| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 40180, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.455e-05, | |
| "loss": 15.6582, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.955e-05, | |
| "loss": 5.6883, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.454999999999999e-05, | |
| "loss": 3.9902, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5.955e-05, | |
| "loss": 3.4038, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 7.455e-05, | |
| "loss": 3.3136, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.955e-05, | |
| "loss": 3.1572, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00010454999999999998, | |
| "loss": 2.8152, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00011954999999999999, | |
| "loss": 2.048, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00013455, | |
| "loss": 1.6334, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00014954999999999998, | |
| "loss": 1.5157, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00016455, | |
| "loss": 1.4378, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00017955, | |
| "loss": 1.4074, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00019454999999999999, | |
| "loss": 1.3959, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00020955, | |
| "loss": 1.4093, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00022455, | |
| "loss": 1.3905, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00023954999999999997, | |
| "loss": 1.4149, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00025455, | |
| "loss": 1.4382, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00026954999999999997, | |
| "loss": 1.4371, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00028455, | |
| "loss": 1.4462, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00029955, | |
| "loss": 1.4792, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.45980095863342285, | |
| "eval_runtime": 620.3123, | |
| "eval_samples_per_second": 23.321, | |
| "eval_steps_per_second": 0.73, | |
| "eval_wer": 0.540401205219563, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00029923782084861184, | |
| "loss": 1.4885, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0002984520691461498, | |
| "loss": 1.4551, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002976663174436878, | |
| "loss": 1.4569, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00029688056574122575, | |
| "loss": 1.4634, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00029609481403876375, | |
| "loss": 1.444, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0002953090623363017, | |
| "loss": 1.4636, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002945233106338397, | |
| "loss": 1.4432, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00029373755893137766, | |
| "loss": 1.4329, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0002929518072289156, | |
| "loss": 1.4414, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0002921660555264536, | |
| "loss": 1.4542, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00029138030382399156, | |
| "loss": 1.4548, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00029059455212152957, | |
| "loss": 1.4287, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0002898088004190675, | |
| "loss": 1.4351, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0002890230487166055, | |
| "loss": 1.4267, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0002882372970141435, | |
| "loss": 1.4405, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0002874515453116815, | |
| "loss": 1.4518, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00028666579360921943, | |
| "loss": 1.4118, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00028588004190675744, | |
| "loss": 1.4273, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0002850942902042954, | |
| "loss": 1.4278, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0002843085385018334, | |
| "loss": 1.449, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.46497029066085815, | |
| "eval_runtime": 620.6238, | |
| "eval_samples_per_second": 23.309, | |
| "eval_steps_per_second": 0.73, | |
| "eval_wer": 0.5610342891839564, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.000283530644316396, | |
| "loss": 1.4281, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0002827527501309586, | |
| "loss": 1.4175, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002819669984284966, | |
| "loss": 1.4174, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00028118124672603454, | |
| "loss": 1.3821, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00028039549502357255, | |
| "loss": 1.4161, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0002796097433211105, | |
| "loss": 1.4188, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0002788239916186485, | |
| "loss": 1.3985, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00027803823991618646, | |
| "loss": 1.4179, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00027725248821372446, | |
| "loss": 1.3996, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0002764667365112624, | |
| "loss": 1.4011, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0002756809848088004, | |
| "loss": 1.4173, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00027489523310633837, | |
| "loss": 1.3953, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00027410948140387637, | |
| "loss": 1.3885, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0002733237297014143, | |
| "loss": 1.3765, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0002725379779989523, | |
| "loss": 1.3912, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0002717522262964903, | |
| "loss": 1.3848, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0002709664745940283, | |
| "loss": 1.3822, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00027018072289156623, | |
| "loss": 1.3737, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00026939497118910424, | |
| "loss": 1.3881, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.0002686092194866422, | |
| "loss": 1.3742, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 0.40005093812942505, | |
| "eval_runtime": 614.9135, | |
| "eval_samples_per_second": 23.525, | |
| "eval_steps_per_second": 0.737, | |
| "eval_wer": 0.49771443628489925, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.0002678234677841802, | |
| "loss": 1.3839, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00026703771608171814, | |
| "loss": 1.3794, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00026625196437925615, | |
| "loss": 1.3735, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0002654740701938187, | |
| "loss": 1.366, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0002646883184913567, | |
| "loss": 1.3521, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.0002639025667888947, | |
| "loss": 1.3545, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0002631168150864327, | |
| "loss": 1.3451, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.00026233106338397063, | |
| "loss": 1.3576, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00026154531168150864, | |
| "loss": 1.3396, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0002607595599790466, | |
| "loss": 1.3379, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0002599738082765846, | |
| "loss": 1.3418, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00025918805657412254, | |
| "loss": 1.3515, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00025840230487166055, | |
| "loss": 1.3452, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.0002576165531691985, | |
| "loss": 1.3598, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002568308014667365, | |
| "loss": 1.3431, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00025604504976427445, | |
| "loss": 1.3377, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00025525929806181246, | |
| "loss": 1.3277, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0002544735463593504, | |
| "loss": 1.3455, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.0002536877946568884, | |
| "loss": 1.3575, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00025290204295442636, | |
| "loss": 1.3375, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 0.3916109502315521, | |
| "eval_runtime": 613.9142, | |
| "eval_samples_per_second": 23.564, | |
| "eval_steps_per_second": 0.738, | |
| "eval_wer": 0.4893626771455085, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0002521162912519643, | |
| "loss": 1.3333, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0002513305395495023, | |
| "loss": 1.3248, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.0002505447878470403, | |
| "loss": 1.356, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.00024975903614457833, | |
| "loss": 1.3227, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.0002489732844421163, | |
| "loss": 1.3066, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0002481875327396543, | |
| "loss": 1.3302, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.00024740178103719224, | |
| "loss": 1.3021, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.00024661602933473024, | |
| "loss": 1.3219, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.0002458302776322682, | |
| "loss": 1.2971, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.00024504452592980614, | |
| "loss": 1.3008, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.00024425877422734415, | |
| "loss": 1.2919, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.00024347302252488212, | |
| "loss": 1.3162, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.0002426951283394447, | |
| "loss": 1.2899, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.00024190937663698267, | |
| "loss": 1.3054, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.00024112362493452065, | |
| "loss": 1.303, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 0.00024033787323205866, | |
| "loss": 1.295, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.00023955212152959663, | |
| "loss": 1.2911, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.0002387663698271346, | |
| "loss": 1.2918, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.0002379806181246726, | |
| "loss": 1.283, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.00023719486642221057, | |
| "loss": 1.2961, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 0.3640899360179901, | |
| "eval_runtime": 609.8404, | |
| "eval_samples_per_second": 23.721, | |
| "eval_steps_per_second": 0.743, | |
| "eval_wer": 0.45692943966455485, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.00023640911471974855, | |
| "loss": 1.2856, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 0.00023562336301728652, | |
| "loss": 1.3074, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0002348376113148245, | |
| "loss": 1.3009, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 0.00023405185961236248, | |
| "loss": 1.2741, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 0.00023326610790990046, | |
| "loss": 1.2986, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.00023248035620743843, | |
| "loss": 1.2725, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 0.0002316946045049764, | |
| "loss": 1.3045, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0002309088528025144, | |
| "loss": 1.3011, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.00023012310110005237, | |
| "loss": 1.2783, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.00022933734939759034, | |
| "loss": 1.2769, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.00022855159769512832, | |
| "loss": 1.2873, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.0002277658459926663, | |
| "loss": 1.2766, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.00022698009429020428, | |
| "loss": 1.284, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.00022619434258774226, | |
| "loss": 1.2579, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.00022540859088528023, | |
| "loss": 1.2829, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.0002246228391828182, | |
| "loss": 1.2682, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.0002238370874803562, | |
| "loss": 1.2713, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.0002230591932949188, | |
| "loss": 1.268, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.00022227344159245677, | |
| "loss": 1.2456, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.00022148768988999474, | |
| "loss": 1.2714, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_loss": 0.3491361737251282, | |
| "eval_runtime": 608.3349, | |
| "eval_samples_per_second": 23.78, | |
| "eval_steps_per_second": 0.745, | |
| "eval_wer": 0.4487838968002108, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.00022070193818753272, | |
| "loss": 1.2614, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 0.0002199161864850707, | |
| "loss": 1.2639, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.00021913043478260868, | |
| "loss": 1.2584, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 0.00021834468308014665, | |
| "loss": 1.2446, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.00021755893137768463, | |
| "loss": 1.2618, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 0.0002167731796752226, | |
| "loss": 1.2505, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 0.0002159874279727606, | |
| "loss": 1.2492, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 0.00021520167627029857, | |
| "loss": 1.245, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.00021441592456783654, | |
| "loss": 1.2452, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 0.00021363017286537452, | |
| "loss": 1.2387, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 0.0002128444211629125, | |
| "loss": 1.235, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 0.00021205866946045048, | |
| "loss": 1.2365, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 0.00021127291775798845, | |
| "loss": 1.2278, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.00021048716605552643, | |
| "loss": 1.2506, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 0.0002097014143530644, | |
| "loss": 1.2353, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 0.0002089156626506024, | |
| "loss": 1.2229, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 0.00020812991094814036, | |
| "loss": 1.2299, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 0.00020734415924567834, | |
| "loss": 1.2543, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 0.00020655840754321635, | |
| "loss": 1.2217, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 0.00020577265584075433, | |
| "loss": 1.2399, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "eval_loss": 0.315110981464386, | |
| "eval_runtime": 611.3226, | |
| "eval_samples_per_second": 23.663, | |
| "eval_steps_per_second": 0.741, | |
| "eval_wer": 0.3986389725846919, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 0.0002049869041382923, | |
| "loss": 1.2282, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 0.00020420900995285487, | |
| "loss": 1.2268, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 0.00020342325825039285, | |
| "loss": 1.2083, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 0.00020263750654793083, | |
| "loss": 1.217, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 0.0002018517548454688, | |
| "loss": 1.2084, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 0.00020106600314300679, | |
| "loss": 1.228, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 0.00020028025144054476, | |
| "loss": 1.2244, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 0.00019949449973808274, | |
| "loss": 1.2171, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 0.00019870874803562072, | |
| "loss": 1.2263, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 0.0001979229963331587, | |
| "loss": 1.2147, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 0.0001971451021477213, | |
| "loss": 1.2233, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 0.00019635935044525927, | |
| "loss": 1.2364, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 0.00019557359874279725, | |
| "loss": 1.2354, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 0.00019478784704033523, | |
| "loss": 1.2229, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 0.0001940020953378732, | |
| "loss": 1.2423, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 0.00019321634363541118, | |
| "loss": 1.2153, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 0.00019243059193294916, | |
| "loss": 1.2089, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.00019164484023048714, | |
| "loss": 1.2064, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 0.00019085908852802512, | |
| "loss": 1.2128, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 0.0001900733368255631, | |
| "loss": 1.2067, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "eval_loss": 0.3081344962120056, | |
| "eval_runtime": 610.5806, | |
| "eval_samples_per_second": 23.692, | |
| "eval_steps_per_second": 0.742, | |
| "eval_wer": 0.392349376195768, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 0.00018928758512310107, | |
| "loss": 1.2088, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.00018850183342063905, | |
| "loss": 1.2136, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 0.00018771608171817703, | |
| "loss": 1.189, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 0.000186930330015715, | |
| "loss": 1.1859, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 0.000186144578313253, | |
| "loss": 1.175, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 0.000185358826610791, | |
| "loss": 1.2116, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 0.00018457307490832897, | |
| "loss": 1.2105, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 0.00018378732320586694, | |
| "loss": 1.2053, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 0.00018300157150340492, | |
| "loss": 1.205, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 0.0001822158198009429, | |
| "loss": 1.193, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 0.00018143006809848088, | |
| "loss": 1.2093, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 0.00018064431639601885, | |
| "loss": 1.1882, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 0.00017985856469355683, | |
| "loss": 1.2025, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 0.0001790728129910948, | |
| "loss": 1.1937, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 0.00017829491880565738, | |
| "loss": 1.1967, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 0.00017750916710319536, | |
| "loss": 1.1987, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 0.00017672341540073334, | |
| "loss": 1.1877, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 0.00017593766369827134, | |
| "loss": 1.1925, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 0.00017515191199580932, | |
| "loss": 1.1892, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 0.0001743661602933473, | |
| "loss": 1.1842, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "eval_loss": 0.28745028376579285, | |
| "eval_runtime": 610.7234, | |
| "eval_samples_per_second": 23.687, | |
| "eval_steps_per_second": 0.742, | |
| "eval_wer": 0.37033006060467194, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 0.00017358040859088528, | |
| "loss": 1.1933, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 0.00017279465688842325, | |
| "loss": 1.1948, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 0.00017200890518596123, | |
| "loss": 1.2035, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 0.0001712231534834992, | |
| "loss": 1.1864, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 0.0001704374017810372, | |
| "loss": 1.1795, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 0.00016965165007857516, | |
| "loss": 1.1715, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 0.00016886589837611314, | |
| "loss": 1.1958, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 0.00016808014667365112, | |
| "loss": 1.1833, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 0.0001672943949711891, | |
| "loss": 1.1747, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 0.00016650864326872708, | |
| "loss": 1.1706, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 0.00016572289156626505, | |
| "loss": 1.176, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 0.00016493713986380303, | |
| "loss": 1.1714, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 0.000164151388161341, | |
| "loss": 1.171, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 0.00016336563645887899, | |
| "loss": 1.1866, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 0.00016257988475641696, | |
| "loss": 1.1781, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 0.00016179413305395494, | |
| "loss": 1.1817, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 0.00016100838135149292, | |
| "loss": 1.1794, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 0.0001602226296490309, | |
| "loss": 1.1763, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 0.00015943687794656888, | |
| "loss": 1.1595, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 0.00015865112624410685, | |
| "loss": 1.1644, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "eval_loss": 0.28402265906333923, | |
| "eval_runtime": 609.6981, | |
| "eval_samples_per_second": 23.726, | |
| "eval_steps_per_second": 0.743, | |
| "eval_wer": 0.36698477436502575, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.00015786537454164483, | |
| "loss": 1.1602, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 0.0001570796228391828, | |
| "loss": 1.161, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 0.00015629387113672076, | |
| "loss": 1.1669, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 0.00015550811943425874, | |
| "loss": 1.1508, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 0.00015472236773179671, | |
| "loss": 1.1735, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 0.0001539366160293347, | |
| "loss": 1.1742, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 0.00015315086432687267, | |
| "loss": 1.1493, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 0.00015236511262441065, | |
| "loss": 1.1572, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 0.00015157936092194868, | |
| "loss": 1.1385, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "learning_rate": 0.00015079360921948666, | |
| "loss": 1.1325, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 0.0001500078575170246, | |
| "loss": 1.1532, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 0.0001492299633315872, | |
| "loss": 1.1506, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 0.00014844421162912518, | |
| "loss": 1.1398, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 0.00014765845992666316, | |
| "loss": 1.1572, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 0.00014687270822420114, | |
| "loss": 1.1434, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 0.00014608695652173912, | |
| "loss": 1.1513, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 0.0001453012048192771, | |
| "loss": 1.1506, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.00014451545311681507, | |
| "loss": 1.1539, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 0.00014372970141435305, | |
| "loss": 1.1476, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 0.00014294394971189103, | |
| "loss": 1.161, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "eval_loss": 0.2790367901325226, | |
| "eval_runtime": 605.6494, | |
| "eval_samples_per_second": 23.885, | |
| "eval_steps_per_second": 0.748, | |
| "eval_wer": 0.35965264014114356, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 0.00014216605552645363, | |
| "loss": 1.1671, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 0.0001413803038239916, | |
| "loss": 1.1353, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 0.00014059455212152958, | |
| "loss": 1.1425, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 0.00013980880041906756, | |
| "loss": 1.1416, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 0.00013902304871660554, | |
| "loss": 1.1557, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 0.00013823729701414352, | |
| "loss": 1.1251, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 0.0001374515453116815, | |
| "loss": 1.1441, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 0.00013666579360921947, | |
| "loss": 1.1505, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 0.00013588004190675745, | |
| "loss": 1.1356, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 0.00013509429020429543, | |
| "loss": 1.1153, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 0.0001343085385018334, | |
| "loss": 1.1381, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 0.00013352278679937138, | |
| "loss": 1.1361, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 0.00013273703509690936, | |
| "loss": 1.1296, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 0.00013195128339444734, | |
| "loss": 1.1012, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 0.00013116553169198532, | |
| "loss": 1.1318, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 0.0001303797799895233, | |
| "loss": 1.1254, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 0.00012959402828706127, | |
| "loss": 1.1353, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 0.00012880827658459925, | |
| "loss": 1.1245, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 0.00012802252488213723, | |
| "loss": 1.1151, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 0.0001272367731796752, | |
| "loss": 1.1303, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "eval_loss": 0.2551780641078949, | |
| "eval_runtime": 603.2404, | |
| "eval_samples_per_second": 23.98, | |
| "eval_steps_per_second": 0.751, | |
| "eval_wer": 0.3272079462004651, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.00012645102147721318, | |
| "loss": 1.1189, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 0.00012566526977475116, | |
| "loss": 1.1265, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 0.00012487951807228916, | |
| "loss": 1.1222, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 0.00012409376636982714, | |
| "loss": 1.0996, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 0.00012330801466736512, | |
| "loss": 1.1118, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 0.00012252226296490307, | |
| "loss": 1.1123, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 0.00012173651126244106, | |
| "loss": 1.0956, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "learning_rate": 0.00012095075955997904, | |
| "loss": 1.1147, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 0.00012016500785751702, | |
| "loss": 1.0942, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 0.000119379256155055, | |
| "loss": 1.101, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 0.00011859350445259297, | |
| "loss": 1.0987, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 0.00011780775275013095, | |
| "loss": 1.1021, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 0.00011702200104766893, | |
| "loss": 1.0861, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 0.0001162362493452069, | |
| "loss": 1.0966, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 0.00011545049764274487, | |
| "loss": 1.0891, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 0.00011466474594028285, | |
| "loss": 1.0871, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 0.00011387899423782083, | |
| "loss": 1.084, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 0.00011309324253535883, | |
| "loss": 1.0913, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 0.0001123074908328968, | |
| "loss": 1.0843, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 0.00011152173913043477, | |
| "loss": 1.0874, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "eval_loss": 0.24053026735782623, | |
| "eval_runtime": 605.3547, | |
| "eval_samples_per_second": 23.897, | |
| "eval_steps_per_second": 0.748, | |
| "eval_wer": 0.31420486441279916, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 0.00011073598742797275, | |
| "loss": 1.0854, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 0.00010995023572551073, | |
| "loss": 1.0945, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 0.0001091644840230487, | |
| "loss": 1.0761, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 0.00010837873232058668, | |
| "loss": 1.0767, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 0.00010759298061812466, | |
| "loss": 1.0684, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 0.00010680722891566264, | |
| "loss": 1.0902, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 0.00010602147721320062, | |
| "loss": 1.083, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.0001052357255107386, | |
| "loss": 1.0797, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 0.00010444997380827657, | |
| "loss": 1.0776, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 0.00010367207962283917, | |
| "loss": 1.0563, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 0.00010288632792037716, | |
| "loss": 1.0719, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 0.00010210057621791514, | |
| "loss": 1.0641, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 0.00010131482451545312, | |
| "loss": 1.0728, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 0.0001005290728129911, | |
| "loss": 1.085, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 9.974332111052907e-05, | |
| "loss": 1.0727, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 9.895756940806704e-05, | |
| "loss": 1.0621, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 9.817967522262964e-05, | |
| "loss": 1.0454, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 9.739392352016761e-05, | |
| "loss": 1.0602, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 9.660817181770559e-05, | |
| "loss": 1.0602, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 9.582242011524357e-05, | |
| "loss": 1.0613, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "eval_loss": 0.23520201444625854, | |
| "eval_runtime": 606.7408, | |
| "eval_samples_per_second": 23.842, | |
| "eval_steps_per_second": 0.747, | |
| "eval_wer": 0.3055208679413888, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 9.503666841278155e-05, | |
| "loss": 1.0715, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 9.425091671031953e-05, | |
| "loss": 1.0453, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 9.34651650078575e-05, | |
| "loss": 1.0602, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 9.26794133053955e-05, | |
| "loss": 1.0548, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 9.189366160293347e-05, | |
| "loss": 1.0447, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 9.110790990047145e-05, | |
| "loss": 1.054, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 9.032215819800943e-05, | |
| "loss": 1.0435, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 8.95364064955474e-05, | |
| "loss": 1.0536, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 8.875065479308538e-05, | |
| "loss": 1.0573, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 8.796490309062336e-05, | |
| "loss": 1.0364, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 8.717915138816134e-05, | |
| "loss": 1.0419, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 8.639339968569932e-05, | |
| "loss": 1.0548, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 8.56076479832373e-05, | |
| "loss": 1.0411, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 8.482189628077526e-05, | |
| "loss": 1.0475, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "learning_rate": 8.403614457831324e-05, | |
| "loss": 1.0396, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 8.325039287585121e-05, | |
| "loss": 1.0371, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 8.246464117338919e-05, | |
| "loss": 1.0346, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 8.167888947092717e-05, | |
| "loss": 1.054, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 8.089313776846516e-05, | |
| "loss": 1.0409, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 8.010738606600314e-05, | |
| "loss": 1.0498, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "eval_loss": 0.224945530295372, | |
| "eval_runtime": 602.7787, | |
| "eval_samples_per_second": 23.999, | |
| "eval_steps_per_second": 0.752, | |
| "eval_wer": 0.2910169899297719, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 7.932163436354112e-05, | |
| "loss": 1.0503, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 7.85358826610791e-05, | |
| "loss": 1.033, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 7.775013095861707e-05, | |
| "loss": 1.0407, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 7.696437925615505e-05, | |
| "loss": 1.0134, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 7.617862755369303e-05, | |
| "loss": 1.0236, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 7.5392875851231e-05, | |
| "loss": 1.0326, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 7.460712414876898e-05, | |
| "loss": 1.0267, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 7.382137244630696e-05, | |
| "loss": 1.0117, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 7.303562074384494e-05, | |
| "loss": 1.0379, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "learning_rate": 7.224986904138292e-05, | |
| "loss": 1.0206, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 7.14641173389209e-05, | |
| "loss": 1.0158, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 7.067836563645887e-05, | |
| "loss": 1.0414, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 6.989261393399685e-05, | |
| "loss": 1.0333, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 6.910686223153483e-05, | |
| "loss": 1.0294, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 6.83211105290728e-05, | |
| "loss": 1.0276, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 6.753535882661078e-05, | |
| "loss": 1.031, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 6.674960712414876e-05, | |
| "loss": 1.0346, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 6.596385542168674e-05, | |
| "loss": 1.0231, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "learning_rate": 6.517810371922473e-05, | |
| "loss": 1.0267, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 6.439235201676269e-05, | |
| "loss": 1.021, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "eval_loss": 0.2117909938097, | |
| "eval_runtime": 603.2899, | |
| "eval_samples_per_second": 23.979, | |
| "eval_steps_per_second": 0.751, | |
| "eval_wer": 0.2751956190498012, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 6.360660031430067e-05, | |
| "loss": 1.0225, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 6.282084861183865e-05, | |
| "loss": 1.0168, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 6.203509690937663e-05, | |
| "loss": 1.0105, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 6.12493452069146e-05, | |
| "loss": 1.0164, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 6.046359350445258e-05, | |
| "loss": 0.9959, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 5.967784180199057e-05, | |
| "loss": 1.0011, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 5.8892090099528544e-05, | |
| "loss": 1.0068, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 5.810633839706652e-05, | |
| "loss": 1.0121, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 5.732844421162912e-05, | |
| "loss": 1.0108, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 5.65426925091671e-05, | |
| "loss": 1.0168, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 5.575694080670508e-05, | |
| "loss": 1.0106, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 5.497118910424306e-05, | |
| "loss": 0.9964, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 5.418543740178103e-05, | |
| "loss": 1.0018, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 5.339968569931901e-05, | |
| "loss": 1.0084, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 5.261393399685699e-05, | |
| "loss": 1.0046, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 5.1828182294394965e-05, | |
| "loss": 0.9994, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 5.104243059193294e-05, | |
| "loss": 0.9993, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 5.025667888947092e-05, | |
| "loss": 1.0077, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 4.9470927187008905e-05, | |
| "loss": 0.9912, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 4.868517548454688e-05, | |
| "loss": 1.0002, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "eval_loss": 0.20461425185203552, | |
| "eval_runtime": 602.4337, | |
| "eval_samples_per_second": 24.013, | |
| "eval_steps_per_second": 0.752, | |
| "eval_wer": 0.2661564723269215, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 4.789942378208486e-05, | |
| "loss": 0.9898, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 4.711367207962284e-05, | |
| "loss": 0.9876, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "learning_rate": 4.6327920377160816e-05, | |
| "loss": 1.0013, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 4.5542168674698787e-05, | |
| "loss": 0.9917, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 4.4756416972236764e-05, | |
| "loss": 0.9846, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 4.397066526977474e-05, | |
| "loss": 0.99, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 4.3184913567312727e-05, | |
| "loss": 0.9822, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 4.2399161864850704e-05, | |
| "loss": 0.9821, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 4.161341016238868e-05, | |
| "loss": 0.9901, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 4.082765845992666e-05, | |
| "loss": 0.9881, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 4.004190675746464e-05, | |
| "loss": 0.9882, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 3.9256155055002615e-05, | |
| "loss": 0.9921, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 3.847040335254059e-05, | |
| "loss": 0.9835, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 3.768465165007857e-05, | |
| "loss": 0.9914, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 3.689889994761655e-05, | |
| "loss": 0.9863, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 3.6113148245154526e-05, | |
| "loss": 0.9712, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 3.5335254059717125e-05, | |
| "loss": 0.9977, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 3.45495023572551e-05, | |
| "loss": 0.9666, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 3.376375065479308e-05, | |
| "loss": 0.9797, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 3.297799895233106e-05, | |
| "loss": 0.9762, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "eval_loss": 0.1968773603439331, | |
| "eval_runtime": 601.2569, | |
| "eval_samples_per_second": 24.06, | |
| "eval_steps_per_second": 0.753, | |
| "eval_wer": 0.2529815436433833, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 3.2192247249869036e-05, | |
| "loss": 0.9754, | |
| "step": 36100 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 3.140649554740702e-05, | |
| "loss": 0.9741, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 3.0620743844945e-05, | |
| "loss": 0.9708, | |
| "step": 36300 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 2.9834992142482973e-05, | |
| "loss": 0.966, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "learning_rate": 2.904924044002095e-05, | |
| "loss": 0.9605, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 2.826348873755893e-05, | |
| "loss": 0.9658, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 2.7477737035096906e-05, | |
| "loss": 0.9721, | |
| "step": 36700 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 2.6691985332634884e-05, | |
| "loss": 0.9634, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 2.5906233630172865e-05, | |
| "loss": 0.9768, | |
| "step": 36900 | |
| }, | |
| { | |
| "epoch": 9.21, | |
| "learning_rate": 2.5120481927710842e-05, | |
| "loss": 0.9449, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 2.433473022524882e-05, | |
| "loss": 0.9615, | |
| "step": 37100 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 2.3548978522786794e-05, | |
| "loss": 0.9711, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 2.2763226820324776e-05, | |
| "loss": 0.9663, | |
| "step": 37300 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 2.1977475117862753e-05, | |
| "loss": 0.9584, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 2.119172341540073e-05, | |
| "loss": 0.9554, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 2.040597171293871e-05, | |
| "loss": 0.9552, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 1.962022001047669e-05, | |
| "loss": 0.9583, | |
| "step": 37700 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 1.8842325825039285e-05, | |
| "loss": 0.9647, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 1.8056574122577263e-05, | |
| "loss": 0.9632, | |
| "step": 37900 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 1.727082242011524e-05, | |
| "loss": 0.9568, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "eval_loss": 0.19168192148208618, | |
| "eval_runtime": 601.9876, | |
| "eval_samples_per_second": 24.03, | |
| "eval_steps_per_second": 0.753, | |
| "eval_wer": 0.24488182661793853, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 1.6485070717653222e-05, | |
| "loss": 0.9501, | |
| "step": 38100 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "learning_rate": 1.56993190151912e-05, | |
| "loss": 0.9567, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 1.4913567312729177e-05, | |
| "loss": 0.9652, | |
| "step": 38300 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 1.4127815610267154e-05, | |
| "loss": 0.9652, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 1.3342063907805133e-05, | |
| "loss": 0.9645, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "learning_rate": 1.255631220534311e-05, | |
| "loss": 0.9612, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 1.1770560502881088e-05, | |
| "loss": 0.9626, | |
| "step": 38700 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 1.0984808800419066e-05, | |
| "loss": 0.9525, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 1.0199057097957046e-05, | |
| "loss": 0.9524, | |
| "step": 38900 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 9.413305395495022e-06, | |
| "loss": 0.9551, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 8.627553693033001e-06, | |
| "loss": 0.9656, | |
| "step": 39100 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 7.841801990570979e-06, | |
| "loss": 0.9604, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 7.056050288108957e-06, | |
| "loss": 0.952, | |
| "step": 39300 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "learning_rate": 6.270298585646935e-06, | |
| "loss": 0.9471, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "learning_rate": 5.484546883184914e-06, | |
| "loss": 0.9516, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 4.6987951807228915e-06, | |
| "loss": 0.9623, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 3.913043478260869e-06, | |
| "loss": 0.9454, | |
| "step": 39700 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 3.127291775798847e-06, | |
| "loss": 0.9483, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 2.341540073336825e-06, | |
| "loss": 0.9492, | |
| "step": 39900 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "learning_rate": 1.5557883708748033e-06, | |
| "loss": 0.953, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "eval_loss": 0.1892675757408142, | |
| "eval_runtime": 603.5821, | |
| "eval_samples_per_second": 23.967, | |
| "eval_steps_per_second": 0.751, | |
| "eval_wer": 0.24252179591462647, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "learning_rate": 7.700366684127815e-07, | |
| "loss": 0.9484, | |
| "step": 40100 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 40180, | |
| "total_flos": 1.7364423346166445e+20, | |
| "train_loss": 1.246090738686713, | |
| "train_runtime": 73537.1599, | |
| "train_samples_per_second": 17.484, | |
| "train_steps_per_second": 0.546 | |
| } | |
| ], | |
| "max_steps": 40180, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.7364423346166445e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |