| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.3350592567023358, | |
| "global_step": 2900, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.0305343511450381e-05, | |
| "loss": 13.0539, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.118320610687023e-05, | |
| "loss": 20.9649, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.206106870229007e-05, | |
| "loss": 21.1001, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.3511450381679383e-05, | |
| "loss": 5.5852, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5.438931297709923e-05, | |
| "loss": 5.2002, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 3.5950469970703125, | |
| "eval_runtime": 194.8685, | |
| "eval_samples_per_second": 24.853, | |
| "eval_steps_per_second": 0.78, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 6.583969465648854e-05, | |
| "loss": 3.281, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 7.495301487862176e-05, | |
| "loss": 3.3442, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 7.472983555207517e-05, | |
| "loss": 3.5229, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.449490994518402e-05, | |
| "loss": 3.089, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 7.427173061863743e-05, | |
| "loss": 3.482, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 3.274627923965454, | |
| "eval_runtime": 194.5649, | |
| "eval_samples_per_second": 24.891, | |
| "eval_steps_per_second": 0.781, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 7.403680501174628e-05, | |
| "loss": 3.1517, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 7.380187940485512e-05, | |
| "loss": 3.1617, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 7.357870007830852e-05, | |
| "loss": 3.2971, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 7.334377447141738e-05, | |
| "loss": 3.022, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 7.312059514487078e-05, | |
| "loss": 3.3322, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 3.0716073513031006, | |
| "eval_runtime": 196.1674, | |
| "eval_samples_per_second": 24.688, | |
| "eval_steps_per_second": 0.775, | |
| "eval_wer": 1.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 7.288566953797964e-05, | |
| "loss": 2.9964, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 7.265074393108849e-05, | |
| "loss": 3.0777, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 7.242756460454189e-05, | |
| "loss": 3.2703, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 7.219263899765073e-05, | |
| "loss": 3.1161, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 7.195771339075958e-05, | |
| "loss": 3.2435, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 3.063333034515381, | |
| "eval_runtime": 190.5938, | |
| "eval_samples_per_second": 25.41, | |
| "eval_steps_per_second": 0.798, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 7.172278778386843e-05, | |
| "loss": 2.9993, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 7.148786217697727e-05, | |
| "loss": 3.0555, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.126468285043069e-05, | |
| "loss": 3.1879, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.102975724353953e-05, | |
| "loss": 2.9861, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.080657791699295e-05, | |
| "loss": 3.0833, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 2.9769718647003174, | |
| "eval_runtime": 195.2639, | |
| "eval_samples_per_second": 24.802, | |
| "eval_steps_per_second": 0.778, | |
| "eval_wer": 1.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.05716523101018e-05, | |
| "loss": 3.1608, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.033672670321064e-05, | |
| "loss": 3.0206, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.01018010963195e-05, | |
| "loss": 3.0523, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 6.986687548942835e-05, | |
| "loss": 3.0222, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 6.964369616288175e-05, | |
| "loss": 3.0913, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 3.052091598510742, | |
| "eval_runtime": 189.8149, | |
| "eval_samples_per_second": 25.514, | |
| "eval_steps_per_second": 0.801, | |
| "eval_wer": 1.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 6.94087705559906e-05, | |
| "loss": 3.1987, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 6.917384494909944e-05, | |
| "loss": 3.1504, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 6.893891934220829e-05, | |
| "loss": 3.2406, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.870399373531715e-05, | |
| "loss": 3.0632, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.848081440877055e-05, | |
| "loss": 3.1487, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 3.1951305866241455, | |
| "eval_runtime": 196.8636, | |
| "eval_samples_per_second": 24.601, | |
| "eval_steps_per_second": 0.772, | |
| "eval_wer": 1.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.824588880187941e-05, | |
| "loss": 3.298, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.801096319498825e-05, | |
| "loss": 3.1669, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.778778386844165e-05, | |
| "loss": 3.2651, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.75528582615505e-05, | |
| "loss": 3.1562, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.732967893500391e-05, | |
| "loss": 3.3254, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 3.0070509910583496, | |
| "eval_runtime": 192.0978, | |
| "eval_samples_per_second": 25.211, | |
| "eval_steps_per_second": 0.791, | |
| "eval_wer": 1.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.709475332811276e-05, | |
| "loss": 3.0487, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.68598277212216e-05, | |
| "loss": 3.1936, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.663664839467502e-05, | |
| "loss": 3.323, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.640172278778387e-05, | |
| "loss": 2.998, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.617854346123726e-05, | |
| "loss": 3.4698, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 2.995044469833374, | |
| "eval_runtime": 195.1464, | |
| "eval_samples_per_second": 24.817, | |
| "eval_steps_per_second": 0.779, | |
| "eval_wer": 1.0, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.594361785434611e-05, | |
| "loss": 3.0048, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 6.570869224745496e-05, | |
| "loss": 3.1447, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.548551292090837e-05, | |
| "loss": 3.3347, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.525058731401722e-05, | |
| "loss": 2.9795, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.503915426781518e-05, | |
| "loss": 3.5905, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 2.9961767196655273, | |
| "eval_runtime": 188.3505, | |
| "eval_samples_per_second": 25.713, | |
| "eval_steps_per_second": 0.807, | |
| "eval_wer": 1.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.480422866092403e-05, | |
| "loss": 2.9884, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.456930305403288e-05, | |
| "loss": 3.175, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.434612372748629e-05, | |
| "loss": 3.3163, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 6.411119812059513e-05, | |
| "loss": 3.0063, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 6.387627251370398e-05, | |
| "loss": 3.4965, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 3.0483579635620117, | |
| "eval_runtime": 193.4167, | |
| "eval_samples_per_second": 25.039, | |
| "eval_steps_per_second": 0.786, | |
| "eval_wer": 1.0, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 6.364134690681284e-05, | |
| "loss": 2.9967, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 6.340642129992169e-05, | |
| "loss": 3.2329, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 6.31832419733751e-05, | |
| "loss": 3.3814, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 6.294831636648395e-05, | |
| "loss": 3.0108, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 6.272513703993735e-05, | |
| "loss": 3.6227, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 3.0750181674957275, | |
| "eval_runtime": 193.4538, | |
| "eval_samples_per_second": 25.034, | |
| "eval_steps_per_second": 0.786, | |
| "eval_wer": 1.0, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 6.24902114330462e-05, | |
| "loss": 2.9917, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 6.225528582615504e-05, | |
| "loss": 3.1386, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 6.203210649960845e-05, | |
| "loss": 3.3022, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 6.17971808927173e-05, | |
| "loss": 3.0139, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 6.157400156617071e-05, | |
| "loss": 3.2921, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 3.019115924835205, | |
| "eval_runtime": 194.2188, | |
| "eval_samples_per_second": 24.936, | |
| "eval_steps_per_second": 0.783, | |
| "eval_wer": 1.0, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 6.133907595927956e-05, | |
| "loss": 3.0432, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 6.11041503523884e-05, | |
| "loss": 3.0951, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 6.088097102584181e-05, | |
| "loss": 3.189, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 6.064604541895066e-05, | |
| "loss": 3.1296, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 6.0422866092404065e-05, | |
| "loss": 3.2907, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 3.06713604927063, | |
| "eval_runtime": 192.5311, | |
| "eval_samples_per_second": 25.154, | |
| "eval_steps_per_second": 0.789, | |
| "eval_wer": 1.0, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 6.018794048551292e-05, | |
| "loss": 3.1849, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 5.9953014878621765e-05, | |
| "loss": 3.1682, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.9729835552075165e-05, | |
| "loss": 3.2002, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 5.949490994518402e-05, | |
| "loss": 3.2207, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 5.9271730618637424e-05, | |
| "loss": 3.1716, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 3.093482732772827, | |
| "eval_runtime": 193.22, | |
| "eval_samples_per_second": 25.065, | |
| "eval_steps_per_second": 0.787, | |
| "eval_wer": 1.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 5.903680501174628e-05, | |
| "loss": 3.2105, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.8801879404855124e-05, | |
| "loss": 3.173, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.857870007830853e-05, | |
| "loss": 3.2066, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.8343774471417384e-05, | |
| "loss": 3.2196, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.812059514487078e-05, | |
| "loss": 3.1788, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 3.092198133468628, | |
| "eval_runtime": 194.0448, | |
| "eval_samples_per_second": 24.958, | |
| "eval_steps_per_second": 0.783, | |
| "eval_wer": 1.0, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.788566953797963e-05, | |
| "loss": 3.2075, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.765074393108848e-05, | |
| "loss": 3.1772, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 5.742756460454189e-05, | |
| "loss": 3.2101, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 5.7192638997650736e-05, | |
| "loss": 3.2115, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 5.69812059514487e-05, | |
| "loss": 3.2986, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 3.092197895050049, | |
| "eval_runtime": 194.3305, | |
| "eval_samples_per_second": 24.921, | |
| "eval_steps_per_second": 0.782, | |
| "eval_wer": 1.0, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 5.674628034455755e-05, | |
| "loss": 3.2063, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 5.65113547376664e-05, | |
| "loss": 3.1723, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 5.627642913077525e-05, | |
| "loss": 3.0945, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 5.6041503523884095e-05, | |
| "loss": 3.2153, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5.580657791699295e-05, | |
| "loss": 3.0761, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 3.092197895050049, | |
| "eval_runtime": 192.7837, | |
| "eval_samples_per_second": 25.121, | |
| "eval_steps_per_second": 0.788, | |
| "eval_wer": 1.0, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 5.5571652310101795e-05, | |
| "loss": 3.2061, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 5.533672670321064e-05, | |
| "loss": 3.1768, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 5.5101801096319495e-05, | |
| "loss": 3.096, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.486687548942834e-05, | |
| "loss": 3.213, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.464369616288175e-05, | |
| "loss": 3.1832, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 3.092197895050049, | |
| "eval_runtime": 196.1769, | |
| "eval_samples_per_second": 24.687, | |
| "eval_steps_per_second": 0.775, | |
| "eval_wer": 1.0, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5.44087705559906e-05, | |
| "loss": 3.2046, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.417384494909945e-05, | |
| "loss": 3.1743, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.395066562255285e-05, | |
| "loss": 3.2055, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 5.37157400156617e-05, | |
| "loss": 3.2152, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 5.349256068911511e-05, | |
| "loss": 3.1845, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 3.092197895050049, | |
| "eval_runtime": 195.9315, | |
| "eval_samples_per_second": 24.718, | |
| "eval_steps_per_second": 0.776, | |
| "eval_wer": 1.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 5.3257635082223954e-05, | |
| "loss": 3.2093, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 5.302270947533281e-05, | |
| "loss": 3.1748, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 5.279953014878621e-05, | |
| "loss": 3.199, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.2564604541895067e-05, | |
| "loss": 3.2169, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 5.2341425215348466e-05, | |
| "loss": 3.1817, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 3.092197895050049, | |
| "eval_runtime": 193.8566, | |
| "eval_samples_per_second": 24.982, | |
| "eval_steps_per_second": 0.784, | |
| "eval_wer": 1.0, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 5.210649960845731e-05, | |
| "loss": 3.2075, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 5.1871574001566166e-05, | |
| "loss": 3.1693, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 5.164839467501957e-05, | |
| "loss": 3.2049, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.1425215348472984e-05, | |
| "loss": 3.3657, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.119028974158183e-05, | |
| "loss": 3.2209, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 3.092197895050049, | |
| "eval_runtime": 194.751, | |
| "eval_samples_per_second": 24.868, | |
| "eval_steps_per_second": 0.78, | |
| "eval_wer": 1.0, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.095536413469068e-05, | |
| "loss": 3.0961, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.073218480814408e-05, | |
| "loss": 3.2735, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.049725920125293e-05, | |
| "loss": 3.1904, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.0274079874706336e-05, | |
| "loss": 3.1892, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.003915426781519e-05, | |
| "loss": 3.2138, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 3.092197895050049, | |
| "eval_runtime": 195.285, | |
| "eval_samples_per_second": 24.8, | |
| "eval_steps_per_second": 0.778, | |
| "eval_wer": 1.0, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.980422866092404e-05, | |
| "loss": 3.0819, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 4.958104933437744e-05, | |
| "loss": 3.272, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 4.9346123727486296e-05, | |
| "loss": 3.2011, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.9122944400939695e-05, | |
| "loss": 3.1918, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.888801879404854e-05, | |
| "loss": 3.2154, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 3.092197895050049, | |
| "eval_runtime": 196.4218, | |
| "eval_samples_per_second": 24.656, | |
| "eval_steps_per_second": 0.774, | |
| "eval_wer": 1.0, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.8653093187157396e-05, | |
| "loss": 3.0946, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.84299138606108e-05, | |
| "loss": 3.2753, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.8194988253719655e-05, | |
| "loss": 3.1829, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.797180892717306e-05, | |
| "loss": 3.1839, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.773688332028191e-05, | |
| "loss": 3.2185, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 3.092197895050049, | |
| "eval_runtime": 192.8929, | |
| "eval_samples_per_second": 25.107, | |
| "eval_steps_per_second": 0.788, | |
| "eval_wer": 1.0, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.750195771339076e-05, | |
| "loss": 3.0971, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.727877838684416e-05, | |
| "loss": 3.2719, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.704385277995301e-05, | |
| "loss": 3.1974, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.680892717306186e-05, | |
| "loss": 3.0775, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.657400156617071e-05, | |
| "loss": 3.2201, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 3.092197895050049, | |
| "eval_runtime": 192.9488, | |
| "eval_samples_per_second": 25.1, | |
| "eval_steps_per_second": 0.788, | |
| "eval_wer": 1.0, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 4.6339075959279554e-05, | |
| "loss": 3.0946, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 4.611589663273297e-05, | |
| "loss": 3.2708, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 4.5880971025841814e-05, | |
| "loss": 3.1949, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 4.564604541895066e-05, | |
| "loss": 3.0763, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 4.5411119812059514e-05, | |
| "loss": 3.2184, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 3.092197895050049, | |
| "eval_runtime": 189.7646, | |
| "eval_samples_per_second": 25.521, | |
| "eval_steps_per_second": 0.801, | |
| "eval_wer": 1.0, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.517619420516836e-05, | |
| "loss": 3.0962, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 4.495301487862176e-05, | |
| "loss": 3.2795, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 4.4718089271730614e-05, | |
| "loss": 3.1901, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.449490994518402e-05, | |
| "loss": 3.1902, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 4.425998433829287e-05, | |
| "loss": 3.2196, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 3.092197895050049, | |
| "eval_runtime": 192.1661, | |
| "eval_samples_per_second": 25.202, | |
| "eval_steps_per_second": 0.791, | |
| "eval_wer": 1.0, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 4.402505873140172e-05, | |
| "loss": 3.0923, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 4.3801879404855126e-05, | |
| "loss": 3.2783, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 4.356695379796398e-05, | |
| "loss": 3.195, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 4.335552075176194e-05, | |
| "loss": 3.3041, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 4.3120595144870784e-05, | |
| "loss": 3.2158, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 3.092197895050049, | |
| "eval_runtime": 194.7934, | |
| "eval_samples_per_second": 24.862, | |
| "eval_steps_per_second": 0.78, | |
| "eval_wer": 1.0, | |
| "step": 2900 | |
| } | |
| ], | |
| "max_steps": 6516, | |
| "num_train_epochs": 3, | |
| "total_flos": 5.539671173723811e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |