| { | |
| "best_metric": 0.8117647058823529, | |
| "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-dmae-humeda-DAV23/checkpoint-170", | |
| "epoch": 37.666666666666664, | |
| "eval_steps": 500, | |
| "global_step": 640, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 10.422093391418457, | |
| "learning_rate": 9.375000000000001e-06, | |
| "loss": 6.4493, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.29411764705882354, | |
| "eval_loss": 1.5280741453170776, | |
| "eval_runtime": 1.7296, | |
| "eval_samples_per_second": 49.145, | |
| "eval_steps_per_second": 1.735, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.4242424242424243, | |
| "grad_norm": 14.379430770874023, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 5.7922, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.38823529411764707, | |
| "eval_loss": 1.317600965499878, | |
| "eval_runtime": 1.301, | |
| "eval_samples_per_second": 65.332, | |
| "eval_steps_per_second": 2.306, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.121212121212121, | |
| "grad_norm": 28.70977783203125, | |
| "learning_rate": 2.8125000000000003e-05, | |
| "loss": 5.0076, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.8484848484848486, | |
| "grad_norm": 24.181316375732422, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 4.2502, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.43529411764705883, | |
| "eval_loss": 1.2014732360839844, | |
| "eval_runtime": 1.3256, | |
| "eval_samples_per_second": 64.12, | |
| "eval_steps_per_second": 2.263, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.5454545454545454, | |
| "grad_norm": 29.8701171875, | |
| "learning_rate": 4.6875e-05, | |
| "loss": 3.2402, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7176470588235294, | |
| "eval_loss": 0.8901777267456055, | |
| "eval_runtime": 1.6039, | |
| "eval_samples_per_second": 52.995, | |
| "eval_steps_per_second": 1.87, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.242424242424242, | |
| "grad_norm": 43.26256561279297, | |
| "learning_rate": 4.930555555555556e-05, | |
| "loss": 2.8895, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.96969696969697, | |
| "grad_norm": 38.71839904785156, | |
| "learning_rate": 4.8263888888888895e-05, | |
| "loss": 2.5386, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7764705882352941, | |
| "eval_loss": 0.6509169340133667, | |
| "eval_runtime": 1.3254, | |
| "eval_samples_per_second": 64.131, | |
| "eval_steps_per_second": 2.263, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 5.666666666666667, | |
| "grad_norm": 35.30036544799805, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 2.0351, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7647058823529411, | |
| "eval_loss": 0.6758585572242737, | |
| "eval_runtime": 1.3401, | |
| "eval_samples_per_second": 63.43, | |
| "eval_steps_per_second": 2.239, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.363636363636363, | |
| "grad_norm": 36.81019973754883, | |
| "learning_rate": 4.618055555555556e-05, | |
| "loss": 1.8225, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7764705882352941, | |
| "eval_loss": 0.6606881022453308, | |
| "eval_runtime": 1.7388, | |
| "eval_samples_per_second": 48.883, | |
| "eval_steps_per_second": 1.725, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 7.0606060606060606, | |
| "grad_norm": 38.81963348388672, | |
| "learning_rate": 4.5138888888888894e-05, | |
| "loss": 1.5799, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.787878787878788, | |
| "grad_norm": 34.68444061279297, | |
| "learning_rate": 4.4097222222222226e-05, | |
| "loss": 1.4778, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7529411764705882, | |
| "eval_loss": 0.7161939740180969, | |
| "eval_runtime": 1.3317, | |
| "eval_samples_per_second": 63.829, | |
| "eval_steps_per_second": 2.253, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.484848484848484, | |
| "grad_norm": 33.96342849731445, | |
| "learning_rate": 4.305555555555556e-05, | |
| "loss": 1.4076, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7294117647058823, | |
| "eval_loss": 0.9084261059761047, | |
| "eval_runtime": 1.3286, | |
| "eval_samples_per_second": 63.976, | |
| "eval_steps_per_second": 2.258, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 9.181818181818182, | |
| "grad_norm": 51.935420989990234, | |
| "learning_rate": 4.201388888888889e-05, | |
| "loss": 1.3522, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 9.909090909090908, | |
| "grad_norm": 35.646156311035156, | |
| "learning_rate": 4.0972222222222225e-05, | |
| "loss": 1.2056, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8117647058823529, | |
| "eval_loss": 0.6900736689567566, | |
| "eval_runtime": 1.3237, | |
| "eval_samples_per_second": 64.212, | |
| "eval_steps_per_second": 2.266, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.606060606060606, | |
| "grad_norm": 39.277122497558594, | |
| "learning_rate": 3.993055555555556e-05, | |
| "loss": 0.9552, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7764705882352941, | |
| "eval_loss": 0.9153303503990173, | |
| "eval_runtime": 1.3258, | |
| "eval_samples_per_second": 64.11, | |
| "eval_steps_per_second": 2.263, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 11.303030303030303, | |
| "grad_norm": 32.70234298706055, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 1.0259, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 27.082563400268555, | |
| "learning_rate": 3.7847222222222224e-05, | |
| "loss": 0.9859, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7529411764705882, | |
| "eval_loss": 0.8693907856941223, | |
| "eval_runtime": 1.3304, | |
| "eval_samples_per_second": 63.892, | |
| "eval_steps_per_second": 2.255, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.727272727272727, | |
| "grad_norm": 25.17854881286621, | |
| "learning_rate": 3.6805555555555556e-05, | |
| "loss": 0.8309, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.7666147351264954, | |
| "eval_runtime": 1.5029, | |
| "eval_samples_per_second": 56.559, | |
| "eval_steps_per_second": 1.996, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 13.424242424242424, | |
| "grad_norm": 42.24884033203125, | |
| "learning_rate": 3.576388888888889e-05, | |
| "loss": 0.7722, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7529411764705882, | |
| "eval_loss": 0.9117515087127686, | |
| "eval_runtime": 1.4392, | |
| "eval_samples_per_second": 59.061, | |
| "eval_steps_per_second": 2.085, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 14.121212121212121, | |
| "grad_norm": 25.000560760498047, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.7479, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 14.848484848484848, | |
| "grad_norm": 23.831018447875977, | |
| "learning_rate": 3.368055555555556e-05, | |
| "loss": 0.7632, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7529411764705882, | |
| "eval_loss": 0.89529949426651, | |
| "eval_runtime": 1.3464, | |
| "eval_samples_per_second": 63.129, | |
| "eval_steps_per_second": 2.228, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 15.545454545454545, | |
| "grad_norm": 37.80634689331055, | |
| "learning_rate": 3.263888888888889e-05, | |
| "loss": 0.5868, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7529411764705882, | |
| "eval_loss": 0.9678363800048828, | |
| "eval_runtime": 1.3437, | |
| "eval_samples_per_second": 63.259, | |
| "eval_steps_per_second": 2.233, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 16.242424242424242, | |
| "grad_norm": 31.965198516845703, | |
| "learning_rate": 3.159722222222222e-05, | |
| "loss": 0.8369, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 16.96969696969697, | |
| "grad_norm": 43.057701110839844, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.6577, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.7764705882352941, | |
| "eval_loss": 1.0502737760543823, | |
| "eval_runtime": 1.7574, | |
| "eval_samples_per_second": 48.368, | |
| "eval_steps_per_second": 1.707, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 17.666666666666668, | |
| "grad_norm": 22.851730346679688, | |
| "learning_rate": 2.951388888888889e-05, | |
| "loss": 0.5816, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7294117647058823, | |
| "eval_loss": 1.0601861476898193, | |
| "eval_runtime": 1.4181, | |
| "eval_samples_per_second": 59.94, | |
| "eval_steps_per_second": 2.116, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 18.363636363636363, | |
| "grad_norm": 24.805330276489258, | |
| "learning_rate": 2.8472222222222223e-05, | |
| "loss": 0.6222, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7764705882352941, | |
| "eval_loss": 1.1542593240737915, | |
| "eval_runtime": 1.3489, | |
| "eval_samples_per_second": 63.014, | |
| "eval_steps_per_second": 2.224, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 19.060606060606062, | |
| "grad_norm": 24.57158851623535, | |
| "learning_rate": 2.743055555555556e-05, | |
| "loss": 0.6667, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 19.78787878787879, | |
| "grad_norm": 52.441471099853516, | |
| "learning_rate": 2.6388888888888892e-05, | |
| "loss": 0.4861, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8117647058823529, | |
| "eval_loss": 0.9739417433738708, | |
| "eval_runtime": 1.3332, | |
| "eval_samples_per_second": 63.755, | |
| "eval_steps_per_second": 2.25, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 20.484848484848484, | |
| "grad_norm": 20.256858825683594, | |
| "learning_rate": 2.534722222222222e-05, | |
| "loss": 0.4422, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 1.035377860069275, | |
| "eval_runtime": 1.7575, | |
| "eval_samples_per_second": 48.365, | |
| "eval_steps_per_second": 1.707, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 21.181818181818183, | |
| "grad_norm": 30.408321380615234, | |
| "learning_rate": 2.4305555555555558e-05, | |
| "loss": 0.5374, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 21.90909090909091, | |
| "grad_norm": 16.08924102783203, | |
| "learning_rate": 2.326388888888889e-05, | |
| "loss": 0.506, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.8117647058823529, | |
| "eval_loss": 1.109660029411316, | |
| "eval_runtime": 1.3601, | |
| "eval_samples_per_second": 62.497, | |
| "eval_steps_per_second": 2.206, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 22.606060606060606, | |
| "grad_norm": 19.899555206298828, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.3833, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7764705882352941, | |
| "eval_loss": 1.2008516788482666, | |
| "eval_runtime": 1.3596, | |
| "eval_samples_per_second": 62.517, | |
| "eval_steps_per_second": 2.206, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 23.303030303030305, | |
| "grad_norm": 23.089004516601562, | |
| "learning_rate": 2.1180555555555556e-05, | |
| "loss": 0.5273, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "grad_norm": 12.893085479736328, | |
| "learning_rate": 2.013888888888889e-05, | |
| "loss": 0.4574, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7764705882352941, | |
| "eval_loss": 1.1365725994110107, | |
| "eval_runtime": 1.3252, | |
| "eval_samples_per_second": 64.141, | |
| "eval_steps_per_second": 2.264, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 24.727272727272727, | |
| "grad_norm": 29.011215209960938, | |
| "learning_rate": 1.9097222222222222e-05, | |
| "loss": 0.4467, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.8117647058823529, | |
| "eval_loss": 1.0601016283035278, | |
| "eval_runtime": 1.4691, | |
| "eval_samples_per_second": 57.86, | |
| "eval_steps_per_second": 2.042, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 25.424242424242426, | |
| "grad_norm": 37.92557907104492, | |
| "learning_rate": 1.8055555555555555e-05, | |
| "loss": 0.4451, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7764705882352941, | |
| "eval_loss": 1.0934613943099976, | |
| "eval_runtime": 1.3569, | |
| "eval_samples_per_second": 62.643, | |
| "eval_steps_per_second": 2.211, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 26.12121212121212, | |
| "grad_norm": 29.263154983520508, | |
| "learning_rate": 1.701388888888889e-05, | |
| "loss": 0.483, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 26.848484848484848, | |
| "grad_norm": 20.336957931518555, | |
| "learning_rate": 1.597222222222222e-05, | |
| "loss": 0.4384, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7647058823529411, | |
| "eval_loss": 1.1616755723953247, | |
| "eval_runtime": 1.3388, | |
| "eval_samples_per_second": 63.492, | |
| "eval_steps_per_second": 2.241, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 27.545454545454547, | |
| "grad_norm": 26.435325622558594, | |
| "learning_rate": 1.4930555555555557e-05, | |
| "loss": 0.4321, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7764705882352941, | |
| "eval_loss": 1.1012462377548218, | |
| "eval_runtime": 1.7645, | |
| "eval_samples_per_second": 48.171, | |
| "eval_steps_per_second": 1.7, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 28.242424242424242, | |
| "grad_norm": 35.24657440185547, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.4068, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 28.96969696969697, | |
| "grad_norm": 29.191991806030273, | |
| "learning_rate": 1.2847222222222222e-05, | |
| "loss": 0.4398, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.788235294117647, | |
| "eval_loss": 1.082492709159851, | |
| "eval_runtime": 1.3299, | |
| "eval_samples_per_second": 63.914, | |
| "eval_steps_per_second": 2.256, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 29.666666666666668, | |
| "grad_norm": 26.035062789916992, | |
| "learning_rate": 1.1805555555555555e-05, | |
| "loss": 0.361, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7647058823529411, | |
| "eval_loss": 1.112740397453308, | |
| "eval_runtime": 1.3356, | |
| "eval_samples_per_second": 63.641, | |
| "eval_steps_per_second": 2.246, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 30.363636363636363, | |
| "grad_norm": 24.128007888793945, | |
| "learning_rate": 1.076388888888889e-05, | |
| "loss": 0.4428, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7529411764705882, | |
| "eval_loss": 1.2024400234222412, | |
| "eval_runtime": 1.8084, | |
| "eval_samples_per_second": 47.003, | |
| "eval_steps_per_second": 1.659, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 31.060606060606062, | |
| "grad_norm": 29.159976959228516, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 0.4293, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 31.78787878787879, | |
| "grad_norm": 19.373197555541992, | |
| "learning_rate": 8.680555555555556e-06, | |
| "loss": 0.451, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7647058823529411, | |
| "eval_loss": 1.1550030708312988, | |
| "eval_runtime": 1.3443, | |
| "eval_samples_per_second": 63.23, | |
| "eval_steps_per_second": 2.232, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 32.484848484848484, | |
| "grad_norm": 12.227431297302246, | |
| "learning_rate": 7.63888888888889e-06, | |
| "loss": 0.403, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7764705882352941, | |
| "eval_loss": 1.1645594835281372, | |
| "eval_runtime": 1.3526, | |
| "eval_samples_per_second": 62.842, | |
| "eval_steps_per_second": 2.218, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 33.18181818181818, | |
| "grad_norm": 20.577377319335938, | |
| "learning_rate": 6.597222222222223e-06, | |
| "loss": 0.4113, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 33.90909090909091, | |
| "grad_norm": 24.493812561035156, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.3059, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7764705882352941, | |
| "eval_loss": 1.2441880702972412, | |
| "eval_runtime": 1.3246, | |
| "eval_samples_per_second": 64.172, | |
| "eval_steps_per_second": 2.265, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 34.60606060606061, | |
| "grad_norm": 28.553544998168945, | |
| "learning_rate": 4.513888888888889e-06, | |
| "loss": 0.3022, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7764705882352941, | |
| "eval_loss": 1.1975644826889038, | |
| "eval_runtime": 1.5644, | |
| "eval_samples_per_second": 54.334, | |
| "eval_steps_per_second": 1.918, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 35.303030303030305, | |
| "grad_norm": 17.071916580200195, | |
| "learning_rate": 3.4722222222222224e-06, | |
| "loss": 0.3343, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "grad_norm": 10.918073654174805, | |
| "learning_rate": 2.4305555555555557e-06, | |
| "loss": 0.319, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7764705882352941, | |
| "eval_loss": 1.1564186811447144, | |
| "eval_runtime": 1.4741, | |
| "eval_samples_per_second": 57.663, | |
| "eval_steps_per_second": 2.035, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 36.72727272727273, | |
| "grad_norm": 8.741593360900879, | |
| "learning_rate": 1.388888888888889e-06, | |
| "loss": 0.3737, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7764705882352941, | |
| "eval_loss": 1.1857171058654785, | |
| "eval_runtime": 1.3517, | |
| "eval_samples_per_second": 62.883, | |
| "eval_steps_per_second": 2.219, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 37.42424242424242, | |
| "grad_norm": 20.94017219543457, | |
| "learning_rate": 3.4722222222222224e-07, | |
| "loss": 0.3063, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 37.666666666666664, | |
| "eval_accuracy": 0.7764705882352941, | |
| "eval_loss": 1.193001627922058, | |
| "eval_runtime": 1.6167, | |
| "eval_samples_per_second": 52.578, | |
| "eval_steps_per_second": 1.856, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 37.666666666666664, | |
| "step": 640, | |
| "total_flos": 2.572737077098709e+18, | |
| "train_loss": 1.1635722614824773, | |
| "train_runtime": 1917.6947, | |
| "train_samples_per_second": 43.782, | |
| "train_steps_per_second": 0.334 | |
| } | |
| ], | |
| "logging_steps": 12, | |
| "max_steps": 640, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 40, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.572737077098709e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |