| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 100.0, | |
| "global_step": 5100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 5.069866666666666e-05, | |
| "loss": 10.7052, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 3.4682674407958984, | |
| "eval_runtime": 13.0004, | |
| "eval_samples_per_second": 26.23, | |
| "eval_steps_per_second": 3.308, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 0.000102432, | |
| "loss": 3.2395, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "eval_loss": 3.14892840385437, | |
| "eval_runtime": 12.7764, | |
| "eval_samples_per_second": 26.69, | |
| "eval_steps_per_second": 3.366, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 0.00015416533333333332, | |
| "loss": 2.9951, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "eval_loss": 2.982297897338867, | |
| "eval_runtime": 12.7866, | |
| "eval_samples_per_second": 26.668, | |
| "eval_steps_per_second": 3.363, | |
| "eval_wer": 1.0007380073800738, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 0.00020589866666666665, | |
| "loss": 2.3574, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "eval_loss": 1.2614495754241943, | |
| "eval_runtime": 12.8042, | |
| "eval_samples_per_second": 26.632, | |
| "eval_steps_per_second": 3.358, | |
| "eval_wer": 0.7597785977859779, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 0.000257632, | |
| "loss": 1.7287, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "eval_loss": 1.1816928386688232, | |
| "eval_runtime": 12.7085, | |
| "eval_samples_per_second": 26.833, | |
| "eval_steps_per_second": 3.384, | |
| "eval_wer": 0.7420664206642067, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "learning_rate": 0.00030936533333333335, | |
| "loss": 1.6144, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "eval_loss": 1.131492257118225, | |
| "eval_runtime": 12.8371, | |
| "eval_samples_per_second": 26.564, | |
| "eval_steps_per_second": 3.35, | |
| "eval_wer": 0.7321033210332103, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 13.73, | |
| "learning_rate": 0.00036109866666666666, | |
| "loss": 1.5598, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 13.73, | |
| "eval_loss": 1.232160210609436, | |
| "eval_runtime": 12.7503, | |
| "eval_samples_per_second": 26.745, | |
| "eval_steps_per_second": 3.372, | |
| "eval_wer": 0.7549815498154981, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 15.69, | |
| "learning_rate": 0.0003837186206896552, | |
| "loss": 1.5418, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 15.69, | |
| "eval_loss": 1.272075891494751, | |
| "eval_runtime": 12.8108, | |
| "eval_samples_per_second": 26.618, | |
| "eval_steps_per_second": 3.357, | |
| "eval_wer": 0.7819188191881918, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 17.65, | |
| "learning_rate": 0.0003747990804597701, | |
| "loss": 1.4578, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 17.65, | |
| "eval_loss": 1.1709508895874023, | |
| "eval_runtime": 12.7848, | |
| "eval_samples_per_second": 26.672, | |
| "eval_steps_per_second": 3.363, | |
| "eval_wer": 0.7531365313653137, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 19.61, | |
| "learning_rate": 0.0003658795402298851, | |
| "loss": 1.4311, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 19.61, | |
| "eval_loss": 1.2042367458343506, | |
| "eval_runtime": 12.6761, | |
| "eval_samples_per_second": 26.901, | |
| "eval_steps_per_second": 3.392, | |
| "eval_wer": 0.7490774907749077, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 21.57, | |
| "learning_rate": 0.00035696, | |
| "loss": 1.3483, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 21.57, | |
| "eval_loss": 1.1702170372009277, | |
| "eval_runtime": 12.5762, | |
| "eval_samples_per_second": 27.115, | |
| "eval_steps_per_second": 3.419, | |
| "eval_wer": 0.7464944649446494, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 23.53, | |
| "learning_rate": 0.0003480404597701149, | |
| "loss": 1.3078, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 23.53, | |
| "eval_loss": 1.1963412761688232, | |
| "eval_runtime": 12.6937, | |
| "eval_samples_per_second": 26.864, | |
| "eval_steps_per_second": 3.387, | |
| "eval_wer": 0.7420664206642067, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 25.49, | |
| "learning_rate": 0.00033912091954022987, | |
| "loss": 1.2576, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 25.49, | |
| "eval_loss": 1.1501450538635254, | |
| "eval_runtime": 12.6626, | |
| "eval_samples_per_second": 26.93, | |
| "eval_steps_per_second": 3.396, | |
| "eval_wer": 0.7280442804428044, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 27.45, | |
| "learning_rate": 0.0003302013793103448, | |
| "loss": 1.2173, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 27.45, | |
| "eval_loss": 1.2525919675827026, | |
| "eval_runtime": 12.6262, | |
| "eval_samples_per_second": 27.007, | |
| "eval_steps_per_second": 3.406, | |
| "eval_wer": 0.7298892988929889, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 29.41, | |
| "learning_rate": 0.00032128183908045977, | |
| "loss": 1.2217, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 29.41, | |
| "eval_loss": 1.2478744983673096, | |
| "eval_runtime": 12.8026, | |
| "eval_samples_per_second": 26.635, | |
| "eval_steps_per_second": 3.359, | |
| "eval_wer": 0.7309963099630996, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 31.37, | |
| "learning_rate": 0.0003123622988505747, | |
| "loss": 1.1536, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 31.37, | |
| "eval_loss": 1.2567418813705444, | |
| "eval_runtime": 12.6734, | |
| "eval_samples_per_second": 26.907, | |
| "eval_steps_per_second": 3.393, | |
| "eval_wer": 0.7431734317343174, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 0.00030344275862068966, | |
| "loss": 1.0939, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "eval_loss": 1.2800976037979126, | |
| "eval_runtime": 12.5686, | |
| "eval_samples_per_second": 27.131, | |
| "eval_steps_per_second": 3.421, | |
| "eval_wer": 0.7247232472324723, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 35.29, | |
| "learning_rate": 0.0002945232183908046, | |
| "loss": 1.0745, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 35.29, | |
| "eval_loss": 1.2340304851531982, | |
| "eval_runtime": 12.6385, | |
| "eval_samples_per_second": 26.981, | |
| "eval_steps_per_second": 3.402, | |
| "eval_wer": 0.7151291512915129, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 37.25, | |
| "learning_rate": 0.00028560367816091956, | |
| "loss": 1.0454, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 37.25, | |
| "eval_loss": 1.237194299697876, | |
| "eval_runtime": 12.4912, | |
| "eval_samples_per_second": 27.299, | |
| "eval_steps_per_second": 3.442, | |
| "eval_wer": 0.7151291512915129, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 39.22, | |
| "learning_rate": 0.00027668413793103446, | |
| "loss": 1.0101, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 39.22, | |
| "eval_loss": 1.2461133003234863, | |
| "eval_runtime": 12.6855, | |
| "eval_samples_per_second": 26.881, | |
| "eval_steps_per_second": 3.39, | |
| "eval_wer": 0.7376383763837638, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 41.18, | |
| "learning_rate": 0.0002677645977011494, | |
| "loss": 0.9833, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 41.18, | |
| "eval_loss": 1.2552708387374878, | |
| "eval_runtime": 12.6273, | |
| "eval_samples_per_second": 27.005, | |
| "eval_steps_per_second": 3.405, | |
| "eval_wer": 0.7269372693726938, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 43.14, | |
| "learning_rate": 0.00025884505747126435, | |
| "loss": 0.9314, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 43.14, | |
| "eval_loss": 1.2371633052825928, | |
| "eval_runtime": 12.5794, | |
| "eval_samples_per_second": 27.108, | |
| "eval_steps_per_second": 3.418, | |
| "eval_wer": 0.7014760147601476, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 45.1, | |
| "learning_rate": 0.0002499255172413793, | |
| "loss": 0.9147, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 45.1, | |
| "eval_loss": 1.3035242557525635, | |
| "eval_runtime": 12.8232, | |
| "eval_samples_per_second": 26.592, | |
| "eval_steps_per_second": 3.353, | |
| "eval_wer": 0.7357933579335794, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 47.06, | |
| "learning_rate": 0.00024109517241379313, | |
| "loss": 0.8758, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 47.06, | |
| "eval_loss": 1.2598013877868652, | |
| "eval_runtime": 12.7812, | |
| "eval_samples_per_second": 26.68, | |
| "eval_steps_per_second": 3.364, | |
| "eval_wer": 0.7092250922509226, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 49.02, | |
| "learning_rate": 0.00023217563218390802, | |
| "loss": 0.8356, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 49.02, | |
| "eval_loss": 1.255703091621399, | |
| "eval_runtime": 12.549, | |
| "eval_samples_per_second": 27.173, | |
| "eval_steps_per_second": 3.427, | |
| "eval_wer": 0.7143911439114391, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 50.98, | |
| "learning_rate": 0.00022325609195402297, | |
| "loss": 0.8105, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 50.98, | |
| "eval_loss": 1.2618709802627563, | |
| "eval_runtime": 12.4348, | |
| "eval_samples_per_second": 27.423, | |
| "eval_steps_per_second": 3.458, | |
| "eval_wer": 0.7236162361623616, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 52.94, | |
| "learning_rate": 0.00021433655172413795, | |
| "loss": 0.7947, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 52.94, | |
| "eval_loss": 1.399444818496704, | |
| "eval_runtime": 12.9361, | |
| "eval_samples_per_second": 26.36, | |
| "eval_steps_per_second": 3.324, | |
| "eval_wer": 0.7490774907749077, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 54.9, | |
| "learning_rate": 0.0002054170114942529, | |
| "loss": 0.7623, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 54.9, | |
| "eval_loss": 1.2931541204452515, | |
| "eval_runtime": 12.7092, | |
| "eval_samples_per_second": 26.831, | |
| "eval_steps_per_second": 3.383, | |
| "eval_wer": 0.7132841328413284, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 56.86, | |
| "learning_rate": 0.0001964974712643678, | |
| "loss": 0.7282, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 56.86, | |
| "eval_loss": 1.2799276113510132, | |
| "eval_runtime": 12.7788, | |
| "eval_samples_per_second": 26.685, | |
| "eval_steps_per_second": 3.365, | |
| "eval_wer": 0.7088560885608856, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 58.82, | |
| "learning_rate": 0.00018757793103448274, | |
| "loss": 0.7108, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 58.82, | |
| "eval_loss": 1.3615078926086426, | |
| "eval_runtime": 12.6509, | |
| "eval_samples_per_second": 26.955, | |
| "eval_steps_per_second": 3.399, | |
| "eval_wer": 0.714760147601476, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 60.78, | |
| "learning_rate": 0.00017865839080459772, | |
| "loss": 0.6896, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 60.78, | |
| "eval_loss": 1.312876582145691, | |
| "eval_runtime": 12.6527, | |
| "eval_samples_per_second": 26.951, | |
| "eval_steps_per_second": 3.398, | |
| "eval_wer": 0.7040590405904059, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 62.75, | |
| "learning_rate": 0.00016973885057471264, | |
| "loss": 0.6496, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 62.75, | |
| "eval_loss": 1.4050244092941284, | |
| "eval_runtime": 12.6982, | |
| "eval_samples_per_second": 26.854, | |
| "eval_steps_per_second": 3.386, | |
| "eval_wer": 0.6933579335793358, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 64.71, | |
| "learning_rate": 0.0001608193103448276, | |
| "loss": 0.6075, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 64.71, | |
| "eval_loss": 1.35708749294281, | |
| "eval_runtime": 12.752, | |
| "eval_samples_per_second": 26.741, | |
| "eval_steps_per_second": 3.372, | |
| "eval_wer": 0.7025830258302583, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 66.67, | |
| "learning_rate": 0.00015189977011494254, | |
| "loss": 0.6242, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 66.67, | |
| "eval_loss": 1.3368754386901855, | |
| "eval_runtime": 12.8446, | |
| "eval_samples_per_second": 26.548, | |
| "eval_steps_per_second": 3.348, | |
| "eval_wer": 0.7062730627306273, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 68.63, | |
| "learning_rate": 0.00014298022988505749, | |
| "loss": 0.5865, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 68.63, | |
| "eval_loss": 1.4367624521255493, | |
| "eval_runtime": 12.5885, | |
| "eval_samples_per_second": 27.088, | |
| "eval_steps_per_second": 3.416, | |
| "eval_wer": 0.7140221402214022, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 70.59, | |
| "learning_rate": 0.0001340606896551724, | |
| "loss": 0.5721, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 70.59, | |
| "eval_loss": 1.4223829507827759, | |
| "eval_runtime": 12.6692, | |
| "eval_samples_per_second": 26.916, | |
| "eval_steps_per_second": 3.394, | |
| "eval_wer": 0.7066420664206642, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 72.55, | |
| "learning_rate": 0.00012514114942528736, | |
| "loss": 0.5475, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 72.55, | |
| "eval_loss": 1.4797747135162354, | |
| "eval_runtime": 12.8068, | |
| "eval_samples_per_second": 26.626, | |
| "eval_steps_per_second": 3.358, | |
| "eval_wer": 0.7118081180811808, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 74.51, | |
| "learning_rate": 0.00011622160919540229, | |
| "loss": 0.5086, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 74.51, | |
| "eval_loss": 1.510679841041565, | |
| "eval_runtime": 12.607, | |
| "eval_samples_per_second": 27.048, | |
| "eval_steps_per_second": 3.411, | |
| "eval_wer": 0.7232472324723247, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 76.47, | |
| "learning_rate": 0.00010730206896551725, | |
| "loss": 0.4958, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 76.47, | |
| "eval_loss": 1.4849300384521484, | |
| "eval_runtime": 12.6845, | |
| "eval_samples_per_second": 26.883, | |
| "eval_steps_per_second": 3.39, | |
| "eval_wer": 0.7088560885608856, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 78.43, | |
| "learning_rate": 9.838252873563218e-05, | |
| "loss": 0.5046, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 78.43, | |
| "eval_loss": 1.4450523853302002, | |
| "eval_runtime": 12.6526, | |
| "eval_samples_per_second": 26.951, | |
| "eval_steps_per_second": 3.399, | |
| "eval_wer": 0.7114391143911439, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 80.39, | |
| "learning_rate": 8.946298850574712e-05, | |
| "loss": 0.4694, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 80.39, | |
| "eval_loss": 1.4674367904663086, | |
| "eval_runtime": 12.49, | |
| "eval_samples_per_second": 27.302, | |
| "eval_steps_per_second": 3.443, | |
| "eval_wer": 0.7088560885608856, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 82.35, | |
| "learning_rate": 8.054344827586206e-05, | |
| "loss": 0.4386, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 82.35, | |
| "eval_loss": 1.524474859237671, | |
| "eval_runtime": 12.6393, | |
| "eval_samples_per_second": 26.979, | |
| "eval_steps_per_second": 3.402, | |
| "eval_wer": 0.7103321033210332, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 84.31, | |
| "learning_rate": 7.162390804597701e-05, | |
| "loss": 0.4516, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 84.31, | |
| "eval_loss": 1.5031787157058716, | |
| "eval_runtime": 12.6415, | |
| "eval_samples_per_second": 26.975, | |
| "eval_steps_per_second": 3.401, | |
| "eval_wer": 0.7103321033210332, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 86.27, | |
| "learning_rate": 6.27935632183908e-05, | |
| "loss": 0.4113, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 86.27, | |
| "eval_loss": 1.5246329307556152, | |
| "eval_runtime": 12.6508, | |
| "eval_samples_per_second": 26.955, | |
| "eval_steps_per_second": 3.399, | |
| "eval_wer": 0.7195571955719557, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 88.24, | |
| "learning_rate": 5.3874022988505745e-05, | |
| "loss": 0.3972, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 88.24, | |
| "eval_loss": 1.5318336486816406, | |
| "eval_runtime": 12.5704, | |
| "eval_samples_per_second": 27.127, | |
| "eval_steps_per_second": 3.421, | |
| "eval_wer": 0.7114391143911439, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 90.2, | |
| "learning_rate": 4.4954482758620694e-05, | |
| "loss": 0.4006, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 90.2, | |
| "eval_loss": 1.554287314414978, | |
| "eval_runtime": 12.5754, | |
| "eval_samples_per_second": 27.116, | |
| "eval_steps_per_second": 3.419, | |
| "eval_wer": 0.6981549815498155, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 92.16, | |
| "learning_rate": 3.603494252873563e-05, | |
| "loss": 0.4014, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 92.16, | |
| "eval_loss": 1.5442076921463013, | |
| "eval_runtime": 12.6146, | |
| "eval_samples_per_second": 27.032, | |
| "eval_steps_per_second": 3.409, | |
| "eval_wer": 0.7047970479704797, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 94.12, | |
| "learning_rate": 2.711540229885057e-05, | |
| "loss": 0.3672, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 94.12, | |
| "eval_loss": 1.5541517734527588, | |
| "eval_runtime": 12.6543, | |
| "eval_samples_per_second": 26.947, | |
| "eval_steps_per_second": 3.398, | |
| "eval_wer": 0.7136531365313653, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 96.08, | |
| "learning_rate": 1.8195862068965517e-05, | |
| "loss": 0.3666, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 96.08, | |
| "eval_loss": 1.5414179563522339, | |
| "eval_runtime": 12.5239, | |
| "eval_samples_per_second": 27.228, | |
| "eval_steps_per_second": 3.433, | |
| "eval_wer": 0.7018450184501845, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 98.04, | |
| "learning_rate": 9.27632183908046e-06, | |
| "loss": 0.3574, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 98.04, | |
| "eval_loss": 1.5465455055236816, | |
| "eval_runtime": 12.7119, | |
| "eval_samples_per_second": 26.825, | |
| "eval_steps_per_second": 3.383, | |
| "eval_wer": 0.7059040590405904, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 3.567816091954023e-07, | |
| "loss": 0.3428, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_loss": 1.5443140268325806, | |
| "eval_runtime": 12.8582, | |
| "eval_samples_per_second": 26.52, | |
| "eval_steps_per_second": 3.344, | |
| "eval_wer": 0.7029520295202952, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 5100, | |
| "total_flos": 9.838577578075728e+18, | |
| "train_loss": 1.1548647121354645, | |
| "train_runtime": 5602.3197, | |
| "train_samples_per_second": 14.458, | |
| "train_steps_per_second": 0.91 | |
| } | |
| ], | |
| "max_steps": 5100, | |
| "num_train_epochs": 100, | |
| "total_flos": 9.838577578075728e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |