|
{ |
|
"best_metric": 1.0, |
|
"best_model_checkpoint": "swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-Lesion-Classification-HAM10000-S/checkpoint-1710", |
|
"epoch": 14.967177242888402, |
|
"global_step": 1710, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 2.9239766081871344e-07, |
|
"loss": 2.0763, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 5.847953216374269e-07, |
|
"loss": 2.0144, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 8.771929824561404e-07, |
|
"loss": 2.0062, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 1.1695906432748538e-06, |
|
"loss": 1.9886, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 1.4619883040935671e-06, |
|
"loss": 1.9744, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 1.7543859649122807e-06, |
|
"loss": 1.9513, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 2.0467836257309943e-06, |
|
"loss": 1.9403, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 2.3391812865497075e-06, |
|
"loss": 1.9093, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 2.631578947368421e-06, |
|
"loss": 1.9076, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 2.9239766081871343e-06, |
|
"loss": 1.8717, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 3.216374269005848e-06, |
|
"loss": 1.8642, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 3.5087719298245615e-06, |
|
"loss": 1.821, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 3.8011695906432747e-06, |
|
"loss": 1.7219, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 4.093567251461989e-06, |
|
"loss": 1.787, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 4.3859649122807014e-06, |
|
"loss": 1.7157, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 4.678362573099415e-06, |
|
"loss": 1.6594, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 4.970760233918129e-06, |
|
"loss": 1.6312, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 5.263157894736842e-06, |
|
"loss": 1.5143, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 5.555555555555556e-06, |
|
"loss": 1.5347, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 5.8479532163742686e-06, |
|
"loss": 1.4393, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 6.140350877192982e-06, |
|
"loss": 1.3955, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 6.432748538011696e-06, |
|
"loss": 1.3289, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.6247947454844006, |
|
"eval_loss": 1.0632905960083008, |
|
"eval_runtime": 838.3049, |
|
"eval_samples_per_second": 1.453, |
|
"eval_steps_per_second": 0.183, |
|
"step": 114 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 6.725146198830409e-06, |
|
"loss": 1.2315, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 7.017543859649123e-06, |
|
"loss": 1.1319, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 7.3099415204678366e-06, |
|
"loss": 1.2158, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 7.602339181286549e-06, |
|
"loss": 1.1509, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 7.894736842105263e-06, |
|
"loss": 1.0971, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 8.187134502923977e-06, |
|
"loss": 1.1285, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 8.47953216374269e-06, |
|
"loss": 0.9948, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 8.771929824561403e-06, |
|
"loss": 0.9737, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 9.064327485380117e-06, |
|
"loss": 1.0149, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 9.35672514619883e-06, |
|
"loss": 0.9684, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 9.649122807017545e-06, |
|
"loss": 0.9588, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 9.941520467836257e-06, |
|
"loss": 0.7973, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 1.023391812865497e-05, |
|
"loss": 0.8688, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 1.0526315789473684e-05, |
|
"loss": 0.9191, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 1.0818713450292397e-05, |
|
"loss": 0.864, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 1.1111111111111112e-05, |
|
"loss": 0.8442, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 1.1403508771929824e-05, |
|
"loss": 0.954, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"learning_rate": 1.1695906432748537e-05, |
|
"loss": 0.7894, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 1.1988304093567252e-05, |
|
"loss": 0.7701, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 1.2280701754385964e-05, |
|
"loss": 0.7477, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 1.2573099415204679e-05, |
|
"loss": 0.7278, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 1.93, |
|
"learning_rate": 1.2865497076023392e-05, |
|
"loss": 0.7302, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.97, |
|
"learning_rate": 1.3157894736842106e-05, |
|
"loss": 0.7956, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.8103448275862069, |
|
"eval_loss": 0.504953145980835, |
|
"eval_runtime": 54.2638, |
|
"eval_samples_per_second": 22.446, |
|
"eval_steps_per_second": 2.82, |
|
"step": 228 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 1.3450292397660819e-05, |
|
"loss": 0.6622, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 2.06, |
|
"learning_rate": 1.3742690058479531e-05, |
|
"loss": 0.6419, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"learning_rate": 1.4035087719298246e-05, |
|
"loss": 0.5583, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 1.4327485380116959e-05, |
|
"loss": 0.6594, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 1.4619883040935673e-05, |
|
"loss": 0.6647, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 2.23, |
|
"learning_rate": 1.4912280701754386e-05, |
|
"loss": 0.5958, |
|
"step": 255 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"learning_rate": 1.5204678362573099e-05, |
|
"loss": 0.6235, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"learning_rate": 1.5497076023391813e-05, |
|
"loss": 0.5793, |
|
"step": 265 |
|
}, |
|
{ |
|
"epoch": 2.36, |
|
"learning_rate": 1.5789473684210526e-05, |
|
"loss": 0.5209, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 2.41, |
|
"learning_rate": 1.608187134502924e-05, |
|
"loss": 0.6693, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 2.45, |
|
"learning_rate": 1.6374269005847955e-05, |
|
"loss": 0.6411, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 2.49, |
|
"learning_rate": 1.6666666666666667e-05, |
|
"loss": 0.5181, |
|
"step": 285 |
|
}, |
|
{ |
|
"epoch": 2.54, |
|
"learning_rate": 1.695906432748538e-05, |
|
"loss": 0.6182, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 2.58, |
|
"learning_rate": 1.7251461988304093e-05, |
|
"loss": 0.5462, |
|
"step": 295 |
|
}, |
|
{ |
|
"epoch": 2.63, |
|
"learning_rate": 1.7543859649122806e-05, |
|
"loss": 0.6361, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"learning_rate": 1.7836257309941522e-05, |
|
"loss": 0.548, |
|
"step": 305 |
|
}, |
|
{ |
|
"epoch": 2.71, |
|
"learning_rate": 1.8128654970760235e-05, |
|
"loss": 0.5446, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 2.76, |
|
"learning_rate": 1.8421052631578947e-05, |
|
"loss": 0.6898, |
|
"step": 315 |
|
}, |
|
{ |
|
"epoch": 2.8, |
|
"learning_rate": 1.871345029239766e-05, |
|
"loss": 0.6384, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 2.84, |
|
"learning_rate": 1.9005847953216373e-05, |
|
"loss": 0.5624, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 2.89, |
|
"learning_rate": 1.929824561403509e-05, |
|
"loss": 0.7614, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 2.93, |
|
"learning_rate": 1.9590643274853802e-05, |
|
"loss": 0.6112, |
|
"step": 335 |
|
}, |
|
{ |
|
"epoch": 2.98, |
|
"learning_rate": 1.9883040935672515e-05, |
|
"loss": 0.5253, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 2.99, |
|
"eval_accuracy": 0.90311986863711, |
|
"eval_loss": 0.30125120282173157, |
|
"eval_runtime": 54.2496, |
|
"eval_samples_per_second": 22.452, |
|
"eval_steps_per_second": 2.82, |
|
"step": 342 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"learning_rate": 2.0175438596491227e-05, |
|
"loss": 0.441, |
|
"step": 345 |
|
}, |
|
{ |
|
"epoch": 3.06, |
|
"learning_rate": 2.046783625730994e-05, |
|
"loss": 0.5173, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 3.11, |
|
"learning_rate": 2.0760233918128656e-05, |
|
"loss": 0.5399, |
|
"step": 355 |
|
}, |
|
{ |
|
"epoch": 3.15, |
|
"learning_rate": 2.105263157894737e-05, |
|
"loss": 0.4442, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 3.19, |
|
"learning_rate": 2.134502923976608e-05, |
|
"loss": 0.5029, |
|
"step": 365 |
|
}, |
|
{ |
|
"epoch": 3.24, |
|
"learning_rate": 2.1637426900584794e-05, |
|
"loss": 0.3489, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 3.28, |
|
"learning_rate": 2.1929824561403507e-05, |
|
"loss": 0.4367, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 3.33, |
|
"learning_rate": 2.2222222222222223e-05, |
|
"loss": 0.3868, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 3.37, |
|
"learning_rate": 2.2514619883040936e-05, |
|
"loss": 0.479, |
|
"step": 385 |
|
}, |
|
{ |
|
"epoch": 3.41, |
|
"learning_rate": 2.280701754385965e-05, |
|
"loss": 0.4852, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 3.46, |
|
"learning_rate": 2.309941520467836e-05, |
|
"loss": 0.4858, |
|
"step": 395 |
|
}, |
|
{ |
|
"epoch": 3.5, |
|
"learning_rate": 2.3391812865497074e-05, |
|
"loss": 0.4333, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 3.54, |
|
"learning_rate": 2.368421052631579e-05, |
|
"loss": 0.5477, |
|
"step": 405 |
|
}, |
|
{ |
|
"epoch": 3.59, |
|
"learning_rate": 2.3976608187134503e-05, |
|
"loss": 0.4052, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 3.63, |
|
"learning_rate": 2.4269005847953216e-05, |
|
"loss": 0.4993, |
|
"step": 415 |
|
}, |
|
{ |
|
"epoch": 3.68, |
|
"learning_rate": 2.456140350877193e-05, |
|
"loss": 0.3349, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 3.72, |
|
"learning_rate": 2.485380116959064e-05, |
|
"loss": 0.3309, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 3.76, |
|
"learning_rate": 2.5146198830409358e-05, |
|
"loss": 0.4864, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 3.81, |
|
"learning_rate": 2.5438596491228074e-05, |
|
"loss": 0.4098, |
|
"step": 435 |
|
}, |
|
{ |
|
"epoch": 3.85, |
|
"learning_rate": 2.5730994152046783e-05, |
|
"loss": 0.3193, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 3.89, |
|
"learning_rate": 2.60233918128655e-05, |
|
"loss": 0.57, |
|
"step": 445 |
|
}, |
|
{ |
|
"epoch": 3.94, |
|
"learning_rate": 2.6315789473684212e-05, |
|
"loss": 0.4372, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 3.98, |
|
"learning_rate": 2.6608187134502928e-05, |
|
"loss": 0.2958, |
|
"step": 455 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.9523809523809523, |
|
"eval_loss": 0.1533823311328888, |
|
"eval_runtime": 54.2646, |
|
"eval_samples_per_second": 22.446, |
|
"eval_steps_per_second": 2.82, |
|
"step": 457 |
|
}, |
|
{ |
|
"epoch": 4.03, |
|
"learning_rate": 2.6900584795321637e-05, |
|
"loss": 0.3616, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 4.07, |
|
"learning_rate": 2.7192982456140354e-05, |
|
"loss": 0.2978, |
|
"step": 465 |
|
}, |
|
{ |
|
"epoch": 4.11, |
|
"learning_rate": 2.7485380116959063e-05, |
|
"loss": 0.3206, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 4.16, |
|
"learning_rate": 2.777777777777778e-05, |
|
"loss": 0.3085, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 4.2, |
|
"learning_rate": 2.8070175438596492e-05, |
|
"loss": 0.3722, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 4.25, |
|
"learning_rate": 2.8362573099415208e-05, |
|
"loss": 0.3702, |
|
"step": 485 |
|
}, |
|
{ |
|
"epoch": 4.29, |
|
"learning_rate": 2.8654970760233917e-05, |
|
"loss": 0.3533, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 4.33, |
|
"learning_rate": 2.8947368421052634e-05, |
|
"loss": 0.2361, |
|
"step": 495 |
|
}, |
|
{ |
|
"epoch": 4.38, |
|
"learning_rate": 2.9239766081871346e-05, |
|
"loss": 0.2779, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 4.42, |
|
"learning_rate": 2.9532163742690062e-05, |
|
"loss": 0.3753, |
|
"step": 505 |
|
}, |
|
{ |
|
"epoch": 4.46, |
|
"learning_rate": 2.9824561403508772e-05, |
|
"loss": 0.3958, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 4.51, |
|
"learning_rate": 3.0116959064327488e-05, |
|
"loss": 0.2555, |
|
"step": 515 |
|
}, |
|
{ |
|
"epoch": 4.55, |
|
"learning_rate": 3.0409356725146197e-05, |
|
"loss": 0.2769, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 4.6, |
|
"learning_rate": 3.0701754385964913e-05, |
|
"loss": 0.3126, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 4.64, |
|
"learning_rate": 3.0994152046783626e-05, |
|
"loss": 0.3055, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 4.68, |
|
"learning_rate": 3.128654970760234e-05, |
|
"loss": 0.3042, |
|
"step": 535 |
|
}, |
|
{ |
|
"epoch": 4.73, |
|
"learning_rate": 3.157894736842105e-05, |
|
"loss": 0.4877, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 4.77, |
|
"learning_rate": 3.187134502923977e-05, |
|
"loss": 0.2869, |
|
"step": 545 |
|
}, |
|
{ |
|
"epoch": 4.81, |
|
"learning_rate": 3.216374269005848e-05, |
|
"loss": 0.2767, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 4.86, |
|
"learning_rate": 3.24561403508772e-05, |
|
"loss": 0.3141, |
|
"step": 555 |
|
}, |
|
{ |
|
"epoch": 4.9, |
|
"learning_rate": 3.274853801169591e-05, |
|
"loss": 0.3657, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 4.95, |
|
"learning_rate": 3.304093567251462e-05, |
|
"loss": 0.2905, |
|
"step": 565 |
|
}, |
|
{ |
|
"epoch": 4.99, |
|
"learning_rate": 3.3333333333333335e-05, |
|
"loss": 0.276, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_accuracy": 0.9334975369458128, |
|
"eval_loss": 0.1825261414051056, |
|
"eval_runtime": 54.1455, |
|
"eval_samples_per_second": 22.495, |
|
"eval_steps_per_second": 2.826, |
|
"step": 571 |
|
}, |
|
{ |
|
"epoch": 5.03, |
|
"learning_rate": 3.362573099415205e-05, |
|
"loss": 0.2115, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 5.08, |
|
"learning_rate": 3.391812865497076e-05, |
|
"loss": 0.34, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 5.12, |
|
"learning_rate": 3.421052631578947e-05, |
|
"loss": 0.3145, |
|
"step": 585 |
|
}, |
|
{ |
|
"epoch": 5.16, |
|
"learning_rate": 3.4502923976608186e-05, |
|
"loss": 0.2357, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 5.21, |
|
"learning_rate": 3.4795321637426905e-05, |
|
"loss": 0.1658, |
|
"step": 595 |
|
}, |
|
{ |
|
"epoch": 5.25, |
|
"learning_rate": 3.508771929824561e-05, |
|
"loss": 0.2002, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 5.3, |
|
"learning_rate": 3.538011695906433e-05, |
|
"loss": 0.2387, |
|
"step": 605 |
|
}, |
|
{ |
|
"epoch": 5.34, |
|
"learning_rate": 3.5672514619883044e-05, |
|
"loss": 0.2309, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 5.38, |
|
"learning_rate": 3.5964912280701756e-05, |
|
"loss": 0.2013, |
|
"step": 615 |
|
}, |
|
{ |
|
"epoch": 5.43, |
|
"learning_rate": 3.625730994152047e-05, |
|
"loss": 0.2333, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 5.47, |
|
"learning_rate": 3.654970760233918e-05, |
|
"loss": 0.4043, |
|
"step": 625 |
|
}, |
|
{ |
|
"epoch": 5.51, |
|
"learning_rate": 3.6842105263157895e-05, |
|
"loss": 0.2156, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 5.56, |
|
"learning_rate": 3.713450292397661e-05, |
|
"loss": 0.3377, |
|
"step": 635 |
|
}, |
|
{ |
|
"epoch": 5.6, |
|
"learning_rate": 3.742690058479532e-05, |
|
"loss": 0.2842, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 5.65, |
|
"learning_rate": 3.771929824561404e-05, |
|
"loss": 0.1925, |
|
"step": 645 |
|
}, |
|
{ |
|
"epoch": 5.69, |
|
"learning_rate": 3.8011695906432746e-05, |
|
"loss": 0.347, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 5.73, |
|
"learning_rate": 3.8304093567251465e-05, |
|
"loss": 0.2794, |
|
"step": 655 |
|
}, |
|
{ |
|
"epoch": 5.78, |
|
"learning_rate": 3.859649122807018e-05, |
|
"loss": 0.244, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 5.82, |
|
"learning_rate": 3.888888888888889e-05, |
|
"loss": 0.3321, |
|
"step": 665 |
|
}, |
|
{ |
|
"epoch": 5.86, |
|
"learning_rate": 3.9181286549707604e-05, |
|
"loss": 0.2099, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 5.91, |
|
"learning_rate": 3.9473684210526316e-05, |
|
"loss": 0.2861, |
|
"step": 675 |
|
}, |
|
{ |
|
"epoch": 5.95, |
|
"learning_rate": 3.976608187134503e-05, |
|
"loss": 0.2936, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"learning_rate": 4.005847953216375e-05, |
|
"loss": 0.2556, |
|
"step": 685 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_accuracy": 0.9729064039408867, |
|
"eval_loss": 0.07233729213476181, |
|
"eval_runtime": 54.3781, |
|
"eval_samples_per_second": 22.399, |
|
"eval_steps_per_second": 2.814, |
|
"step": 685 |
|
}, |
|
{ |
|
"epoch": 6.04, |
|
"learning_rate": 4.0350877192982455e-05, |
|
"loss": 0.2191, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 6.08, |
|
"learning_rate": 4.0643274853801174e-05, |
|
"loss": 0.2091, |
|
"step": 695 |
|
}, |
|
{ |
|
"epoch": 6.13, |
|
"learning_rate": 4.093567251461988e-05, |
|
"loss": 0.3105, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 6.17, |
|
"learning_rate": 4.12280701754386e-05, |
|
"loss": 0.1681, |
|
"step": 705 |
|
}, |
|
{ |
|
"epoch": 6.21, |
|
"learning_rate": 4.152046783625731e-05, |
|
"loss": 0.2344, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 6.26, |
|
"learning_rate": 4.1812865497076025e-05, |
|
"loss": 0.3378, |
|
"step": 715 |
|
}, |
|
{ |
|
"epoch": 6.3, |
|
"learning_rate": 4.210526315789474e-05, |
|
"loss": 0.3698, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 6.35, |
|
"learning_rate": 4.239766081871345e-05, |
|
"loss": 0.2361, |
|
"step": 725 |
|
}, |
|
{ |
|
"epoch": 6.39, |
|
"learning_rate": 4.269005847953216e-05, |
|
"loss": 0.4333, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 6.43, |
|
"learning_rate": 4.298245614035088e-05, |
|
"loss": 0.3148, |
|
"step": 735 |
|
}, |
|
{ |
|
"epoch": 6.48, |
|
"learning_rate": 4.327485380116959e-05, |
|
"loss": 0.3368, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 6.52, |
|
"learning_rate": 4.356725146198831e-05, |
|
"loss": 0.2656, |
|
"step": 745 |
|
}, |
|
{ |
|
"epoch": 6.56, |
|
"learning_rate": 4.3859649122807014e-05, |
|
"loss": 0.2234, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 6.61, |
|
"learning_rate": 4.4152046783625734e-05, |
|
"loss": 0.1766, |
|
"step": 755 |
|
}, |
|
{ |
|
"epoch": 6.65, |
|
"learning_rate": 4.4444444444444447e-05, |
|
"loss": 0.2741, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 6.7, |
|
"learning_rate": 4.473684210526316e-05, |
|
"loss": 0.473, |
|
"step": 765 |
|
}, |
|
{ |
|
"epoch": 6.74, |
|
"learning_rate": 4.502923976608187e-05, |
|
"loss": 0.3843, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 6.78, |
|
"learning_rate": 4.5321637426900585e-05, |
|
"loss": 0.2639, |
|
"step": 775 |
|
}, |
|
{ |
|
"epoch": 6.83, |
|
"learning_rate": 4.56140350877193e-05, |
|
"loss": 0.2179, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 6.87, |
|
"learning_rate": 4.590643274853802e-05, |
|
"loss": 0.1746, |
|
"step": 785 |
|
}, |
|
{ |
|
"epoch": 6.91, |
|
"learning_rate": 4.619883040935672e-05, |
|
"loss": 0.233, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 6.96, |
|
"learning_rate": 4.649122807017544e-05, |
|
"loss": 0.3624, |
|
"step": 795 |
|
}, |
|
{ |
|
"epoch": 6.99, |
|
"eval_accuracy": 0.9482758620689655, |
|
"eval_loss": 0.12682275474071503, |
|
"eval_runtime": 54.3592, |
|
"eval_samples_per_second": 22.407, |
|
"eval_steps_per_second": 2.815, |
|
"step": 799 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"learning_rate": 4.678362573099415e-05, |
|
"loss": 0.2835, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 7.05, |
|
"learning_rate": 4.707602339181287e-05, |
|
"loss": 0.2004, |
|
"step": 805 |
|
}, |
|
{ |
|
"epoch": 7.09, |
|
"learning_rate": 4.736842105263158e-05, |
|
"loss": 0.2604, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 7.13, |
|
"learning_rate": 4.7660818713450294e-05, |
|
"loss": 0.2926, |
|
"step": 815 |
|
}, |
|
{ |
|
"epoch": 7.18, |
|
"learning_rate": 4.7953216374269006e-05, |
|
"loss": 0.1887, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 7.22, |
|
"learning_rate": 4.824561403508772e-05, |
|
"loss": 0.2633, |
|
"step": 825 |
|
}, |
|
{ |
|
"epoch": 7.26, |
|
"learning_rate": 4.853801169590643e-05, |
|
"loss": 0.382, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 7.31, |
|
"learning_rate": 4.883040935672515e-05, |
|
"loss": 0.2431, |
|
"step": 835 |
|
}, |
|
{ |
|
"epoch": 7.35, |
|
"learning_rate": 4.912280701754386e-05, |
|
"loss": 0.2928, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 7.4, |
|
"learning_rate": 4.941520467836258e-05, |
|
"loss": 0.2424, |
|
"step": 845 |
|
}, |
|
{ |
|
"epoch": 7.44, |
|
"learning_rate": 4.970760233918128e-05, |
|
"loss": 0.3165, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 7.48, |
|
"learning_rate": 5e-05, |
|
"loss": 0.4459, |
|
"step": 855 |
|
}, |
|
{ |
|
"epoch": 7.53, |
|
"learning_rate": 4.970760233918128e-05, |
|
"loss": 0.2964, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 7.57, |
|
"learning_rate": 4.941520467836258e-05, |
|
"loss": 0.37, |
|
"step": 865 |
|
}, |
|
{ |
|
"epoch": 7.61, |
|
"learning_rate": 4.912280701754386e-05, |
|
"loss": 0.2116, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 7.66, |
|
"learning_rate": 4.883040935672515e-05, |
|
"loss": 0.1844, |
|
"step": 875 |
|
}, |
|
{ |
|
"epoch": 7.7, |
|
"learning_rate": 4.853801169590643e-05, |
|
"loss": 0.215, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 7.75, |
|
"learning_rate": 4.824561403508772e-05, |
|
"loss": 0.3179, |
|
"step": 885 |
|
}, |
|
{ |
|
"epoch": 7.79, |
|
"learning_rate": 4.7953216374269006e-05, |
|
"loss": 0.2767, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 7.83, |
|
"learning_rate": 4.7660818713450294e-05, |
|
"loss": 0.3065, |
|
"step": 895 |
|
}, |
|
{ |
|
"epoch": 7.88, |
|
"learning_rate": 4.736842105263158e-05, |
|
"loss": 0.2597, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 7.92, |
|
"learning_rate": 4.707602339181287e-05, |
|
"loss": 0.3216, |
|
"step": 905 |
|
}, |
|
{ |
|
"epoch": 7.96, |
|
"learning_rate": 4.678362573099415e-05, |
|
"loss": 0.1986, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_accuracy": 0.9778325123152709, |
|
"eval_loss": 0.052232660353183746, |
|
"eval_runtime": 54.3544, |
|
"eval_samples_per_second": 22.408, |
|
"eval_steps_per_second": 2.815, |
|
"step": 914 |
|
}, |
|
{ |
|
"epoch": 8.01, |
|
"learning_rate": 4.649122807017544e-05, |
|
"loss": 0.197, |
|
"step": 915 |
|
}, |
|
{ |
|
"epoch": 8.05, |
|
"learning_rate": 4.619883040935672e-05, |
|
"loss": 0.2028, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 8.1, |
|
"learning_rate": 4.590643274853802e-05, |
|
"loss": 0.1589, |
|
"step": 925 |
|
}, |
|
{ |
|
"epoch": 8.14, |
|
"learning_rate": 4.56140350877193e-05, |
|
"loss": 0.1238, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 8.18, |
|
"learning_rate": 4.5321637426900585e-05, |
|
"loss": 0.1461, |
|
"step": 935 |
|
}, |
|
{ |
|
"epoch": 8.23, |
|
"learning_rate": 4.502923976608187e-05, |
|
"loss": 0.146, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 8.27, |
|
"learning_rate": 4.473684210526316e-05, |
|
"loss": 0.2098, |
|
"step": 945 |
|
}, |
|
{ |
|
"epoch": 8.32, |
|
"learning_rate": 4.4444444444444447e-05, |
|
"loss": 0.1078, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 8.36, |
|
"learning_rate": 4.4152046783625734e-05, |
|
"loss": 0.2042, |
|
"step": 955 |
|
}, |
|
{ |
|
"epoch": 8.4, |
|
"learning_rate": 4.3859649122807014e-05, |
|
"loss": 0.2362, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 8.45, |
|
"learning_rate": 4.356725146198831e-05, |
|
"loss": 0.2723, |
|
"step": 965 |
|
}, |
|
{ |
|
"epoch": 8.49, |
|
"learning_rate": 4.327485380116959e-05, |
|
"loss": 0.2668, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 8.53, |
|
"learning_rate": 4.298245614035088e-05, |
|
"loss": 0.1731, |
|
"step": 975 |
|
}, |
|
{ |
|
"epoch": 8.58, |
|
"learning_rate": 4.269005847953216e-05, |
|
"loss": 0.2237, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 8.62, |
|
"learning_rate": 4.239766081871345e-05, |
|
"loss": 0.2593, |
|
"step": 985 |
|
}, |
|
{ |
|
"epoch": 8.67, |
|
"learning_rate": 4.210526315789474e-05, |
|
"loss": 0.1881, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 8.71, |
|
"learning_rate": 4.1812865497076025e-05, |
|
"loss": 0.1066, |
|
"step": 995 |
|
}, |
|
{ |
|
"epoch": 8.75, |
|
"learning_rate": 4.152046783625731e-05, |
|
"loss": 0.1722, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 8.8, |
|
"learning_rate": 4.12280701754386e-05, |
|
"loss": 0.2162, |
|
"step": 1005 |
|
}, |
|
{ |
|
"epoch": 8.84, |
|
"learning_rate": 4.093567251461988e-05, |
|
"loss": 0.2242, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 8.88, |
|
"learning_rate": 4.0643274853801174e-05, |
|
"loss": 0.2441, |
|
"step": 1015 |
|
}, |
|
{ |
|
"epoch": 8.93, |
|
"learning_rate": 4.0350877192982455e-05, |
|
"loss": 0.1766, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 8.97, |
|
"learning_rate": 4.005847953216375e-05, |
|
"loss": 0.1554, |
|
"step": 1025 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_accuracy": 0.9926108374384236, |
|
"eval_loss": 0.020505670458078384, |
|
"eval_runtime": 54.405, |
|
"eval_samples_per_second": 22.388, |
|
"eval_steps_per_second": 2.812, |
|
"step": 1028 |
|
}, |
|
{ |
|
"epoch": 9.02, |
|
"learning_rate": 3.976608187134503e-05, |
|
"loss": 0.0887, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 9.06, |
|
"learning_rate": 3.9473684210526316e-05, |
|
"loss": 0.2388, |
|
"step": 1035 |
|
}, |
|
{ |
|
"epoch": 9.1, |
|
"learning_rate": 3.9181286549707604e-05, |
|
"loss": 0.2096, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 9.15, |
|
"learning_rate": 3.888888888888889e-05, |
|
"loss": 0.2445, |
|
"step": 1045 |
|
}, |
|
{ |
|
"epoch": 9.19, |
|
"learning_rate": 3.859649122807018e-05, |
|
"loss": 0.2204, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 9.23, |
|
"learning_rate": 3.8304093567251465e-05, |
|
"loss": 0.1205, |
|
"step": 1055 |
|
}, |
|
{ |
|
"epoch": 9.28, |
|
"learning_rate": 3.8011695906432746e-05, |
|
"loss": 0.1625, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 9.32, |
|
"learning_rate": 3.771929824561404e-05, |
|
"loss": 0.1143, |
|
"step": 1065 |
|
}, |
|
{ |
|
"epoch": 9.37, |
|
"learning_rate": 3.742690058479532e-05, |
|
"loss": 0.1649, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 9.41, |
|
"learning_rate": 3.713450292397661e-05, |
|
"loss": 0.2073, |
|
"step": 1075 |
|
}, |
|
{ |
|
"epoch": 9.45, |
|
"learning_rate": 3.6842105263157895e-05, |
|
"loss": 0.1361, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 9.5, |
|
"learning_rate": 3.654970760233918e-05, |
|
"loss": 0.1194, |
|
"step": 1085 |
|
}, |
|
{ |
|
"epoch": 9.54, |
|
"learning_rate": 3.625730994152047e-05, |
|
"loss": 0.2756, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 9.58, |
|
"learning_rate": 3.5964912280701756e-05, |
|
"loss": 0.2033, |
|
"step": 1095 |
|
}, |
|
{ |
|
"epoch": 9.63, |
|
"learning_rate": 3.5672514619883044e-05, |
|
"loss": 0.1373, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 9.67, |
|
"learning_rate": 3.538011695906433e-05, |
|
"loss": 0.1226, |
|
"step": 1105 |
|
}, |
|
{ |
|
"epoch": 9.72, |
|
"learning_rate": 3.508771929824561e-05, |
|
"loss": 0.1087, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 9.76, |
|
"learning_rate": 3.4795321637426905e-05, |
|
"loss": 0.0839, |
|
"step": 1115 |
|
}, |
|
{ |
|
"epoch": 9.8, |
|
"learning_rate": 3.4502923976608186e-05, |
|
"loss": 0.1183, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 9.85, |
|
"learning_rate": 3.421052631578947e-05, |
|
"loss": 0.2259, |
|
"step": 1125 |
|
}, |
|
{ |
|
"epoch": 9.89, |
|
"learning_rate": 3.391812865497076e-05, |
|
"loss": 0.1027, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 9.93, |
|
"learning_rate": 3.362573099415205e-05, |
|
"loss": 0.0893, |
|
"step": 1135 |
|
}, |
|
{ |
|
"epoch": 9.98, |
|
"learning_rate": 3.3333333333333335e-05, |
|
"loss": 0.1636, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"eval_accuracy": 0.9950738916256158, |
|
"eval_loss": 0.019661663100123405, |
|
"eval_runtime": 54.4421, |
|
"eval_samples_per_second": 22.372, |
|
"eval_steps_per_second": 2.81, |
|
"step": 1142 |
|
}, |
|
{ |
|
"epoch": 10.02, |
|
"learning_rate": 3.304093567251462e-05, |
|
"loss": 0.1459, |
|
"step": 1145 |
|
}, |
|
{ |
|
"epoch": 10.07, |
|
"learning_rate": 3.274853801169591e-05, |
|
"loss": 0.1303, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 10.11, |
|
"learning_rate": 3.24561403508772e-05, |
|
"loss": 0.2256, |
|
"step": 1155 |
|
}, |
|
{ |
|
"epoch": 10.15, |
|
"learning_rate": 3.216374269005848e-05, |
|
"loss": 0.2763, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 10.2, |
|
"learning_rate": 3.187134502923977e-05, |
|
"loss": 0.1605, |
|
"step": 1165 |
|
}, |
|
{ |
|
"epoch": 10.24, |
|
"learning_rate": 3.157894736842105e-05, |
|
"loss": 0.14, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 10.28, |
|
"learning_rate": 3.128654970760234e-05, |
|
"loss": 0.1832, |
|
"step": 1175 |
|
}, |
|
{ |
|
"epoch": 10.33, |
|
"learning_rate": 3.0994152046783626e-05, |
|
"loss": 0.1387, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 10.37, |
|
"learning_rate": 3.0701754385964913e-05, |
|
"loss": 0.1055, |
|
"step": 1185 |
|
}, |
|
{ |
|
"epoch": 10.42, |
|
"learning_rate": 3.0409356725146197e-05, |
|
"loss": 0.1302, |
|
"step": 1190 |
|
}, |
|
{ |
|
"epoch": 10.46, |
|
"learning_rate": 3.0116959064327488e-05, |
|
"loss": 0.0993, |
|
"step": 1195 |
|
}, |
|
{ |
|
"epoch": 10.5, |
|
"learning_rate": 2.9824561403508772e-05, |
|
"loss": 0.174, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 10.55, |
|
"learning_rate": 2.9532163742690062e-05, |
|
"loss": 0.1348, |
|
"step": 1205 |
|
}, |
|
{ |
|
"epoch": 10.59, |
|
"learning_rate": 2.9239766081871346e-05, |
|
"loss": 0.12, |
|
"step": 1210 |
|
}, |
|
{ |
|
"epoch": 10.63, |
|
"learning_rate": 2.8947368421052634e-05, |
|
"loss": 0.2483, |
|
"step": 1215 |
|
}, |
|
{ |
|
"epoch": 10.68, |
|
"learning_rate": 2.8654970760233917e-05, |
|
"loss": 0.0965, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 10.72, |
|
"learning_rate": 2.8362573099415208e-05, |
|
"loss": 0.1754, |
|
"step": 1225 |
|
}, |
|
{ |
|
"epoch": 10.77, |
|
"learning_rate": 2.8070175438596492e-05, |
|
"loss": 0.1192, |
|
"step": 1230 |
|
}, |
|
{ |
|
"epoch": 10.81, |
|
"learning_rate": 2.777777777777778e-05, |
|
"loss": 0.1869, |
|
"step": 1235 |
|
}, |
|
{ |
|
"epoch": 10.85, |
|
"learning_rate": 2.7485380116959063e-05, |
|
"loss": 0.0549, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 10.9, |
|
"learning_rate": 2.7192982456140354e-05, |
|
"loss": 0.1127, |
|
"step": 1245 |
|
}, |
|
{ |
|
"epoch": 10.94, |
|
"learning_rate": 2.6900584795321637e-05, |
|
"loss": 0.1294, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 10.98, |
|
"learning_rate": 2.6608187134502928e-05, |
|
"loss": 0.1147, |
|
"step": 1255 |
|
}, |
|
{ |
|
"epoch": 10.99, |
|
"eval_accuracy": 0.9835796387520526, |
|
"eval_loss": 0.05173669755458832, |
|
"eval_runtime": 54.2024, |
|
"eval_samples_per_second": 22.471, |
|
"eval_steps_per_second": 2.823, |
|
"step": 1256 |
|
}, |
|
{ |
|
"epoch": 11.03, |
|
"learning_rate": 2.6315789473684212e-05, |
|
"loss": 0.1873, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 11.07, |
|
"learning_rate": 2.60233918128655e-05, |
|
"loss": 0.1212, |
|
"step": 1265 |
|
}, |
|
{ |
|
"epoch": 11.12, |
|
"learning_rate": 2.5730994152046783e-05, |
|
"loss": 0.0422, |
|
"step": 1270 |
|
}, |
|
{ |
|
"epoch": 11.16, |
|
"learning_rate": 2.5438596491228074e-05, |
|
"loss": 0.1971, |
|
"step": 1275 |
|
}, |
|
{ |
|
"epoch": 11.2, |
|
"learning_rate": 2.5146198830409358e-05, |
|
"loss": 0.0876, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 11.25, |
|
"learning_rate": 2.485380116959064e-05, |
|
"loss": 0.1424, |
|
"step": 1285 |
|
}, |
|
{ |
|
"epoch": 11.29, |
|
"learning_rate": 2.456140350877193e-05, |
|
"loss": 0.0589, |
|
"step": 1290 |
|
}, |
|
{ |
|
"epoch": 11.33, |
|
"learning_rate": 2.4269005847953216e-05, |
|
"loss": 0.0975, |
|
"step": 1295 |
|
}, |
|
{ |
|
"epoch": 11.38, |
|
"learning_rate": 2.3976608187134503e-05, |
|
"loss": 0.1219, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 11.42, |
|
"learning_rate": 2.368421052631579e-05, |
|
"loss": 0.1359, |
|
"step": 1305 |
|
}, |
|
{ |
|
"epoch": 11.47, |
|
"learning_rate": 2.3391812865497074e-05, |
|
"loss": 0.0449, |
|
"step": 1310 |
|
}, |
|
{ |
|
"epoch": 11.51, |
|
"learning_rate": 2.309941520467836e-05, |
|
"loss": 0.1362, |
|
"step": 1315 |
|
}, |
|
{ |
|
"epoch": 11.55, |
|
"learning_rate": 2.280701754385965e-05, |
|
"loss": 0.1156, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 11.6, |
|
"learning_rate": 2.2514619883040936e-05, |
|
"loss": 0.0743, |
|
"step": 1325 |
|
}, |
|
{ |
|
"epoch": 11.64, |
|
"learning_rate": 2.2222222222222223e-05, |
|
"loss": 0.2625, |
|
"step": 1330 |
|
}, |
|
{ |
|
"epoch": 11.68, |
|
"learning_rate": 2.1929824561403507e-05, |
|
"loss": 0.065, |
|
"step": 1335 |
|
}, |
|
{ |
|
"epoch": 11.73, |
|
"learning_rate": 2.1637426900584794e-05, |
|
"loss": 0.1152, |
|
"step": 1340 |
|
}, |
|
{ |
|
"epoch": 11.77, |
|
"learning_rate": 2.134502923976608e-05, |
|
"loss": 0.1055, |
|
"step": 1345 |
|
}, |
|
{ |
|
"epoch": 11.82, |
|
"learning_rate": 2.105263157894737e-05, |
|
"loss": 0.0941, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 11.86, |
|
"learning_rate": 2.0760233918128656e-05, |
|
"loss": 0.1564, |
|
"step": 1355 |
|
}, |
|
{ |
|
"epoch": 11.9, |
|
"learning_rate": 2.046783625730994e-05, |
|
"loss": 0.151, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 11.95, |
|
"learning_rate": 2.0175438596491227e-05, |
|
"loss": 0.0964, |
|
"step": 1365 |
|
}, |
|
{ |
|
"epoch": 11.99, |
|
"learning_rate": 1.9883040935672515e-05, |
|
"loss": 0.1663, |
|
"step": 1370 |
|
}, |
|
{ |
|
"epoch": 12.0, |
|
"eval_accuracy": 0.9958949096880131, |
|
"eval_loss": 0.005566800944507122, |
|
"eval_runtime": 54.1153, |
|
"eval_samples_per_second": 22.507, |
|
"eval_steps_per_second": 2.827, |
|
"step": 1371 |
|
}, |
|
{ |
|
"epoch": 12.04, |
|
"learning_rate": 1.9590643274853802e-05, |
|
"loss": 0.0835, |
|
"step": 1375 |
|
}, |
|
{ |
|
"epoch": 12.08, |
|
"learning_rate": 1.929824561403509e-05, |
|
"loss": 0.0809, |
|
"step": 1380 |
|
}, |
|
{ |
|
"epoch": 12.12, |
|
"learning_rate": 1.9005847953216373e-05, |
|
"loss": 0.1657, |
|
"step": 1385 |
|
}, |
|
{ |
|
"epoch": 12.17, |
|
"learning_rate": 1.871345029239766e-05, |
|
"loss": 0.0642, |
|
"step": 1390 |
|
}, |
|
{ |
|
"epoch": 12.21, |
|
"learning_rate": 1.8421052631578947e-05, |
|
"loss": 0.1124, |
|
"step": 1395 |
|
}, |
|
{ |
|
"epoch": 12.25, |
|
"learning_rate": 1.8128654970760235e-05, |
|
"loss": 0.1444, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 12.3, |
|
"learning_rate": 1.7836257309941522e-05, |
|
"loss": 0.0315, |
|
"step": 1405 |
|
}, |
|
{ |
|
"epoch": 12.34, |
|
"learning_rate": 1.7543859649122806e-05, |
|
"loss": 0.1471, |
|
"step": 1410 |
|
}, |
|
{ |
|
"epoch": 12.39, |
|
"learning_rate": 1.7251461988304093e-05, |
|
"loss": 0.091, |
|
"step": 1415 |
|
}, |
|
{ |
|
"epoch": 12.43, |
|
"learning_rate": 1.695906432748538e-05, |
|
"loss": 0.167, |
|
"step": 1420 |
|
}, |
|
{ |
|
"epoch": 12.47, |
|
"learning_rate": 1.6666666666666667e-05, |
|
"loss": 0.0769, |
|
"step": 1425 |
|
}, |
|
{ |
|
"epoch": 12.52, |
|
"learning_rate": 1.6374269005847955e-05, |
|
"loss": 0.1187, |
|
"step": 1430 |
|
}, |
|
{ |
|
"epoch": 12.56, |
|
"learning_rate": 1.608187134502924e-05, |
|
"loss": 0.1473, |
|
"step": 1435 |
|
}, |
|
{ |
|
"epoch": 12.6, |
|
"learning_rate": 1.5789473684210526e-05, |
|
"loss": 0.0737, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 12.65, |
|
"learning_rate": 1.5497076023391813e-05, |
|
"loss": 0.0668, |
|
"step": 1445 |
|
}, |
|
{ |
|
"epoch": 12.69, |
|
"learning_rate": 1.5204678362573099e-05, |
|
"loss": 0.1488, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 12.74, |
|
"learning_rate": 1.4912280701754386e-05, |
|
"loss": 0.0413, |
|
"step": 1455 |
|
}, |
|
{ |
|
"epoch": 12.78, |
|
"learning_rate": 1.4619883040935673e-05, |
|
"loss": 0.1062, |
|
"step": 1460 |
|
}, |
|
{ |
|
"epoch": 12.82, |
|
"learning_rate": 1.4327485380116959e-05, |
|
"loss": 0.1047, |
|
"step": 1465 |
|
}, |
|
{ |
|
"epoch": 12.87, |
|
"learning_rate": 1.4035087719298246e-05, |
|
"loss": 0.068, |
|
"step": 1470 |
|
}, |
|
{ |
|
"epoch": 12.91, |
|
"learning_rate": 1.3742690058479531e-05, |
|
"loss": 0.03, |
|
"step": 1475 |
|
}, |
|
{ |
|
"epoch": 12.95, |
|
"learning_rate": 1.3450292397660819e-05, |
|
"loss": 0.0708, |
|
"step": 1480 |
|
}, |
|
{ |
|
"epoch": 13.0, |
|
"learning_rate": 1.3157894736842106e-05, |
|
"loss": 0.094, |
|
"step": 1485 |
|
}, |
|
{ |
|
"epoch": 13.0, |
|
"eval_accuracy": 0.9991789819376026, |
|
"eval_loss": 0.002953051822260022, |
|
"eval_runtime": 54.2489, |
|
"eval_samples_per_second": 22.452, |
|
"eval_steps_per_second": 2.82, |
|
"step": 1485 |
|
}, |
|
{ |
|
"epoch": 13.04, |
|
"learning_rate": 1.2865497076023392e-05, |
|
"loss": 0.1298, |
|
"step": 1490 |
|
}, |
|
{ |
|
"epoch": 13.09, |
|
"learning_rate": 1.2573099415204679e-05, |
|
"loss": 0.1349, |
|
"step": 1495 |
|
}, |
|
{ |
|
"epoch": 13.13, |
|
"learning_rate": 1.2280701754385964e-05, |
|
"loss": 0.1136, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 13.17, |
|
"learning_rate": 1.1988304093567252e-05, |
|
"loss": 0.0972, |
|
"step": 1505 |
|
}, |
|
{ |
|
"epoch": 13.22, |
|
"learning_rate": 1.1695906432748537e-05, |
|
"loss": 0.0589, |
|
"step": 1510 |
|
}, |
|
{ |
|
"epoch": 13.26, |
|
"learning_rate": 1.1403508771929824e-05, |
|
"loss": 0.0569, |
|
"step": 1515 |
|
}, |
|
{ |
|
"epoch": 13.3, |
|
"learning_rate": 1.1111111111111112e-05, |
|
"loss": 0.085, |
|
"step": 1520 |
|
}, |
|
{ |
|
"epoch": 13.35, |
|
"learning_rate": 1.0818713450292397e-05, |
|
"loss": 0.1057, |
|
"step": 1525 |
|
}, |
|
{ |
|
"epoch": 13.39, |
|
"learning_rate": 1.0526315789473684e-05, |
|
"loss": 0.0953, |
|
"step": 1530 |
|
}, |
|
{ |
|
"epoch": 13.44, |
|
"learning_rate": 1.023391812865497e-05, |
|
"loss": 0.085, |
|
"step": 1535 |
|
}, |
|
{ |
|
"epoch": 13.48, |
|
"learning_rate": 9.941520467836257e-06, |
|
"loss": 0.043, |
|
"step": 1540 |
|
}, |
|
{ |
|
"epoch": 13.52, |
|
"learning_rate": 9.649122807017545e-06, |
|
"loss": 0.0555, |
|
"step": 1545 |
|
}, |
|
{ |
|
"epoch": 13.57, |
|
"learning_rate": 9.35672514619883e-06, |
|
"loss": 0.0452, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 13.61, |
|
"learning_rate": 9.064327485380117e-06, |
|
"loss": 0.0489, |
|
"step": 1555 |
|
}, |
|
{ |
|
"epoch": 13.65, |
|
"learning_rate": 8.771929824561403e-06, |
|
"loss": 0.1405, |
|
"step": 1560 |
|
}, |
|
{ |
|
"epoch": 13.7, |
|
"learning_rate": 8.47953216374269e-06, |
|
"loss": 0.0661, |
|
"step": 1565 |
|
}, |
|
{ |
|
"epoch": 13.74, |
|
"learning_rate": 8.187134502923977e-06, |
|
"loss": 0.1128, |
|
"step": 1570 |
|
}, |
|
{ |
|
"epoch": 13.79, |
|
"learning_rate": 7.894736842105263e-06, |
|
"loss": 0.0803, |
|
"step": 1575 |
|
}, |
|
{ |
|
"epoch": 13.83, |
|
"learning_rate": 7.602339181286549e-06, |
|
"loss": 0.0843, |
|
"step": 1580 |
|
}, |
|
{ |
|
"epoch": 13.87, |
|
"learning_rate": 7.3099415204678366e-06, |
|
"loss": 0.0902, |
|
"step": 1585 |
|
}, |
|
{ |
|
"epoch": 13.92, |
|
"learning_rate": 7.017543859649123e-06, |
|
"loss": 0.094, |
|
"step": 1590 |
|
}, |
|
{ |
|
"epoch": 13.96, |
|
"learning_rate": 6.725146198830409e-06, |
|
"loss": 0.1308, |
|
"step": 1595 |
|
}, |
|
{ |
|
"epoch": 14.0, |
|
"eval_accuracy": 0.9991789819376026, |
|
"eval_loss": 0.0011125708697363734, |
|
"eval_runtime": 54.0922, |
|
"eval_samples_per_second": 22.517, |
|
"eval_steps_per_second": 2.829, |
|
"step": 1599 |
|
}, |
|
{ |
|
"epoch": 14.0, |
|
"learning_rate": 6.432748538011696e-06, |
|
"loss": 0.0785, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 14.05, |
|
"learning_rate": 6.140350877192982e-06, |
|
"loss": 0.079, |
|
"step": 1605 |
|
}, |
|
{ |
|
"epoch": 14.09, |
|
"learning_rate": 5.8479532163742686e-06, |
|
"loss": 0.1075, |
|
"step": 1610 |
|
}, |
|
{ |
|
"epoch": 14.14, |
|
"learning_rate": 5.555555555555556e-06, |
|
"loss": 0.0769, |
|
"step": 1615 |
|
}, |
|
{ |
|
"epoch": 14.18, |
|
"learning_rate": 5.263157894736842e-06, |
|
"loss": 0.0705, |
|
"step": 1620 |
|
}, |
|
{ |
|
"epoch": 14.22, |
|
"learning_rate": 4.970760233918129e-06, |
|
"loss": 0.0779, |
|
"step": 1625 |
|
}, |
|
{ |
|
"epoch": 14.27, |
|
"learning_rate": 4.678362573099415e-06, |
|
"loss": 0.0319, |
|
"step": 1630 |
|
}, |
|
{ |
|
"epoch": 14.31, |
|
"learning_rate": 4.3859649122807014e-06, |
|
"loss": 0.0495, |
|
"step": 1635 |
|
}, |
|
{ |
|
"epoch": 14.35, |
|
"learning_rate": 4.093567251461989e-06, |
|
"loss": 0.0851, |
|
"step": 1640 |
|
}, |
|
{ |
|
"epoch": 14.4, |
|
"learning_rate": 3.8011695906432747e-06, |
|
"loss": 0.1291, |
|
"step": 1645 |
|
}, |
|
{ |
|
"epoch": 14.44, |
|
"learning_rate": 3.5087719298245615e-06, |
|
"loss": 0.0778, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 14.49, |
|
"learning_rate": 3.216374269005848e-06, |
|
"loss": 0.0826, |
|
"step": 1655 |
|
}, |
|
{ |
|
"epoch": 14.53, |
|
"learning_rate": 2.9239766081871343e-06, |
|
"loss": 0.0836, |
|
"step": 1660 |
|
}, |
|
{ |
|
"epoch": 14.57, |
|
"learning_rate": 2.631578947368421e-06, |
|
"loss": 0.0562, |
|
"step": 1665 |
|
}, |
|
{ |
|
"epoch": 14.62, |
|
"learning_rate": 2.3391812865497075e-06, |
|
"loss": 0.065, |
|
"step": 1670 |
|
}, |
|
{ |
|
"epoch": 14.66, |
|
"learning_rate": 2.0467836257309943e-06, |
|
"loss": 0.0644, |
|
"step": 1675 |
|
}, |
|
{ |
|
"epoch": 14.7, |
|
"learning_rate": 1.7543859649122807e-06, |
|
"loss": 0.056, |
|
"step": 1680 |
|
}, |
|
{ |
|
"epoch": 14.75, |
|
"learning_rate": 1.4619883040935671e-06, |
|
"loss": 0.1165, |
|
"step": 1685 |
|
}, |
|
{ |
|
"epoch": 14.79, |
|
"learning_rate": 1.1695906432748538e-06, |
|
"loss": 0.0744, |
|
"step": 1690 |
|
}, |
|
{ |
|
"epoch": 14.84, |
|
"learning_rate": 8.771929824561404e-07, |
|
"loss": 0.0856, |
|
"step": 1695 |
|
}, |
|
{ |
|
"epoch": 14.88, |
|
"learning_rate": 5.847953216374269e-07, |
|
"loss": 0.0425, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 14.92, |
|
"learning_rate": 2.9239766081871344e-07, |
|
"loss": 0.0536, |
|
"step": 1705 |
|
}, |
|
{ |
|
"epoch": 14.97, |
|
"learning_rate": 0.0, |
|
"loss": 0.1557, |
|
"step": 1710 |
|
}, |
|
{ |
|
"epoch": 14.97, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.0007466585957445204, |
|
"eval_runtime": 54.1734, |
|
"eval_samples_per_second": 22.483, |
|
"eval_steps_per_second": 2.824, |
|
"step": 1710 |
|
}, |
|
{ |
|
"epoch": 14.97, |
|
"step": 1710, |
|
"total_flos": 1.2584990004785971e+19, |
|
"train_loss": 0.38356898541164675, |
|
"train_runtime": 11197.9622, |
|
"train_samples_per_second": 4.891, |
|
"train_steps_per_second": 0.153 |
|
} |
|
], |
|
"max_steps": 1710, |
|
"num_train_epochs": 15, |
|
"total_flos": 1.2584990004785971e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|