|
{ |
|
"best_metric": 0.959917780061665, |
|
"best_model_checkpoint": "convnextv2-large-1k-224-finetuned-eurosat-50/checkpoint-1464", |
|
"epoch": 12.0, |
|
"global_step": 1464, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 1.8968133535660094e-07, |
|
"loss": 1.9544, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 3.793626707132019e-07, |
|
"loss": 1.954, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 5.690440060698028e-07, |
|
"loss": 1.951, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 7.587253414264037e-07, |
|
"loss": 1.9528, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 9.484066767830046e-07, |
|
"loss": 1.9471, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 1.1380880121396055e-06, |
|
"loss": 1.947, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 1.3277693474962064e-06, |
|
"loss": 1.9508, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 1.5174506828528075e-06, |
|
"loss": 1.9384, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 1.7071320182094082e-06, |
|
"loss": 1.948, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 1.8968133535660093e-06, |
|
"loss": 1.9439, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 2.0864946889226104e-06, |
|
"loss": 1.9423, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 2.276176024279211e-06, |
|
"loss": 1.9408, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 2.465857359635812e-06, |
|
"loss": 1.9368, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 2.655538694992413e-06, |
|
"loss": 1.9364, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 2.845220030349014e-06, |
|
"loss": 1.9306, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 3.034901365705615e-06, |
|
"loss": 1.9377, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 3.2245827010622157e-06, |
|
"loss": 1.9302, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 3.4142640364188163e-06, |
|
"loss": 1.9252, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 3.6039453717754174e-06, |
|
"loss": 1.9258, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 3.7936267071320185e-06, |
|
"loss": 1.9203, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 3.983308042488619e-06, |
|
"loss": 1.9125, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 4.172989377845221e-06, |
|
"loss": 1.9065, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 4.362670713201821e-06, |
|
"loss": 1.8906, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 4.552352048558422e-06, |
|
"loss": 1.9003, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.35868448098663924, |
|
"eval_loss": 1.8892042636871338, |
|
"eval_runtime": 11.8873, |
|
"eval_samples_per_second": 81.852, |
|
"eval_steps_per_second": 5.132, |
|
"step": 122 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 4.742033383915024e-06, |
|
"loss": 1.8889, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 4.931714719271624e-06, |
|
"loss": 1.8796, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 5.121396054628225e-06, |
|
"loss": 1.8824, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 5.311077389984826e-06, |
|
"loss": 1.8762, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 5.500758725341427e-06, |
|
"loss": 1.8633, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 5.690440060698028e-06, |
|
"loss": 1.853, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 5.8801213960546285e-06, |
|
"loss": 1.8513, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 6.06980273141123e-06, |
|
"loss": 1.8323, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 6.259484066767831e-06, |
|
"loss": 1.8144, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 6.449165402124431e-06, |
|
"loss": 1.8161, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 6.638846737481032e-06, |
|
"loss": 1.7914, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 6.828528072837633e-06, |
|
"loss": 1.7982, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 7.018209408194234e-06, |
|
"loss": 1.8019, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 7.207890743550835e-06, |
|
"loss": 1.773, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 7.3975720789074356e-06, |
|
"loss": 1.7587, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 7.587253414264037e-06, |
|
"loss": 1.7561, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 7.776934749620638e-06, |
|
"loss": 1.7305, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 7.966616084977238e-06, |
|
"loss": 1.7126, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 8.15629742033384e-06, |
|
"loss": 1.7, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 8.345978755690441e-06, |
|
"loss": 1.6841, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 8.535660091047042e-06, |
|
"loss": 1.7156, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"learning_rate": 8.725341426403643e-06, |
|
"loss": 1.6539, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.93, |
|
"learning_rate": 8.915022761760243e-06, |
|
"loss": 1.6598, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 1.97, |
|
"learning_rate": 9.104704097116844e-06, |
|
"loss": 1.6055, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.5765673175745119, |
|
"eval_loss": 1.5935580730438232, |
|
"eval_runtime": 11.9403, |
|
"eval_samples_per_second": 81.489, |
|
"eval_steps_per_second": 5.109, |
|
"step": 244 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 9.294385432473445e-06, |
|
"loss": 1.5524, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"learning_rate": 9.484066767830047e-06, |
|
"loss": 1.5695, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"learning_rate": 9.673748103186648e-06, |
|
"loss": 1.5425, |
|
"step": 255 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 9.863429438543249e-06, |
|
"loss": 1.5754, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 2.17, |
|
"learning_rate": 1.005311077389985e-05, |
|
"loss": 1.5203, |
|
"step": 265 |
|
}, |
|
{ |
|
"epoch": 2.21, |
|
"learning_rate": 1.024279210925645e-05, |
|
"loss": 1.5106, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 2.25, |
|
"learning_rate": 1.043247344461305e-05, |
|
"loss": 1.5314, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 2.3, |
|
"learning_rate": 1.0622154779969651e-05, |
|
"loss": 1.4853, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 2.34, |
|
"learning_rate": 1.0811836115326254e-05, |
|
"loss": 1.5059, |
|
"step": 285 |
|
}, |
|
{ |
|
"epoch": 2.38, |
|
"learning_rate": 1.1001517450682854e-05, |
|
"loss": 1.487, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 2.42, |
|
"learning_rate": 1.1191198786039455e-05, |
|
"loss": 1.4139, |
|
"step": 295 |
|
}, |
|
{ |
|
"epoch": 2.46, |
|
"learning_rate": 1.1380880121396056e-05, |
|
"loss": 1.4453, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 1.1570561456752656e-05, |
|
"loss": 1.4686, |
|
"step": 305 |
|
}, |
|
{ |
|
"epoch": 2.54, |
|
"learning_rate": 1.1760242792109257e-05, |
|
"loss": 1.4578, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 2.58, |
|
"learning_rate": 1.194992412746586e-05, |
|
"loss": 1.4197, |
|
"step": 315 |
|
}, |
|
{ |
|
"epoch": 2.62, |
|
"learning_rate": 1.213960546282246e-05, |
|
"loss": 1.3656, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 2.66, |
|
"learning_rate": 1.232928679817906e-05, |
|
"loss": 1.3697, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 2.7, |
|
"learning_rate": 1.2518968133535661e-05, |
|
"loss": 1.3767, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"learning_rate": 1.2708649468892262e-05, |
|
"loss": 1.3423, |
|
"step": 335 |
|
}, |
|
{ |
|
"epoch": 2.79, |
|
"learning_rate": 1.2898330804248863e-05, |
|
"loss": 1.3328, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 2.83, |
|
"learning_rate": 1.3088012139605463e-05, |
|
"loss": 1.35, |
|
"step": 345 |
|
}, |
|
{ |
|
"epoch": 2.87, |
|
"learning_rate": 1.3277693474962064e-05, |
|
"loss": 1.3423, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 2.91, |
|
"learning_rate": 1.3467374810318665e-05, |
|
"loss": 1.3148, |
|
"step": 355 |
|
}, |
|
{ |
|
"epoch": 2.95, |
|
"learning_rate": 1.3657056145675265e-05, |
|
"loss": 1.3198, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 2.99, |
|
"learning_rate": 1.3846737481031868e-05, |
|
"loss": 1.2982, |
|
"step": 365 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.6639260020554985, |
|
"eval_loss": 1.2567955255508423, |
|
"eval_runtime": 11.8557, |
|
"eval_samples_per_second": 82.07, |
|
"eval_steps_per_second": 5.145, |
|
"step": 366 |
|
}, |
|
{ |
|
"epoch": 3.03, |
|
"learning_rate": 1.4036418816388468e-05, |
|
"loss": 1.1929, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 3.07, |
|
"learning_rate": 1.4226100151745069e-05, |
|
"loss": 1.2679, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 3.11, |
|
"learning_rate": 1.441578148710167e-05, |
|
"loss": 1.2275, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 3.16, |
|
"learning_rate": 1.460546282245827e-05, |
|
"loss": 1.2417, |
|
"step": 385 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"learning_rate": 1.4795144157814871e-05, |
|
"loss": 1.2056, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 3.24, |
|
"learning_rate": 1.4984825493171473e-05, |
|
"loss": 1.1807, |
|
"step": 395 |
|
}, |
|
{ |
|
"epoch": 3.28, |
|
"learning_rate": 1.5174506828528074e-05, |
|
"loss": 1.106, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 3.32, |
|
"learning_rate": 1.5364188163884675e-05, |
|
"loss": 1.1657, |
|
"step": 405 |
|
}, |
|
{ |
|
"epoch": 3.36, |
|
"learning_rate": 1.5553869499241275e-05, |
|
"loss": 1.2021, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 3.4, |
|
"learning_rate": 1.5743550834597876e-05, |
|
"loss": 1.2094, |
|
"step": 415 |
|
}, |
|
{ |
|
"epoch": 3.44, |
|
"learning_rate": 1.5933232169954477e-05, |
|
"loss": 1.1491, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 3.48, |
|
"learning_rate": 1.6122913505311078e-05, |
|
"loss": 1.0782, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 3.52, |
|
"learning_rate": 1.631259484066768e-05, |
|
"loss": 1.0925, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 3.57, |
|
"learning_rate": 1.6502276176024282e-05, |
|
"loss": 1.1184, |
|
"step": 435 |
|
}, |
|
{ |
|
"epoch": 3.61, |
|
"learning_rate": 1.6691957511380883e-05, |
|
"loss": 1.1348, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 3.65, |
|
"learning_rate": 1.6881638846737484e-05, |
|
"loss": 1.0526, |
|
"step": 445 |
|
}, |
|
{ |
|
"epoch": 3.69, |
|
"learning_rate": 1.7071320182094084e-05, |
|
"loss": 0.9797, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 3.73, |
|
"learning_rate": 1.7261001517450685e-05, |
|
"loss": 1.0631, |
|
"step": 455 |
|
}, |
|
{ |
|
"epoch": 3.77, |
|
"learning_rate": 1.7450682852807286e-05, |
|
"loss": 1.0432, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 3.81, |
|
"learning_rate": 1.7640364188163886e-05, |
|
"loss": 0.9974, |
|
"step": 465 |
|
}, |
|
{ |
|
"epoch": 3.85, |
|
"learning_rate": 1.7830045523520487e-05, |
|
"loss": 1.0787, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 3.89, |
|
"learning_rate": 1.8019726858877088e-05, |
|
"loss": 1.0131, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 3.93, |
|
"learning_rate": 1.8209408194233688e-05, |
|
"loss": 1.0752, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 3.98, |
|
"learning_rate": 1.839908952959029e-05, |
|
"loss": 1.0273, |
|
"step": 485 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.7430626927029804, |
|
"eval_loss": 0.9558310508728027, |
|
"eval_runtime": 11.8822, |
|
"eval_samples_per_second": 81.887, |
|
"eval_steps_per_second": 5.134, |
|
"step": 488 |
|
}, |
|
{ |
|
"epoch": 4.02, |
|
"learning_rate": 1.858877086494689e-05, |
|
"loss": 0.9755, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 4.06, |
|
"learning_rate": 1.8778452200303494e-05, |
|
"loss": 0.9962, |
|
"step": 495 |
|
}, |
|
{ |
|
"epoch": 4.1, |
|
"learning_rate": 1.8968133535660094e-05, |
|
"loss": 0.9966, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 4.14, |
|
"learning_rate": 1.9157814871016695e-05, |
|
"loss": 0.9923, |
|
"step": 505 |
|
}, |
|
{ |
|
"epoch": 4.18, |
|
"learning_rate": 1.9347496206373296e-05, |
|
"loss": 0.9137, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 4.22, |
|
"learning_rate": 1.9537177541729896e-05, |
|
"loss": 1.0109, |
|
"step": 515 |
|
}, |
|
{ |
|
"epoch": 4.26, |
|
"learning_rate": 1.9726858877086497e-05, |
|
"loss": 0.9439, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 4.3, |
|
"learning_rate": 1.9916540212443098e-05, |
|
"loss": 0.9156, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 4.34, |
|
"learning_rate": 2.01062215477997e-05, |
|
"loss": 0.8519, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 4.39, |
|
"learning_rate": 2.02959028831563e-05, |
|
"loss": 0.9473, |
|
"step": 535 |
|
}, |
|
{ |
|
"epoch": 4.43, |
|
"learning_rate": 2.04855842185129e-05, |
|
"loss": 0.939, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 4.47, |
|
"learning_rate": 2.06752655538695e-05, |
|
"loss": 0.9095, |
|
"step": 545 |
|
}, |
|
{ |
|
"epoch": 4.51, |
|
"learning_rate": 2.08649468892261e-05, |
|
"loss": 0.8301, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 4.55, |
|
"learning_rate": 2.1054628224582702e-05, |
|
"loss": 0.8271, |
|
"step": 555 |
|
}, |
|
{ |
|
"epoch": 4.59, |
|
"learning_rate": 2.1244309559939302e-05, |
|
"loss": 0.857, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 4.63, |
|
"learning_rate": 2.1433990895295907e-05, |
|
"loss": 0.8767, |
|
"step": 565 |
|
}, |
|
{ |
|
"epoch": 4.67, |
|
"learning_rate": 2.1623672230652507e-05, |
|
"loss": 0.9534, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 4.71, |
|
"learning_rate": 2.1813353566009108e-05, |
|
"loss": 0.9347, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 4.75, |
|
"learning_rate": 2.200303490136571e-05, |
|
"loss": 0.7686, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 4.8, |
|
"learning_rate": 2.219271623672231e-05, |
|
"loss": 0.8167, |
|
"step": 585 |
|
}, |
|
{ |
|
"epoch": 4.84, |
|
"learning_rate": 2.238239757207891e-05, |
|
"loss": 0.8233, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 4.88, |
|
"learning_rate": 2.257207890743551e-05, |
|
"loss": 0.9185, |
|
"step": 595 |
|
}, |
|
{ |
|
"epoch": 4.92, |
|
"learning_rate": 2.276176024279211e-05, |
|
"loss": 0.8313, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 4.96, |
|
"learning_rate": 2.2951441578148712e-05, |
|
"loss": 0.9356, |
|
"step": 605 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 2.3141122913505313e-05, |
|
"loss": 0.7863, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_accuracy": 0.7965056526207606, |
|
"eval_loss": 0.7439751029014587, |
|
"eval_runtime": 12.0083, |
|
"eval_samples_per_second": 81.027, |
|
"eval_steps_per_second": 5.08, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 5.04, |
|
"learning_rate": 2.3330804248861913e-05, |
|
"loss": 0.8137, |
|
"step": 615 |
|
}, |
|
{ |
|
"epoch": 5.08, |
|
"learning_rate": 2.3520485584218514e-05, |
|
"loss": 0.8272, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 5.12, |
|
"learning_rate": 2.3710166919575115e-05, |
|
"loss": 0.7473, |
|
"step": 625 |
|
}, |
|
{ |
|
"epoch": 5.16, |
|
"learning_rate": 2.389984825493172e-05, |
|
"loss": 0.7376, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 5.2, |
|
"learning_rate": 2.408952959028832e-05, |
|
"loss": 0.7829, |
|
"step": 635 |
|
}, |
|
{ |
|
"epoch": 5.25, |
|
"learning_rate": 2.427921092564492e-05, |
|
"loss": 0.758, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 5.29, |
|
"learning_rate": 2.446889226100152e-05, |
|
"loss": 0.701, |
|
"step": 645 |
|
}, |
|
{ |
|
"epoch": 5.33, |
|
"learning_rate": 2.465857359635812e-05, |
|
"loss": 0.6879, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 5.37, |
|
"learning_rate": 2.4848254931714722e-05, |
|
"loss": 0.6456, |
|
"step": 655 |
|
}, |
|
{ |
|
"epoch": 5.41, |
|
"learning_rate": 2.5037936267071323e-05, |
|
"loss": 0.7036, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 5.45, |
|
"learning_rate": 2.5227617602427923e-05, |
|
"loss": 0.783, |
|
"step": 665 |
|
}, |
|
{ |
|
"epoch": 5.49, |
|
"learning_rate": 2.5417298937784524e-05, |
|
"loss": 0.6819, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 5.53, |
|
"learning_rate": 2.5606980273141125e-05, |
|
"loss": 0.6658, |
|
"step": 675 |
|
}, |
|
{ |
|
"epoch": 5.57, |
|
"learning_rate": 2.5796661608497725e-05, |
|
"loss": 0.8285, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 5.61, |
|
"learning_rate": 2.5986342943854326e-05, |
|
"loss": 0.7133, |
|
"step": 685 |
|
}, |
|
{ |
|
"epoch": 5.66, |
|
"learning_rate": 2.6176024279210927e-05, |
|
"loss": 0.7303, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 5.7, |
|
"learning_rate": 2.6365705614567527e-05, |
|
"loss": 0.6853, |
|
"step": 695 |
|
}, |
|
{ |
|
"epoch": 5.74, |
|
"learning_rate": 2.6555386949924128e-05, |
|
"loss": 0.6256, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 5.78, |
|
"learning_rate": 2.674506828528073e-05, |
|
"loss": 0.704, |
|
"step": 705 |
|
}, |
|
{ |
|
"epoch": 5.82, |
|
"learning_rate": 2.693474962063733e-05, |
|
"loss": 0.6546, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 5.86, |
|
"learning_rate": 2.712443095599393e-05, |
|
"loss": 0.6958, |
|
"step": 715 |
|
}, |
|
{ |
|
"epoch": 5.9, |
|
"learning_rate": 2.731411229135053e-05, |
|
"loss": 0.8073, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 5.94, |
|
"learning_rate": 2.7503793626707135e-05, |
|
"loss": 0.8113, |
|
"step": 725 |
|
}, |
|
{ |
|
"epoch": 5.98, |
|
"learning_rate": 2.7693474962063735e-05, |
|
"loss": 0.8142, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_accuracy": 0.8304213771839671, |
|
"eval_loss": 0.6205604076385498, |
|
"eval_runtime": 11.9351, |
|
"eval_samples_per_second": 81.524, |
|
"eval_steps_per_second": 5.111, |
|
"step": 732 |
|
}, |
|
{ |
|
"epoch": 6.02, |
|
"learning_rate": 2.7883156297420336e-05, |
|
"loss": 0.7085, |
|
"step": 735 |
|
}, |
|
{ |
|
"epoch": 6.07, |
|
"learning_rate": 2.8072837632776937e-05, |
|
"loss": 0.5364, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 6.11, |
|
"learning_rate": 2.8262518968133538e-05, |
|
"loss": 0.6429, |
|
"step": 745 |
|
}, |
|
{ |
|
"epoch": 6.15, |
|
"learning_rate": 2.8452200303490138e-05, |
|
"loss": 0.6991, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 6.19, |
|
"learning_rate": 2.864188163884674e-05, |
|
"loss": 0.6271, |
|
"step": 755 |
|
}, |
|
{ |
|
"epoch": 6.23, |
|
"learning_rate": 2.883156297420334e-05, |
|
"loss": 0.5728, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 6.27, |
|
"learning_rate": 2.902124430955994e-05, |
|
"loss": 0.6842, |
|
"step": 765 |
|
}, |
|
{ |
|
"epoch": 6.31, |
|
"learning_rate": 2.921092564491654e-05, |
|
"loss": 0.6012, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 6.35, |
|
"learning_rate": 2.940060698027314e-05, |
|
"loss": 0.7262, |
|
"step": 775 |
|
}, |
|
{ |
|
"epoch": 6.39, |
|
"learning_rate": 2.9590288315629742e-05, |
|
"loss": 0.6369, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 6.43, |
|
"learning_rate": 2.9779969650986346e-05, |
|
"loss": 0.6995, |
|
"step": 785 |
|
}, |
|
{ |
|
"epoch": 6.48, |
|
"learning_rate": 2.9969650986342947e-05, |
|
"loss": 0.6273, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 6.52, |
|
"learning_rate": 3.0159332321699548e-05, |
|
"loss": 0.5492, |
|
"step": 795 |
|
}, |
|
{ |
|
"epoch": 6.56, |
|
"learning_rate": 3.0349013657056148e-05, |
|
"loss": 0.6101, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 6.6, |
|
"learning_rate": 3.0538694992412746e-05, |
|
"loss": 0.687, |
|
"step": 805 |
|
}, |
|
{ |
|
"epoch": 6.64, |
|
"learning_rate": 3.072837632776935e-05, |
|
"loss": 0.5513, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 6.68, |
|
"learning_rate": 3.091805766312595e-05, |
|
"loss": 0.6282, |
|
"step": 815 |
|
}, |
|
{ |
|
"epoch": 6.72, |
|
"learning_rate": 3.110773899848255e-05, |
|
"loss": 0.4794, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 6.76, |
|
"learning_rate": 3.129742033383915e-05, |
|
"loss": 0.6553, |
|
"step": 825 |
|
}, |
|
{ |
|
"epoch": 6.8, |
|
"learning_rate": 3.148710166919575e-05, |
|
"loss": 0.5745, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 6.84, |
|
"learning_rate": 3.167678300455235e-05, |
|
"loss": 0.5344, |
|
"step": 835 |
|
}, |
|
{ |
|
"epoch": 6.89, |
|
"learning_rate": 3.1866464339908954e-05, |
|
"loss": 0.4892, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 6.93, |
|
"learning_rate": 3.205614567526555e-05, |
|
"loss": 0.5903, |
|
"step": 845 |
|
}, |
|
{ |
|
"epoch": 6.97, |
|
"learning_rate": 3.2245827010622155e-05, |
|
"loss": 0.6118, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_accuracy": 0.868448098663926, |
|
"eval_loss": 0.4672134518623352, |
|
"eval_runtime": 12.226, |
|
"eval_samples_per_second": 79.585, |
|
"eval_steps_per_second": 4.989, |
|
"step": 854 |
|
}, |
|
{ |
|
"epoch": 7.01, |
|
"learning_rate": 3.243550834597875e-05, |
|
"loss": 0.5181, |
|
"step": 855 |
|
}, |
|
{ |
|
"epoch": 7.05, |
|
"learning_rate": 3.262518968133536e-05, |
|
"loss": 0.3732, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 7.09, |
|
"learning_rate": 3.281487101669196e-05, |
|
"loss": 0.4032, |
|
"step": 865 |
|
}, |
|
{ |
|
"epoch": 7.13, |
|
"learning_rate": 3.3004552352048564e-05, |
|
"loss": 0.5019, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 7.17, |
|
"learning_rate": 3.319423368740516e-05, |
|
"loss": 0.4093, |
|
"step": 875 |
|
}, |
|
{ |
|
"epoch": 7.21, |
|
"learning_rate": 3.3383915022761766e-05, |
|
"loss": 0.4367, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 7.25, |
|
"learning_rate": 3.357359635811836e-05, |
|
"loss": 0.4733, |
|
"step": 885 |
|
}, |
|
{ |
|
"epoch": 7.3, |
|
"learning_rate": 3.376327769347497e-05, |
|
"loss": 0.5154, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 7.34, |
|
"learning_rate": 3.3952959028831564e-05, |
|
"loss": 0.5145, |
|
"step": 895 |
|
}, |
|
{ |
|
"epoch": 7.38, |
|
"learning_rate": 3.414264036418817e-05, |
|
"loss": 0.508, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 7.42, |
|
"learning_rate": 3.4332321699544766e-05, |
|
"loss": 0.526, |
|
"step": 905 |
|
}, |
|
{ |
|
"epoch": 7.46, |
|
"learning_rate": 3.452200303490137e-05, |
|
"loss": 0.5291, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 7.5, |
|
"learning_rate": 3.471168437025797e-05, |
|
"loss": 0.3899, |
|
"step": 915 |
|
}, |
|
{ |
|
"epoch": 7.54, |
|
"learning_rate": 3.490136570561457e-05, |
|
"loss": 0.5636, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 7.58, |
|
"learning_rate": 3.509104704097117e-05, |
|
"loss": 0.4793, |
|
"step": 925 |
|
}, |
|
{ |
|
"epoch": 7.62, |
|
"learning_rate": 3.528072837632777e-05, |
|
"loss": 0.503, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 7.66, |
|
"learning_rate": 3.547040971168437e-05, |
|
"loss": 0.4772, |
|
"step": 935 |
|
}, |
|
{ |
|
"epoch": 7.7, |
|
"learning_rate": 3.5660091047040974e-05, |
|
"loss": 0.4556, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 7.75, |
|
"learning_rate": 3.584977238239757e-05, |
|
"loss": 0.5154, |
|
"step": 945 |
|
}, |
|
{ |
|
"epoch": 7.79, |
|
"learning_rate": 3.6039453717754175e-05, |
|
"loss": 0.5092, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 7.83, |
|
"learning_rate": 3.622913505311077e-05, |
|
"loss": 0.4981, |
|
"step": 955 |
|
}, |
|
{ |
|
"epoch": 7.87, |
|
"learning_rate": 3.6418816388467377e-05, |
|
"loss": 0.4195, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 7.91, |
|
"learning_rate": 3.6608497723823974e-05, |
|
"loss": 0.5142, |
|
"step": 965 |
|
}, |
|
{ |
|
"epoch": 7.95, |
|
"learning_rate": 3.679817905918058e-05, |
|
"loss": 0.4527, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 7.99, |
|
"learning_rate": 3.6987860394537175e-05, |
|
"loss": 0.4776, |
|
"step": 975 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_accuracy": 0.9075025693730729, |
|
"eval_loss": 0.3755611181259155, |
|
"eval_runtime": 11.9045, |
|
"eval_samples_per_second": 81.734, |
|
"eval_steps_per_second": 5.124, |
|
"step": 976 |
|
}, |
|
{ |
|
"epoch": 8.03, |
|
"learning_rate": 3.717754172989378e-05, |
|
"loss": 0.338, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 8.07, |
|
"learning_rate": 3.7367223065250377e-05, |
|
"loss": 0.4652, |
|
"step": 985 |
|
}, |
|
{ |
|
"epoch": 8.11, |
|
"learning_rate": 3.755690440060699e-05, |
|
"loss": 0.4183, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 8.16, |
|
"learning_rate": 3.7746585735963585e-05, |
|
"loss": 0.3755, |
|
"step": 995 |
|
}, |
|
{ |
|
"epoch": 8.2, |
|
"learning_rate": 3.793626707132019e-05, |
|
"loss": 0.3371, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 8.24, |
|
"learning_rate": 3.8125948406676786e-05, |
|
"loss": 0.3297, |
|
"step": 1005 |
|
}, |
|
{ |
|
"epoch": 8.28, |
|
"learning_rate": 3.831562974203339e-05, |
|
"loss": 0.3811, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 8.32, |
|
"learning_rate": 3.850531107738999e-05, |
|
"loss": 0.4417, |
|
"step": 1015 |
|
}, |
|
{ |
|
"epoch": 8.36, |
|
"learning_rate": 3.869499241274659e-05, |
|
"loss": 0.5017, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 8.4, |
|
"learning_rate": 3.888467374810319e-05, |
|
"loss": 0.6332, |
|
"step": 1025 |
|
}, |
|
{ |
|
"epoch": 8.44, |
|
"learning_rate": 3.907435508345979e-05, |
|
"loss": 0.562, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 8.48, |
|
"learning_rate": 3.926403641881639e-05, |
|
"loss": 0.5705, |
|
"step": 1035 |
|
}, |
|
{ |
|
"epoch": 8.52, |
|
"learning_rate": 3.9453717754172994e-05, |
|
"loss": 0.5141, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 8.57, |
|
"learning_rate": 3.964339908952959e-05, |
|
"loss": 0.4335, |
|
"step": 1045 |
|
}, |
|
{ |
|
"epoch": 8.61, |
|
"learning_rate": 3.9833080424886195e-05, |
|
"loss": 0.4115, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 8.65, |
|
"learning_rate": 4.002276176024279e-05, |
|
"loss": 0.5901, |
|
"step": 1055 |
|
}, |
|
{ |
|
"epoch": 8.69, |
|
"learning_rate": 4.02124430955994e-05, |
|
"loss": 0.4286, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 8.73, |
|
"learning_rate": 4.0402124430955994e-05, |
|
"loss": 0.5023, |
|
"step": 1065 |
|
}, |
|
{ |
|
"epoch": 8.77, |
|
"learning_rate": 4.05918057663126e-05, |
|
"loss": 0.4989, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 8.81, |
|
"learning_rate": 4.0781487101669195e-05, |
|
"loss": 0.431, |
|
"step": 1075 |
|
}, |
|
{ |
|
"epoch": 8.85, |
|
"learning_rate": 4.09711684370258e-05, |
|
"loss": 0.3568, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 8.89, |
|
"learning_rate": 4.11608497723824e-05, |
|
"loss": 0.3954, |
|
"step": 1085 |
|
}, |
|
{ |
|
"epoch": 8.93, |
|
"learning_rate": 4.1350531107739e-05, |
|
"loss": 0.3494, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 8.98, |
|
"learning_rate": 4.15402124430956e-05, |
|
"loss": 0.4176, |
|
"step": 1095 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_accuracy": 0.9301130524152107, |
|
"eval_loss": 0.30650582909584045, |
|
"eval_runtime": 11.9828, |
|
"eval_samples_per_second": 81.2, |
|
"eval_steps_per_second": 5.091, |
|
"step": 1098 |
|
}, |
|
{ |
|
"epoch": 9.02, |
|
"learning_rate": 4.17298937784522e-05, |
|
"loss": 0.3928, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 9.06, |
|
"learning_rate": 4.19195751138088e-05, |
|
"loss": 0.3845, |
|
"step": 1105 |
|
}, |
|
{ |
|
"epoch": 9.1, |
|
"learning_rate": 4.2109256449165404e-05, |
|
"loss": 0.27, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 9.14, |
|
"learning_rate": 4.2298937784522e-05, |
|
"loss": 0.3805, |
|
"step": 1115 |
|
}, |
|
{ |
|
"epoch": 9.18, |
|
"learning_rate": 4.2488619119878605e-05, |
|
"loss": 0.4107, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 9.22, |
|
"learning_rate": 4.267830045523521e-05, |
|
"loss": 0.5721, |
|
"step": 1125 |
|
}, |
|
{ |
|
"epoch": 9.26, |
|
"learning_rate": 4.286798179059181e-05, |
|
"loss": 0.3963, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 9.3, |
|
"learning_rate": 4.305766312594841e-05, |
|
"loss": 0.4238, |
|
"step": 1135 |
|
}, |
|
{ |
|
"epoch": 9.34, |
|
"learning_rate": 4.3247344461305014e-05, |
|
"loss": 0.3778, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 9.39, |
|
"learning_rate": 4.343702579666161e-05, |
|
"loss": 0.37, |
|
"step": 1145 |
|
}, |
|
{ |
|
"epoch": 9.43, |
|
"learning_rate": 4.3626707132018216e-05, |
|
"loss": 0.3632, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 9.47, |
|
"learning_rate": 4.381638846737481e-05, |
|
"loss": 0.3126, |
|
"step": 1155 |
|
}, |
|
{ |
|
"epoch": 9.51, |
|
"learning_rate": 4.400606980273142e-05, |
|
"loss": 0.3515, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 9.55, |
|
"learning_rate": 4.4195751138088014e-05, |
|
"loss": 0.3789, |
|
"step": 1165 |
|
}, |
|
{ |
|
"epoch": 9.59, |
|
"learning_rate": 4.438543247344462e-05, |
|
"loss": 0.3313, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 9.63, |
|
"learning_rate": 4.4575113808801216e-05, |
|
"loss": 0.3433, |
|
"step": 1175 |
|
}, |
|
{ |
|
"epoch": 9.67, |
|
"learning_rate": 4.476479514415782e-05, |
|
"loss": 0.4228, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 9.71, |
|
"learning_rate": 4.495447647951442e-05, |
|
"loss": 0.4865, |
|
"step": 1185 |
|
}, |
|
{ |
|
"epoch": 9.75, |
|
"learning_rate": 4.514415781487102e-05, |
|
"loss": 0.4787, |
|
"step": 1190 |
|
}, |
|
{ |
|
"epoch": 9.8, |
|
"learning_rate": 4.533383915022762e-05, |
|
"loss": 0.3663, |
|
"step": 1195 |
|
}, |
|
{ |
|
"epoch": 9.84, |
|
"learning_rate": 4.552352048558422e-05, |
|
"loss": 0.3406, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 9.88, |
|
"learning_rate": 4.571320182094082e-05, |
|
"loss": 0.4317, |
|
"step": 1205 |
|
}, |
|
{ |
|
"epoch": 9.92, |
|
"learning_rate": 4.5902883156297424e-05, |
|
"loss": 0.4784, |
|
"step": 1210 |
|
}, |
|
{ |
|
"epoch": 9.96, |
|
"learning_rate": 4.609256449165402e-05, |
|
"loss": 0.4965, |
|
"step": 1215 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 4.6282245827010625e-05, |
|
"loss": 0.282, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"eval_accuracy": 0.9403905447070915, |
|
"eval_loss": 0.2586072087287903, |
|
"eval_runtime": 11.8947, |
|
"eval_samples_per_second": 81.801, |
|
"eval_steps_per_second": 5.128, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 10.04, |
|
"learning_rate": 4.647192716236722e-05, |
|
"loss": 0.3029, |
|
"step": 1225 |
|
}, |
|
{ |
|
"epoch": 10.08, |
|
"learning_rate": 4.6661608497723826e-05, |
|
"loss": 0.3526, |
|
"step": 1230 |
|
}, |
|
{ |
|
"epoch": 10.12, |
|
"learning_rate": 4.6851289833080424e-05, |
|
"loss": 0.3814, |
|
"step": 1235 |
|
}, |
|
{ |
|
"epoch": 10.16, |
|
"learning_rate": 4.704097116843703e-05, |
|
"loss": 0.2817, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 10.2, |
|
"learning_rate": 4.7230652503793625e-05, |
|
"loss": 0.445, |
|
"step": 1245 |
|
}, |
|
{ |
|
"epoch": 10.25, |
|
"learning_rate": 4.742033383915023e-05, |
|
"loss": 0.4277, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 10.29, |
|
"learning_rate": 4.761001517450683e-05, |
|
"loss": 0.403, |
|
"step": 1255 |
|
}, |
|
{ |
|
"epoch": 10.33, |
|
"learning_rate": 4.779969650986344e-05, |
|
"loss": 0.3276, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 10.37, |
|
"learning_rate": 4.7989377845220035e-05, |
|
"loss": 0.3324, |
|
"step": 1265 |
|
}, |
|
{ |
|
"epoch": 10.41, |
|
"learning_rate": 4.817905918057664e-05, |
|
"loss": 0.3084, |
|
"step": 1270 |
|
}, |
|
{ |
|
"epoch": 10.45, |
|
"learning_rate": 4.8368740515933236e-05, |
|
"loss": 0.4288, |
|
"step": 1275 |
|
}, |
|
{ |
|
"epoch": 10.49, |
|
"learning_rate": 4.855842185128984e-05, |
|
"loss": 0.4472, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 10.53, |
|
"learning_rate": 4.874810318664644e-05, |
|
"loss": 0.3513, |
|
"step": 1285 |
|
}, |
|
{ |
|
"epoch": 10.57, |
|
"learning_rate": 4.893778452200304e-05, |
|
"loss": 0.5989, |
|
"step": 1290 |
|
}, |
|
{ |
|
"epoch": 10.61, |
|
"learning_rate": 4.912746585735964e-05, |
|
"loss": 0.4029, |
|
"step": 1295 |
|
}, |
|
{ |
|
"epoch": 10.66, |
|
"learning_rate": 4.931714719271624e-05, |
|
"loss": 0.4033, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 10.7, |
|
"learning_rate": 4.950682852807284e-05, |
|
"loss": 0.3184, |
|
"step": 1305 |
|
}, |
|
{ |
|
"epoch": 10.74, |
|
"learning_rate": 4.9696509863429444e-05, |
|
"loss": 0.3415, |
|
"step": 1310 |
|
}, |
|
{ |
|
"epoch": 10.78, |
|
"learning_rate": 4.988619119878604e-05, |
|
"loss": 0.3692, |
|
"step": 1315 |
|
}, |
|
{ |
|
"epoch": 10.82, |
|
"learning_rate": 4.9315068493150684e-05, |
|
"loss": 0.2073, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 10.86, |
|
"learning_rate": 4.7602739726027403e-05, |
|
"loss": 0.3404, |
|
"step": 1325 |
|
}, |
|
{ |
|
"epoch": 10.9, |
|
"learning_rate": 4.589041095890411e-05, |
|
"loss": 0.4278, |
|
"step": 1330 |
|
}, |
|
{ |
|
"epoch": 10.94, |
|
"learning_rate": 4.417808219178082e-05, |
|
"loss": 0.3163, |
|
"step": 1335 |
|
}, |
|
{ |
|
"epoch": 10.98, |
|
"learning_rate": 4.2465753424657536e-05, |
|
"loss": 0.306, |
|
"step": 1340 |
|
}, |
|
{ |
|
"epoch": 11.0, |
|
"eval_accuracy": 0.947584789311408, |
|
"eval_loss": 0.20978114008903503, |
|
"eval_runtime": 11.8894, |
|
"eval_samples_per_second": 81.838, |
|
"eval_steps_per_second": 5.131, |
|
"step": 1342 |
|
}, |
|
{ |
|
"epoch": 11.02, |
|
"learning_rate": 4.075342465753425e-05, |
|
"loss": 0.3474, |
|
"step": 1345 |
|
}, |
|
{ |
|
"epoch": 11.07, |
|
"learning_rate": 3.904109589041096e-05, |
|
"loss": 0.2353, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 11.11, |
|
"learning_rate": 3.7328767123287675e-05, |
|
"loss": 0.2806, |
|
"step": 1355 |
|
}, |
|
{ |
|
"epoch": 11.15, |
|
"learning_rate": 3.561643835616438e-05, |
|
"loss": 0.2532, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 11.19, |
|
"learning_rate": 3.39041095890411e-05, |
|
"loss": 0.2483, |
|
"step": 1365 |
|
}, |
|
{ |
|
"epoch": 11.23, |
|
"learning_rate": 3.219178082191781e-05, |
|
"loss": 0.2504, |
|
"step": 1370 |
|
}, |
|
{ |
|
"epoch": 11.27, |
|
"learning_rate": 3.047945205479452e-05, |
|
"loss": 0.26, |
|
"step": 1375 |
|
}, |
|
{ |
|
"epoch": 11.31, |
|
"learning_rate": 2.8767123287671234e-05, |
|
"loss": 0.3612, |
|
"step": 1380 |
|
}, |
|
{ |
|
"epoch": 11.35, |
|
"learning_rate": 2.7054794520547947e-05, |
|
"loss": 0.297, |
|
"step": 1385 |
|
}, |
|
{ |
|
"epoch": 11.39, |
|
"learning_rate": 2.534246575342466e-05, |
|
"loss": 0.3056, |
|
"step": 1390 |
|
}, |
|
{ |
|
"epoch": 11.43, |
|
"learning_rate": 2.363013698630137e-05, |
|
"loss": 0.2741, |
|
"step": 1395 |
|
}, |
|
{ |
|
"epoch": 11.48, |
|
"learning_rate": 2.1917808219178083e-05, |
|
"loss": 0.279, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 11.52, |
|
"learning_rate": 2.0205479452054797e-05, |
|
"loss": 0.2717, |
|
"step": 1405 |
|
}, |
|
{ |
|
"epoch": 11.56, |
|
"learning_rate": 1.8493150684931506e-05, |
|
"loss": 0.2219, |
|
"step": 1410 |
|
}, |
|
{ |
|
"epoch": 11.6, |
|
"learning_rate": 1.678082191780822e-05, |
|
"loss": 0.1998, |
|
"step": 1415 |
|
}, |
|
{ |
|
"epoch": 11.64, |
|
"learning_rate": 1.5068493150684931e-05, |
|
"loss": 0.1851, |
|
"step": 1420 |
|
}, |
|
{ |
|
"epoch": 11.68, |
|
"learning_rate": 1.3356164383561646e-05, |
|
"loss": 0.184, |
|
"step": 1425 |
|
}, |
|
{ |
|
"epoch": 11.72, |
|
"learning_rate": 1.1643835616438355e-05, |
|
"loss": 0.2026, |
|
"step": 1430 |
|
}, |
|
{ |
|
"epoch": 11.76, |
|
"learning_rate": 9.931506849315069e-06, |
|
"loss": 0.1976, |
|
"step": 1435 |
|
}, |
|
{ |
|
"epoch": 11.8, |
|
"learning_rate": 8.21917808219178e-06, |
|
"loss": 0.2929, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 11.84, |
|
"learning_rate": 6.506849315068493e-06, |
|
"loss": 0.1399, |
|
"step": 1445 |
|
}, |
|
{ |
|
"epoch": 11.89, |
|
"learning_rate": 4.7945205479452054e-06, |
|
"loss": 0.2801, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 11.93, |
|
"learning_rate": 3.0821917808219177e-06, |
|
"loss": 0.1279, |
|
"step": 1455 |
|
}, |
|
{ |
|
"epoch": 11.97, |
|
"learning_rate": 1.3698630136986302e-06, |
|
"loss": 0.2006, |
|
"step": 1460 |
|
}, |
|
{ |
|
"epoch": 12.0, |
|
"eval_accuracy": 0.959917780061665, |
|
"eval_loss": 0.16148746013641357, |
|
"eval_runtime": 11.9707, |
|
"eval_samples_per_second": 81.282, |
|
"eval_steps_per_second": 5.096, |
|
"step": 1464 |
|
}, |
|
{ |
|
"epoch": 12.0, |
|
"step": 1464, |
|
"total_flos": 8.283619840147513e+18, |
|
"train_loss": 0.8678286689552454, |
|
"train_runtime": 9120.8487, |
|
"train_samples_per_second": 5.119, |
|
"train_steps_per_second": 0.161 |
|
} |
|
], |
|
"max_steps": 1464, |
|
"num_train_epochs": 12, |
|
"total_flos": 8.283619840147513e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|