| { | |
| "best_metric": 0.6735167503356934, | |
| "best_model_checkpoint": "../checkpoints/YourTTS2ASR/Wav2Vec-voxpopuli/one-speaker/just-TTS/PT/140-epoch-high-bs/checkpoint-1920", | |
| "epoch": 129.99481865284974, | |
| "global_step": 2080, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.0000000000000002e-07, | |
| "loss": 12.0818, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 12.243678092956543, | |
| "eval_runtime": 49.2931, | |
| "eval_samples_per_second": 10.143, | |
| "eval_wer": 1.0009390651085142, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 12.257490158081055, | |
| "eval_runtime": 50.2087, | |
| "eval_samples_per_second": 9.958, | |
| "eval_wer": 1.0005217028380635, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_loss": 11.961856842041016, | |
| "eval_runtime": 48.9816, | |
| "eval_samples_per_second": 10.208, | |
| "eval_wer": 0.9989565943238731, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_loss": 10.610284805297852, | |
| "eval_runtime": 49.2335, | |
| "eval_samples_per_second": 10.156, | |
| "eval_wer": 0.9995826377295493, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_loss": 8.434402465820312, | |
| "eval_runtime": 50.1138, | |
| "eval_samples_per_second": 9.977, | |
| "eval_wer": 1.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "eval_loss": 6.819848537445068, | |
| "eval_runtime": 50.2226, | |
| "eval_samples_per_second": 9.956, | |
| "eval_wer": 1.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 11.0338, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_loss": 5.784036159515381, | |
| "eval_runtime": 49.485, | |
| "eval_samples_per_second": 10.104, | |
| "eval_wer": 1.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "eval_loss": 5.032914161682129, | |
| "eval_runtime": 49.5792, | |
| "eval_samples_per_second": 10.085, | |
| "eval_wer": 1.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_loss": 4.575235366821289, | |
| "eval_runtime": 48.3292, | |
| "eval_samples_per_second": 10.346, | |
| "eval_wer": 1.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "eval_loss": 4.227362155914307, | |
| "eval_runtime": 50.081, | |
| "eval_samples_per_second": 9.984, | |
| "eval_wer": 1.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_loss": 3.977447271347046, | |
| "eval_runtime": 49.6321, | |
| "eval_samples_per_second": 10.074, | |
| "eval_wer": 1.0, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "eval_loss": 3.8090567588806152, | |
| "eval_runtime": 49.5094, | |
| "eval_samples_per_second": 10.099, | |
| "eval_wer": 1.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 2.9282296650717705e-05, | |
| "loss": 5.2367, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_loss": 3.6537370681762695, | |
| "eval_runtime": 49.2195, | |
| "eval_samples_per_second": 10.159, | |
| "eval_wer": 1.0, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "eval_loss": 3.5310537815093994, | |
| "eval_runtime": 48.9715, | |
| "eval_samples_per_second": 10.21, | |
| "eval_wer": 1.0, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_loss": 3.4466352462768555, | |
| "eval_runtime": 49.4588, | |
| "eval_samples_per_second": 10.109, | |
| "eval_wer": 1.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "eval_loss": 3.325173854827881, | |
| "eval_runtime": 48.5474, | |
| "eval_samples_per_second": 10.299, | |
| "eval_wer": 1.0, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_loss": 3.2516260147094727, | |
| "eval_runtime": 49.5175, | |
| "eval_samples_per_second": 10.097, | |
| "eval_wer": 1.0, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 17.99, | |
| "eval_loss": 3.1839869022369385, | |
| "eval_runtime": 48.9663, | |
| "eval_samples_per_second": 10.211, | |
| "eval_wer": 1.0, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "learning_rate": 2.784688995215311e-05, | |
| "loss": 3.5824, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_loss": 3.1358871459960938, | |
| "eval_runtime": 49.4599, | |
| "eval_samples_per_second": 10.109, | |
| "eval_wer": 1.0, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 19.99, | |
| "eval_loss": 3.0906283855438232, | |
| "eval_runtime": 49.5292, | |
| "eval_samples_per_second": 10.095, | |
| "eval_wer": 1.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_loss": 3.0470166206359863, | |
| "eval_runtime": 49.8959, | |
| "eval_samples_per_second": 10.021, | |
| "eval_wer": 1.0, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 21.99, | |
| "eval_loss": 3.0199356079101562, | |
| "eval_runtime": 48.7586, | |
| "eval_samples_per_second": 10.255, | |
| "eval_wer": 1.0, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 22.99, | |
| "eval_loss": 2.993663787841797, | |
| "eval_runtime": 49.2925, | |
| "eval_samples_per_second": 10.144, | |
| "eval_wer": 1.0, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 23.99, | |
| "eval_loss": 2.9856507778167725, | |
| "eval_runtime": 48.889, | |
| "eval_samples_per_second": 10.227, | |
| "eval_wer": 1.0, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "learning_rate": 2.6411483253588518e-05, | |
| "loss": 3.088, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_loss": 2.952263116836548, | |
| "eval_runtime": 49.1389, | |
| "eval_samples_per_second": 10.175, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 25.99, | |
| "eval_loss": 2.9487361907958984, | |
| "eval_runtime": 49.3941, | |
| "eval_samples_per_second": 10.123, | |
| "eval_wer": 1.0, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "eval_loss": 2.9333157539367676, | |
| "eval_runtime": 49.2595, | |
| "eval_samples_per_second": 10.15, | |
| "eval_wer": 1.0, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 27.99, | |
| "eval_loss": 2.9365267753601074, | |
| "eval_runtime": 49.5918, | |
| "eval_samples_per_second": 10.082, | |
| "eval_wer": 1.0, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_loss": 2.926832914352417, | |
| "eval_runtime": 49.5193, | |
| "eval_samples_per_second": 10.097, | |
| "eval_wer": 1.0, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 29.99, | |
| "eval_loss": 2.9162416458129883, | |
| "eval_runtime": 49.57, | |
| "eval_samples_per_second": 10.087, | |
| "eval_wer": 1.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 30.99, | |
| "eval_loss": 2.9036505222320557, | |
| "eval_runtime": 49.6143, | |
| "eval_samples_per_second": 10.078, | |
| "eval_wer": 1.0, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 31.25, | |
| "learning_rate": 2.4976076555023923e-05, | |
| "loss": 2.9504, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 31.99, | |
| "eval_loss": 2.9000539779663086, | |
| "eval_runtime": 49.4941, | |
| "eval_samples_per_second": 10.102, | |
| "eval_wer": 1.0, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 32.99, | |
| "eval_loss": 2.893620491027832, | |
| "eval_runtime": 50.1869, | |
| "eval_samples_per_second": 9.963, | |
| "eval_wer": 1.0, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 33.99, | |
| "eval_loss": 2.8881995677948, | |
| "eval_runtime": 49.8317, | |
| "eval_samples_per_second": 10.034, | |
| "eval_wer": 1.0, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 34.99, | |
| "eval_loss": 2.8850040435791016, | |
| "eval_runtime": 49.2167, | |
| "eval_samples_per_second": 10.159, | |
| "eval_wer": 1.0, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 35.99, | |
| "eval_loss": 2.8831725120544434, | |
| "eval_runtime": 49.9233, | |
| "eval_samples_per_second": 10.015, | |
| "eval_wer": 1.0, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 36.99, | |
| "eval_loss": 2.8862743377685547, | |
| "eval_runtime": 49.9603, | |
| "eval_samples_per_second": 10.008, | |
| "eval_wer": 1.0, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "learning_rate": 2.354066985645933e-05, | |
| "loss": 2.9116, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 37.99, | |
| "eval_loss": 2.8713128566741943, | |
| "eval_runtime": 48.8267, | |
| "eval_samples_per_second": 10.24, | |
| "eval_wer": 1.0, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 38.99, | |
| "eval_loss": 2.8694326877593994, | |
| "eval_runtime": 50.3391, | |
| "eval_samples_per_second": 9.933, | |
| "eval_wer": 1.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 39.99, | |
| "eval_loss": 2.8684744834899902, | |
| "eval_runtime": 49.7451, | |
| "eval_samples_per_second": 10.051, | |
| "eval_wer": 1.0, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 40.99, | |
| "eval_loss": 2.8572192192077637, | |
| "eval_runtime": 50.1709, | |
| "eval_samples_per_second": 9.966, | |
| "eval_wer": 1.0, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 41.99, | |
| "eval_loss": 2.8502085208892822, | |
| "eval_runtime": 49.5484, | |
| "eval_samples_per_second": 10.091, | |
| "eval_wer": 1.0, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 42.99, | |
| "eval_loss": 2.8417484760284424, | |
| "eval_runtime": 49.0891, | |
| "eval_samples_per_second": 10.186, | |
| "eval_wer": 1.0, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 43.75, | |
| "learning_rate": 2.2105263157894736e-05, | |
| "loss": 2.8836, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 43.99, | |
| "eval_loss": 2.8355417251586914, | |
| "eval_runtime": 49.7, | |
| "eval_samples_per_second": 10.06, | |
| "eval_wer": 1.0, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 44.99, | |
| "eval_loss": 2.8320789337158203, | |
| "eval_runtime": 49.7957, | |
| "eval_samples_per_second": 10.041, | |
| "eval_wer": 1.0, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 45.99, | |
| "eval_loss": 2.8173515796661377, | |
| "eval_runtime": 49.7947, | |
| "eval_samples_per_second": 10.041, | |
| "eval_wer": 1.0, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 46.99, | |
| "eval_loss": 2.799645185470581, | |
| "eval_runtime": 49.4675, | |
| "eval_samples_per_second": 10.108, | |
| "eval_wer": 1.0, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 47.99, | |
| "eval_loss": 2.783804178237915, | |
| "eval_runtime": 49.2068, | |
| "eval_samples_per_second": 10.161, | |
| "eval_wer": 1.0, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 48.99, | |
| "eval_loss": 2.759208917617798, | |
| "eval_runtime": 49.4097, | |
| "eval_samples_per_second": 10.119, | |
| "eval_wer": 1.0, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 49.99, | |
| "learning_rate": 2.0669856459330144e-05, | |
| "loss": 2.8277, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 49.99, | |
| "eval_loss": 2.7332029342651367, | |
| "eval_runtime": 49.4948, | |
| "eval_samples_per_second": 10.102, | |
| "eval_wer": 1.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 50.99, | |
| "eval_loss": 2.709989309310913, | |
| "eval_runtime": 48.8084, | |
| "eval_samples_per_second": 10.244, | |
| "eval_wer": 0.9984348914858097, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 51.99, | |
| "eval_loss": 2.6740872859954834, | |
| "eval_runtime": 49.8376, | |
| "eval_samples_per_second": 10.033, | |
| "eval_wer": 0.9957220367278798, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 52.99, | |
| "eval_loss": 2.646063804626465, | |
| "eval_runtime": 49.3421, | |
| "eval_samples_per_second": 10.133, | |
| "eval_wer": 0.9908180300500835, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 53.99, | |
| "eval_loss": 2.6031899452209473, | |
| "eval_runtime": 49.5023, | |
| "eval_samples_per_second": 10.101, | |
| "eval_wer": 0.9760016694490818, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 54.99, | |
| "eval_loss": 2.5573575496673584, | |
| "eval_runtime": 49.9478, | |
| "eval_samples_per_second": 10.01, | |
| "eval_wer": 0.9698455759599333, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 55.99, | |
| "eval_loss": 2.488868236541748, | |
| "eval_runtime": 50.1085, | |
| "eval_samples_per_second": 9.978, | |
| "eval_wer": 0.9582637729549248, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 56.25, | |
| "learning_rate": 1.9234449760765553e-05, | |
| "loss": 2.6844, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 56.99, | |
| "eval_loss": 2.4326117038726807, | |
| "eval_runtime": 50.1267, | |
| "eval_samples_per_second": 9.975, | |
| "eval_wer": 0.9516903171953256, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 57.99, | |
| "eval_loss": 2.357138156890869, | |
| "eval_runtime": 50.0431, | |
| "eval_samples_per_second": 9.991, | |
| "eval_wer": 0.9559682804674458, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 58.99, | |
| "eval_loss": 2.2913711071014404, | |
| "eval_runtime": 50.0784, | |
| "eval_samples_per_second": 9.984, | |
| "eval_wer": 0.9559682804674458, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 59.99, | |
| "eval_loss": 2.21211314201355, | |
| "eval_runtime": 49.4565, | |
| "eval_samples_per_second": 10.11, | |
| "eval_wer": 0.9565943238731218, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 60.99, | |
| "eval_loss": 2.1155571937561035, | |
| "eval_runtime": 48.9205, | |
| "eval_samples_per_second": 10.221, | |
| "eval_wer": 0.9346828046744574, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 61.99, | |
| "eval_loss": 2.0269429683685303, | |
| "eval_runtime": 49.2233, | |
| "eval_samples_per_second": 10.158, | |
| "eval_wer": 0.9186143572621035, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 62.5, | |
| "learning_rate": 1.7799043062200958e-05, | |
| "loss": 2.3941, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 62.99, | |
| "eval_loss": 1.9515246152877808, | |
| "eval_runtime": 49.3099, | |
| "eval_samples_per_second": 10.14, | |
| "eval_wer": 0.9009808013355592, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 63.99, | |
| "eval_loss": 1.8633095026016235, | |
| "eval_runtime": 49.6022, | |
| "eval_samples_per_second": 10.08, | |
| "eval_wer": 0.8821994991652755, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 64.99, | |
| "eval_loss": 1.7742440700531006, | |
| "eval_runtime": 49.4148, | |
| "eval_samples_per_second": 10.118, | |
| "eval_wer": 0.8746869782971619, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 65.99, | |
| "eval_loss": 1.6952035427093506, | |
| "eval_runtime": 49.4954, | |
| "eval_samples_per_second": 10.102, | |
| "eval_wer": 0.8543405676126878, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 66.99, | |
| "eval_loss": 1.6496139764785767, | |
| "eval_runtime": 50.2365, | |
| "eval_samples_per_second": 9.953, | |
| "eval_wer": 0.8415066777963273, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 67.99, | |
| "eval_loss": 1.577644944190979, | |
| "eval_runtime": 49.0048, | |
| "eval_samples_per_second": 10.203, | |
| "eval_wer": 0.8229340567612687, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 68.75, | |
| "learning_rate": 1.6363636363636363e-05, | |
| "loss": 1.9737, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 68.99, | |
| "eval_loss": 1.5079734325408936, | |
| "eval_runtime": 49.8276, | |
| "eval_samples_per_second": 10.035, | |
| "eval_wer": 0.7996661101836394, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 69.99, | |
| "eval_loss": 1.4567533731460571, | |
| "eval_runtime": 48.81, | |
| "eval_samples_per_second": 10.244, | |
| "eval_wer": 0.7835976627712855, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 70.99, | |
| "eval_loss": 1.4095492362976074, | |
| "eval_runtime": 50.121, | |
| "eval_samples_per_second": 9.976, | |
| "eval_wer": 0.7838063439065108, | |
| "step": 1136 | |
| }, | |
| { | |
| "epoch": 71.99, | |
| "eval_loss": 1.3987743854522705, | |
| "eval_runtime": 49.582, | |
| "eval_samples_per_second": 10.084, | |
| "eval_wer": 0.7634599332220368, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 72.99, | |
| "eval_loss": 1.3577879667282104, | |
| "eval_runtime": 49.6213, | |
| "eval_samples_per_second": 10.076, | |
| "eval_wer": 0.7589732888146912, | |
| "step": 1168 | |
| }, | |
| { | |
| "epoch": 73.99, | |
| "eval_loss": 1.3037357330322266, | |
| "eval_runtime": 49.3802, | |
| "eval_samples_per_second": 10.126, | |
| "eval_wer": 0.7461393989983306, | |
| "step": 1184 | |
| }, | |
| { | |
| "epoch": 74.99, | |
| "learning_rate": 1.492822966507177e-05, | |
| "loss": 1.6567, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 74.99, | |
| "eval_loss": 1.2708954811096191, | |
| "eval_runtime": 49.4247, | |
| "eval_samples_per_second": 10.116, | |
| "eval_wer": 0.7350792988313857, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 75.99, | |
| "eval_loss": 1.2239230871200562, | |
| "eval_runtime": 50.0296, | |
| "eval_samples_per_second": 9.994, | |
| "eval_wer": 0.7258973288814691, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 76.99, | |
| "eval_loss": 1.1831496953964233, | |
| "eval_runtime": 49.5093, | |
| "eval_samples_per_second": 10.099, | |
| "eval_wer": 0.7141068447412354, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 77.99, | |
| "eval_loss": 1.1715855598449707, | |
| "eval_runtime": 50.4813, | |
| "eval_samples_per_second": 9.905, | |
| "eval_wer": 0.7060726210350584, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 78.99, | |
| "eval_loss": 1.1489920616149902, | |
| "eval_runtime": 49.5198, | |
| "eval_samples_per_second": 10.097, | |
| "eval_wer": 0.7013772954924875, | |
| "step": 1264 | |
| }, | |
| { | |
| "epoch": 79.99, | |
| "eval_loss": 1.1155155897140503, | |
| "eval_runtime": 49.0369, | |
| "eval_samples_per_second": 10.196, | |
| "eval_wer": 0.6840567612687813, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 80.99, | |
| "eval_loss": 1.091223955154419, | |
| "eval_runtime": 49.9086, | |
| "eval_samples_per_second": 10.018, | |
| "eval_wer": 0.6698664440734557, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 81.25, | |
| "learning_rate": 1.3492822966507177e-05, | |
| "loss": 1.4388, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 81.99, | |
| "eval_loss": 1.0740453004837036, | |
| "eval_runtime": 49.6299, | |
| "eval_samples_per_second": 10.075, | |
| "eval_wer": 0.659432387312187, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 82.99, | |
| "eval_loss": 1.0269348621368408, | |
| "eval_runtime": 49.8552, | |
| "eval_samples_per_second": 10.029, | |
| "eval_wer": 0.648059265442404, | |
| "step": 1328 | |
| }, | |
| { | |
| "epoch": 83.99, | |
| "eval_loss": 0.9962567090988159, | |
| "eval_runtime": 49.19, | |
| "eval_samples_per_second": 10.165, | |
| "eval_wer": 0.6295909849749582, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 84.99, | |
| "eval_loss": 0.989078164100647, | |
| "eval_runtime": 49.4835, | |
| "eval_samples_per_second": 10.104, | |
| "eval_wer": 0.6127921535893155, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 85.99, | |
| "eval_loss": 0.9740233421325684, | |
| "eval_runtime": 49.61, | |
| "eval_samples_per_second": 10.079, | |
| "eval_wer": 0.6173831385642737, | |
| "step": 1376 | |
| }, | |
| { | |
| "epoch": 86.99, | |
| "eval_loss": 0.9527219533920288, | |
| "eval_runtime": 49.7235, | |
| "eval_samples_per_second": 10.056, | |
| "eval_wer": 0.6007929883138564, | |
| "step": 1392 | |
| }, | |
| { | |
| "epoch": 87.5, | |
| "learning_rate": 1.2057416267942584e-05, | |
| "loss": 1.2741, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 87.99, | |
| "eval_loss": 0.926001787185669, | |
| "eval_runtime": 50.147, | |
| "eval_samples_per_second": 9.971, | |
| "eval_wer": 0.5874373956594324, | |
| "step": 1408 | |
| }, | |
| { | |
| "epoch": 88.99, | |
| "eval_loss": 0.928646445274353, | |
| "eval_runtime": 50.0432, | |
| "eval_samples_per_second": 9.991, | |
| "eval_wer": 0.5846202003338898, | |
| "step": 1424 | |
| }, | |
| { | |
| "epoch": 89.99, | |
| "eval_loss": 0.915071964263916, | |
| "eval_runtime": 48.6625, | |
| "eval_samples_per_second": 10.275, | |
| "eval_wer": 0.5746035058430717, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 90.99, | |
| "eval_loss": 0.8867021203041077, | |
| "eval_runtime": 49.6538, | |
| "eval_samples_per_second": 10.07, | |
| "eval_wer": 0.5595784641068448, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 91.99, | |
| "eval_loss": 0.8880752921104431, | |
| "eval_runtime": 49.9668, | |
| "eval_samples_per_second": 10.007, | |
| "eval_wer": 0.5575959933222037, | |
| "step": 1472 | |
| }, | |
| { | |
| "epoch": 92.99, | |
| "eval_loss": 0.8759620189666748, | |
| "eval_runtime": 49.4232, | |
| "eval_samples_per_second": 10.117, | |
| "eval_wer": 0.550813856427379, | |
| "step": 1488 | |
| }, | |
| { | |
| "epoch": 93.75, | |
| "learning_rate": 1.062200956937799e-05, | |
| "loss": 1.1621, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 93.99, | |
| "eval_loss": 0.8622854948043823, | |
| "eval_runtime": 50.0666, | |
| "eval_samples_per_second": 9.987, | |
| "eval_wer": 0.5416318864774624, | |
| "step": 1504 | |
| }, | |
| { | |
| "epoch": 94.99, | |
| "eval_loss": 0.829269528388977, | |
| "eval_runtime": 49.9208, | |
| "eval_samples_per_second": 10.016, | |
| "eval_wer": 0.5364148580968281, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 95.99, | |
| "eval_loss": 0.8396909832954407, | |
| "eval_runtime": 48.9453, | |
| "eval_samples_per_second": 10.215, | |
| "eval_wer": 0.5285893155258765, | |
| "step": 1536 | |
| }, | |
| { | |
| "epoch": 96.99, | |
| "eval_loss": 0.8327041268348694, | |
| "eval_runtime": 49.8765, | |
| "eval_samples_per_second": 10.025, | |
| "eval_wer": 0.5255634390651085, | |
| "step": 1552 | |
| }, | |
| { | |
| "epoch": 97.99, | |
| "eval_loss": 0.8415578603744507, | |
| "eval_runtime": 49.2064, | |
| "eval_samples_per_second": 10.161, | |
| "eval_wer": 0.528067612687813, | |
| "step": 1568 | |
| }, | |
| { | |
| "epoch": 98.99, | |
| "eval_loss": 0.8029292225837708, | |
| "eval_runtime": 49.3718, | |
| "eval_samples_per_second": 10.127, | |
| "eval_wer": 0.5109557595993323, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 99.99, | |
| "learning_rate": 9.186602870813397e-06, | |
| "loss": 1.0779, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 99.99, | |
| "eval_loss": 0.8305151462554932, | |
| "eval_runtime": 50.2704, | |
| "eval_samples_per_second": 9.946, | |
| "eval_wer": 0.5202420701168614, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 100.99, | |
| "eval_loss": 0.794418215751648, | |
| "eval_runtime": 48.8334, | |
| "eval_samples_per_second": 10.239, | |
| "eval_wer": 0.5020868113522537, | |
| "step": 1616 | |
| }, | |
| { | |
| "epoch": 101.99, | |
| "eval_loss": 0.8060072064399719, | |
| "eval_runtime": 50.0476, | |
| "eval_samples_per_second": 9.99, | |
| "eval_wer": 0.5134599332220368, | |
| "step": 1632 | |
| }, | |
| { | |
| "epoch": 102.99, | |
| "eval_loss": 0.7654790878295898, | |
| "eval_runtime": 49.2057, | |
| "eval_samples_per_second": 10.161, | |
| "eval_wer": 0.4867487479131887, | |
| "step": 1648 | |
| }, | |
| { | |
| "epoch": 103.99, | |
| "eval_loss": 0.7860442996025085, | |
| "eval_runtime": 49.9368, | |
| "eval_samples_per_second": 10.013, | |
| "eval_wer": 0.49947829716193654, | |
| "step": 1664 | |
| }, | |
| { | |
| "epoch": 104.99, | |
| "eval_loss": 0.7663349509239197, | |
| "eval_runtime": 49.0409, | |
| "eval_samples_per_second": 10.196, | |
| "eval_wer": 0.4897746243739566, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 105.99, | |
| "eval_loss": 0.7740986347198486, | |
| "eval_runtime": 49.5176, | |
| "eval_samples_per_second": 10.097, | |
| "eval_wer": 0.4820534223706177, | |
| "step": 1696 | |
| }, | |
| { | |
| "epoch": 106.25, | |
| "learning_rate": 7.751196172248804e-06, | |
| "loss": 1.0149, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 106.99, | |
| "eval_loss": 0.72774338722229, | |
| "eval_runtime": 49.0666, | |
| "eval_samples_per_second": 10.19, | |
| "eval_wer": 0.4803839732888147, | |
| "step": 1712 | |
| }, | |
| { | |
| "epoch": 107.99, | |
| "eval_loss": 0.7349050641059875, | |
| "eval_runtime": 49.3653, | |
| "eval_samples_per_second": 10.129, | |
| "eval_wer": 0.46869782971619367, | |
| "step": 1728 | |
| }, | |
| { | |
| "epoch": 108.99, | |
| "eval_loss": 0.730620265007019, | |
| "eval_runtime": 48.8671, | |
| "eval_samples_per_second": 10.232, | |
| "eval_wer": 0.4691151919866444, | |
| "step": 1744 | |
| }, | |
| { | |
| "epoch": 109.99, | |
| "eval_loss": 0.7221301198005676, | |
| "eval_runtime": 50.0918, | |
| "eval_samples_per_second": 9.982, | |
| "eval_wer": 0.4692195325542571, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 110.99, | |
| "eval_loss": 0.7237880825996399, | |
| "eval_runtime": 49.0461, | |
| "eval_samples_per_second": 10.194, | |
| "eval_wer": 0.4645242070116861, | |
| "step": 1776 | |
| }, | |
| { | |
| "epoch": 111.99, | |
| "eval_loss": 0.7305303812026978, | |
| "eval_runtime": 49.3111, | |
| "eval_samples_per_second": 10.14, | |
| "eval_wer": 0.46128964941569284, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 112.5, | |
| "learning_rate": 6.31578947368421e-06, | |
| "loss": 0.9691, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 112.99, | |
| "eval_loss": 0.7333260774612427, | |
| "eval_runtime": 49.8629, | |
| "eval_samples_per_second": 10.027, | |
| "eval_wer": 0.46295909849749584, | |
| "step": 1808 | |
| }, | |
| { | |
| "epoch": 113.99, | |
| "eval_loss": 0.738413393497467, | |
| "eval_runtime": 49.8063, | |
| "eval_samples_per_second": 10.039, | |
| "eval_wer": 0.4565943238731219, | |
| "step": 1824 | |
| }, | |
| { | |
| "epoch": 114.99, | |
| "eval_loss": 0.7188318371772766, | |
| "eval_runtime": 49.6388, | |
| "eval_samples_per_second": 10.073, | |
| "eval_wer": 0.46212437395659434, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 115.99, | |
| "eval_loss": 0.6936877369880676, | |
| "eval_runtime": 50.2237, | |
| "eval_samples_per_second": 9.955, | |
| "eval_wer": 0.4554465776293823, | |
| "step": 1856 | |
| }, | |
| { | |
| "epoch": 116.99, | |
| "eval_loss": 0.7130375504493713, | |
| "eval_runtime": 49.1949, | |
| "eval_samples_per_second": 10.164, | |
| "eval_wer": 0.4492904841402337, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 117.99, | |
| "eval_loss": 0.7151590585708618, | |
| "eval_runtime": 49.9104, | |
| "eval_samples_per_second": 10.018, | |
| "eval_wer": 0.4492904841402337, | |
| "step": 1888 | |
| }, | |
| { | |
| "epoch": 118.75, | |
| "learning_rate": 4.880382775119617e-06, | |
| "loss": 0.9391, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 118.99, | |
| "eval_loss": 0.7040448188781738, | |
| "eval_runtime": 49.7002, | |
| "eval_samples_per_second": 10.06, | |
| "eval_wer": 0.45398580968280466, | |
| "step": 1904 | |
| }, | |
| { | |
| "epoch": 119.99, | |
| "eval_loss": 0.6735167503356934, | |
| "eval_runtime": 49.7634, | |
| "eval_samples_per_second": 10.048, | |
| "eval_wer": 0.4393781302170284, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 120.99, | |
| "eval_loss": 0.6741155385971069, | |
| "eval_runtime": 49.3263, | |
| "eval_samples_per_second": 10.137, | |
| "eval_wer": 0.4453255425709516, | |
| "step": 1936 | |
| }, | |
| { | |
| "epoch": 121.99, | |
| "eval_loss": 0.7235249280929565, | |
| "eval_runtime": 49.3356, | |
| "eval_samples_per_second": 10.135, | |
| "eval_wer": 0.4561769616026711, | |
| "step": 1952 | |
| }, | |
| { | |
| "epoch": 122.99, | |
| "eval_loss": 0.6766911745071411, | |
| "eval_runtime": 49.3909, | |
| "eval_samples_per_second": 10.123, | |
| "eval_wer": 0.43541318864774625, | |
| "step": 1968 | |
| }, | |
| { | |
| "epoch": 123.99, | |
| "eval_loss": 0.6751864552497864, | |
| "eval_runtime": 49.3541, | |
| "eval_samples_per_second": 10.131, | |
| "eval_wer": 0.43343071786310516, | |
| "step": 1984 | |
| }, | |
| { | |
| "epoch": 124.99, | |
| "learning_rate": 3.444976076555024e-06, | |
| "loss": 0.9094, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 124.99, | |
| "eval_loss": 0.6876149773597717, | |
| "eval_runtime": 49.706, | |
| "eval_samples_per_second": 10.059, | |
| "eval_wer": 0.4397954924874791, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 125.99, | |
| "eval_loss": 0.7010783553123474, | |
| "eval_runtime": 49.0784, | |
| "eval_samples_per_second": 10.188, | |
| "eval_wer": 0.44835141903171954, | |
| "step": 2016 | |
| }, | |
| { | |
| "epoch": 126.99, | |
| "eval_loss": 0.6755461692810059, | |
| "eval_runtime": 48.3236, | |
| "eval_samples_per_second": 10.347, | |
| "eval_wer": 0.42497913188647746, | |
| "step": 2032 | |
| }, | |
| { | |
| "epoch": 127.99, | |
| "eval_loss": 0.7173025608062744, | |
| "eval_runtime": 49.6709, | |
| "eval_samples_per_second": 10.066, | |
| "eval_wer": 0.4476210350584307, | |
| "step": 2048 | |
| }, | |
| { | |
| "epoch": 128.99, | |
| "eval_loss": 0.7063612937927246, | |
| "eval_runtime": 49.982, | |
| "eval_samples_per_second": 10.004, | |
| "eval_wer": 0.44209098497495825, | |
| "step": 2064 | |
| }, | |
| { | |
| "epoch": 129.99, | |
| "eval_loss": 0.6794615387916565, | |
| "eval_runtime": 49.1686, | |
| "eval_samples_per_second": 10.169, | |
| "eval_wer": 0.43426544240400666, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 129.99, | |
| "step": 2080, | |
| "total_flos": 0, | |
| "train_runtime": 94419.6153, | |
| "train_samples_per_second": 0.024 | |
| } | |
| ], | |
| "max_steps": 2240, | |
| "num_train_epochs": 140, | |
| "total_flos": 0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |