| { | |
| "best_metric": 0.87, | |
| "best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-1356", | |
| "epoch": 12.0, | |
| "global_step": 1356, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.1061946902654867e-06, | |
| "loss": 2.3091, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 2.2123893805309734e-06, | |
| "loss": 2.3013, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 3.3185840707964607e-06, | |
| "loss": 2.304, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.424778761061947e-06, | |
| "loss": 2.307, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 5.5309734513274346e-06, | |
| "loss": 2.3035, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 6.6371681415929215e-06, | |
| "loss": 2.2975, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.743362831858407e-06, | |
| "loss": 2.2995, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.849557522123894e-06, | |
| "loss": 2.2945, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.95575221238938e-06, | |
| "loss": 2.2868, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1061946902654869e-05, | |
| "loss": 2.2764, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.2168141592920354e-05, | |
| "loss": 2.2802, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.3274336283185843e-05, | |
| "loss": 2.2647, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.4380530973451328e-05, | |
| "loss": 2.2792, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.5486725663716813e-05, | |
| "loss": 2.2499, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.6592920353982302e-05, | |
| "loss": 2.2809, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.7699115044247787e-05, | |
| "loss": 2.2683, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.8805309734513272e-05, | |
| "loss": 2.2492, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.991150442477876e-05, | |
| "loss": 2.239, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 2.101769911504425e-05, | |
| "loss": 2.2239, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.2123893805309738e-05, | |
| "loss": 2.1822, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.3230088495575223e-05, | |
| "loss": 2.1901, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.433628318584071e-05, | |
| "loss": 2.2018, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.37, | |
| "eval_loss": 2.124462842941284, | |
| "eval_runtime": 37.2852, | |
| "eval_samples_per_second": 2.682, | |
| "eval_steps_per_second": 0.349, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 2.5442477876106197e-05, | |
| "loss": 2.1462, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 2.6548672566371686e-05, | |
| "loss": 2.1083, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2.7654867256637168e-05, | |
| "loss": 2.0828, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 2.8761061946902656e-05, | |
| "loss": 2.0594, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 2.9867256637168145e-05, | |
| "loss": 2.0813, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.097345132743363e-05, | |
| "loss": 2.0167, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.185840707964602e-05, | |
| "loss": 1.9729, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.296460176991151e-05, | |
| "loss": 1.9886, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 3.407079646017699e-05, | |
| "loss": 1.9951, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 3.517699115044248e-05, | |
| "loss": 1.9228, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 3.628318584070797e-05, | |
| "loss": 1.9038, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 3.7389380530973455e-05, | |
| "loss": 1.857, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 3.849557522123894e-05, | |
| "loss": 1.922, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 3.9601769911504426e-05, | |
| "loss": 1.8138, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.0707964601769914e-05, | |
| "loss": 1.7358, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.1814159292035396e-05, | |
| "loss": 1.6802, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 4.2920353982300885e-05, | |
| "loss": 1.6438, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 4.4026548672566373e-05, | |
| "loss": 1.67, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 4.491150442477876e-05, | |
| "loss": 1.8038, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 4.579646017699115e-05, | |
| "loss": 1.7205, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 4.690265486725664e-05, | |
| "loss": 1.7188, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 4.800884955752213e-05, | |
| "loss": 1.5285, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 4.911504424778761e-05, | |
| "loss": 1.5528, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.56, | |
| "eval_loss": 1.5200048685073853, | |
| "eval_runtime": 36.9619, | |
| "eval_samples_per_second": 2.705, | |
| "eval_steps_per_second": 0.352, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 4.997541789577188e-05, | |
| "loss": 1.5776, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 4.985250737463127e-05, | |
| "loss": 1.5497, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 4.972959685349066e-05, | |
| "loss": 1.4853, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 4.960668633235005e-05, | |
| "loss": 1.5263, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 4.9483775811209444e-05, | |
| "loss": 1.4766, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 4.936086529006883e-05, | |
| "loss": 1.4554, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 4.923795476892822e-05, | |
| "loss": 1.3716, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 4.911504424778761e-05, | |
| "loss": 1.3669, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 4.8992133726647006e-05, | |
| "loss": 1.4348, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 4.8869223205506394e-05, | |
| "loss": 1.275, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 4.874631268436578e-05, | |
| "loss": 1.4206, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 4.862340216322517e-05, | |
| "loss": 1.4962, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.850049164208457e-05, | |
| "loss": 1.2934, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 4.8377581120943956e-05, | |
| "loss": 1.263, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 4.825467059980335e-05, | |
| "loss": 1.2592, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 4.813176007866273e-05, | |
| "loss": 1.1302, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.800884955752213e-05, | |
| "loss": 1.242, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 4.788593903638152e-05, | |
| "loss": 1.2154, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 4.776302851524091e-05, | |
| "loss": 1.1873, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 4.7640117994100294e-05, | |
| "loss": 1.2688, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 4.751720747295968e-05, | |
| "loss": 1.1488, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 4.739429695181908e-05, | |
| "loss": 1.2506, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.71, | |
| "eval_loss": 1.1110644340515137, | |
| "eval_runtime": 37.2461, | |
| "eval_samples_per_second": 2.685, | |
| "eval_steps_per_second": 0.349, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 4.727138643067847e-05, | |
| "loss": 1.2124, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 4.714847590953786e-05, | |
| "loss": 1.1278, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 4.7025565388397244e-05, | |
| "loss": 1.1197, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 4.690265486725664e-05, | |
| "loss": 0.9486, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 4.677974434611603e-05, | |
| "loss": 1.0949, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 4.6656833824975424e-05, | |
| "loss": 1.1837, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 4.655850540806293e-05, | |
| "loss": 1.0059, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 4.643559488692232e-05, | |
| "loss": 1.0395, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 4.631268436578171e-05, | |
| "loss": 1.1674, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 4.6189773844641105e-05, | |
| "loss": 0.9608, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 4.606686332350049e-05, | |
| "loss": 1.2654, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 4.594395280235988e-05, | |
| "loss": 0.8788, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 4.582104228121927e-05, | |
| "loss": 0.9846, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 4.5698131760078666e-05, | |
| "loss": 0.8597, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 4.5575221238938055e-05, | |
| "loss": 1.1485, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 4.545231071779745e-05, | |
| "loss": 1.0469, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 4.532940019665683e-05, | |
| "loss": 0.9581, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 4.520648967551623e-05, | |
| "loss": 0.9821, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 4.5083579154375616e-05, | |
| "loss": 1.0122, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 4.496066863323501e-05, | |
| "loss": 0.8543, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 4.48377581120944e-05, | |
| "loss": 0.8246, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 4.471484759095379e-05, | |
| "loss": 0.891, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 4.459193706981318e-05, | |
| "loss": 1.0517, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.74, | |
| "eval_loss": 0.950592041015625, | |
| "eval_runtime": 37.0565, | |
| "eval_samples_per_second": 2.699, | |
| "eval_steps_per_second": 0.351, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 4.446902654867257e-05, | |
| "loss": 0.7031, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 4.434611602753196e-05, | |
| "loss": 0.6235, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 4.422320550639135e-05, | |
| "loss": 0.8002, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 4.410029498525074e-05, | |
| "loss": 0.9738, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 4.397738446411013e-05, | |
| "loss": 0.8511, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 4.385447394296952e-05, | |
| "loss": 0.6335, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 4.373156342182891e-05, | |
| "loss": 0.644, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 4.36086529006883e-05, | |
| "loss": 0.8481, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 4.348574237954769e-05, | |
| "loss": 0.6972, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 4.3362831858407084e-05, | |
| "loss": 0.8044, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 4.323992133726647e-05, | |
| "loss": 0.7073, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 4.311701081612586e-05, | |
| "loss": 0.8473, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 4.301868239921337e-05, | |
| "loss": 0.7983, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 4.2895771878072765e-05, | |
| "loss": 0.5702, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 4.2772861356932154e-05, | |
| "loss": 0.649, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 4.264995083579155e-05, | |
| "loss": 0.6669, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 4.252704031465093e-05, | |
| "loss": 0.5829, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 4.2404129793510327e-05, | |
| "loss": 0.65, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 4.2281219272369715e-05, | |
| "loss": 0.81, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 4.215830875122911e-05, | |
| "loss": 0.7507, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 4.20353982300885e-05, | |
| "loss": 0.6655, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 4.191248770894789e-05, | |
| "loss": 0.6181, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.178957718780728e-05, | |
| "loss": 0.8272, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.83, | |
| "eval_loss": 0.7394164800643921, | |
| "eval_runtime": 37.0651, | |
| "eval_samples_per_second": 2.698, | |
| "eval_steps_per_second": 0.351, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.6379, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 4.154375614552606e-05, | |
| "loss": 0.5593, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 4.142084562438545e-05, | |
| "loss": 0.524, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 4.129793510324484e-05, | |
| "loss": 0.4926, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 4.1175024582104233e-05, | |
| "loss": 0.6712, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 4.105211406096362e-05, | |
| "loss": 0.59, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 4.092920353982301e-05, | |
| "loss": 0.3684, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 4.08062930186824e-05, | |
| "loss": 0.5484, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 4.068338249754179e-05, | |
| "loss": 0.4718, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 4.0560471976401183e-05, | |
| "loss": 0.5205, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 4.043756145526057e-05, | |
| "loss": 0.4103, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 4.031465093411996e-05, | |
| "loss": 0.6238, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 4.019174041297935e-05, | |
| "loss": 0.391, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 4.0068829891838745e-05, | |
| "loss": 0.626, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 3.9945919370698133e-05, | |
| "loss": 0.5142, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 3.982300884955752e-05, | |
| "loss": 0.5664, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 3.970009832841691e-05, | |
| "loss": 0.3242, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 3.9577187807276306e-05, | |
| "loss": 0.4262, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 3.9454277286135695e-05, | |
| "loss": 0.6169, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 3.9331366764995083e-05, | |
| "loss": 0.436, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 3.920845624385447e-05, | |
| "loss": 0.2636, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 3.908554572271387e-05, | |
| "loss": 0.3728, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.81, | |
| "eval_loss": 0.6849124431610107, | |
| "eval_runtime": 37.0876, | |
| "eval_samples_per_second": 2.696, | |
| "eval_steps_per_second": 0.351, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 3.8962635201573256e-05, | |
| "loss": 0.4045, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 3.883972468043265e-05, | |
| "loss": 0.2084, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 3.8716814159292034e-05, | |
| "loss": 0.3604, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 3.859390363815143e-05, | |
| "loss": 0.3663, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 3.847099311701082e-05, | |
| "loss": 0.3161, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 3.834808259587021e-05, | |
| "loss": 0.4456, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 3.82251720747296e-05, | |
| "loss": 0.2935, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 3.810226155358899e-05, | |
| "loss": 0.2577, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 3.797935103244838e-05, | |
| "loss": 0.2841, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 3.7856440511307774e-05, | |
| "loss": 0.2892, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 3.773352999016716e-05, | |
| "loss": 0.2578, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 3.7610619469026545e-05, | |
| "loss": 0.2938, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 3.748770894788594e-05, | |
| "loss": 0.2936, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 3.736479842674533e-05, | |
| "loss": 0.426, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 3.7241887905604724e-05, | |
| "loss": 0.2328, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 3.711897738446411e-05, | |
| "loss": 0.2715, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 3.69960668633235e-05, | |
| "loss": 0.3068, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 3.687315634218289e-05, | |
| "loss": 0.4009, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 3.6750245821042286e-05, | |
| "loss": 0.3685, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 3.6627335299901674e-05, | |
| "loss": 0.3065, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 3.650442477876106e-05, | |
| "loss": 0.2677, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 3.638151425762045e-05, | |
| "loss": 0.3096, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 3.625860373647985e-05, | |
| "loss": 0.3878, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.647432267665863, | |
| "eval_runtime": 36.7252, | |
| "eval_samples_per_second": 2.723, | |
| "eval_steps_per_second": 0.354, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 3.6135693215339236e-05, | |
| "loss": 0.1663, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 3.6012782694198624e-05, | |
| "loss": 0.2787, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 3.588987217305801e-05, | |
| "loss": 0.1559, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 3.576696165191741e-05, | |
| "loss": 0.1331, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 3.56440511307768e-05, | |
| "loss": 0.1643, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 3.5521140609636186e-05, | |
| "loss": 0.1594, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 3.54228121927237e-05, | |
| "loss": 0.1871, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 3.529990167158309e-05, | |
| "loss": 0.1745, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 3.517699115044248e-05, | |
| "loss": 0.125, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 3.5054080629301874e-05, | |
| "loss": 0.1259, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 3.493117010816126e-05, | |
| "loss": 0.2476, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 3.480825958702065e-05, | |
| "loss": 0.0858, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 3.468534906588004e-05, | |
| "loss": 0.1988, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 3.4562438544739435e-05, | |
| "loss": 0.1398, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 3.4439528023598824e-05, | |
| "loss": 0.1934, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 3.431661750245821e-05, | |
| "loss": 0.0942, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 3.41937069813176e-05, | |
| "loss": 0.1991, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 3.407079646017699e-05, | |
| "loss": 0.1436, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 3.3947885939036385e-05, | |
| "loss": 0.0865, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 3.3824975417895774e-05, | |
| "loss": 0.1405, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 3.370206489675516e-05, | |
| "loss": 0.285, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 3.357915437561455e-05, | |
| "loss": 0.1119, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.83, | |
| "eval_loss": 0.5846229791641235, | |
| "eval_runtime": 37.7892, | |
| "eval_samples_per_second": 2.646, | |
| "eval_steps_per_second": 0.344, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 3.3456243854473946e-05, | |
| "loss": 0.1696, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1067, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 3.3210422812192724e-05, | |
| "loss": 0.0852, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 3.308751229105211e-05, | |
| "loss": 0.1015, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 3.296460176991151e-05, | |
| "loss": 0.1699, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 3.2841691248770896e-05, | |
| "loss": 0.0691, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 3.2718780727630285e-05, | |
| "loss": 0.0661, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 3.2595870206489674e-05, | |
| "loss": 0.0512, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 3.247295968534907e-05, | |
| "loss": 0.1003, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 3.235004916420846e-05, | |
| "loss": 0.0523, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 3.222713864306785e-05, | |
| "loss": 0.0893, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 3.2104228121927235e-05, | |
| "loss": 0.053, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "learning_rate": 3.198131760078663e-05, | |
| "loss": 0.0592, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 3.185840707964602e-05, | |
| "loss": 0.0779, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "learning_rate": 3.1735496558505414e-05, | |
| "loss": 0.0611, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 3.16125860373648e-05, | |
| "loss": 0.0776, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 3.148967551622419e-05, | |
| "loss": 0.1722, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 3.136676499508358e-05, | |
| "loss": 0.0809, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 3.124385447394297e-05, | |
| "loss": 0.185, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 3.1120943952802364e-05, | |
| "loss": 0.0357, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 3.0998033431661746e-05, | |
| "loss": 0.082, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "learning_rate": 3.087512291052114e-05, | |
| "loss": 0.1928, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 3.075221238938053e-05, | |
| "loss": 0.1312, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.84, | |
| "eval_loss": 0.5652107000350952, | |
| "eval_runtime": 36.9689, | |
| "eval_samples_per_second": 2.705, | |
| "eval_steps_per_second": 0.352, | |
| "step": 1017 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 3.0629301868239926e-05, | |
| "loss": 0.0416, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 3.050639134709931e-05, | |
| "loss": 0.1309, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 3.0383480825958703e-05, | |
| "loss": 0.1201, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 3.0260570304818092e-05, | |
| "loss": 0.0265, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 3.0137659783677484e-05, | |
| "loss": 0.0291, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 3.0014749262536872e-05, | |
| "loss": 0.0306, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "learning_rate": 2.9891838741396268e-05, | |
| "loss": 0.0262, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 9.34, | |
| "learning_rate": 2.9768928220255653e-05, | |
| "loss": 0.0262, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 2.964601769911505e-05, | |
| "loss": 0.0243, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 2.9523107177974434e-05, | |
| "loss": 0.0314, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 2.940019665683383e-05, | |
| "loss": 0.0218, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "learning_rate": 2.9277286135693215e-05, | |
| "loss": 0.0294, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 2.915437561455261e-05, | |
| "loss": 0.0187, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 2.9031465093412e-05, | |
| "loss": 0.0614, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 2.890855457227139e-05, | |
| "loss": 0.0269, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 9.69, | |
| "learning_rate": 2.878564405113078e-05, | |
| "loss": 0.0591, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 2.866273352999017e-05, | |
| "loss": 0.0282, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 2.853982300884956e-05, | |
| "loss": 0.0242, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 2.8416912487708945e-05, | |
| "loss": 0.0709, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 9.87, | |
| "learning_rate": 2.829400196656834e-05, | |
| "loss": 0.0158, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 2.8171091445427726e-05, | |
| "loss": 0.1044, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "learning_rate": 2.804818092428712e-05, | |
| "loss": 0.0404, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 2.792527040314651e-05, | |
| "loss": 0.0149, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.84, | |
| "eval_loss": 0.707106351852417, | |
| "eval_runtime": 37.5782, | |
| "eval_samples_per_second": 2.661, | |
| "eval_steps_per_second": 0.346, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 2.7802359882005902e-05, | |
| "loss": 0.1165, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 10.09, | |
| "learning_rate": 2.767944936086529e-05, | |
| "loss": 0.0129, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 10.13, | |
| "learning_rate": 2.7556538839724683e-05, | |
| "loss": 0.0624, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 10.18, | |
| "learning_rate": 2.743362831858407e-05, | |
| "loss": 0.0272, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 2.7310717797443463e-05, | |
| "loss": 0.0176, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 10.27, | |
| "learning_rate": 2.7187807276302852e-05, | |
| "loss": 0.0138, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 10.31, | |
| "learning_rate": 2.7064896755162244e-05, | |
| "loss": 0.0138, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 10.35, | |
| "learning_rate": 2.6941986234021633e-05, | |
| "loss": 0.0177, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 2.6819075712881025e-05, | |
| "loss": 0.024, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 10.44, | |
| "learning_rate": 2.6696165191740413e-05, | |
| "loss": 0.0676, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "learning_rate": 2.6573254670599805e-05, | |
| "loss": 0.0112, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 10.53, | |
| "learning_rate": 2.6450344149459194e-05, | |
| "loss": 0.011, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 10.58, | |
| "learning_rate": 2.6327433628318586e-05, | |
| "loss": 0.0118, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 2.6204523107177975e-05, | |
| "loss": 0.018, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 10.66, | |
| "learning_rate": 2.6081612586037367e-05, | |
| "loss": 0.017, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 2.5958702064896756e-05, | |
| "loss": 0.0117, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "learning_rate": 2.583579154375615e-05, | |
| "loss": 0.01, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "learning_rate": 2.5712881022615536e-05, | |
| "loss": 0.0101, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 10.84, | |
| "learning_rate": 2.558997050147493e-05, | |
| "loss": 0.017, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 2.5467059980334317e-05, | |
| "loss": 0.0094, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 10.93, | |
| "learning_rate": 2.5344149459193706e-05, | |
| "loss": 0.0085, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 2.5221238938053098e-05, | |
| "loss": 0.0154, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.84, | |
| "eval_loss": 0.7669206261634827, | |
| "eval_runtime": 37.5505, | |
| "eval_samples_per_second": 2.663, | |
| "eval_steps_per_second": 0.346, | |
| "step": 1243 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 2.5098328416912486e-05, | |
| "loss": 0.0085, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "learning_rate": 2.4975417895771878e-05, | |
| "loss": 0.0091, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 2.485250737463127e-05, | |
| "loss": 0.0086, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 11.15, | |
| "learning_rate": 2.4729596853490662e-05, | |
| "loss": 0.0087, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 11.19, | |
| "learning_rate": 2.460668633235005e-05, | |
| "loss": 0.008, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 2.4483775811209443e-05, | |
| "loss": 0.0078, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 11.28, | |
| "learning_rate": 2.436086529006883e-05, | |
| "loss": 0.0076, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 11.33, | |
| "learning_rate": 2.4237954768928224e-05, | |
| "loss": 0.0074, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 11.37, | |
| "learning_rate": 2.411504424778761e-05, | |
| "loss": 0.0076, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 11.42, | |
| "learning_rate": 2.3992133726647e-05, | |
| "loss": 0.0071, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 11.46, | |
| "learning_rate": 2.3869223205506393e-05, | |
| "loss": 0.0078, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "learning_rate": 2.374631268436578e-05, | |
| "loss": 0.0069, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 11.55, | |
| "learning_rate": 2.3623402163225174e-05, | |
| "loss": 0.0071, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "learning_rate": 2.3500491642084562e-05, | |
| "loss": 0.0086, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 2.3377581120943954e-05, | |
| "loss": 0.0075, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "learning_rate": 2.3254670599803343e-05, | |
| "loss": 0.0072, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 11.73, | |
| "learning_rate": 2.3131760078662735e-05, | |
| "loss": 0.0078, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 11.77, | |
| "learning_rate": 2.3008849557522124e-05, | |
| "loss": 0.0398, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 11.81, | |
| "learning_rate": 2.2885939036381516e-05, | |
| "loss": 0.0069, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "learning_rate": 2.2763028515240904e-05, | |
| "loss": 0.0069, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 11.9, | |
| "learning_rate": 2.2640117994100296e-05, | |
| "loss": 0.0057, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "learning_rate": 2.2517207472959685e-05, | |
| "loss": 0.0108, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 2.2394296951819077e-05, | |
| "loss": 0.1238, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.87, | |
| "eval_loss": 0.7153857350349426, | |
| "eval_runtime": 37.3772, | |
| "eval_samples_per_second": 2.675, | |
| "eval_steps_per_second": 0.348, | |
| "step": 1356 | |
| } | |
| ], | |
| "max_steps": 2260, | |
| "num_train_epochs": 20, | |
| "total_flos": 3.6803929647744e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |