| { | |
| "best_metric": 0.5552828907966614, | |
| "best_model_checkpoint": "wav2vec2-large-xlsr-coraa-exp-9/checkpoint-1512", | |
| "epoch": 128.0, | |
| "global_step": 1792, | |
| "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": 37.5508, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 23.137550354003906, | |
| "eval_runtime": 52.9452, | |
| "eval_samples_per_second": 10.237, | |
| "eval_steps_per_second": 1.284, | |
| "eval_wer": 1.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 6.50360107421875, | |
| "eval_runtime": 52.53, | |
| "eval_samples_per_second": 10.318, | |
| "eval_steps_per_second": 1.294, | |
| "eval_wer": 1.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 4.391931056976318, | |
| "eval_runtime": 52.983, | |
| "eval_samples_per_second": 10.23, | |
| "eval_steps_per_second": 1.283, | |
| "eval_wer": 1.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.944124221801758, | |
| "eval_runtime": 52.4812, | |
| "eval_samples_per_second": 10.328, | |
| "eval_steps_per_second": 1.296, | |
| "eval_wer": 1.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.730649709701538, | |
| "eval_runtime": 52.6687, | |
| "eval_samples_per_second": 10.291, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 1.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.5761733055114746, | |
| "eval_runtime": 52.4991, | |
| "eval_samples_per_second": 10.324, | |
| "eval_steps_per_second": 1.295, | |
| "eval_wer": 1.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.4128713607788086, | |
| "eval_runtime": 52.9491, | |
| "eval_samples_per_second": 10.236, | |
| "eval_steps_per_second": 1.284, | |
| "eval_wer": 1.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 2.8614285714285714e-05, | |
| "loss": 8.6902, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.285918951034546, | |
| "eval_runtime": 52.5221, | |
| "eval_samples_per_second": 10.319, | |
| "eval_steps_per_second": 1.295, | |
| "eval_wer": 1.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.219179391860962, | |
| "eval_runtime": 53.0718, | |
| "eval_samples_per_second": 10.213, | |
| "eval_steps_per_second": 1.281, | |
| "eval_wer": 1.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.1479437351226807, | |
| "eval_runtime": 52.485, | |
| "eval_samples_per_second": 10.327, | |
| "eval_steps_per_second": 1.296, | |
| "eval_wer": 1.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.106292963027954, | |
| "eval_runtime": 52.586, | |
| "eval_samples_per_second": 10.307, | |
| "eval_steps_per_second": 1.293, | |
| "eval_wer": 1.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0896878242492676, | |
| "eval_runtime": 52.4874, | |
| "eval_samples_per_second": 10.326, | |
| "eval_steps_per_second": 1.296, | |
| "eval_wer": 1.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.084855794906616, | |
| "eval_runtime": 52.6206, | |
| "eval_samples_per_second": 10.3, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 1.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.048473596572876, | |
| "eval_runtime": 52.5487, | |
| "eval_samples_per_second": 10.314, | |
| "eval_steps_per_second": 1.294, | |
| "eval_wer": 1.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 2.7185714285714287e-05, | |
| "loss": 3.059, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0495524406433105, | |
| "eval_runtime": 52.5935, | |
| "eval_samples_per_second": 10.305, | |
| "eval_steps_per_second": 1.293, | |
| "eval_wer": 1.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0509705543518066, | |
| "eval_runtime": 52.5135, | |
| "eval_samples_per_second": 10.321, | |
| "eval_steps_per_second": 1.295, | |
| "eval_wer": 1.0, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.042844533920288, | |
| "eval_runtime": 52.5458, | |
| "eval_samples_per_second": 10.315, | |
| "eval_steps_per_second": 1.294, | |
| "eval_wer": 1.0, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.033111572265625, | |
| "eval_runtime": 52.5883, | |
| "eval_samples_per_second": 10.306, | |
| "eval_steps_per_second": 1.293, | |
| "eval_wer": 1.0, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.035349130630493, | |
| "eval_runtime": 52.5405, | |
| "eval_samples_per_second": 10.316, | |
| "eval_steps_per_second": 1.294, | |
| "eval_wer": 1.0, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0217459201812744, | |
| "eval_runtime": 52.6413, | |
| "eval_samples_per_second": 10.296, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 1.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0107431411743164, | |
| "eval_runtime": 52.5958, | |
| "eval_samples_per_second": 10.305, | |
| "eval_steps_per_second": 1.293, | |
| "eval_wer": 1.0, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "learning_rate": 2.5757142857142857e-05, | |
| "loss": 2.9492, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0068299770355225, | |
| "eval_runtime": 52.8053, | |
| "eval_samples_per_second": 10.264, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 1.0, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.9949989318847656, | |
| "eval_runtime": 52.5717, | |
| "eval_samples_per_second": 10.31, | |
| "eval_steps_per_second": 1.293, | |
| "eval_wer": 1.0, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.989611864089966, | |
| "eval_runtime": 53.0076, | |
| "eval_samples_per_second": 10.225, | |
| "eval_steps_per_second": 1.283, | |
| "eval_wer": 1.0, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.9687271118164062, | |
| "eval_runtime": 52.6125, | |
| "eval_samples_per_second": 10.302, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 1.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.947374105453491, | |
| "eval_runtime": 52.5637, | |
| "eval_samples_per_second": 10.311, | |
| "eval_steps_per_second": 1.294, | |
| "eval_wer": 1.0, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.9414024353027344, | |
| "eval_runtime": 52.648, | |
| "eval_samples_per_second": 10.295, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 1.0, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.84250807762146, | |
| "eval_runtime": 52.5712, | |
| "eval_samples_per_second": 10.31, | |
| "eval_steps_per_second": 1.293, | |
| "eval_wer": 1.0, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 2.432857142857143e-05, | |
| "loss": 2.8892, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.7813332080841064, | |
| "eval_runtime": 52.64, | |
| "eval_samples_per_second": 10.296, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 1.0, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.7269773483276367, | |
| "eval_runtime": 52.5989, | |
| "eval_samples_per_second": 10.304, | |
| "eval_steps_per_second": 1.293, | |
| "eval_wer": 1.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_cer": 0.9606187443130119, | |
| "eval_loss": 2.6644980907440186, | |
| "eval_runtime": 52.6591, | |
| "eval_samples_per_second": 10.293, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 1.0, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_cer": 0.9138853503184713, | |
| "eval_loss": 2.5593061447143555, | |
| "eval_runtime": 52.5942, | |
| "eval_samples_per_second": 10.305, | |
| "eval_steps_per_second": 1.293, | |
| "eval_wer": 1.0, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_cer": 0.7002729754322111, | |
| "eval_loss": 2.3229565620422363, | |
| "eval_runtime": 53.1245, | |
| "eval_samples_per_second": 10.202, | |
| "eval_steps_per_second": 1.28, | |
| "eval_wer": 1.0, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_cer": 0.535796178343949, | |
| "eval_loss": 1.9706292152404785, | |
| "eval_runtime": 52.7199, | |
| "eval_samples_per_second": 10.281, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 1.0, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_cer": 0.45481346678798906, | |
| "eval_loss": 1.7085232734680176, | |
| "eval_runtime": 52.7281, | |
| "eval_samples_per_second": 10.279, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.9997968305566842, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 35.71, | |
| "learning_rate": 2.29e-05, | |
| "loss": 2.3937, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_cer": 0.4063694267515924, | |
| "eval_loss": 1.449361801147461, | |
| "eval_runtime": 52.6273, | |
| "eval_samples_per_second": 10.299, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 1.0, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_cer": 0.38471337579617837, | |
| "eval_loss": 1.286526083946228, | |
| "eval_runtime": 52.7236, | |
| "eval_samples_per_second": 10.28, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 1.0, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_cer": 0.3659326660600546, | |
| "eval_loss": 1.1509252786636353, | |
| "eval_runtime": 52.6429, | |
| "eval_samples_per_second": 10.296, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.9947175944737912, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_cer": 0.3182893539581438, | |
| "eval_loss": 1.0466662645339966, | |
| "eval_runtime": 52.7531, | |
| "eval_samples_per_second": 10.274, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.903088175538399, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_cer": 0.24043676069153777, | |
| "eval_loss": 0.9831815361976624, | |
| "eval_runtime": 52.6494, | |
| "eval_samples_per_second": 10.295, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.5960991466883381, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_cer": 0.22227479526842583, | |
| "eval_loss": 0.892058789730072, | |
| "eval_runtime": 53.2461, | |
| "eval_samples_per_second": 10.179, | |
| "eval_steps_per_second": 1.277, | |
| "eval_wer": 0.5048760666395774, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_cer": 0.21233848953594175, | |
| "eval_loss": 0.8306074738502502, | |
| "eval_runtime": 52.8348, | |
| "eval_samples_per_second": 10.258, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.4687119057293783, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 42.86, | |
| "learning_rate": 2.1471428571428574e-05, | |
| "loss": 1.0877, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_cer": 0.20880800727934487, | |
| "eval_loss": 0.8016981482505798, | |
| "eval_runtime": 52.6157, | |
| "eval_samples_per_second": 10.301, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.45631856968711904, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_cer": 0.2045859872611465, | |
| "eval_loss": 0.7715625166893005, | |
| "eval_runtime": 52.6399, | |
| "eval_samples_per_second": 10.296, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.4404713531084925, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_cer": 0.2053867151956324, | |
| "eval_loss": 0.7693753838539124, | |
| "eval_runtime": 52.708, | |
| "eval_samples_per_second": 10.283, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.4406745225518082, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_cer": 0.20367606915377617, | |
| "eval_loss": 0.7451383471488953, | |
| "eval_runtime": 52.7002, | |
| "eval_samples_per_second": 10.285, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.4315318976026006, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_cer": 0.19956323930846223, | |
| "eval_loss": 0.7111817598342896, | |
| "eval_runtime": 53.2448, | |
| "eval_samples_per_second": 10.179, | |
| "eval_steps_per_second": 1.277, | |
| "eval_wer": 0.42503047541649736, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_cer": 0.19581437670609644, | |
| "eval_loss": 0.7007989883422852, | |
| "eval_runtime": 52.7775, | |
| "eval_samples_per_second": 10.27, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.41162129215765947, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_cer": 0.19799818016378526, | |
| "eval_loss": 0.7140166163444519, | |
| "eval_runtime": 52.6495, | |
| "eval_samples_per_second": 10.294, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.40572937830150346, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 2.004285714285714e-05, | |
| "loss": 0.6292, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_cer": 0.19883530482256598, | |
| "eval_loss": 0.7207656502723694, | |
| "eval_runtime": 52.6919, | |
| "eval_samples_per_second": 10.286, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.41141812271434375, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_cer": 0.19366696997270247, | |
| "eval_loss": 0.6675068140029907, | |
| "eval_runtime": 52.8778, | |
| "eval_samples_per_second": 10.25, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 0.40329134498171476, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_cer": 0.19384895359417653, | |
| "eval_loss": 0.6650232672691345, | |
| "eval_runtime": 52.6583, | |
| "eval_samples_per_second": 10.293, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.4014628199918732, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_cer": 0.1937761601455869, | |
| "eval_loss": 0.6550155878067017, | |
| "eval_runtime": 52.7667, | |
| "eval_samples_per_second": 10.272, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.4012596505485575, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_cer": 0.19315741583257506, | |
| "eval_loss": 0.6477207541465759, | |
| "eval_runtime": 52.6665, | |
| "eval_samples_per_second": 10.291, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.3990247866720845, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_cer": 0.19319381255686988, | |
| "eval_loss": 0.6361698508262634, | |
| "eval_runtime": 52.6325, | |
| "eval_samples_per_second": 10.298, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.39597724502234866, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_cer": 0.192975432211101, | |
| "eval_loss": 0.632267951965332, | |
| "eval_runtime": 52.7108, | |
| "eval_samples_per_second": 10.283, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.39191385615603413, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_cer": 0.19206551410373066, | |
| "eval_loss": 0.626406192779541, | |
| "eval_runtime": 52.675, | |
| "eval_samples_per_second": 10.29, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.38703778951645673, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 57.14, | |
| "learning_rate": 1.8614285714285715e-05, | |
| "loss": 0.4739, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_cer": 0.19210191082802547, | |
| "eval_loss": 0.6290065050125122, | |
| "eval_runtime": 52.661, | |
| "eval_samples_per_second": 10.292, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.38724095895977245, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_cer": 0.19253867151956325, | |
| "eval_loss": 0.6206580400466919, | |
| "eval_runtime": 52.6443, | |
| "eval_samples_per_second": 10.296, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.38642828118650957, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_cer": 0.19184713375796178, | |
| "eval_loss": 0.6177613735198975, | |
| "eval_runtime": 52.6855, | |
| "eval_samples_per_second": 10.287, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.38581877285656235, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_cer": 0.19177434030937215, | |
| "eval_loss": 0.6217214465141296, | |
| "eval_runtime": 53.1515, | |
| "eval_samples_per_second": 10.197, | |
| "eval_steps_per_second": 1.279, | |
| "eval_wer": 0.3860219422998781, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_cer": 0.1899545040946315, | |
| "eval_loss": 0.6078172922134399, | |
| "eval_runtime": 52.6994, | |
| "eval_samples_per_second": 10.285, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.37992685900040635, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_cer": 0.1889353958143767, | |
| "eval_loss": 0.6072229146957397, | |
| "eval_runtime": 52.8038, | |
| "eval_samples_per_second": 10.264, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.3780983340105648, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_cer": 0.18831665150136487, | |
| "eval_loss": 0.6067555546760559, | |
| "eval_runtime": 52.6766, | |
| "eval_samples_per_second": 10.289, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.37606663957740755, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 64.29, | |
| "learning_rate": 1.7185714285714285e-05, | |
| "loss": 0.3855, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_cer": 0.1870427661510464, | |
| "eval_loss": 0.5944907665252686, | |
| "eval_runtime": 52.7345, | |
| "eval_samples_per_second": 10.278, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.3748476229175132, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_cer": 0.1899545040946315, | |
| "eval_loss": 0.6194169521331787, | |
| "eval_runtime": 52.7092, | |
| "eval_samples_per_second": 10.283, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.37992685900040635, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_cer": 0.18846223839854412, | |
| "eval_loss": 0.6044437289237976, | |
| "eval_runtime": 52.6167, | |
| "eval_samples_per_second": 10.301, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.3793173506704592, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_cer": 0.18798908098271155, | |
| "eval_loss": 0.5945860147476196, | |
| "eval_runtime": 52.6643, | |
| "eval_samples_per_second": 10.292, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.37505079236082894, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_cer": 0.18798908098271155, | |
| "eval_loss": 0.6115556955337524, | |
| "eval_runtime": 52.6187, | |
| "eval_samples_per_second": 10.301, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.37139374238114586, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_cer": 0.18609645131938127, | |
| "eval_loss": 0.5876884460449219, | |
| "eval_runtime": 52.6386, | |
| "eval_samples_per_second": 10.297, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.36793986184477856, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_cer": 0.18627843494085533, | |
| "eval_loss": 0.5861026048660278, | |
| "eval_runtime": 52.6444, | |
| "eval_samples_per_second": 10.296, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.36793986184477856, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 71.43, | |
| "learning_rate": 1.5757142857142858e-05, | |
| "loss": 0.3302, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_cer": 0.18562329390354868, | |
| "eval_loss": 0.580510139465332, | |
| "eval_runtime": 52.6419, | |
| "eval_samples_per_second": 10.296, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.3685493701747257, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_cer": 0.1862056414922657, | |
| "eval_loss": 0.586155354976654, | |
| "eval_runtime": 52.6421, | |
| "eval_samples_per_second": 10.296, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.37139374238114586, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_cer": 0.18656960873521383, | |
| "eval_loss": 0.5920763611793518, | |
| "eval_runtime": 52.6765, | |
| "eval_samples_per_second": 10.289, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.372003250711093, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_cer": 0.185368516833485, | |
| "eval_loss": 0.5692393779754639, | |
| "eval_runtime": 52.7333, | |
| "eval_samples_per_second": 10.278, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.36834620073141, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_cer": 0.18777070063694268, | |
| "eval_loss": 0.5922245979309082, | |
| "eval_runtime": 52.7512, | |
| "eval_samples_per_second": 10.275, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.37017472572125154, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_cer": 0.18828025477707006, | |
| "eval_loss": 0.6105178594589233, | |
| "eval_runtime": 52.65, | |
| "eval_samples_per_second": 10.294, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.3709874034945144, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_cer": 0.18558689717925386, | |
| "eval_loss": 0.5873062014579773, | |
| "eval_runtime": 53.0336, | |
| "eval_samples_per_second": 10.22, | |
| "eval_steps_per_second": 1.282, | |
| "eval_wer": 0.36834620073141, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 78.57, | |
| "learning_rate": 1.4328571428571428e-05, | |
| "loss": 0.3046, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_cer": 0.18587807097361236, | |
| "eval_loss": 0.5825892090797424, | |
| "eval_runtime": 52.7458, | |
| "eval_samples_per_second": 10.276, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.3681430312880943, | |
| "step": 1106 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_cer": 0.18445859872611464, | |
| "eval_loss": 0.5792315006256104, | |
| "eval_runtime": 53.1292, | |
| "eval_samples_per_second": 10.202, | |
| "eval_steps_per_second": 1.28, | |
| "eval_wer": 0.3632669646485169, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_cer": 0.18347588717015467, | |
| "eval_loss": 0.5737511515617371, | |
| "eval_runtime": 52.6677, | |
| "eval_samples_per_second": 10.291, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.3610321007720439, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_cer": 0.1843130118289354, | |
| "eval_loss": 0.579399585723877, | |
| "eval_runtime": 53.0003, | |
| "eval_samples_per_second": 10.226, | |
| "eval_steps_per_second": 1.283, | |
| "eval_wer": 0.36245428687525394, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_cer": 0.18289353958143767, | |
| "eval_loss": 0.5766276121139526, | |
| "eval_runtime": 52.6724, | |
| "eval_samples_per_second": 10.29, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.3563592035757822, | |
| "step": 1162 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_cer": 0.1830027297543221, | |
| "eval_loss": 0.5745117664337158, | |
| "eval_runtime": 52.7431, | |
| "eval_samples_per_second": 10.276, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.35778138967899226, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_cer": 0.18140127388535032, | |
| "eval_loss": 0.561495840549469, | |
| "eval_runtime": 52.6016, | |
| "eval_samples_per_second": 10.304, | |
| "eval_steps_per_second": 1.293, | |
| "eval_wer": 0.3555465258025193, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 85.71, | |
| "learning_rate": 1.29e-05, | |
| "loss": 0.2927, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_cer": 0.18282074613284804, | |
| "eval_loss": 0.5853651762008667, | |
| "eval_runtime": 52.6345, | |
| "eval_samples_per_second": 10.297, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.36143843965867534, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_cer": 0.1835122838944495, | |
| "eval_loss": 0.5817971229553223, | |
| "eval_runtime": 52.7194, | |
| "eval_samples_per_second": 10.281, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.36245428687525394, | |
| "step": 1218 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_cer": 0.18154686078252957, | |
| "eval_loss": 0.5613023638725281, | |
| "eval_runtime": 52.6918, | |
| "eval_samples_per_second": 10.286, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.35778138967899226, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_cer": 0.18125568698817107, | |
| "eval_loss": 0.5661023259162903, | |
| "eval_runtime": 52.6276, | |
| "eval_samples_per_second": 10.299, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.3549370174725721, | |
| "step": 1246 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_cer": 0.18202001819836214, | |
| "eval_loss": 0.5794751048088074, | |
| "eval_runtime": 52.7536, | |
| "eval_samples_per_second": 10.274, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.36042259244209673, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_cer": 0.18020018198362148, | |
| "eval_loss": 0.5604133605957031, | |
| "eval_runtime": 52.6351, | |
| "eval_samples_per_second": 10.297, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.35209264526615197, | |
| "step": 1274 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_cer": 0.1821656050955414, | |
| "eval_loss": 0.5738141536712646, | |
| "eval_runtime": 52.6638, | |
| "eval_samples_per_second": 10.292, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.35900040633888664, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 92.86, | |
| "learning_rate": 1.1471428571428572e-05, | |
| "loss": 0.2576, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_cer": 0.18140127388535032, | |
| "eval_loss": 0.5658465623855591, | |
| "eval_runtime": 52.9846, | |
| "eval_samples_per_second": 10.229, | |
| "eval_steps_per_second": 1.283, | |
| "eval_wer": 0.3573750507923608, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_cer": 0.1808189262966333, | |
| "eval_loss": 0.5620054006576538, | |
| "eval_runtime": 52.617, | |
| "eval_samples_per_second": 10.301, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.35107679804957337, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_cer": 0.18100090991810738, | |
| "eval_loss": 0.5709471106529236, | |
| "eval_runtime": 52.6962, | |
| "eval_samples_per_second": 10.285, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.35412433969930923, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_cer": 0.1799454049135578, | |
| "eval_loss": 0.5674740076065063, | |
| "eval_runtime": 52.6892, | |
| "eval_samples_per_second": 10.287, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.35026412027631043, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_cer": 0.18151046405823476, | |
| "eval_loss": 0.5788221955299377, | |
| "eval_runtime": 53.0799, | |
| "eval_samples_per_second": 10.211, | |
| "eval_steps_per_second": 1.281, | |
| "eval_wer": 0.3549370174725721, | |
| "step": 1358 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_cer": 0.18096451319381257, | |
| "eval_loss": 0.5730317234992981, | |
| "eval_runtime": 52.5988, | |
| "eval_samples_per_second": 10.304, | |
| "eval_steps_per_second": 1.293, | |
| "eval_wer": 0.3524989841527834, | |
| "step": 1372 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_cer": 0.1802729754322111, | |
| "eval_loss": 0.5693602561950684, | |
| "eval_runtime": 52.6503, | |
| "eval_samples_per_second": 10.294, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.35107679804957337, | |
| "step": 1386 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 1.0042857142857144e-05, | |
| "loss": 0.2273, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_cer": 0.18070973612374885, | |
| "eval_loss": 0.5747684240341187, | |
| "eval_runtime": 52.7106, | |
| "eval_samples_per_second": 10.283, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.35270215359609913, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 101.0, | |
| "eval_cer": 0.17965423111919926, | |
| "eval_loss": 0.5688263773918152, | |
| "eval_runtime": 52.691, | |
| "eval_samples_per_second": 10.286, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.3512799674928891, | |
| "step": 1414 | |
| }, | |
| { | |
| "epoch": 102.0, | |
| "eval_cer": 0.18045495905368517, | |
| "eval_loss": 0.5767450332641602, | |
| "eval_runtime": 52.6967, | |
| "eval_samples_per_second": 10.285, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.35534335635920355, | |
| "step": 1428 | |
| }, | |
| { | |
| "epoch": 103.0, | |
| "eval_cer": 0.18118289353958145, | |
| "eval_loss": 0.5758454203605652, | |
| "eval_runtime": 52.6575, | |
| "eval_samples_per_second": 10.293, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.35290532303941485, | |
| "step": 1442 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "eval_cer": 0.17929026387625113, | |
| "eval_loss": 0.5641180872917175, | |
| "eval_runtime": 52.7234, | |
| "eval_samples_per_second": 10.28, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.35067045916294187, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "eval_cer": 0.178926296633303, | |
| "eval_loss": 0.5628452897071838, | |
| "eval_runtime": 52.9721, | |
| "eval_samples_per_second": 10.232, | |
| "eval_steps_per_second": 1.284, | |
| "eval_wer": 0.34945144250304755, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 106.0, | |
| "eval_cer": 0.1788898999090082, | |
| "eval_loss": 0.5728613138198853, | |
| "eval_runtime": 52.6612, | |
| "eval_samples_per_second": 10.292, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.3466070702966274, | |
| "step": 1484 | |
| }, | |
| { | |
| "epoch": 107.0, | |
| "eval_cer": 0.17983621474067335, | |
| "eval_loss": 0.5722076892852783, | |
| "eval_runtime": 52.7987, | |
| "eval_samples_per_second": 10.265, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.34965461194636327, | |
| "step": 1498 | |
| }, | |
| { | |
| "epoch": 107.14, | |
| "learning_rate": 8.614285714285714e-06, | |
| "loss": 0.2181, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 108.0, | |
| "eval_cer": 0.17881710646041857, | |
| "eval_loss": 0.5552828907966614, | |
| "eval_runtime": 52.6793, | |
| "eval_samples_per_second": 10.289, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.3466070702966274, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 109.0, | |
| "eval_cer": 0.1792174704276615, | |
| "eval_loss": 0.5581598877906799, | |
| "eval_runtime": 52.8837, | |
| "eval_samples_per_second": 10.249, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 0.3484355952864689, | |
| "step": 1526 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "eval_cer": 0.18020018198362148, | |
| "eval_loss": 0.5701535940170288, | |
| "eval_runtime": 52.7198, | |
| "eval_samples_per_second": 10.281, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.35209264526615197, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 111.0, | |
| "eval_cer": 0.17976342129208372, | |
| "eval_loss": 0.5691486597061157, | |
| "eval_runtime": 52.7934, | |
| "eval_samples_per_second": 10.266, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.35046728971962615, | |
| "step": 1554 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "eval_cer": 0.17856232939035488, | |
| "eval_loss": 0.560352087020874, | |
| "eval_runtime": 52.6568, | |
| "eval_samples_per_second": 10.293, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.34701340918325885, | |
| "step": 1568 | |
| }, | |
| { | |
| "epoch": 113.0, | |
| "eval_cer": 0.17950864422202, | |
| "eval_loss": 0.5661062002182007, | |
| "eval_runtime": 52.8124, | |
| "eval_samples_per_second": 10.263, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.34823242584315317, | |
| "step": 1582 | |
| }, | |
| { | |
| "epoch": 114.0, | |
| "eval_cer": 0.17961783439490445, | |
| "eval_loss": 0.5682941675186157, | |
| "eval_runtime": 52.7057, | |
| "eval_samples_per_second": 10.284, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.35107679804957337, | |
| "step": 1596 | |
| }, | |
| { | |
| "epoch": 114.29, | |
| "learning_rate": 7.185714285714286e-06, | |
| "loss": 0.2171, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 115.0, | |
| "eval_cer": 0.17979981801637854, | |
| "eval_loss": 0.573845624923706, | |
| "eval_runtime": 52.7754, | |
| "eval_samples_per_second": 10.27, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.3508736286062576, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 116.0, | |
| "eval_cer": 0.17932666060054595, | |
| "eval_loss": 0.5730240941047668, | |
| "eval_runtime": 52.7098, | |
| "eval_samples_per_second": 10.283, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.34579439252336447, | |
| "step": 1624 | |
| }, | |
| { | |
| "epoch": 117.0, | |
| "eval_cer": 0.178926296633303, | |
| "eval_loss": 0.5704598426818848, | |
| "eval_runtime": 52.6695, | |
| "eval_samples_per_second": 10.291, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.34559122308004875, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 118.0, | |
| "eval_cer": 0.17961783439490445, | |
| "eval_loss": 0.5813525319099426, | |
| "eval_runtime": 53.1651, | |
| "eval_samples_per_second": 10.195, | |
| "eval_steps_per_second": 1.279, | |
| "eval_wer": 0.3466070702966274, | |
| "step": 1652 | |
| }, | |
| { | |
| "epoch": 119.0, | |
| "eval_cer": 0.17907188353048226, | |
| "eval_loss": 0.5714964866638184, | |
| "eval_runtime": 52.764, | |
| "eval_samples_per_second": 10.272, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.3441690369768387, | |
| "step": 1666 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "eval_cer": 0.17976342129208372, | |
| "eval_loss": 0.5720311403274536, | |
| "eval_runtime": 53.0408, | |
| "eval_samples_per_second": 10.219, | |
| "eval_steps_per_second": 1.282, | |
| "eval_wer": 0.34701340918325885, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 121.0, | |
| "eval_cer": 0.17969062784349407, | |
| "eval_loss": 0.5768777132034302, | |
| "eval_runtime": 52.7851, | |
| "eval_samples_per_second": 10.268, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.34701340918325885, | |
| "step": 1694 | |
| }, | |
| { | |
| "epoch": 121.43, | |
| "learning_rate": 5.7571428571428574e-06, | |
| "loss": 0.1986, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 122.0, | |
| "eval_cer": 0.1791810737033667, | |
| "eval_loss": 0.571117639541626, | |
| "eval_runtime": 52.9656, | |
| "eval_samples_per_second": 10.233, | |
| "eval_steps_per_second": 1.284, | |
| "eval_wer": 0.3464039008533117, | |
| "step": 1708 | |
| }, | |
| { | |
| "epoch": 123.0, | |
| "eval_cer": 0.17903548680618744, | |
| "eval_loss": 0.5728168487548828, | |
| "eval_runtime": 52.927, | |
| "eval_samples_per_second": 10.241, | |
| "eval_steps_per_second": 1.285, | |
| "eval_wer": 0.3441690369768387, | |
| "step": 1722 | |
| }, | |
| { | |
| "epoch": 124.0, | |
| "eval_cer": 0.17830755232029116, | |
| "eval_loss": 0.5667761564254761, | |
| "eval_runtime": 52.78, | |
| "eval_samples_per_second": 10.269, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.3449817147501016, | |
| "step": 1736 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "eval_cer": 0.17969062784349407, | |
| "eval_loss": 0.5855135321617126, | |
| "eval_runtime": 52.7911, | |
| "eval_samples_per_second": 10.267, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.3484355952864689, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 126.0, | |
| "eval_cer": 0.17827115559599635, | |
| "eval_loss": 0.5667468905448914, | |
| "eval_runtime": 52.8968, | |
| "eval_samples_per_second": 10.246, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 0.3427468508736286, | |
| "step": 1764 | |
| }, | |
| { | |
| "epoch": 127.0, | |
| "eval_cer": 0.1788898999090082, | |
| "eval_loss": 0.5710840821266174, | |
| "eval_runtime": 52.7705, | |
| "eval_samples_per_second": 10.271, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.3459975619666802, | |
| "step": 1778 | |
| }, | |
| { | |
| "epoch": 128.0, | |
| "eval_cer": 0.1781255686988171, | |
| "eval_loss": 0.5681577920913696, | |
| "eval_runtime": 52.7919, | |
| "eval_samples_per_second": 10.267, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.3443722064201544, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 128.0, | |
| "step": 1792, | |
| "total_flos": 1.5995217836155625e+19, | |
| "train_loss": 1.3990157055003303, | |
| "train_runtime": 26333.2616, | |
| "train_samples_per_second": 2.552, | |
| "train_steps_per_second": 0.08 | |
| } | |
| ], | |
| "max_steps": 2100, | |
| "num_train_epochs": 150, | |
| "total_flos": 1.5995217836155625e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |