| { | |
| "best_metric": 0.556138277053833, | |
| "best_model_checkpoint": "wav2vec2-large-xlsr-coraa-exp-13/checkpoint-1736", | |
| "epoch": 144.0, | |
| "global_step": 2016, | |
| "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": 38.268, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_cer": 0.9430027297543221, | |
| "eval_loss": 32.05844497680664, | |
| "eval_runtime": 53.1315, | |
| "eval_samples_per_second": 10.201, | |
| "eval_steps_per_second": 1.28, | |
| "eval_wer": 1.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 10.376302719116211, | |
| "eval_runtime": 52.6044, | |
| "eval_samples_per_second": 10.303, | |
| "eval_steps_per_second": 1.293, | |
| "eval_wer": 1.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 4.8976359367370605, | |
| "eval_runtime": 52.7604, | |
| "eval_samples_per_second": 10.273, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 1.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 4.040638446807861, | |
| "eval_runtime": 53.2305, | |
| "eval_samples_per_second": 10.182, | |
| "eval_steps_per_second": 1.277, | |
| "eval_wer": 1.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.7469818592071533, | |
| "eval_runtime": 52.5947, | |
| "eval_samples_per_second": 10.305, | |
| "eval_steps_per_second": 1.293, | |
| "eval_wer": 1.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.5903122425079346, | |
| "eval_runtime": 52.8025, | |
| "eval_samples_per_second": 10.265, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 1.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.474977493286133, | |
| "eval_runtime": 52.6757, | |
| "eval_samples_per_second": 10.289, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 1.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 2.862857142857143e-05, | |
| "loss": 10.1654, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.3405568599700928, | |
| "eval_runtime": 52.6172, | |
| "eval_samples_per_second": 10.301, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 1.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.226734161376953, | |
| "eval_runtime": 52.664, | |
| "eval_samples_per_second": 10.292, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 1.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.1887271404266357, | |
| "eval_runtime": 52.6591, | |
| "eval_samples_per_second": 10.293, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 1.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.130089521408081, | |
| "eval_runtime": 53.0211, | |
| "eval_samples_per_second": 10.222, | |
| "eval_steps_per_second": 1.283, | |
| "eval_wer": 1.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.1045610904693604, | |
| "eval_runtime": 52.5606, | |
| "eval_samples_per_second": 10.312, | |
| "eval_steps_per_second": 1.294, | |
| "eval_wer": 1.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.090874433517456, | |
| "eval_runtime": 52.5759, | |
| "eval_samples_per_second": 10.309, | |
| "eval_steps_per_second": 1.293, | |
| "eval_wer": 1.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0602762699127197, | |
| "eval_runtime": 52.7319, | |
| "eval_samples_per_second": 10.278, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 1.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 2.72e-05, | |
| "loss": 3.0823, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0584146976470947, | |
| "eval_runtime": 52.6179, | |
| "eval_samples_per_second": 10.301, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 1.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0485479831695557, | |
| "eval_runtime": 52.7143, | |
| "eval_samples_per_second": 10.282, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 1.0, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.046433925628662, | |
| "eval_runtime": 52.6205, | |
| "eval_samples_per_second": 10.3, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 1.0, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.024200916290283, | |
| "eval_runtime": 52.7522, | |
| "eval_samples_per_second": 10.274, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 1.0, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0237276554107666, | |
| "eval_runtime": 52.648, | |
| "eval_samples_per_second": 10.295, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 1.0, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0304243564605713, | |
| "eval_runtime": 52.7771, | |
| "eval_samples_per_second": 10.27, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 1.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0118603706359863, | |
| "eval_runtime": 52.6742, | |
| "eval_samples_per_second": 10.29, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 1.0, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "learning_rate": 2.5771428571428574e-05, | |
| "loss": 2.9562, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.014829158782959, | |
| "eval_runtime": 52.6427, | |
| "eval_samples_per_second": 10.296, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 1.0, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0060625076293945, | |
| "eval_runtime": 52.7555, | |
| "eval_samples_per_second": 10.274, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 1.0, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0041589736938477, | |
| "eval_runtime": 52.7518, | |
| "eval_samples_per_second": 10.275, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 1.0, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.003258228302002, | |
| "eval_runtime": 52.9828, | |
| "eval_samples_per_second": 10.23, | |
| "eval_steps_per_second": 1.283, | |
| "eval_wer": 1.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.0028507709503174, | |
| "eval_runtime": 52.639, | |
| "eval_samples_per_second": 10.297, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 1.0, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 3.008204460144043, | |
| "eval_runtime": 52.7037, | |
| "eval_samples_per_second": 10.284, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 1.0, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.9955995082855225, | |
| "eval_runtime": 52.6334, | |
| "eval_samples_per_second": 10.298, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 1.0, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 2.434285714285714e-05, | |
| "loss": 2.9262, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.994765043258667, | |
| "eval_runtime": 52.6138, | |
| "eval_samples_per_second": 10.301, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 1.0, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.998243808746338, | |
| "eval_runtime": 52.831, | |
| "eval_samples_per_second": 10.259, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 1.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.996180295944214, | |
| "eval_runtime": 52.6837, | |
| "eval_samples_per_second": 10.288, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 1.0, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.9930543899536133, | |
| "eval_runtime": 53.1611, | |
| "eval_samples_per_second": 10.195, | |
| "eval_steps_per_second": 1.279, | |
| "eval_wer": 1.0, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.9809184074401855, | |
| "eval_runtime": 52.778, | |
| "eval_samples_per_second": 10.269, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 1.0, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.980422019958496, | |
| "eval_runtime": 52.6744, | |
| "eval_samples_per_second": 10.29, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 1.0, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.9742188453674316, | |
| "eval_runtime": 52.6886, | |
| "eval_samples_per_second": 10.287, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 1.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 35.71, | |
| "learning_rate": 2.2914285714285714e-05, | |
| "loss": 2.9125, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.95219349861145, | |
| "eval_runtime": 52.7664, | |
| "eval_samples_per_second": 10.272, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 1.0, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.9014649391174316, | |
| "eval_runtime": 52.6811, | |
| "eval_samples_per_second": 10.288, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 1.0, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.852219581604004, | |
| "eval_runtime": 52.7271, | |
| "eval_samples_per_second": 10.279, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 1.0, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 2.828482151031494, | |
| "eval_runtime": 52.6182, | |
| "eval_samples_per_second": 10.301, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 1.0, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_cer": 0.9614558689717926, | |
| "eval_loss": 2.729363441467285, | |
| "eval_runtime": 52.6938, | |
| "eval_samples_per_second": 10.286, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 1.0, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_cer": 0.9605095541401274, | |
| "eval_loss": 2.6491127014160156, | |
| "eval_runtime": 53.1167, | |
| "eval_samples_per_second": 10.204, | |
| "eval_steps_per_second": 1.28, | |
| "eval_wer": 1.0, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_cer": 0.8949590536851684, | |
| "eval_loss": 2.4882705211639404, | |
| "eval_runtime": 52.7981, | |
| "eval_samples_per_second": 10.266, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 1.0, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 42.86, | |
| "learning_rate": 2.1485714285714284e-05, | |
| "loss": 2.7205, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_cer": 0.836505914467698, | |
| "eval_loss": 2.3630661964416504, | |
| "eval_runtime": 52.7032, | |
| "eval_samples_per_second": 10.284, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 1.0, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_cer": 0.607424931756142, | |
| "eval_loss": 2.054628610610962, | |
| "eval_runtime": 52.7506, | |
| "eval_samples_per_second": 10.275, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 1.0, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_cer": 0.5147952684258417, | |
| "eval_loss": 1.7867237329483032, | |
| "eval_runtime": 53.2436, | |
| "eval_samples_per_second": 10.18, | |
| "eval_steps_per_second": 1.277, | |
| "eval_wer": 1.0, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_cer": 0.4532120109190173, | |
| "eval_loss": 1.5452687740325928, | |
| "eval_runtime": 52.8784, | |
| "eval_samples_per_second": 10.25, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 1.0, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_cer": 0.40640582347588716, | |
| "eval_loss": 1.3553940057754517, | |
| "eval_runtime": 52.7768, | |
| "eval_samples_per_second": 10.27, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.9989841527834213, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_cer": 0.3669881710646042, | |
| "eval_loss": 1.201612114906311, | |
| "eval_runtime": 52.8752, | |
| "eval_samples_per_second": 10.251, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 0.982933766761479, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_cer": 0.3167242948134668, | |
| "eval_loss": 1.0777251720428467, | |
| "eval_runtime": 52.8059, | |
| "eval_samples_per_second": 10.264, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.8805363673303536, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 2.0057142857142858e-05, | |
| "loss": 1.6469, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_cer": 0.2594358507734304, | |
| "eval_loss": 0.978954017162323, | |
| "eval_runtime": 52.919, | |
| "eval_samples_per_second": 10.242, | |
| "eval_steps_per_second": 1.285, | |
| "eval_wer": 0.7029662738724096, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_cer": 0.22238398544131027, | |
| "eval_loss": 0.8961830735206604, | |
| "eval_runtime": 52.8398, | |
| "eval_samples_per_second": 10.257, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.5270215359609914, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_cer": 0.21757961783439492, | |
| "eval_loss": 0.8428747653961182, | |
| "eval_runtime": 52.8781, | |
| "eval_samples_per_second": 10.25, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 0.4973587972368956, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_cer": 0.2089171974522293, | |
| "eval_loss": 0.8158747553825378, | |
| "eval_runtime": 53.3812, | |
| "eval_samples_per_second": 10.153, | |
| "eval_steps_per_second": 1.274, | |
| "eval_wer": 0.4658675335229581, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_cer": 0.20658780709736124, | |
| "eval_loss": 0.7980368137359619, | |
| "eval_runtime": 52.8695, | |
| "eval_samples_per_second": 10.252, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 0.4512393336042259, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_cer": 0.20440400363967243, | |
| "eval_loss": 0.7540920376777649, | |
| "eval_runtime": 52.8272, | |
| "eval_samples_per_second": 10.26, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.4441284030881755, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_cer": 0.20152866242038217, | |
| "eval_loss": 0.7299144864082336, | |
| "eval_runtime": 52.846, | |
| "eval_samples_per_second": 10.256, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.42726533929297034, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_cer": 0.1964331210191083, | |
| "eval_loss": 0.7077798843383789, | |
| "eval_runtime": 52.7856, | |
| "eval_samples_per_second": 10.268, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.40918325883787077, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 57.14, | |
| "learning_rate": 1.8628571428571428e-05, | |
| "loss": 0.7997, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_cer": 0.1973430391264786, | |
| "eval_loss": 0.7078654170036316, | |
| "eval_runtime": 52.7848, | |
| "eval_samples_per_second": 10.268, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.4110117838277123, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_cer": 0.19832575068243857, | |
| "eval_loss": 0.6861252784729004, | |
| "eval_runtime": 52.8203, | |
| "eval_samples_per_second": 10.261, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.41365298659081673, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_cer": 0.1975250227479527, | |
| "eval_loss": 0.7035004496574402, | |
| "eval_runtime": 53.0259, | |
| "eval_samples_per_second": 10.221, | |
| "eval_steps_per_second": 1.282, | |
| "eval_wer": 0.4010564811052418, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_cer": 0.19417652411282985, | |
| "eval_loss": 0.6675873398780823, | |
| "eval_runtime": 52.839, | |
| "eval_samples_per_second": 10.258, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.4000406338886631, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_cer": 0.19366696997270247, | |
| "eval_loss": 0.6562079787254333, | |
| "eval_runtime": 52.8072, | |
| "eval_samples_per_second": 10.264, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.3980089394555059, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_cer": 0.1910828025477707, | |
| "eval_loss": 0.6579793691635132, | |
| "eval_runtime": 52.8351, | |
| "eval_samples_per_second": 10.258, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.38500609508329947, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_cer": 0.19253867151956325, | |
| "eval_loss": 0.6642553806304932, | |
| "eval_runtime": 52.8162, | |
| "eval_samples_per_second": 10.262, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.39110117838277125, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 64.29, | |
| "learning_rate": 1.72e-05, | |
| "loss": 0.5379, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_cer": 0.19282984531392175, | |
| "eval_loss": 0.6532391309738159, | |
| "eval_runtime": 52.87, | |
| "eval_samples_per_second": 10.252, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 0.39292970337261274, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_cer": 0.19064604185623293, | |
| "eval_loss": 0.6483404040336609, | |
| "eval_runtime": 52.7892, | |
| "eval_samples_per_second": 10.267, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.3866314506298253, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_cer": 0.18696997270245677, | |
| "eval_loss": 0.6266820430755615, | |
| "eval_runtime": 53.3837, | |
| "eval_samples_per_second": 10.153, | |
| "eval_steps_per_second": 1.274, | |
| "eval_wer": 0.3756603006907761, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_cer": 0.18798908098271155, | |
| "eval_loss": 0.6296297907829285, | |
| "eval_runtime": 52.8207, | |
| "eval_samples_per_second": 10.261, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.3793173506704592, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_cer": 0.19020928116469518, | |
| "eval_loss": 0.6414676904678345, | |
| "eval_runtime": 52.8153, | |
| "eval_samples_per_second": 10.262, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.37850467289719625, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_cer": 0.18846223839854412, | |
| "eval_loss": 0.6227236986160278, | |
| "eval_runtime": 52.8625, | |
| "eval_samples_per_second": 10.253, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 0.3746444534741975, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_cer": 0.1878434940855323, | |
| "eval_loss": 0.6213016510009766, | |
| "eval_runtime": 52.7591, | |
| "eval_samples_per_second": 10.273, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.37383177570093457, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 71.43, | |
| "learning_rate": 1.577142857142857e-05, | |
| "loss": 0.4372, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_cer": 0.18718835304822565, | |
| "eval_loss": 0.6110479831695557, | |
| "eval_runtime": 52.7876, | |
| "eval_samples_per_second": 10.268, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.37261275904104024, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_cer": 0.1861692447679709, | |
| "eval_loss": 0.6018897294998169, | |
| "eval_runtime": 52.8613, | |
| "eval_samples_per_second": 10.253, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 0.3695652173913043, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_cer": 0.18671519563239308, | |
| "eval_loss": 0.6036959290504456, | |
| "eval_runtime": 53.2023, | |
| "eval_samples_per_second": 10.188, | |
| "eval_steps_per_second": 1.278, | |
| "eval_wer": 0.3722064201544088, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_cer": 0.188098271155596, | |
| "eval_loss": 0.5993600487709045, | |
| "eval_runtime": 52.8215, | |
| "eval_samples_per_second": 10.261, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.3657049979683056, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_cer": 0.18806187443130118, | |
| "eval_loss": 0.6083250641822815, | |
| "eval_runtime": 52.971, | |
| "eval_samples_per_second": 10.232, | |
| "eval_steps_per_second": 1.284, | |
| "eval_wer": 0.37037789516456726, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_cer": 0.1864968152866242, | |
| "eval_loss": 0.5837586522102356, | |
| "eval_runtime": 53.4695, | |
| "eval_samples_per_second": 10.137, | |
| "eval_steps_per_second": 1.272, | |
| "eval_wer": 0.3695652173913043, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_cer": 0.18547770700636942, | |
| "eval_loss": 0.5794845819473267, | |
| "eval_runtime": 52.8335, | |
| "eval_samples_per_second": 10.259, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.3718000812677773, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 78.57, | |
| "learning_rate": 1.4342857142857143e-05, | |
| "loss": 0.3912, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_cer": 0.18773430391264787, | |
| "eval_loss": 0.6201197504997253, | |
| "eval_runtime": 52.909, | |
| "eval_samples_per_second": 10.244, | |
| "eval_steps_per_second": 1.285, | |
| "eval_wer": 0.37139374238114586, | |
| "step": 1106 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_cer": 0.1854413102820746, | |
| "eval_loss": 0.5914958715438843, | |
| "eval_runtime": 52.8551, | |
| "eval_samples_per_second": 10.254, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.366111336854937, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_cer": 0.18427661510464058, | |
| "eval_loss": 0.5893952250480652, | |
| "eval_runtime": 52.9037, | |
| "eval_samples_per_second": 10.245, | |
| "eval_steps_per_second": 1.285, | |
| "eval_wer": 0.3650954896383584, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_cer": 0.18591446769790718, | |
| "eval_loss": 0.5993715524673462, | |
| "eval_runtime": 52.7967, | |
| "eval_samples_per_second": 10.266, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.3681430312880943, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_cer": 0.18642402183803458, | |
| "eval_loss": 0.6001280546188354, | |
| "eval_runtime": 52.869, | |
| "eval_samples_per_second": 10.252, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 0.36550182852498986, | |
| "step": 1162 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_cer": 0.1864968152866242, | |
| "eval_loss": 0.6007617115974426, | |
| "eval_runtime": 52.8415, | |
| "eval_samples_per_second": 10.257, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.36529865908167414, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_cer": 0.18322111010009098, | |
| "eval_loss": 0.5769873857498169, | |
| "eval_runtime": 52.8264, | |
| "eval_samples_per_second": 10.26, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.36021942299878096, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 85.71, | |
| "learning_rate": 1.2914285714285713e-05, | |
| "loss": 0.3485, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_cer": 0.18358507734303914, | |
| "eval_loss": 0.5905404686927795, | |
| "eval_runtime": 52.731, | |
| "eval_samples_per_second": 10.279, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.35656237301909793, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_cer": 0.18278434940855323, | |
| "eval_loss": 0.5810394287109375, | |
| "eval_runtime": 52.802, | |
| "eval_samples_per_second": 10.265, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.35798455912230803, | |
| "step": 1218 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_cer": 0.1829663330300273, | |
| "eval_loss": 0.5765053033828735, | |
| "eval_runtime": 53.0488, | |
| "eval_samples_per_second": 10.217, | |
| "eval_steps_per_second": 1.282, | |
| "eval_wer": 0.3583908980089395, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_cer": 0.18453139217470427, | |
| "eval_loss": 0.5901545286178589, | |
| "eval_runtime": 52.796, | |
| "eval_samples_per_second": 10.266, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.36407964242177976, | |
| "step": 1246 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_cer": 0.18307552320291173, | |
| "eval_loss": 0.581239640712738, | |
| "eval_runtime": 52.8224, | |
| "eval_samples_per_second": 10.261, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.36143843965867534, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_cer": 0.18438580527752502, | |
| "eval_loss": 0.5965577960014343, | |
| "eval_runtime": 52.9107, | |
| "eval_samples_per_second": 10.244, | |
| "eval_steps_per_second": 1.285, | |
| "eval_wer": 0.3585940674522552, | |
| "step": 1274 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_cer": 0.18223839854413104, | |
| "eval_loss": 0.5686241388320923, | |
| "eval_runtime": 53.3712, | |
| "eval_samples_per_second": 10.155, | |
| "eval_steps_per_second": 1.274, | |
| "eval_wer": 0.35574969524583505, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 92.86, | |
| "learning_rate": 1.1485714285714285e-05, | |
| "loss": 0.3234, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_cer": 0.18282074613284804, | |
| "eval_loss": 0.5839269161224365, | |
| "eval_runtime": 52.8855, | |
| "eval_samples_per_second": 10.249, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 0.35534335635920355, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_cer": 0.18198362147406733, | |
| "eval_loss": 0.5765420198440552, | |
| "eval_runtime": 52.892, | |
| "eval_samples_per_second": 10.247, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 0.35534335635920355, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_cer": 0.18202001819836214, | |
| "eval_loss": 0.5779678225517273, | |
| "eval_runtime": 52.8619, | |
| "eval_samples_per_second": 10.253, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 0.35656237301909793, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_cer": 0.18343949044585986, | |
| "eval_loss": 0.5862200260162354, | |
| "eval_runtime": 52.9527, | |
| "eval_samples_per_second": 10.236, | |
| "eval_steps_per_second": 1.284, | |
| "eval_wer": 0.3596099146688338, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_cer": 0.18209281164695176, | |
| "eval_loss": 0.5701762437820435, | |
| "eval_runtime": 52.8493, | |
| "eval_samples_per_second": 10.256, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.3555465258025193, | |
| "step": 1358 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_cer": 0.18205641492265695, | |
| "eval_loss": 0.5787171721458435, | |
| "eval_runtime": 52.8738, | |
| "eval_samples_per_second": 10.251, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 0.3547338480292564, | |
| "step": 1372 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_cer": 0.1823839854413103, | |
| "eval_loss": 0.5766745209693909, | |
| "eval_runtime": 52.9499, | |
| "eval_samples_per_second": 10.236, | |
| "eval_steps_per_second": 1.284, | |
| "eval_wer": 0.3531084924827306, | |
| "step": 1386 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 1.0057142857142857e-05, | |
| "loss": 0.2803, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_cer": 0.18183803457688807, | |
| "eval_loss": 0.5778467655181885, | |
| "eval_runtime": 53.096, | |
| "eval_samples_per_second": 10.208, | |
| "eval_steps_per_second": 1.281, | |
| "eval_wer": 0.3569687119057294, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 101.0, | |
| "eval_cer": 0.18172884440400364, | |
| "eval_loss": 0.5759402513504028, | |
| "eval_runtime": 53.4646, | |
| "eval_samples_per_second": 10.138, | |
| "eval_steps_per_second": 1.272, | |
| "eval_wer": 0.35432750914262495, | |
| "step": 1414 | |
| }, | |
| { | |
| "epoch": 102.0, | |
| "eval_cer": 0.1823839854413103, | |
| "eval_loss": 0.5838054418563843, | |
| "eval_runtime": 53.0092, | |
| "eval_samples_per_second": 10.225, | |
| "eval_steps_per_second": 1.283, | |
| "eval_wer": 0.3571718813490451, | |
| "step": 1428 | |
| }, | |
| { | |
| "epoch": 103.0, | |
| "eval_cer": 0.18154686078252957, | |
| "eval_loss": 0.569597065448761, | |
| "eval_runtime": 53.1914, | |
| "eval_samples_per_second": 10.19, | |
| "eval_steps_per_second": 1.278, | |
| "eval_wer": 0.35412433969930923, | |
| "step": 1442 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "eval_cer": 0.18202001819836214, | |
| "eval_loss": 0.5723647475242615, | |
| "eval_runtime": 52.9421, | |
| "eval_samples_per_second": 10.238, | |
| "eval_steps_per_second": 1.284, | |
| "eval_wer": 0.35412433969930923, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "eval_cer": 0.18202001819836214, | |
| "eval_loss": 0.5698366165161133, | |
| "eval_runtime": 53.0166, | |
| "eval_samples_per_second": 10.223, | |
| "eval_steps_per_second": 1.283, | |
| "eval_wer": 0.35432750914262495, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 106.0, | |
| "eval_cer": 0.1816196542311192, | |
| "eval_loss": 0.5727118253707886, | |
| "eval_runtime": 52.9397, | |
| "eval_samples_per_second": 10.238, | |
| "eval_steps_per_second": 1.284, | |
| "eval_wer": 0.3522958147094677, | |
| "step": 1484 | |
| }, | |
| { | |
| "epoch": 107.0, | |
| "eval_cer": 0.1808553230209281, | |
| "eval_loss": 0.5609294176101685, | |
| "eval_runtime": 53.3257, | |
| "eval_samples_per_second": 10.164, | |
| "eval_steps_per_second": 1.275, | |
| "eval_wer": 0.35107679804957337, | |
| "step": 1498 | |
| }, | |
| { | |
| "epoch": 107.14, | |
| "learning_rate": 8.628571428571429e-06, | |
| "loss": 0.2718, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 108.0, | |
| "eval_cer": 0.18070973612374885, | |
| "eval_loss": 0.5654597282409668, | |
| "eval_runtime": 52.8748, | |
| "eval_samples_per_second": 10.251, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 0.34965461194636327, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 109.0, | |
| "eval_cer": 0.18158325750682439, | |
| "eval_loss": 0.5761396884918213, | |
| "eval_runtime": 52.7804, | |
| "eval_samples_per_second": 10.269, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.35351483136936207, | |
| "step": 1526 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "eval_cer": 0.18147406733393995, | |
| "eval_loss": 0.5753419995307922, | |
| "eval_runtime": 52.7887, | |
| "eval_samples_per_second": 10.267, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.3522958147094677, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 111.0, | |
| "eval_cer": 0.18049135577797998, | |
| "eval_loss": 0.5703160762786865, | |
| "eval_runtime": 52.7573, | |
| "eval_samples_per_second": 10.273, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.35026412027631043, | |
| "step": 1554 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "eval_cer": 0.18020018198362148, | |
| "eval_loss": 0.5622747540473938, | |
| "eval_runtime": 52.7621, | |
| "eval_samples_per_second": 10.273, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.34701340918325885, | |
| "step": 1568 | |
| }, | |
| { | |
| "epoch": 113.0, | |
| "eval_cer": 0.18129208371246588, | |
| "eval_loss": 0.5722905993461609, | |
| "eval_runtime": 52.84, | |
| "eval_samples_per_second": 10.257, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.35107679804957337, | |
| "step": 1582 | |
| }, | |
| { | |
| "epoch": 114.0, | |
| "eval_cer": 0.18030937215650591, | |
| "eval_loss": 0.5607832670211792, | |
| "eval_runtime": 52.8599, | |
| "eval_samples_per_second": 10.254, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 0.34863876472978467, | |
| "step": 1596 | |
| }, | |
| { | |
| "epoch": 114.29, | |
| "learning_rate": 7.2e-06, | |
| "loss": 0.2614, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 115.0, | |
| "eval_cer": 0.18089171974522292, | |
| "eval_loss": 0.5612644553184509, | |
| "eval_runtime": 52.8176, | |
| "eval_samples_per_second": 10.262, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.35107679804957337, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 116.0, | |
| "eval_cer": 0.18172884440400364, | |
| "eval_loss": 0.5742478370666504, | |
| "eval_runtime": 52.8139, | |
| "eval_samples_per_second": 10.262, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.35331166192604635, | |
| "step": 1624 | |
| }, | |
| { | |
| "epoch": 117.0, | |
| "eval_cer": 0.18172884440400364, | |
| "eval_loss": 0.5715382695198059, | |
| "eval_runtime": 52.8096, | |
| "eval_samples_per_second": 10.263, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.3522958147094677, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 118.0, | |
| "eval_cer": 0.18169244767970882, | |
| "eval_loss": 0.5695165395736694, | |
| "eval_runtime": 52.7498, | |
| "eval_samples_per_second": 10.275, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.35331166192604635, | |
| "step": 1652 | |
| }, | |
| { | |
| "epoch": 119.0, | |
| "eval_cer": 0.18245677888989992, | |
| "eval_loss": 0.571264386177063, | |
| "eval_runtime": 52.7339, | |
| "eval_samples_per_second": 10.278, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.3531084924827306, | |
| "step": 1666 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "eval_cer": 0.18205641492265695, | |
| "eval_loss": 0.5664474368095398, | |
| "eval_runtime": 52.8509, | |
| "eval_samples_per_second": 10.255, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.35331166192604635, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 121.0, | |
| "eval_cer": 0.1821656050955414, | |
| "eval_loss": 0.5716355443000793, | |
| "eval_runtime": 52.7551, | |
| "eval_samples_per_second": 10.274, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.3531084924827306, | |
| "step": 1694 | |
| }, | |
| { | |
| "epoch": 121.43, | |
| "learning_rate": 5.7714285714285715e-06, | |
| "loss": 0.2463, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 122.0, | |
| "eval_cer": 0.18100090991810738, | |
| "eval_loss": 0.568006694316864, | |
| "eval_runtime": 52.7861, | |
| "eval_samples_per_second": 10.268, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.347622917513206, | |
| "step": 1708 | |
| }, | |
| { | |
| "epoch": 123.0, | |
| "eval_cer": 0.18169244767970882, | |
| "eval_loss": 0.5760354399681091, | |
| "eval_runtime": 52.8132, | |
| "eval_samples_per_second": 10.263, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.35270215359609913, | |
| "step": 1722 | |
| }, | |
| { | |
| "epoch": 124.0, | |
| "eval_cer": 0.1802729754322111, | |
| "eval_loss": 0.556138277053833, | |
| "eval_runtime": 52.7767, | |
| "eval_samples_per_second": 10.27, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.34559122308004875, | |
| "step": 1736 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "eval_cer": 0.18118289353958145, | |
| "eval_loss": 0.5698420405387878, | |
| "eval_runtime": 52.7433, | |
| "eval_samples_per_second": 10.276, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.34782608695652173, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 126.0, | |
| "eval_cer": 0.18111010009099182, | |
| "eval_loss": 0.5667452216148376, | |
| "eval_runtime": 52.7698, | |
| "eval_samples_per_second": 10.271, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.34823242584315317, | |
| "step": 1764 | |
| }, | |
| { | |
| "epoch": 127.0, | |
| "eval_cer": 0.1813284804367607, | |
| "eval_loss": 0.5677050948143005, | |
| "eval_runtime": 52.7873, | |
| "eval_samples_per_second": 10.268, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.34782608695652173, | |
| "step": 1778 | |
| }, | |
| { | |
| "epoch": 128.0, | |
| "eval_cer": 0.18045495905368517, | |
| "eval_loss": 0.5681147575378418, | |
| "eval_runtime": 53.1709, | |
| "eval_samples_per_second": 10.194, | |
| "eval_steps_per_second": 1.279, | |
| "eval_wer": 0.34457537586347015, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 128.57, | |
| "learning_rate": 4.342857142857143e-06, | |
| "loss": 0.2477, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 129.0, | |
| "eval_cer": 0.18089171974522292, | |
| "eval_loss": 0.5665947794914246, | |
| "eval_runtime": 52.9379, | |
| "eval_samples_per_second": 10.238, | |
| "eval_steps_per_second": 1.285, | |
| "eval_wer": 0.34701340918325885, | |
| "step": 1806 | |
| }, | |
| { | |
| "epoch": 130.0, | |
| "eval_cer": 0.18041856232939035, | |
| "eval_loss": 0.5696049928665161, | |
| "eval_runtime": 52.7984, | |
| "eval_samples_per_second": 10.265, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.34579439252336447, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 131.0, | |
| "eval_cer": 0.1810373066424022, | |
| "eval_loss": 0.5704218149185181, | |
| "eval_runtime": 52.8548, | |
| "eval_samples_per_second": 10.255, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.34782608695652173, | |
| "step": 1834 | |
| }, | |
| { | |
| "epoch": 132.0, | |
| "eval_cer": 0.18078252957233848, | |
| "eval_loss": 0.5655524134635925, | |
| "eval_runtime": 52.9545, | |
| "eval_samples_per_second": 10.235, | |
| "eval_steps_per_second": 1.284, | |
| "eval_wer": 0.34701340918325885, | |
| "step": 1848 | |
| }, | |
| { | |
| "epoch": 133.0, | |
| "eval_cer": 0.18070973612374885, | |
| "eval_loss": 0.5696657299995422, | |
| "eval_runtime": 52.865, | |
| "eval_samples_per_second": 10.253, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 0.34721657862657457, | |
| "step": 1862 | |
| }, | |
| { | |
| "epoch": 134.0, | |
| "eval_cer": 0.18096451319381257, | |
| "eval_loss": 0.5716409683227539, | |
| "eval_runtime": 52.8035, | |
| "eval_samples_per_second": 10.264, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.34721657862657457, | |
| "step": 1876 | |
| }, | |
| { | |
| "epoch": 135.0, | |
| "eval_cer": 0.18096451319381257, | |
| "eval_loss": 0.5742436647415161, | |
| "eval_runtime": 52.961, | |
| "eval_samples_per_second": 10.234, | |
| "eval_steps_per_second": 1.284, | |
| "eval_wer": 0.3484355952864689, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 135.71, | |
| "learning_rate": 2.9142857142857142e-06, | |
| "loss": 0.221, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 136.0, | |
| "eval_cer": 0.18074613284804367, | |
| "eval_loss": 0.567115306854248, | |
| "eval_runtime": 52.8477, | |
| "eval_samples_per_second": 10.256, | |
| "eval_steps_per_second": 1.287, | |
| "eval_wer": 0.34721657862657457, | |
| "step": 1904 | |
| }, | |
| { | |
| "epoch": 137.0, | |
| "eval_cer": 0.18096451319381257, | |
| "eval_loss": 0.5669675469398499, | |
| "eval_runtime": 52.9196, | |
| "eval_samples_per_second": 10.242, | |
| "eval_steps_per_second": 1.285, | |
| "eval_wer": 0.3462007314099959, | |
| "step": 1918 | |
| }, | |
| { | |
| "epoch": 138.0, | |
| "eval_cer": 0.18100090991810738, | |
| "eval_loss": 0.5674601793289185, | |
| "eval_runtime": 53.2148, | |
| "eval_samples_per_second": 10.185, | |
| "eval_steps_per_second": 1.278, | |
| "eval_wer": 0.3459975619666802, | |
| "step": 1932 | |
| }, | |
| { | |
| "epoch": 139.0, | |
| "eval_cer": 0.18100090991810738, | |
| "eval_loss": 0.5703522562980652, | |
| "eval_runtime": 53.4902, | |
| "eval_samples_per_second": 10.133, | |
| "eval_steps_per_second": 1.271, | |
| "eval_wer": 0.3462007314099959, | |
| "step": 1946 | |
| }, | |
| { | |
| "epoch": 140.0, | |
| "eval_cer": 0.1808189262966333, | |
| "eval_loss": 0.5675067901611328, | |
| "eval_runtime": 53.2601, | |
| "eval_samples_per_second": 10.176, | |
| "eval_steps_per_second": 1.277, | |
| "eval_wer": 0.34579439252336447, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 141.0, | |
| "eval_cer": 0.1800181983621474, | |
| "eval_loss": 0.5617998838424683, | |
| "eval_runtime": 53.8381, | |
| "eval_samples_per_second": 10.067, | |
| "eval_steps_per_second": 1.263, | |
| "eval_wer": 0.3443722064201544, | |
| "step": 1974 | |
| }, | |
| { | |
| "epoch": 142.0, | |
| "eval_cer": 0.1799818016378526, | |
| "eval_loss": 0.563258171081543, | |
| "eval_runtime": 53.4467, | |
| "eval_samples_per_second": 10.141, | |
| "eval_steps_per_second": 1.272, | |
| "eval_wer": 0.34538805363673303, | |
| "step": 1988 | |
| }, | |
| { | |
| "epoch": 142.86, | |
| "learning_rate": 1.4857142857142858e-06, | |
| "loss": 0.2217, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 143.0, | |
| "eval_cer": 0.18067333939945404, | |
| "eval_loss": 0.5663711428642273, | |
| "eval_runtime": 53.0769, | |
| "eval_samples_per_second": 10.212, | |
| "eval_steps_per_second": 1.281, | |
| "eval_wer": 0.34559122308004875, | |
| "step": 2002 | |
| }, | |
| { | |
| "epoch": 144.0, | |
| "eval_cer": 0.18100090991810738, | |
| "eval_loss": 0.5682144165039062, | |
| "eval_runtime": 53.3453, | |
| "eval_samples_per_second": 10.16, | |
| "eval_steps_per_second": 1.275, | |
| "eval_wer": 0.3462007314099959, | |
| "step": 2016 | |
| }, | |
| { | |
| "epoch": 144.0, | |
| "step": 2016, | |
| "total_flos": 1.799432351021922e+19, | |
| "train_loss": 1.5532687327691488, | |
| "train_runtime": 29581.7912, | |
| "train_samples_per_second": 2.272, | |
| "train_steps_per_second": 0.071 | |
| } | |
| ], | |
| "max_steps": 2100, | |
| "num_train_epochs": 150, | |
| "total_flos": 1.799432351021922e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |