, | |
| "eval_wer": 0.3650954896383584, | |
| "step": 1106 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_cer": 0.1846041856232939, | |
| "eval_loss": 0.5696778297424316, | |
| "eval_per": 0.35067045916294187, | |
| "eval_runtime": 16.3755, | |
| "eval_samples_per_second": 33.098, | |
| "eval_steps_per_second": 4.153, | |
| "eval_wer": 0.3644859813084112, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_cer": 0.18409463148316652, | |
| "eval_loss": 0.5643677711486816, | |
| "eval_per": 0.34924827305973183, | |
| "eval_runtime": 16.3983, | |
| "eval_samples_per_second": 33.052, | |
| "eval_steps_per_second": 4.147, | |
| "eval_wer": 0.36306379520520116, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_cer": 0.1843494085532302, | |
| "eval_loss": 0.56571364402771, | |
| "eval_per": 0.34802925639983745, | |
| "eval_runtime": 16.5291, | |
| "eval_samples_per_second": 32.791, | |
| "eval_steps_per_second": 4.114, | |
| "eval_wer": 0.36265745631856966, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_cer": 0.1875523202911738, | |
| "eval_loss": 0.5830783247947693, | |
| "eval_per": 0.3522958147094677, | |
| "eval_runtime": 16.4238, | |
| "eval_samples_per_second": 33.001, | |
| "eval_steps_per_second": 4.14, | |
| "eval_wer": 0.36793986184477856, | |
| "step": 1162 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_cer": 0.1861692447679709, | |
| "eval_loss": 0.5823647975921631, | |
| "eval_per": 0.3522958147094677, | |
| "eval_runtime": 17.5122, | |
| "eval_samples_per_second": 30.95, | |
| "eval_steps_per_second": 3.883, | |
| "eval_wer": 0.3659081674116213, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_cer": 0.18333030027297542, | |
| "eval_loss": 0.5567490458488464, | |
| "eval_per": 0.3508736286062576, | |
| "eval_runtime": 16.4517, | |
| "eval_samples_per_second": 32.945, | |
| "eval_steps_per_second": 4.133, | |
| "eval_wer": 0.36529865908167414, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 85.71, | |
| "learning_rate": 1.7373737373737375e-05, | |
| "loss": 0.3073, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_cer": 0.1851501364877161, | |
| "eval_loss": 0.5755050778388977, | |
| "eval_per": 0.35067045916294187, | |
| "eval_runtime": 17.6602, | |
| "eval_samples_per_second": 30.691, | |
| "eval_steps_per_second": 3.85, | |
| "eval_wer": 0.36489232019504264, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_cer": 0.18289353958143767, | |
| "eval_loss": 0.5590367913246155, | |
| "eval_per": 0.3449817147501016, | |
| "eval_runtime": 16.7556, | |
| "eval_samples_per_second": 32.347, | |
| "eval_steps_per_second": 4.058, | |
| "eval_wer": 0.3585940674522552, | |
| "step": 1218 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_cer": 0.18347588717015467, | |
| "eval_loss": 0.5662943720817566, | |
| "eval_per": 0.34802925639983745, | |
| "eval_runtime": 16.6011, | |
| "eval_samples_per_second": 32.649, | |
| "eval_steps_per_second": 4.096, | |
| "eval_wer": 0.3610321007720439, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_cer": 0.18507734303912649, | |
| "eval_loss": 0.5733785629272461, | |
| "eval_per": 0.3468102397399431, | |
| "eval_runtime": 16.1986, | |
| "eval_samples_per_second": 33.46, | |
| "eval_steps_per_second": 4.198, | |
| "eval_wer": 0.3618447785453068, | |
| "step": 1246 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_cer": 0.18303912647861692, | |
| "eval_loss": 0.5656831860542297, | |
| "eval_per": 0.34579439252336447, | |
| "eval_runtime": 16.3772, | |
| "eval_samples_per_second": 33.095, | |
| "eval_steps_per_second": 4.152, | |
| "eval_wer": 0.36021942299878096, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_cer": 0.18278434940855323, | |
| "eval_loss": 0.5650802850723267, | |
| "eval_per": 0.3441690369768387, | |
| "eval_runtime": 17.4779, | |
| "eval_samples_per_second": 31.011, | |
| "eval_steps_per_second": 3.891, | |
| "eval_wer": 0.35778138967899226, | |
| "step": 1274 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_cer": 0.18202001819836214, | |
| "eval_loss": 0.5608470439910889, | |
| "eval_per": 0.3415278342137342, | |
| "eval_runtime": 16.5014, | |
| "eval_samples_per_second": 32.846, | |
| "eval_steps_per_second": 4.121, | |
| "eval_wer": 0.35574969524583505, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 92.86, | |
| "learning_rate": 1.544973544973545e-05, | |
| "loss": 0.2836, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_cer": 0.18067333939945404, | |
| "eval_loss": 0.5504541993141174, | |
| "eval_per": 0.3388866314506298, | |
| "eval_runtime": 16.701, | |
| "eval_samples_per_second": 32.453, | |
| "eval_steps_per_second": 4.072, | |
| "eval_wer": 0.3524989841527834, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_cer": 0.17979981801637854, | |
| "eval_loss": 0.5494620203971863, | |
| "eval_per": 0.33746444534741976, | |
| "eval_runtime": 17.2521, | |
| "eval_samples_per_second": 31.416, | |
| "eval_steps_per_second": 3.942, | |
| "eval_wer": 0.3500609508329947, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_cer": 0.1816196542311192, | |
| "eval_loss": 0.5693331360816956, | |
| "eval_per": 0.34315318976026005, | |
| "eval_runtime": 16.3033, | |
| "eval_samples_per_second": 33.245, | |
| "eval_steps_per_second": 4.171, | |
| "eval_wer": 0.35574969524583505, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_cer": 0.1822020018198362, | |
| "eval_loss": 0.5638025999069214, | |
| "eval_per": 0.34173100365705, | |
| "eval_runtime": 16.8945, | |
| "eval_samples_per_second": 32.081, | |
| "eval_steps_per_second": 4.025, | |
| "eval_wer": 0.3563592035757822, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_cer": 0.17969062784349407, | |
| "eval_loss": 0.5485906004905701, | |
| "eval_per": 0.3386834620073141, | |
| "eval_runtime": 16.6823, | |
| "eval_samples_per_second": 32.489, | |
| "eval_steps_per_second": 4.076, | |
| "eval_wer": 0.35107679804957337, | |
| "step": 1358 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_cer": 0.18096451319381257, | |
| "eval_loss": 0.5618489980697632, | |
| "eval_per": 0.3415278342137342, | |
| "eval_runtime": 16.6547, | |
| "eval_samples_per_second": 32.543, | |
| "eval_steps_per_second": 4.083, | |
| "eval_wer": 0.3545306785859407, | |
| "step": 1372 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_cer": 0.1799818016378526, | |
| "eval_loss": 0.5637105703353882, | |
| "eval_per": 0.33990247866720846, | |
| "eval_runtime": 16.8199, | |
| "eval_samples_per_second": 32.224, | |
| "eval_steps_per_second": 4.043, | |
| "eval_wer": 0.3514831369362048, | |
| "step": 1386 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 1.3525733525733527e-05, | |
| "loss": 0.2502, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_cer": 0.1810373066424022, | |
| "eval_loss": 0.5658114552497864, | |
| "eval_per": 0.3437626980902072, | |
| "eval_runtime": 16.859, | |
| "eval_samples_per_second": 32.149, | |
| "eval_steps_per_second": 4.033, | |
| "eval_wer": 0.3555465258025193, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 101.0, | |
| "eval_cer": 0.17954504094631482, | |
| "eval_loss": 0.552661657333374, | |
| "eval_per": 0.3411214953271028, | |
| "eval_runtime": 17.0552, | |
| "eval_samples_per_second": 31.779, | |
| "eval_steps_per_second": 3.987, | |
| "eval_wer": 0.3524989841527834, | |
| "step": 1414 | |
| }, | |
| { | |
| "epoch": 102.0, | |
| "eval_cer": 0.18067333939945404, | |
| "eval_loss": 0.5701059699058533, | |
| "eval_per": 0.343965867533523, | |
| "eval_runtime": 17.649, | |
| "eval_samples_per_second": 30.71, | |
| "eval_steps_per_second": 3.853, | |
| "eval_wer": 0.3561560341324665, | |
| "step": 1428 | |
| }, | |
| { | |
| "epoch": 103.0, | |
| "eval_cer": 0.17936305732484076, | |
| "eval_loss": 0.554296612739563, | |
| "eval_per": 0.3388866314506298, | |
| "eval_runtime": 16.2178, | |
| "eval_samples_per_second": 33.42, | |
| "eval_steps_per_second": 4.193, | |
| "eval_wer": 0.34965461194636327, | |
| "step": 1442 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "eval_cer": 0.18034576888080073, | |
| "eval_loss": 0.5659683346748352, | |
| "eval_per": 0.33990247866720846, | |
| "eval_runtime": 16.8247, | |
| "eval_samples_per_second": 32.214, | |
| "eval_steps_per_second": 4.042, | |
| "eval_wer": 0.3508736286062576, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "eval_cer": 0.17950864422202, | |
| "eval_loss": 0.5542871952056885, | |
| "eval_per": 0.33990247866720846, | |
| "eval_runtime": 16.8641, | |
| "eval_samples_per_second": 32.139, | |
| "eval_steps_per_second": 4.032, | |
| "eval_wer": 0.3500609508329947, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 106.0, | |
| "eval_cer": 0.181656050955414, | |
| "eval_loss": 0.5742031931877136, | |
| "eval_per": 0.34315318976026005, | |
| "eval_runtime": 16.2772, | |
| "eval_samples_per_second": 33.298, | |
| "eval_steps_per_second": 4.178, | |
| "eval_wer": 0.3547338480292564, | |
| "step": 1484 | |
| }, | |
| { | |
| "epoch": 107.0, | |
| "eval_cer": 0.178926296633303, | |
| "eval_loss": 0.5526788830757141, | |
| "eval_per": 0.33502641202763106, | |
| "eval_runtime": 16.3123, | |
| "eval_samples_per_second": 33.227, | |
| "eval_steps_per_second": 4.169, | |
| "eval_wer": 0.34538805363673303, | |
| "step": 1498 | |
| }, | |
| { | |
| "epoch": 107.14, | |
| "learning_rate": 1.1601731601731604e-05, | |
| "loss": 0.2368, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 108.0, | |
| "eval_cer": 0.178926296633303, | |
| "eval_loss": 0.5576502084732056, | |
| "eval_per": 0.3378707842340512, | |
| "eval_runtime": 16.2769, | |
| "eval_samples_per_second": 33.299, | |
| "eval_steps_per_second": 4.178, | |
| "eval_wer": 0.34965461194636327, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 109.0, | |
| "eval_cer": 0.1788898999090082, | |
| "eval_loss": 0.5539444088935852, | |
| "eval_per": 0.3356359203575782, | |
| "eval_runtime": 17.6723, | |
| "eval_samples_per_second": 30.669, | |
| "eval_steps_per_second": 3.848, | |
| "eval_wer": 0.3451848841934173, | |
| "step": 1526 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "eval_cer": 0.18020018198362148, | |
| "eval_loss": 0.5699580311775208, | |
| "eval_per": 0.34173100365705, | |
| "eval_runtime": 16.5072, | |
| "eval_samples_per_second": 32.834, | |
| "eval_steps_per_second": 4.119, | |
| "eval_wer": 0.35168630637952053, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 111.0, | |
| "eval_cer": 0.17939945404913557, | |
| "eval_loss": 0.5626676678657532, | |
| "eval_per": 0.33969930922389274, | |
| "eval_runtime": 16.5149, | |
| "eval_samples_per_second": 32.819, | |
| "eval_steps_per_second": 4.117, | |
| "eval_wer": 0.3500609508329947, | |
| "step": 1554 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "eval_cer": 0.17965423111919926, | |
| "eval_loss": 0.5622020363807678, | |
| "eval_per": 0.3405119869971556, | |
| "eval_runtime": 18.514, | |
| "eval_samples_per_second": 29.275, | |
| "eval_steps_per_second": 3.673, | |
| "eval_wer": 0.34965461194636327, | |
| "step": 1568 | |
| }, | |
| { | |
| "epoch": 113.0, | |
| "eval_cer": 0.18005459508644223, | |
| "eval_loss": 0.570824146270752, | |
| "eval_per": 0.3403088175538399, | |
| "eval_runtime": 16.7958, | |
| "eval_samples_per_second": 32.27, | |
| "eval_steps_per_second": 4.049, | |
| "eval_wer": 0.34945144250304755, | |
| "step": 1582 | |
| }, | |
| { | |
| "epoch": 114.0, | |
| "eval_cer": 0.18045495905368517, | |
| "eval_loss": 0.5732950568199158, | |
| "eval_per": 0.3401056481105242, | |
| "eval_runtime": 17.5602, | |
| "eval_samples_per_second": 30.865, | |
| "eval_steps_per_second": 3.872, | |
| "eval_wer": 0.35107679804957337, | |
| "step": 1596 | |
| }, | |
| { | |
| "epoch": 114.29, | |
| "learning_rate": 9.677729677729679e-06, | |
| "loss": 0.2288, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 115.0, | |
| "eval_cer": 0.17950864422202, | |
| "eval_loss": 0.5614627599716187, | |
| "eval_per": 0.3386834620073141, | |
| "eval_runtime": 18.0091, | |
| "eval_samples_per_second": 30.096, | |
| "eval_steps_per_second": 3.776, | |
| "eval_wer": 0.34863876472978467, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 116.0, | |
| "eval_cer": 0.1808553230209281, | |
| "eval_loss": 0.5741183757781982, | |
| "eval_per": 0.33969930922389274, | |
| "eval_runtime": 16.588, | |
| "eval_samples_per_second": 32.674, | |
| "eval_steps_per_second": 4.099, | |
| "eval_wer": 0.34965461194636327, | |
| "step": 1624 | |
| }, | |
| { | |
| "epoch": 117.0, | |
| "eval_cer": 0.17958143767060963, | |
| "eval_loss": 0.5609710812568665, | |
| "eval_per": 0.33726127590410404, | |
| "eval_runtime": 16.4333, | |
| "eval_samples_per_second": 32.982, | |
| "eval_steps_per_second": 4.138, | |
| "eval_wer": 0.3459975619666802, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 117.0, | |
| "step": 1638, | |
| "total_flos": 1.462030946643386e+19, | |
| "train_loss": 1.771814914558979, | |
| "train_runtime": 12938.9921, | |
| "train_samples_per_second": 5.194, | |
| "train_steps_per_second": 0.162 | |
| } | |
| ], | |
| "max_steps": 2100, | |
| "num_train_epochs": 150, | |
| "total_flos": 1.462030946643386e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |