| { |
| "best_metric": 0.42036938667297363, |
| "best_model_checkpoint": "ai-light-dance_drums_ft_pretrain_wav2vec2-base-new_onset-idmt-mdb-2/checkpoint-374", |
| "epoch": 99.97777777777777, |
| "global_step": 1100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.89, |
| "learning_rate": 9.999999999999999e-05, |
| "loss": 0.2599, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.98, |
| "eval_loss": 0.42808040976524353, |
| "eval_runtime": 2.3932, |
| "eval_samples_per_second": 7.103, |
| "eval_steps_per_second": 2.089, |
| "eval_wer": 0.21976401179941002, |
| "step": 11 |
| }, |
| { |
| "epoch": 1.8, |
| "learning_rate": 0.00019999999999999998, |
| "loss": 0.2491, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.98, |
| "eval_loss": 0.48912692070007324, |
| "eval_runtime": 2.4857, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 2.011, |
| "eval_wer": 0.19469026548672566, |
| "step": 22 |
| }, |
| { |
| "epoch": 2.71, |
| "learning_rate": 0.0003, |
| "loss": 0.2619, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.98, |
| "eval_loss": 0.5496053099632263, |
| "eval_runtime": 2.4967, |
| "eval_samples_per_second": 6.809, |
| "eval_steps_per_second": 2.003, |
| "eval_wer": 0.2182890855457227, |
| "step": 33 |
| }, |
| { |
| "epoch": 3.62, |
| "learning_rate": 0.00029747663551401866, |
| "loss": 0.3354, |
| "step": 40 |
| }, |
| { |
| "epoch": 3.98, |
| "eval_loss": 0.5201741456985474, |
| "eval_runtime": 2.5002, |
| "eval_samples_per_second": 6.799, |
| "eval_steps_per_second": 2.0, |
| "eval_wer": 0.20943952802359883, |
| "step": 44 |
| }, |
| { |
| "epoch": 4.53, |
| "learning_rate": 0.0002946728971962617, |
| "loss": 0.277, |
| "step": 50 |
| }, |
| { |
| "epoch": 4.98, |
| "eval_loss": 0.4573761224746704, |
| "eval_runtime": 2.5614, |
| "eval_samples_per_second": 6.637, |
| "eval_steps_per_second": 1.952, |
| "eval_wer": 0.2079646017699115, |
| "step": 55 |
| }, |
| { |
| "epoch": 5.44, |
| "learning_rate": 0.00029186915887850464, |
| "loss": 0.3065, |
| "step": 60 |
| }, |
| { |
| "epoch": 5.98, |
| "eval_loss": 0.47488853335380554, |
| "eval_runtime": 2.5674, |
| "eval_samples_per_second": 6.621, |
| "eval_steps_per_second": 1.947, |
| "eval_wer": 0.2079646017699115, |
| "step": 66 |
| }, |
| { |
| "epoch": 6.36, |
| "learning_rate": 0.00028906542056074766, |
| "loss": 0.2669, |
| "step": 70 |
| }, |
| { |
| "epoch": 6.98, |
| "eval_loss": 0.5901708602905273, |
| "eval_runtime": 2.5163, |
| "eval_samples_per_second": 6.756, |
| "eval_steps_per_second": 1.987, |
| "eval_wer": 0.2182890855457227, |
| "step": 77 |
| }, |
| { |
| "epoch": 7.27, |
| "learning_rate": 0.0002862616822429906, |
| "loss": 0.2829, |
| "step": 80 |
| }, |
| { |
| "epoch": 7.98, |
| "eval_loss": 0.8560299873352051, |
| "eval_runtime": 2.4999, |
| "eval_samples_per_second": 6.8, |
| "eval_steps_per_second": 2.0, |
| "eval_wer": 0.20501474926253688, |
| "step": 88 |
| }, |
| { |
| "epoch": 8.18, |
| "learning_rate": 0.00028345794392523364, |
| "loss": 0.2509, |
| "step": 90 |
| }, |
| { |
| "epoch": 8.98, |
| "eval_loss": 0.6189576983451843, |
| "eval_runtime": 2.597, |
| "eval_samples_per_second": 6.546, |
| "eval_steps_per_second": 1.925, |
| "eval_wer": 0.20353982300884957, |
| "step": 99 |
| }, |
| { |
| "epoch": 9.09, |
| "learning_rate": 0.0002806542056074766, |
| "loss": 0.2754, |
| "step": 100 |
| }, |
| { |
| "epoch": 9.98, |
| "learning_rate": 0.0002778504672897196, |
| "loss": 0.2728, |
| "step": 110 |
| }, |
| { |
| "epoch": 9.98, |
| "eval_loss": 0.6561536192893982, |
| "eval_runtime": 2.5862, |
| "eval_samples_per_second": 6.573, |
| "eval_steps_per_second": 1.933, |
| "eval_wer": 0.21091445427728614, |
| "step": 110 |
| }, |
| { |
| "epoch": 10.89, |
| "learning_rate": 0.0002750467289719626, |
| "loss": 0.2615, |
| "step": 120 |
| }, |
| { |
| "epoch": 10.98, |
| "eval_loss": 0.6290748119354248, |
| "eval_runtime": 2.4827, |
| "eval_samples_per_second": 6.847, |
| "eval_steps_per_second": 2.014, |
| "eval_wer": 0.20648967551622419, |
| "step": 121 |
| }, |
| { |
| "epoch": 11.8, |
| "learning_rate": 0.0002722429906542056, |
| "loss": 0.2586, |
| "step": 130 |
| }, |
| { |
| "epoch": 11.98, |
| "eval_loss": 0.6167445778846741, |
| "eval_runtime": 2.4578, |
| "eval_samples_per_second": 6.917, |
| "eval_steps_per_second": 2.034, |
| "eval_wer": 0.18436578171091444, |
| "step": 132 |
| }, |
| { |
| "epoch": 12.71, |
| "learning_rate": 0.00026943925233644856, |
| "loss": 0.2441, |
| "step": 140 |
| }, |
| { |
| "epoch": 12.98, |
| "eval_loss": 0.6735682487487793, |
| "eval_runtime": 2.4754, |
| "eval_samples_per_second": 6.867, |
| "eval_steps_per_second": 2.02, |
| "eval_wer": 0.19616519174041297, |
| "step": 143 |
| }, |
| { |
| "epoch": 13.62, |
| "learning_rate": 0.0002666355140186916, |
| "loss": 0.233, |
| "step": 150 |
| }, |
| { |
| "epoch": 13.98, |
| "eval_loss": 0.5727431774139404, |
| "eval_runtime": 2.4735, |
| "eval_samples_per_second": 6.873, |
| "eval_steps_per_second": 2.021, |
| "eval_wer": 0.20501474926253688, |
| "step": 154 |
| }, |
| { |
| "epoch": 14.53, |
| "learning_rate": 0.00026383177570093454, |
| "loss": 0.2567, |
| "step": 160 |
| }, |
| { |
| "epoch": 14.98, |
| "eval_loss": 0.6164781451225281, |
| "eval_runtime": 2.4905, |
| "eval_samples_per_second": 6.826, |
| "eval_steps_per_second": 2.008, |
| "eval_wer": 0.1873156342182891, |
| "step": 165 |
| }, |
| { |
| "epoch": 15.44, |
| "learning_rate": 0.00026102803738317756, |
| "loss": 0.2264, |
| "step": 170 |
| }, |
| { |
| "epoch": 15.98, |
| "eval_loss": 0.7506299018859863, |
| "eval_runtime": 2.5014, |
| "eval_samples_per_second": 6.796, |
| "eval_steps_per_second": 1.999, |
| "eval_wer": 0.2079646017699115, |
| "step": 176 |
| }, |
| { |
| "epoch": 16.36, |
| "learning_rate": 0.0002582242990654205, |
| "loss": 0.2346, |
| "step": 180 |
| }, |
| { |
| "epoch": 16.98, |
| "eval_loss": 0.701734185218811, |
| "eval_runtime": 2.4973, |
| "eval_samples_per_second": 6.807, |
| "eval_steps_per_second": 2.002, |
| "eval_wer": 0.1887905604719764, |
| "step": 187 |
| }, |
| { |
| "epoch": 17.27, |
| "learning_rate": 0.00025542056074766354, |
| "loss": 0.2343, |
| "step": 190 |
| }, |
| { |
| "epoch": 17.98, |
| "eval_loss": 0.5930327773094177, |
| "eval_runtime": 2.5093, |
| "eval_samples_per_second": 6.775, |
| "eval_steps_per_second": 1.993, |
| "eval_wer": 0.20943952802359883, |
| "step": 198 |
| }, |
| { |
| "epoch": 18.18, |
| "learning_rate": 0.0002526168224299065, |
| "loss": 0.2638, |
| "step": 200 |
| }, |
| { |
| "epoch": 18.98, |
| "eval_loss": 0.5729739665985107, |
| "eval_runtime": 2.4782, |
| "eval_samples_per_second": 6.86, |
| "eval_steps_per_second": 2.018, |
| "eval_wer": 0.20058997050147492, |
| "step": 209 |
| }, |
| { |
| "epoch": 19.09, |
| "learning_rate": 0.0002498130841121495, |
| "loss": 0.2332, |
| "step": 210 |
| }, |
| { |
| "epoch": 19.98, |
| "learning_rate": 0.0002470093457943925, |
| "loss": 0.2543, |
| "step": 220 |
| }, |
| { |
| "epoch": 19.98, |
| "eval_loss": 0.4991203248500824, |
| "eval_runtime": 2.4588, |
| "eval_samples_per_second": 6.914, |
| "eval_steps_per_second": 2.034, |
| "eval_wer": 0.21976401179941002, |
| "step": 220 |
| }, |
| { |
| "epoch": 20.89, |
| "learning_rate": 0.0002442056074766355, |
| "loss": 0.2476, |
| "step": 230 |
| }, |
| { |
| "epoch": 20.98, |
| "eval_loss": 0.6363905668258667, |
| "eval_runtime": 2.4779, |
| "eval_samples_per_second": 6.861, |
| "eval_steps_per_second": 2.018, |
| "eval_wer": 0.20648967551622419, |
| "step": 231 |
| }, |
| { |
| "epoch": 21.8, |
| "learning_rate": 0.00024140186915887847, |
| "loss": 0.2777, |
| "step": 240 |
| }, |
| { |
| "epoch": 21.98, |
| "eval_loss": 0.6247313618659973, |
| "eval_runtime": 2.4757, |
| "eval_samples_per_second": 6.867, |
| "eval_steps_per_second": 2.02, |
| "eval_wer": 0.18436578171091444, |
| "step": 242 |
| }, |
| { |
| "epoch": 22.71, |
| "learning_rate": 0.00023859813084112146, |
| "loss": 0.2661, |
| "step": 250 |
| }, |
| { |
| "epoch": 22.98, |
| "eval_loss": 0.5588754415512085, |
| "eval_runtime": 2.5016, |
| "eval_samples_per_second": 6.796, |
| "eval_steps_per_second": 1.999, |
| "eval_wer": 0.20058997050147492, |
| "step": 253 |
| }, |
| { |
| "epoch": 23.62, |
| "learning_rate": 0.00023579439252336445, |
| "loss": 0.2094, |
| "step": 260 |
| }, |
| { |
| "epoch": 23.98, |
| "eval_loss": 0.531648576259613, |
| "eval_runtime": 2.4851, |
| "eval_samples_per_second": 6.841, |
| "eval_steps_per_second": 2.012, |
| "eval_wer": 0.2079646017699115, |
| "step": 264 |
| }, |
| { |
| "epoch": 24.53, |
| "learning_rate": 0.00023299065420560744, |
| "loss": 0.2496, |
| "step": 270 |
| }, |
| { |
| "epoch": 24.98, |
| "eval_loss": 0.8821189999580383, |
| "eval_runtime": 2.49, |
| "eval_samples_per_second": 6.827, |
| "eval_steps_per_second": 2.008, |
| "eval_wer": 0.18436578171091444, |
| "step": 275 |
| }, |
| { |
| "epoch": 25.44, |
| "learning_rate": 0.00023018691588785043, |
| "loss": 0.2302, |
| "step": 280 |
| }, |
| { |
| "epoch": 25.98, |
| "eval_loss": 0.5408168435096741, |
| "eval_runtime": 2.4887, |
| "eval_samples_per_second": 6.831, |
| "eval_steps_per_second": 2.009, |
| "eval_wer": 0.18141592920353983, |
| "step": 286 |
| }, |
| { |
| "epoch": 26.36, |
| "learning_rate": 0.00022738317757009342, |
| "loss": 0.2651, |
| "step": 290 |
| }, |
| { |
| "epoch": 26.98, |
| "eval_loss": 0.6479179859161377, |
| "eval_runtime": 2.4859, |
| "eval_samples_per_second": 6.838, |
| "eval_steps_per_second": 2.011, |
| "eval_wer": 0.20943952802359883, |
| "step": 297 |
| }, |
| { |
| "epoch": 27.27, |
| "learning_rate": 0.00022457943925233641, |
| "loss": 0.2119, |
| "step": 300 |
| }, |
| { |
| "epoch": 27.98, |
| "eval_loss": 0.5875303745269775, |
| "eval_runtime": 2.5001, |
| "eval_samples_per_second": 6.8, |
| "eval_steps_per_second": 2.0, |
| "eval_wer": 0.18141592920353983, |
| "step": 308 |
| }, |
| { |
| "epoch": 28.18, |
| "learning_rate": 0.0002217757009345794, |
| "loss": 0.2468, |
| "step": 310 |
| }, |
| { |
| "epoch": 28.98, |
| "eval_loss": 0.7614116072654724, |
| "eval_runtime": 2.4857, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 2.012, |
| "eval_wer": 0.1976401179941003, |
| "step": 319 |
| }, |
| { |
| "epoch": 29.09, |
| "learning_rate": 0.0002189719626168224, |
| "loss": 0.267, |
| "step": 320 |
| }, |
| { |
| "epoch": 29.98, |
| "learning_rate": 0.00021616822429906539, |
| "loss": 0.2239, |
| "step": 330 |
| }, |
| { |
| "epoch": 29.98, |
| "eval_loss": 0.4908014237880707, |
| "eval_runtime": 2.5125, |
| "eval_samples_per_second": 6.766, |
| "eval_steps_per_second": 1.99, |
| "eval_wer": 0.1902654867256637, |
| "step": 330 |
| }, |
| { |
| "epoch": 30.89, |
| "learning_rate": 0.00021336448598130838, |
| "loss": 0.2514, |
| "step": 340 |
| }, |
| { |
| "epoch": 30.98, |
| "eval_loss": 0.5196467638015747, |
| "eval_runtime": 2.4757, |
| "eval_samples_per_second": 6.867, |
| "eval_steps_per_second": 2.02, |
| "eval_wer": 0.20353982300884957, |
| "step": 341 |
| }, |
| { |
| "epoch": 31.8, |
| "learning_rate": 0.00021056074766355137, |
| "loss": 0.2244, |
| "step": 350 |
| }, |
| { |
| "epoch": 31.98, |
| "eval_loss": 0.5580195784568787, |
| "eval_runtime": 2.5054, |
| "eval_samples_per_second": 6.785, |
| "eval_steps_per_second": 1.996, |
| "eval_wer": 0.19911504424778761, |
| "step": 352 |
| }, |
| { |
| "epoch": 32.71, |
| "learning_rate": 0.00020775700934579436, |
| "loss": 0.2524, |
| "step": 360 |
| }, |
| { |
| "epoch": 32.98, |
| "eval_loss": 0.5342008471488953, |
| "eval_runtime": 2.483, |
| "eval_samples_per_second": 6.847, |
| "eval_steps_per_second": 2.014, |
| "eval_wer": 0.20206489675516223, |
| "step": 363 |
| }, |
| { |
| "epoch": 33.62, |
| "learning_rate": 0.00020495327102803735, |
| "loss": 0.2516, |
| "step": 370 |
| }, |
| { |
| "epoch": 33.98, |
| "eval_loss": 0.42036938667297363, |
| "eval_runtime": 2.4952, |
| "eval_samples_per_second": 6.813, |
| "eval_steps_per_second": 2.004, |
| "eval_wer": 0.18436578171091444, |
| "step": 374 |
| }, |
| { |
| "epoch": 34.53, |
| "learning_rate": 0.00020214953271028034, |
| "loss": 0.2515, |
| "step": 380 |
| }, |
| { |
| "epoch": 34.98, |
| "eval_loss": 0.5135067105293274, |
| "eval_runtime": 2.4689, |
| "eval_samples_per_second": 6.886, |
| "eval_steps_per_second": 2.025, |
| "eval_wer": 0.21238938053097345, |
| "step": 385 |
| }, |
| { |
| "epoch": 35.44, |
| "learning_rate": 0.00019934579439252333, |
| "loss": 0.2542, |
| "step": 390 |
| }, |
| { |
| "epoch": 35.98, |
| "eval_loss": 0.8149600028991699, |
| "eval_runtime": 2.5099, |
| "eval_samples_per_second": 6.773, |
| "eval_steps_per_second": 1.992, |
| "eval_wer": 0.19616519174041297, |
| "step": 396 |
| }, |
| { |
| "epoch": 36.36, |
| "learning_rate": 0.00019654205607476632, |
| "loss": 0.2269, |
| "step": 400 |
| }, |
| { |
| "epoch": 36.98, |
| "eval_loss": 0.8832700252532959, |
| "eval_runtime": 2.5448, |
| "eval_samples_per_second": 6.68, |
| "eval_steps_per_second": 1.965, |
| "eval_wer": 0.20943952802359883, |
| "step": 407 |
| }, |
| { |
| "epoch": 37.27, |
| "learning_rate": 0.0001937383177570093, |
| "loss": 0.212, |
| "step": 410 |
| }, |
| { |
| "epoch": 37.98, |
| "eval_loss": 1.3234660625457764, |
| "eval_runtime": 2.4758, |
| "eval_samples_per_second": 6.867, |
| "eval_steps_per_second": 2.02, |
| "eval_wer": 0.2182890855457227, |
| "step": 418 |
| }, |
| { |
| "epoch": 38.18, |
| "learning_rate": 0.0001909345794392523, |
| "loss": 0.2119, |
| "step": 420 |
| }, |
| { |
| "epoch": 38.98, |
| "eval_loss": 0.6919201016426086, |
| "eval_runtime": 2.478, |
| "eval_samples_per_second": 6.86, |
| "eval_steps_per_second": 2.018, |
| "eval_wer": 0.20206489675516223, |
| "step": 429 |
| }, |
| { |
| "epoch": 39.09, |
| "learning_rate": 0.0001881308411214953, |
| "loss": 0.2196, |
| "step": 430 |
| }, |
| { |
| "epoch": 39.98, |
| "learning_rate": 0.00018532710280373828, |
| "loss": 0.2228, |
| "step": 440 |
| }, |
| { |
| "epoch": 39.98, |
| "eval_loss": 0.6712406873703003, |
| "eval_runtime": 2.4899, |
| "eval_samples_per_second": 6.827, |
| "eval_steps_per_second": 2.008, |
| "eval_wer": 0.20206489675516223, |
| "step": 440 |
| }, |
| { |
| "epoch": 40.89, |
| "learning_rate": 0.00018252336448598127, |
| "loss": 0.2127, |
| "step": 450 |
| }, |
| { |
| "epoch": 40.98, |
| "eval_loss": 0.755742073059082, |
| "eval_runtime": 2.4974, |
| "eval_samples_per_second": 6.807, |
| "eval_steps_per_second": 2.002, |
| "eval_wer": 0.1976401179941003, |
| "step": 451 |
| }, |
| { |
| "epoch": 41.8, |
| "learning_rate": 0.00017971962616822426, |
| "loss": 0.2064, |
| "step": 460 |
| }, |
| { |
| "epoch": 41.98, |
| "eval_loss": 0.5917617082595825, |
| "eval_runtime": 2.4802, |
| "eval_samples_per_second": 6.854, |
| "eval_steps_per_second": 2.016, |
| "eval_wer": 0.19469026548672566, |
| "step": 462 |
| }, |
| { |
| "epoch": 42.71, |
| "learning_rate": 0.00017691588785046725, |
| "loss": 0.2147, |
| "step": 470 |
| }, |
| { |
| "epoch": 42.98, |
| "eval_loss": 0.804908275604248, |
| "eval_runtime": 2.4373, |
| "eval_samples_per_second": 6.975, |
| "eval_steps_per_second": 2.051, |
| "eval_wer": 0.19616519174041297, |
| "step": 473 |
| }, |
| { |
| "epoch": 43.62, |
| "learning_rate": 0.00017411214953271025, |
| "loss": 0.193, |
| "step": 480 |
| }, |
| { |
| "epoch": 43.98, |
| "eval_loss": 0.7116745710372925, |
| "eval_runtime": 2.4658, |
| "eval_samples_per_second": 6.894, |
| "eval_steps_per_second": 2.028, |
| "eval_wer": 0.1976401179941003, |
| "step": 484 |
| }, |
| { |
| "epoch": 44.53, |
| "learning_rate": 0.00017130841121495324, |
| "loss": 0.2063, |
| "step": 490 |
| }, |
| { |
| "epoch": 44.98, |
| "eval_loss": 0.554362416267395, |
| "eval_runtime": 2.4717, |
| "eval_samples_per_second": 6.878, |
| "eval_steps_per_second": 2.023, |
| "eval_wer": 0.19616519174041297, |
| "step": 495 |
| }, |
| { |
| "epoch": 45.44, |
| "learning_rate": 0.00016850467289719623, |
| "loss": 0.1989, |
| "step": 500 |
| }, |
| { |
| "epoch": 45.98, |
| "eval_loss": 0.5782185196876526, |
| "eval_runtime": 2.4456, |
| "eval_samples_per_second": 6.951, |
| "eval_steps_per_second": 2.044, |
| "eval_wer": 0.1887905604719764, |
| "step": 506 |
| }, |
| { |
| "epoch": 46.36, |
| "learning_rate": 0.00016570093457943922, |
| "loss": 0.2193, |
| "step": 510 |
| }, |
| { |
| "epoch": 46.98, |
| "eval_loss": 0.5216302275657654, |
| "eval_runtime": 2.4591, |
| "eval_samples_per_second": 6.913, |
| "eval_steps_per_second": 2.033, |
| "eval_wer": 0.19469026548672566, |
| "step": 517 |
| }, |
| { |
| "epoch": 47.27, |
| "learning_rate": 0.0001628971962616822, |
| "loss": 0.2012, |
| "step": 520 |
| }, |
| { |
| "epoch": 47.98, |
| "eval_loss": 0.5268691778182983, |
| "eval_runtime": 2.4596, |
| "eval_samples_per_second": 6.912, |
| "eval_steps_per_second": 2.033, |
| "eval_wer": 0.19174041297935104, |
| "step": 528 |
| }, |
| { |
| "epoch": 48.18, |
| "learning_rate": 0.0001600934579439252, |
| "loss": 0.2187, |
| "step": 530 |
| }, |
| { |
| "epoch": 48.98, |
| "eval_loss": 0.4635768532752991, |
| "eval_runtime": 2.4781, |
| "eval_samples_per_second": 6.86, |
| "eval_steps_per_second": 2.018, |
| "eval_wer": 0.18436578171091444, |
| "step": 539 |
| }, |
| { |
| "epoch": 49.09, |
| "learning_rate": 0.0001572897196261682, |
| "loss": 0.1857, |
| "step": 540 |
| }, |
| { |
| "epoch": 49.98, |
| "learning_rate": 0.00015448598130841118, |
| "loss": 0.2128, |
| "step": 550 |
| }, |
| { |
| "epoch": 49.98, |
| "eval_loss": 0.49676355719566345, |
| "eval_runtime": 2.4581, |
| "eval_samples_per_second": 6.916, |
| "eval_steps_per_second": 2.034, |
| "eval_wer": 0.1887905604719764, |
| "step": 550 |
| }, |
| { |
| "epoch": 50.89, |
| "learning_rate": 0.00015168224299065417, |
| "loss": 0.2041, |
| "step": 560 |
| }, |
| { |
| "epoch": 50.98, |
| "eval_loss": 0.47835999727249146, |
| "eval_runtime": 2.4475, |
| "eval_samples_per_second": 6.946, |
| "eval_steps_per_second": 2.043, |
| "eval_wer": 0.1887905604719764, |
| "step": 561 |
| }, |
| { |
| "epoch": 51.8, |
| "learning_rate": 0.0001488785046728972, |
| "loss": 0.1993, |
| "step": 570 |
| }, |
| { |
| "epoch": 51.98, |
| "eval_loss": 0.5591913461685181, |
| "eval_runtime": 2.4775, |
| "eval_samples_per_second": 6.862, |
| "eval_steps_per_second": 2.018, |
| "eval_wer": 0.17551622418879056, |
| "step": 572 |
| }, |
| { |
| "epoch": 52.71, |
| "learning_rate": 0.00014607476635514018, |
| "loss": 0.1981, |
| "step": 580 |
| }, |
| { |
| "epoch": 52.98, |
| "eval_loss": 0.4870879352092743, |
| "eval_runtime": 2.4711, |
| "eval_samples_per_second": 6.88, |
| "eval_steps_per_second": 2.023, |
| "eval_wer": 0.17846607669616518, |
| "step": 583 |
| }, |
| { |
| "epoch": 53.62, |
| "learning_rate": 0.00014327102803738317, |
| "loss": 0.1808, |
| "step": 590 |
| }, |
| { |
| "epoch": 53.98, |
| "eval_loss": 0.47705358266830444, |
| "eval_runtime": 2.4668, |
| "eval_samples_per_second": 6.891, |
| "eval_steps_per_second": 2.027, |
| "eval_wer": 0.17404129793510326, |
| "step": 594 |
| }, |
| { |
| "epoch": 54.53, |
| "learning_rate": 0.00014046728971962616, |
| "loss": 0.2317, |
| "step": 600 |
| }, |
| { |
| "epoch": 54.98, |
| "eval_loss": 0.5285036563873291, |
| "eval_runtime": 2.4608, |
| "eval_samples_per_second": 6.908, |
| "eval_steps_per_second": 2.032, |
| "eval_wer": 0.18141592920353983, |
| "step": 605 |
| }, |
| { |
| "epoch": 55.44, |
| "learning_rate": 0.00013766355140186915, |
| "loss": 0.1906, |
| "step": 610 |
| }, |
| { |
| "epoch": 55.98, |
| "eval_loss": 0.5485416650772095, |
| "eval_runtime": 2.4937, |
| "eval_samples_per_second": 6.817, |
| "eval_steps_per_second": 2.005, |
| "eval_wer": 0.18436578171091444, |
| "step": 616 |
| }, |
| { |
| "epoch": 56.36, |
| "learning_rate": 0.00013485981308411214, |
| "loss": 0.1924, |
| "step": 620 |
| }, |
| { |
| "epoch": 56.98, |
| "eval_loss": 0.5615388751029968, |
| "eval_runtime": 2.4859, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 2.011, |
| "eval_wer": 0.18141592920353983, |
| "step": 627 |
| }, |
| { |
| "epoch": 57.27, |
| "learning_rate": 0.00013205607476635513, |
| "loss": 0.1761, |
| "step": 630 |
| }, |
| { |
| "epoch": 57.98, |
| "eval_loss": 0.46036362648010254, |
| "eval_runtime": 2.4852, |
| "eval_samples_per_second": 6.84, |
| "eval_steps_per_second": 2.012, |
| "eval_wer": 0.17994100294985252, |
| "step": 638 |
| }, |
| { |
| "epoch": 58.18, |
| "learning_rate": 0.00012925233644859812, |
| "loss": 0.2047, |
| "step": 640 |
| }, |
| { |
| "epoch": 58.98, |
| "eval_loss": 0.422275573015213, |
| "eval_runtime": 2.4837, |
| "eval_samples_per_second": 6.845, |
| "eval_steps_per_second": 2.013, |
| "eval_wer": 0.18289085545722714, |
| "step": 649 |
| }, |
| { |
| "epoch": 59.09, |
| "learning_rate": 0.00012644859813084111, |
| "loss": 0.2295, |
| "step": 650 |
| }, |
| { |
| "epoch": 59.98, |
| "learning_rate": 0.0001236448598130841, |
| "loss": 0.1992, |
| "step": 660 |
| }, |
| { |
| "epoch": 59.98, |
| "eval_loss": 0.47056129574775696, |
| "eval_runtime": 2.4575, |
| "eval_samples_per_second": 6.918, |
| "eval_steps_per_second": 2.035, |
| "eval_wer": 0.1873156342182891, |
| "step": 660 |
| }, |
| { |
| "epoch": 60.89, |
| "learning_rate": 0.0001208411214953271, |
| "loss": 0.1949, |
| "step": 670 |
| }, |
| { |
| "epoch": 60.98, |
| "eval_loss": 0.4633275866508484, |
| "eval_runtime": 2.458, |
| "eval_samples_per_second": 6.916, |
| "eval_steps_per_second": 2.034, |
| "eval_wer": 0.18436578171091444, |
| "step": 671 |
| }, |
| { |
| "epoch": 61.8, |
| "learning_rate": 0.00011803738317757009, |
| "loss": 0.2034, |
| "step": 680 |
| }, |
| { |
| "epoch": 61.98, |
| "eval_loss": 0.48540210723876953, |
| "eval_runtime": 2.4576, |
| "eval_samples_per_second": 6.917, |
| "eval_steps_per_second": 2.035, |
| "eval_wer": 0.18141592920353983, |
| "step": 682 |
| }, |
| { |
| "epoch": 62.71, |
| "learning_rate": 0.00011523364485981308, |
| "loss": 0.2147, |
| "step": 690 |
| }, |
| { |
| "epoch": 62.98, |
| "eval_loss": 0.4488876163959503, |
| "eval_runtime": 2.4838, |
| "eval_samples_per_second": 6.844, |
| "eval_steps_per_second": 2.013, |
| "eval_wer": 0.18436578171091444, |
| "step": 693 |
| }, |
| { |
| "epoch": 63.62, |
| "learning_rate": 0.00011242990654205607, |
| "loss": 0.2135, |
| "step": 700 |
| }, |
| { |
| "epoch": 63.98, |
| "eval_loss": 0.48737475275993347, |
| "eval_runtime": 2.4621, |
| "eval_samples_per_second": 6.905, |
| "eval_steps_per_second": 2.031, |
| "eval_wer": 0.17256637168141592, |
| "step": 704 |
| }, |
| { |
| "epoch": 64.53, |
| "learning_rate": 0.00010962616822429906, |
| "loss": 0.2021, |
| "step": 710 |
| }, |
| { |
| "epoch": 64.98, |
| "eval_loss": 0.4635281562805176, |
| "eval_runtime": 2.4487, |
| "eval_samples_per_second": 6.942, |
| "eval_steps_per_second": 2.042, |
| "eval_wer": 0.18141592920353983, |
| "step": 715 |
| }, |
| { |
| "epoch": 65.44, |
| "learning_rate": 0.00010682242990654205, |
| "loss": 0.1822, |
| "step": 720 |
| }, |
| { |
| "epoch": 65.98, |
| "eval_loss": 0.48127830028533936, |
| "eval_runtime": 2.4625, |
| "eval_samples_per_second": 6.904, |
| "eval_steps_per_second": 2.03, |
| "eval_wer": 0.17846607669616518, |
| "step": 726 |
| }, |
| { |
| "epoch": 66.36, |
| "learning_rate": 0.00010401869158878504, |
| "loss": 0.1882, |
| "step": 730 |
| }, |
| { |
| "epoch": 66.98, |
| "eval_loss": 0.5075557827949524, |
| "eval_runtime": 2.4867, |
| "eval_samples_per_second": 6.836, |
| "eval_steps_per_second": 2.011, |
| "eval_wer": 0.17994100294985252, |
| "step": 737 |
| }, |
| { |
| "epoch": 67.27, |
| "learning_rate": 0.00010121495327102803, |
| "loss": 0.2014, |
| "step": 740 |
| }, |
| { |
| "epoch": 67.98, |
| "eval_loss": 0.5182777047157288, |
| "eval_runtime": 2.4749, |
| "eval_samples_per_second": 6.869, |
| "eval_steps_per_second": 2.02, |
| "eval_wer": 0.1887905604719764, |
| "step": 748 |
| }, |
| { |
| "epoch": 68.18, |
| "learning_rate": 9.841121495327102e-05, |
| "loss": 0.1869, |
| "step": 750 |
| }, |
| { |
| "epoch": 68.98, |
| "eval_loss": 0.5035397410392761, |
| "eval_runtime": 2.4735, |
| "eval_samples_per_second": 6.873, |
| "eval_steps_per_second": 2.021, |
| "eval_wer": 0.17994100294985252, |
| "step": 759 |
| }, |
| { |
| "epoch": 69.09, |
| "learning_rate": 9.560747663551401e-05, |
| "loss": 0.2118, |
| "step": 760 |
| }, |
| { |
| "epoch": 69.98, |
| "learning_rate": 9.2803738317757e-05, |
| "loss": 0.1914, |
| "step": 770 |
| }, |
| { |
| "epoch": 69.98, |
| "eval_loss": 0.4693587124347687, |
| "eval_runtime": 2.5588, |
| "eval_samples_per_second": 6.644, |
| "eval_steps_per_second": 1.954, |
| "eval_wer": 0.18436578171091444, |
| "step": 770 |
| }, |
| { |
| "epoch": 70.89, |
| "learning_rate": 8.999999999999999e-05, |
| "loss": 0.1972, |
| "step": 780 |
| }, |
| { |
| "epoch": 70.98, |
| "eval_loss": 0.4484705626964569, |
| "eval_runtime": 2.5088, |
| "eval_samples_per_second": 6.776, |
| "eval_steps_per_second": 1.993, |
| "eval_wer": 0.18436578171091444, |
| "step": 781 |
| }, |
| { |
| "epoch": 71.8, |
| "learning_rate": 8.719626168224298e-05, |
| "loss": 0.1724, |
| "step": 790 |
| }, |
| { |
| "epoch": 71.98, |
| "eval_loss": 0.457947701215744, |
| "eval_runtime": 2.4982, |
| "eval_samples_per_second": 6.805, |
| "eval_steps_per_second": 2.001, |
| "eval_wer": 0.18289085545722714, |
| "step": 792 |
| }, |
| { |
| "epoch": 72.71, |
| "learning_rate": 8.439252336448597e-05, |
| "loss": 0.195, |
| "step": 800 |
| }, |
| { |
| "epoch": 72.98, |
| "eval_loss": 0.5178218483924866, |
| "eval_runtime": 2.4797, |
| "eval_samples_per_second": 6.856, |
| "eval_steps_per_second": 2.016, |
| "eval_wer": 0.18141592920353983, |
| "step": 803 |
| }, |
| { |
| "epoch": 73.62, |
| "learning_rate": 8.158878504672896e-05, |
| "loss": 0.2017, |
| "step": 810 |
| }, |
| { |
| "epoch": 73.98, |
| "eval_loss": 0.49777284264564514, |
| "eval_runtime": 2.4694, |
| "eval_samples_per_second": 6.884, |
| "eval_steps_per_second": 2.025, |
| "eval_wer": 0.18289085545722714, |
| "step": 814 |
| }, |
| { |
| "epoch": 74.53, |
| "learning_rate": 7.878504672897195e-05, |
| "loss": 0.1874, |
| "step": 820 |
| }, |
| { |
| "epoch": 74.98, |
| "eval_loss": 0.5034937858581543, |
| "eval_runtime": 2.4472, |
| "eval_samples_per_second": 6.947, |
| "eval_steps_per_second": 2.043, |
| "eval_wer": 0.1873156342182891, |
| "step": 825 |
| }, |
| { |
| "epoch": 75.44, |
| "learning_rate": 7.598130841121495e-05, |
| "loss": 0.1925, |
| "step": 830 |
| }, |
| { |
| "epoch": 75.98, |
| "eval_loss": 0.5495364665985107, |
| "eval_runtime": 2.4633, |
| "eval_samples_per_second": 6.901, |
| "eval_steps_per_second": 2.03, |
| "eval_wer": 0.18289085545722714, |
| "step": 836 |
| }, |
| { |
| "epoch": 76.36, |
| "learning_rate": 7.317757009345794e-05, |
| "loss": 0.1845, |
| "step": 840 |
| }, |
| { |
| "epoch": 76.98, |
| "eval_loss": 0.5394346117973328, |
| "eval_runtime": 2.4749, |
| "eval_samples_per_second": 6.869, |
| "eval_steps_per_second": 2.02, |
| "eval_wer": 0.17994100294985252, |
| "step": 847 |
| }, |
| { |
| "epoch": 77.27, |
| "learning_rate": 7.037383177570093e-05, |
| "loss": 0.1718, |
| "step": 850 |
| }, |
| { |
| "epoch": 77.98, |
| "eval_loss": 0.507049024105072, |
| "eval_runtime": 2.4857, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 2.012, |
| "eval_wer": 0.1710914454277286, |
| "step": 858 |
| }, |
| { |
| "epoch": 78.18, |
| "learning_rate": 6.757009345794392e-05, |
| "loss": 0.1824, |
| "step": 860 |
| }, |
| { |
| "epoch": 78.98, |
| "eval_loss": 0.49118277430534363, |
| "eval_runtime": 2.4521, |
| "eval_samples_per_second": 6.933, |
| "eval_steps_per_second": 2.039, |
| "eval_wer": 0.17699115044247787, |
| "step": 869 |
| }, |
| { |
| "epoch": 79.09, |
| "learning_rate": 6.476635514018691e-05, |
| "loss": 0.1904, |
| "step": 870 |
| }, |
| { |
| "epoch": 79.98, |
| "learning_rate": 6.19626168224299e-05, |
| "loss": 0.1702, |
| "step": 880 |
| }, |
| { |
| "epoch": 79.98, |
| "eval_loss": 0.46315157413482666, |
| "eval_runtime": 2.4682, |
| "eval_samples_per_second": 6.888, |
| "eval_steps_per_second": 2.026, |
| "eval_wer": 0.17256637168141592, |
| "step": 880 |
| }, |
| { |
| "epoch": 80.89, |
| "learning_rate": 5.9158878504672896e-05, |
| "loss": 0.1563, |
| "step": 890 |
| }, |
| { |
| "epoch": 80.98, |
| "eval_loss": 0.44120773673057556, |
| "eval_runtime": 2.4609, |
| "eval_samples_per_second": 6.908, |
| "eval_steps_per_second": 2.032, |
| "eval_wer": 0.17256637168141592, |
| "step": 891 |
| }, |
| { |
| "epoch": 81.8, |
| "learning_rate": 5.635514018691589e-05, |
| "loss": 0.1858, |
| "step": 900 |
| }, |
| { |
| "epoch": 81.98, |
| "eval_loss": 0.46348273754119873, |
| "eval_runtime": 2.4786, |
| "eval_samples_per_second": 6.859, |
| "eval_steps_per_second": 2.017, |
| "eval_wer": 0.16666666666666666, |
| "step": 902 |
| }, |
| { |
| "epoch": 82.71, |
| "learning_rate": 5.355140186915888e-05, |
| "loss": 0.1701, |
| "step": 910 |
| }, |
| { |
| "epoch": 82.98, |
| "eval_loss": 0.4837586581707001, |
| "eval_runtime": 2.4341, |
| "eval_samples_per_second": 6.984, |
| "eval_steps_per_second": 2.054, |
| "eval_wer": 0.17256637168141592, |
| "step": 913 |
| }, |
| { |
| "epoch": 83.62, |
| "learning_rate": 5.074766355140187e-05, |
| "loss": 0.188, |
| "step": 920 |
| }, |
| { |
| "epoch": 83.98, |
| "eval_loss": 0.4775279462337494, |
| "eval_runtime": 2.5362, |
| "eval_samples_per_second": 6.703, |
| "eval_steps_per_second": 1.971, |
| "eval_wer": 0.18141592920353983, |
| "step": 924 |
| }, |
| { |
| "epoch": 84.53, |
| "learning_rate": 4.794392523364486e-05, |
| "loss": 0.1789, |
| "step": 930 |
| }, |
| { |
| "epoch": 84.98, |
| "eval_loss": 0.4800940752029419, |
| "eval_runtime": 2.4737, |
| "eval_samples_per_second": 6.872, |
| "eval_steps_per_second": 2.021, |
| "eval_wer": 0.17404129793510326, |
| "step": 935 |
| }, |
| { |
| "epoch": 85.44, |
| "learning_rate": 4.514018691588785e-05, |
| "loss": 0.2134, |
| "step": 940 |
| }, |
| { |
| "epoch": 85.98, |
| "eval_loss": 0.45418649911880493, |
| "eval_runtime": 2.4552, |
| "eval_samples_per_second": 6.924, |
| "eval_steps_per_second": 2.037, |
| "eval_wer": 0.17846607669616518, |
| "step": 946 |
| }, |
| { |
| "epoch": 86.36, |
| "learning_rate": 4.233644859813084e-05, |
| "loss": 0.2141, |
| "step": 950 |
| }, |
| { |
| "epoch": 86.98, |
| "eval_loss": 0.4498932659626007, |
| "eval_runtime": 2.4831, |
| "eval_samples_per_second": 6.846, |
| "eval_steps_per_second": 2.014, |
| "eval_wer": 0.17846607669616518, |
| "step": 957 |
| }, |
| { |
| "epoch": 87.27, |
| "learning_rate": 3.953271028037383e-05, |
| "loss": 0.1599, |
| "step": 960 |
| }, |
| { |
| "epoch": 87.98, |
| "eval_loss": 0.4594888687133789, |
| "eval_runtime": 2.4694, |
| "eval_samples_per_second": 6.884, |
| "eval_steps_per_second": 2.025, |
| "eval_wer": 0.17699115044247787, |
| "step": 968 |
| }, |
| { |
| "epoch": 88.18, |
| "learning_rate": 3.672897196261682e-05, |
| "loss": 0.1927, |
| "step": 970 |
| }, |
| { |
| "epoch": 88.98, |
| "eval_loss": 0.4772101640701294, |
| "eval_runtime": 2.4616, |
| "eval_samples_per_second": 6.906, |
| "eval_steps_per_second": 2.031, |
| "eval_wer": 0.17551622418879056, |
| "step": 979 |
| }, |
| { |
| "epoch": 89.09, |
| "learning_rate": 3.392523364485981e-05, |
| "loss": 0.1715, |
| "step": 980 |
| }, |
| { |
| "epoch": 89.98, |
| "learning_rate": 3.11214953271028e-05, |
| "loss": 0.1709, |
| "step": 990 |
| }, |
| { |
| "epoch": 89.98, |
| "eval_loss": 0.458842009305954, |
| "eval_runtime": 2.4896, |
| "eval_samples_per_second": 6.828, |
| "eval_steps_per_second": 2.008, |
| "eval_wer": 0.17699115044247787, |
| "step": 990 |
| }, |
| { |
| "epoch": 90.89, |
| "learning_rate": 2.831775700934579e-05, |
| "loss": 0.1588, |
| "step": 1000 |
| }, |
| { |
| "epoch": 90.98, |
| "eval_loss": 0.4606749713420868, |
| "eval_runtime": 2.4588, |
| "eval_samples_per_second": 6.914, |
| "eval_steps_per_second": 2.033, |
| "eval_wer": 0.17846607669616518, |
| "step": 1001 |
| }, |
| { |
| "epoch": 91.8, |
| "learning_rate": 2.5514018691588784e-05, |
| "loss": 0.1702, |
| "step": 1010 |
| }, |
| { |
| "epoch": 91.98, |
| "eval_loss": 0.46561577916145325, |
| "eval_runtime": 2.4745, |
| "eval_samples_per_second": 6.87, |
| "eval_steps_per_second": 2.021, |
| "eval_wer": 0.18289085545722714, |
| "step": 1012 |
| }, |
| { |
| "epoch": 92.71, |
| "learning_rate": 2.2710280373831774e-05, |
| "loss": 0.1646, |
| "step": 1020 |
| }, |
| { |
| "epoch": 92.98, |
| "eval_loss": 0.46306708455085754, |
| "eval_runtime": 2.4484, |
| "eval_samples_per_second": 6.943, |
| "eval_steps_per_second": 2.042, |
| "eval_wer": 0.18289085545722714, |
| "step": 1023 |
| }, |
| { |
| "epoch": 93.62, |
| "learning_rate": 1.9906542056074765e-05, |
| "loss": 0.1867, |
| "step": 1030 |
| }, |
| { |
| "epoch": 93.98, |
| "eval_loss": 0.4757649600505829, |
| "eval_runtime": 2.4618, |
| "eval_samples_per_second": 6.906, |
| "eval_steps_per_second": 2.031, |
| "eval_wer": 0.18141592920353983, |
| "step": 1034 |
| }, |
| { |
| "epoch": 94.53, |
| "learning_rate": 1.7102803738317756e-05, |
| "loss": 0.1799, |
| "step": 1040 |
| }, |
| { |
| "epoch": 94.98, |
| "eval_loss": 0.48200085759162903, |
| "eval_runtime": 2.4572, |
| "eval_samples_per_second": 6.919, |
| "eval_steps_per_second": 2.035, |
| "eval_wer": 0.17551622418879056, |
| "step": 1045 |
| }, |
| { |
| "epoch": 95.44, |
| "learning_rate": 1.4299065420560746e-05, |
| "loss": 0.1611, |
| "step": 1050 |
| }, |
| { |
| "epoch": 95.98, |
| "eval_loss": 0.48464781045913696, |
| "eval_runtime": 2.4952, |
| "eval_samples_per_second": 6.813, |
| "eval_steps_per_second": 2.004, |
| "eval_wer": 0.17846607669616518, |
| "step": 1056 |
| }, |
| { |
| "epoch": 96.36, |
| "learning_rate": 1.1495327102803737e-05, |
| "loss": 0.1685, |
| "step": 1060 |
| }, |
| { |
| "epoch": 96.98, |
| "eval_loss": 0.48164939880371094, |
| "eval_runtime": 2.5142, |
| "eval_samples_per_second": 6.762, |
| "eval_steps_per_second": 1.989, |
| "eval_wer": 0.17699115044247787, |
| "step": 1067 |
| }, |
| { |
| "epoch": 97.27, |
| "learning_rate": 8.691588785046728e-06, |
| "loss": 0.19, |
| "step": 1070 |
| }, |
| { |
| "epoch": 97.98, |
| "eval_loss": 0.4781480133533478, |
| "eval_runtime": 2.5523, |
| "eval_samples_per_second": 6.661, |
| "eval_steps_per_second": 1.959, |
| "eval_wer": 0.17699115044247787, |
| "step": 1078 |
| }, |
| { |
| "epoch": 98.18, |
| "learning_rate": 5.887850467289719e-06, |
| "loss": 0.1953, |
| "step": 1080 |
| }, |
| { |
| "epoch": 98.98, |
| "eval_loss": 0.47668424248695374, |
| "eval_runtime": 2.4703, |
| "eval_samples_per_second": 6.882, |
| "eval_steps_per_second": 2.024, |
| "eval_wer": 0.17699115044247787, |
| "step": 1089 |
| }, |
| { |
| "epoch": 99.09, |
| "learning_rate": 3.08411214953271e-06, |
| "loss": 0.1635, |
| "step": 1090 |
| }, |
| { |
| "epoch": 99.98, |
| "learning_rate": 2.803738317757009e-07, |
| "loss": 0.188, |
| "step": 1100 |
| }, |
| { |
| "epoch": 99.98, |
| "eval_loss": 0.47740593552589417, |
| "eval_runtime": 2.4786, |
| "eval_samples_per_second": 6.859, |
| "eval_steps_per_second": 2.017, |
| "eval_wer": 0.17699115044247787, |
| "step": 1100 |
| }, |
| { |
| "epoch": 99.98, |
| "step": 1100, |
| "total_flos": 1.8082449930602819e+18, |
| "train_loss": 0.2150352662259882, |
| "train_runtime": 4203.5944, |
| "train_samples_per_second": 4.258, |
| "train_steps_per_second": 0.262 |
| } |
| ], |
| "max_steps": 1100, |
| "num_train_epochs": 100, |
| "total_flos": 1.8082449930602819e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
