| { | |
| "best_metric": 0.8710034489631653, | |
| "best_model_checkpoint": "./checkpoint-400", | |
| "epoch": 33.32911392405063, | |
| "global_step": 1300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 3.3709, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.333333333333334e-06, | |
| "loss": 2.8912, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 8.666666666666668e-06, | |
| "loss": 2.2169, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.777777777777779e-06, | |
| "loss": 1.6923, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 9.407407407407408e-06, | |
| "loss": 1.3934, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 9.037037037037037e-06, | |
| "loss": 1.2336, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 8.666666666666668e-06, | |
| "loss": 1.1522, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.296296296296297e-06, | |
| "loss": 1.1339, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.925925925925926e-06, | |
| "loss": 0.9576, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.555555555555556e-06, | |
| "loss": 0.9153, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 1.0240015983581543, | |
| "eval_runtime": 182.7755, | |
| "eval_samples_per_second": 2.801, | |
| "eval_steps_per_second": 0.088, | |
| "eval_wer": 68.9863608183509, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 7.185185185185186e-06, | |
| "loss": 0.8884, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 6.814814814814815e-06, | |
| "loss": 0.8334, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 6.444444444444445e-06, | |
| "loss": 0.7989, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 6.0740740740740745e-06, | |
| "loss": 0.7718, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 5.7037037037037045e-06, | |
| "loss": 0.7671, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 5.333333333333334e-06, | |
| "loss": 0.8208, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 4.962962962962964e-06, | |
| "loss": 0.7219, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 4.592592592592593e-06, | |
| "loss": 0.7034, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 4.222222222222223e-06, | |
| "loss": 0.6966, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.851851851851852e-06, | |
| "loss": 0.6865, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.8967972993850708, | |
| "eval_runtime": 172.9658, | |
| "eval_samples_per_second": 2.96, | |
| "eval_steps_per_second": 0.093, | |
| "eval_wer": 61.7660411622276, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 6.255319148936171e-06, | |
| "loss": 0.6414, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 6.042553191489362e-06, | |
| "loss": 0.6552, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 5.829787234042553e-06, | |
| "loss": 0.6445, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 5.617021276595746e-06, | |
| "loss": 0.622, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 5.404255319148937e-06, | |
| "loss": 0.6004, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 5.191489361702128e-06, | |
| "loss": 0.5882, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 4.9787234042553195e-06, | |
| "loss": 0.6016, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.765957446808511e-06, | |
| "loss": 0.5682, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 4.553191489361702e-06, | |
| "loss": 0.5672, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 4.340425531914894e-06, | |
| "loss": 0.5474, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "eval_loss": 0.8744030594825745, | |
| "eval_runtime": 190.8413, | |
| "eval_samples_per_second": 2.683, | |
| "eval_steps_per_second": 0.084, | |
| "eval_wer": 60.55538740920097, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 4.127659574468085e-06, | |
| "loss": 0.5432, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 3.914893617021277e-06, | |
| "loss": 0.534, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 3.702127659574468e-06, | |
| "loss": 0.5164, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 3.48936170212766e-06, | |
| "loss": 0.5223, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 3.276595744680851e-06, | |
| "loss": 0.5126, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 3.0638297872340428e-06, | |
| "loss": 0.5059, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 2.8510638297872346e-06, | |
| "loss": 0.4958, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 2.6382978723404256e-06, | |
| "loss": 0.4928, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 2.425531914893617e-06, | |
| "loss": 0.4856, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 2.2127659574468085e-06, | |
| "loss": 0.4646, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.8710034489631653, | |
| "eval_runtime": 173.1105, | |
| "eval_samples_per_second": 2.958, | |
| "eval_steps_per_second": 0.092, | |
| "eval_wer": 60.05599273607748, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 10.25, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.4711, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "learning_rate": 1.7872340425531918e-06, | |
| "loss": 0.472, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "learning_rate": 1.5744680851063832e-06, | |
| "loss": 0.4745, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 1.3617021276595746e-06, | |
| "loss": 0.4546, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "learning_rate": 1.148936170212766e-06, | |
| "loss": 0.4702, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "learning_rate": 9.361702127659575e-07, | |
| "loss": 0.448, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 11.75, | |
| "learning_rate": 7.234042553191489e-07, | |
| "loss": 0.4584, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 5.106382978723404e-07, | |
| "loss": 0.4719, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 12.25, | |
| "learning_rate": 2.9787234042553196e-07, | |
| "loss": 0.45, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 8.510638297872341e-08, | |
| "loss": 0.4557, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "eval_loss": 0.873198390007019, | |
| "eval_runtime": 187.2044, | |
| "eval_samples_per_second": 2.735, | |
| "eval_steps_per_second": 0.085, | |
| "eval_wer": 59.465799031477, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 12.75, | |
| "learning_rate": 5.092783505154639e-06, | |
| "loss": 0.4501, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.989690721649485e-06, | |
| "loss": 0.4693, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 13.25, | |
| "learning_rate": 4.88659793814433e-06, | |
| "loss": 0.4261, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "learning_rate": 4.783505154639176e-06, | |
| "loss": 0.4336, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "learning_rate": 4.680412371134021e-06, | |
| "loss": 0.4303, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.577319587628866e-06, | |
| "loss": 0.4231, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 14.25, | |
| "learning_rate": 4.474226804123712e-06, | |
| "loss": 0.4178, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 14.5, | |
| "learning_rate": 4.371134020618557e-06, | |
| "loss": 0.4046, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 14.75, | |
| "learning_rate": 4.2680412371134025e-06, | |
| "loss": 0.3927, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 4.164948453608248e-06, | |
| "loss": 0.3882, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.8819407224655151, | |
| "eval_runtime": 211.3554, | |
| "eval_samples_per_second": 2.422, | |
| "eval_steps_per_second": 0.076, | |
| "eval_wer": 59.06476997578692, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 15.25, | |
| "learning_rate": 4.061855670103093e-06, | |
| "loss": 0.372, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 15.5, | |
| "learning_rate": 3.958762886597938e-06, | |
| "loss": 0.3832, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 15.75, | |
| "learning_rate": 3.855670103092784e-06, | |
| "loss": 0.3756, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.752577319587629e-06, | |
| "loss": 0.3818, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 16.25, | |
| "learning_rate": 3.6494845360824745e-06, | |
| "loss": 0.3669, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 16.5, | |
| "learning_rate": 3.54639175257732e-06, | |
| "loss": 0.3481, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 16.75, | |
| "learning_rate": 3.443298969072165e-06, | |
| "loss": 0.3568, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 3.3402061855670103e-06, | |
| "loss": 0.3567, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "learning_rate": 3.2371134020618563e-06, | |
| "loss": 0.3513, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 3.1340206185567014e-06, | |
| "loss": 0.3346, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "eval_loss": 0.9031797647476196, | |
| "eval_runtime": 183.8672, | |
| "eval_samples_per_second": 2.785, | |
| "eval_steps_per_second": 0.087, | |
| "eval_wer": 59.480932203389834, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 17.75, | |
| "learning_rate": 3.0309278350515465e-06, | |
| "loss": 0.3322, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 2.927835051546392e-06, | |
| "loss": 0.3114, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 18.25, | |
| "learning_rate": 2.8247422680412372e-06, | |
| "loss": 0.3155, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 18.5, | |
| "learning_rate": 2.7216494845360823e-06, | |
| "loss": 0.3295, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "learning_rate": 2.6185567010309283e-06, | |
| "loss": 0.314, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 2.5154639175257734e-06, | |
| "loss": 0.3068, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 19.25, | |
| "learning_rate": 2.412371134020619e-06, | |
| "loss": 0.312, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 19.5, | |
| "learning_rate": 2.309278350515464e-06, | |
| "loss": 0.2938, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 19.75, | |
| "learning_rate": 2.2061855670103092e-06, | |
| "loss": 0.3052, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.1030927835051548e-06, | |
| "loss": 0.2947, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.9144465923309326, | |
| "eval_runtime": 185.6121, | |
| "eval_samples_per_second": 2.758, | |
| "eval_steps_per_second": 0.086, | |
| "eval_wer": 59.76846246973365, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 20.25, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.2897, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 20.5, | |
| "learning_rate": 1.8969072164948455e-06, | |
| "loss": 0.2856, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 20.75, | |
| "learning_rate": 1.7938144329896908e-06, | |
| "loss": 0.3027, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 1.6907216494845363e-06, | |
| "loss": 0.3446, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 21.25, | |
| "learning_rate": 1.5876288659793815e-06, | |
| "loss": 0.2766, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 21.5, | |
| "learning_rate": 1.484536082474227e-06, | |
| "loss": 0.2816, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 21.75, | |
| "learning_rate": 1.3814432989690724e-06, | |
| "loss": 0.2845, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 1.2783505154639175e-06, | |
| "loss": 0.2828, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 22.25, | |
| "learning_rate": 1.175257731958763e-06, | |
| "loss": 0.2766, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "learning_rate": 1.0721649484536084e-06, | |
| "loss": 0.2724, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "eval_loss": 0.9288888573646545, | |
| "eval_runtime": 275.793, | |
| "eval_samples_per_second": 1.856, | |
| "eval_steps_per_second": 0.058, | |
| "eval_wer": 58.98153753026635, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 22.75, | |
| "learning_rate": 9.690721649484537e-07, | |
| "loss": 0.267, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 8.65979381443299e-07, | |
| "loss": 0.2602, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 23.25, | |
| "learning_rate": 7.628865979381445e-07, | |
| "loss": 0.2692, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 23.5, | |
| "learning_rate": 6.597938144329897e-07, | |
| "loss": 0.2623, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 23.75, | |
| "learning_rate": 5.567010309278352e-07, | |
| "loss": 0.2729, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 4.5360824742268044e-07, | |
| "loss": 0.263, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 24.25, | |
| "learning_rate": 3.505154639175258e-07, | |
| "loss": 0.2656, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 24.5, | |
| "learning_rate": 2.474226804123711e-07, | |
| "loss": 0.2633, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 24.75, | |
| "learning_rate": 1.443298969072165e-07, | |
| "loss": 0.2661, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 4.123711340206186e-08, | |
| "loss": 0.2785, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.933917224407196, | |
| "eval_runtime": 339.9994, | |
| "eval_samples_per_second": 1.506, | |
| "eval_steps_per_second": 0.047, | |
| "eval_wer": 59.200968523002416, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 25.25, | |
| "learning_rate": 1.6581196581196582e-06, | |
| "loss": 0.2704, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 25.5, | |
| "learning_rate": 1.5726495726495727e-06, | |
| "loss": 0.2582, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 25.75, | |
| "learning_rate": 1.4871794871794873e-06, | |
| "loss": 0.2634, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 1.401709401709402e-06, | |
| "loss": 0.2451, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 26.25, | |
| "learning_rate": 1.3162393162393163e-06, | |
| "loss": 0.2546, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 26.5, | |
| "learning_rate": 1.230769230769231e-06, | |
| "loss": 0.2604, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 26.75, | |
| "learning_rate": 1.1452991452991454e-06, | |
| "loss": 0.2459, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 1.0598290598290598e-06, | |
| "loss": 0.255, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 27.25, | |
| "learning_rate": 9.743589743589745e-07, | |
| "loss": 0.2505, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 27.5, | |
| "learning_rate": 8.88888888888889e-07, | |
| "loss": 0.2454, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 27.5, | |
| "eval_loss": 0.9438697099685669, | |
| "eval_runtime": 297.6469, | |
| "eval_samples_per_second": 1.72, | |
| "eval_steps_per_second": 0.054, | |
| "eval_wer": 59.193401937046005, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 27.75, | |
| "learning_rate": 8.034188034188035e-07, | |
| "loss": 0.2506, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 7.179487179487179e-07, | |
| "loss": 0.2497, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 28.25, | |
| "learning_rate": 6.324786324786325e-07, | |
| "loss": 0.2477, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 28.5, | |
| "learning_rate": 5.470085470085471e-07, | |
| "loss": 0.2489, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 28.75, | |
| "learning_rate": 4.615384615384616e-07, | |
| "loss": 0.2428, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 3.760683760683761e-07, | |
| "loss": 0.2395, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 29.25, | |
| "learning_rate": 2.905982905982906e-07, | |
| "loss": 0.2438, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 29.5, | |
| "learning_rate": 2.0512820512820514e-07, | |
| "loss": 0.2403, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 29.75, | |
| "learning_rate": 1.1965811965811967e-07, | |
| "loss": 0.2469, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 3.418803418803419e-08, | |
| "loss": 0.2297, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.9485259652137756, | |
| "eval_runtime": 355.4454, | |
| "eval_samples_per_second": 1.44, | |
| "eval_steps_per_second": 0.045, | |
| "eval_wer": 59.042070217917676, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 31.03, | |
| "learning_rate": 7.833333333333335e-07, | |
| "loss": 0.2489, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 31.28, | |
| "learning_rate": 7.000000000000001e-07, | |
| "loss": 0.2397, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 31.53, | |
| "learning_rate": 6.166666666666668e-07, | |
| "loss": 0.2362, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 31.78, | |
| "learning_rate": 5.333333333333335e-07, | |
| "loss": 0.2419, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 4.5000000000000003e-07, | |
| "loss": 0.2533, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 32.3, | |
| "learning_rate": 3.666666666666667e-07, | |
| "loss": 0.2321, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 32.56, | |
| "learning_rate": 2.8333333333333336e-07, | |
| "loss": 0.232, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 32.81, | |
| "learning_rate": 2.0000000000000002e-07, | |
| "loss": 0.2421, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 33.08, | |
| "learning_rate": 1.1666666666666668e-07, | |
| "loss": 0.2457, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 3.333333333333334e-08, | |
| "loss": 0.2383, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "eval_loss": 0.9528815746307373, | |
| "eval_runtime": 176.305, | |
| "eval_samples_per_second": 2.904, | |
| "eval_steps_per_second": 0.182, | |
| "eval_wer": 59.07990314769975, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "step": 1300, | |
| "total_flos": 5.27396086775808e+18, | |
| "train_loss": 0.018539312619429368, | |
| "train_runtime": 504.1118, | |
| "train_samples_per_second": 165.043, | |
| "train_steps_per_second": 2.579 | |
| } | |
| ], | |
| "max_steps": 1300, | |
| "num_train_epochs": 34, | |
| "total_flos": 5.27396086775808e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |