|
{ |
|
"best_metric": 0.0007819964084774256, |
|
"best_model_checkpoint": "./vit-base-blur/checkpoint-1100", |
|
"epoch": 12.0, |
|
"global_step": 1176, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 9.914965986394558e-05, |
|
"loss": 0.5188, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 9.829931972789116e-05, |
|
"loss": 0.1389, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 9.744897959183674e-05, |
|
"loss": 0.0755, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 9.659863945578231e-05, |
|
"loss": 0.1305, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 9.574829931972789e-05, |
|
"loss": 0.0554, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 9.489795918367348e-05, |
|
"loss": 0.0147, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 9.404761904761905e-05, |
|
"loss": 0.0139, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 9.319727891156463e-05, |
|
"loss": 0.0534, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 9.234693877551021e-05, |
|
"loss": 0.0101, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 9.149659863945579e-05, |
|
"loss": 0.0082, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.010711735114455223, |
|
"eval_runtime": 105.4365, |
|
"eval_samples_per_second": 1.641, |
|
"eval_steps_per_second": 0.209, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 9.07312925170068e-05, |
|
"loss": 0.0375, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 8.988095238095238e-05, |
|
"loss": 0.0296, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 8.903061224489796e-05, |
|
"loss": 0.0466, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 8.818027210884354e-05, |
|
"loss": 0.0289, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 8.732993197278912e-05, |
|
"loss": 0.0084, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 8.64795918367347e-05, |
|
"loss": 0.0185, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 8.562925170068028e-05, |
|
"loss": 0.0879, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 8.477891156462585e-05, |
|
"loss": 0.0612, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 8.392857142857144e-05, |
|
"loss": 0.0176, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 8.3078231292517e-05, |
|
"loss": 0.0079, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.005197448190301657, |
|
"eval_runtime": 5.9181, |
|
"eval_samples_per_second": 29.232, |
|
"eval_steps_per_second": 3.717, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 8.222789115646259e-05, |
|
"loss": 0.005, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 8.137755102040817e-05, |
|
"loss": 0.0226, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 2.35, |
|
"learning_rate": 8.052721088435375e-05, |
|
"loss": 0.0894, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 2.45, |
|
"learning_rate": 7.967687074829932e-05, |
|
"loss": 0.0067, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 2.55, |
|
"learning_rate": 7.882653061224489e-05, |
|
"loss": 0.0039, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 2.65, |
|
"learning_rate": 7.797619047619048e-05, |
|
"loss": 0.0035, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 2.76, |
|
"learning_rate": 7.712585034013606e-05, |
|
"loss": 0.0034, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 2.86, |
|
"learning_rate": 7.627551020408163e-05, |
|
"loss": 0.0032, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 2.96, |
|
"learning_rate": 7.542517006802722e-05, |
|
"loss": 0.0032, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 3.06, |
|
"learning_rate": 7.457482993197279e-05, |
|
"loss": 0.0029, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 3.06, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.0028241325635463, |
|
"eval_runtime": 4.5591, |
|
"eval_samples_per_second": 37.946, |
|
"eval_steps_per_second": 4.826, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 3.16, |
|
"learning_rate": 7.372448979591837e-05, |
|
"loss": 0.0028, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 3.27, |
|
"learning_rate": 7.287414965986395e-05, |
|
"loss": 0.0027, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 3.37, |
|
"learning_rate": 7.202380952380953e-05, |
|
"loss": 0.0026, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 3.47, |
|
"learning_rate": 7.117346938775511e-05, |
|
"loss": 0.0025, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 3.57, |
|
"learning_rate": 7.032312925170068e-05, |
|
"loss": 0.0024, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 3.67, |
|
"learning_rate": 6.947278911564627e-05, |
|
"loss": 0.0023, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 3.78, |
|
"learning_rate": 6.862244897959184e-05, |
|
"loss": 0.0022, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 3.88, |
|
"learning_rate": 6.777210884353741e-05, |
|
"loss": 0.0021, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 3.98, |
|
"learning_rate": 6.6921768707483e-05, |
|
"loss": 0.0021, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 4.08, |
|
"learning_rate": 6.607142857142857e-05, |
|
"loss": 0.002, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 4.08, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.001991536468267441, |
|
"eval_runtime": 5.3318, |
|
"eval_samples_per_second": 32.447, |
|
"eval_steps_per_second": 4.126, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 4.18, |
|
"learning_rate": 6.522108843537415e-05, |
|
"loss": 0.002, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 4.29, |
|
"learning_rate": 6.437074829931973e-05, |
|
"loss": 0.0019, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 4.39, |
|
"learning_rate": 6.352040816326531e-05, |
|
"loss": 0.0019, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 4.49, |
|
"learning_rate": 6.267006802721088e-05, |
|
"loss": 0.0018, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 4.59, |
|
"learning_rate": 6.181972789115646e-05, |
|
"loss": 0.0018, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 4.69, |
|
"learning_rate": 6.0969387755102046e-05, |
|
"loss": 0.0017, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 4.8, |
|
"learning_rate": 6.011904761904762e-05, |
|
"loss": 0.0017, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 4.9, |
|
"learning_rate": 5.92687074829932e-05, |
|
"loss": 0.0016, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 5.841836734693877e-05, |
|
"loss": 0.0016, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 5.1, |
|
"learning_rate": 5.756802721088436e-05, |
|
"loss": 0.0016, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 5.1, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.0015397485112771392, |
|
"eval_runtime": 5.4131, |
|
"eval_samples_per_second": 31.959, |
|
"eval_steps_per_second": 4.064, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 5.2, |
|
"learning_rate": 5.671768707482994e-05, |
|
"loss": 0.0015, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 5.31, |
|
"learning_rate": 5.586734693877551e-05, |
|
"loss": 0.0015, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 5.41, |
|
"learning_rate": 5.501700680272109e-05, |
|
"loss": 0.0015, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 5.51, |
|
"learning_rate": 5.4166666666666664e-05, |
|
"loss": 0.0014, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 5.61, |
|
"learning_rate": 5.331632653061225e-05, |
|
"loss": 0.0014, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 5.71, |
|
"learning_rate": 5.246598639455783e-05, |
|
"loss": 0.0014, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 5.82, |
|
"learning_rate": 5.1615646258503404e-05, |
|
"loss": 0.0014, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 5.92, |
|
"learning_rate": 5.076530612244898e-05, |
|
"loss": 0.0013, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 6.02, |
|
"learning_rate": 4.991496598639456e-05, |
|
"loss": 0.0013, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 6.12, |
|
"learning_rate": 4.906462585034014e-05, |
|
"loss": 0.0013, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 6.12, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.0012603328796103597, |
|
"eval_runtime": 6.365, |
|
"eval_samples_per_second": 27.18, |
|
"eval_steps_per_second": 3.456, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 6.22, |
|
"learning_rate": 4.8214285714285716e-05, |
|
"loss": 0.0013, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 6.33, |
|
"learning_rate": 4.7363945578231296e-05, |
|
"loss": 0.0012, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 6.43, |
|
"learning_rate": 4.651360544217687e-05, |
|
"loss": 0.0012, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 6.53, |
|
"learning_rate": 4.566326530612245e-05, |
|
"loss": 0.0012, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 6.63, |
|
"learning_rate": 4.4812925170068035e-05, |
|
"loss": 0.0012, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 6.73, |
|
"learning_rate": 4.396258503401361e-05, |
|
"loss": 0.0012, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 6.84, |
|
"learning_rate": 4.311224489795919e-05, |
|
"loss": 0.0011, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 6.94, |
|
"learning_rate": 4.226190476190476e-05, |
|
"loss": 0.0011, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 7.04, |
|
"learning_rate": 4.141156462585034e-05, |
|
"loss": 0.0011, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 7.14, |
|
"learning_rate": 4.056122448979592e-05, |
|
"loss": 0.0011, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 7.14, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.0010760421864688396, |
|
"eval_runtime": 5.8839, |
|
"eval_samples_per_second": 29.402, |
|
"eval_steps_per_second": 3.739, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 7.24, |
|
"learning_rate": 3.97108843537415e-05, |
|
"loss": 0.0011, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 7.35, |
|
"learning_rate": 3.886054421768708e-05, |
|
"loss": 0.0011, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 7.45, |
|
"learning_rate": 3.801020408163265e-05, |
|
"loss": 0.001, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 7.55, |
|
"learning_rate": 3.715986394557823e-05, |
|
"loss": 0.001, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 7.65, |
|
"learning_rate": 3.630952380952381e-05, |
|
"loss": 0.001, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 7.76, |
|
"learning_rate": 3.5459183673469385e-05, |
|
"loss": 0.001, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 7.86, |
|
"learning_rate": 3.460884353741497e-05, |
|
"loss": 0.001, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 7.96, |
|
"learning_rate": 3.3758503401360545e-05, |
|
"loss": 0.001, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 8.06, |
|
"learning_rate": 3.2908163265306125e-05, |
|
"loss": 0.001, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 8.16, |
|
"learning_rate": 3.2057823129251705e-05, |
|
"loss": 0.001, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 8.16, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.0009508325601927936, |
|
"eval_runtime": 4.4253, |
|
"eval_samples_per_second": 39.093, |
|
"eval_steps_per_second": 4.971, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 8.27, |
|
"learning_rate": 3.120748299319728e-05, |
|
"loss": 0.0009, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 8.37, |
|
"learning_rate": 3.0357142857142857e-05, |
|
"loss": 0.0009, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 8.47, |
|
"learning_rate": 2.950680272108844e-05, |
|
"loss": 0.0009, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 8.57, |
|
"learning_rate": 2.8656462585034017e-05, |
|
"loss": 0.0009, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 8.67, |
|
"learning_rate": 2.7806122448979593e-05, |
|
"loss": 0.0009, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 8.78, |
|
"learning_rate": 2.695578231292517e-05, |
|
"loss": 0.0009, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 8.88, |
|
"learning_rate": 2.610544217687075e-05, |
|
"loss": 0.0009, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 8.98, |
|
"learning_rate": 2.5255102040816326e-05, |
|
"loss": 0.0009, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 9.08, |
|
"learning_rate": 2.4404761904761906e-05, |
|
"loss": 0.0009, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 9.18, |
|
"learning_rate": 2.3554421768707485e-05, |
|
"loss": 0.0009, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 9.18, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.0008663248154334724, |
|
"eval_runtime": 5.3859, |
|
"eval_samples_per_second": 32.121, |
|
"eval_steps_per_second": 4.085, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 9.29, |
|
"learning_rate": 2.2704081632653062e-05, |
|
"loss": 0.0009, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 9.39, |
|
"learning_rate": 2.1853741496598638e-05, |
|
"loss": 0.0009, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 9.49, |
|
"learning_rate": 2.100340136054422e-05, |
|
"loss": 0.0009, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 9.59, |
|
"learning_rate": 2.0153061224489798e-05, |
|
"loss": 0.0008, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 9.69, |
|
"learning_rate": 1.9302721088435374e-05, |
|
"loss": 0.0008, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 9.8, |
|
"learning_rate": 1.8452380952380954e-05, |
|
"loss": 0.0008, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 9.9, |
|
"learning_rate": 1.760204081632653e-05, |
|
"loss": 0.0008, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 1.675170068027211e-05, |
|
"loss": 0.0008, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 10.1, |
|
"learning_rate": 1.590136054421769e-05, |
|
"loss": 0.0008, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 10.2, |
|
"learning_rate": 1.5051020408163266e-05, |
|
"loss": 0.0008, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 10.2, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.0008117146790027618, |
|
"eval_runtime": 4.9611, |
|
"eval_samples_per_second": 34.871, |
|
"eval_steps_per_second": 4.435, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 10.31, |
|
"learning_rate": 1.4200680272108843e-05, |
|
"loss": 0.0008, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 10.41, |
|
"learning_rate": 1.3350340136054423e-05, |
|
"loss": 0.0008, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 10.51, |
|
"learning_rate": 1.25e-05, |
|
"loss": 0.0008, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 10.61, |
|
"learning_rate": 1.1649659863945579e-05, |
|
"loss": 0.0008, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 10.71, |
|
"learning_rate": 1.0799319727891157e-05, |
|
"loss": 0.0008, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 10.82, |
|
"learning_rate": 9.948979591836735e-06, |
|
"loss": 0.0008, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 10.92, |
|
"learning_rate": 9.098639455782313e-06, |
|
"loss": 0.0008, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 11.02, |
|
"learning_rate": 8.248299319727891e-06, |
|
"loss": 0.0008, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 11.12, |
|
"learning_rate": 7.39795918367347e-06, |
|
"loss": 0.0008, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 11.22, |
|
"learning_rate": 6.547619047619048e-06, |
|
"loss": 0.0008, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 11.22, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.0007819964084774256, |
|
"eval_runtime": 4.6463, |
|
"eval_samples_per_second": 37.234, |
|
"eval_steps_per_second": 4.735, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 11.33, |
|
"learning_rate": 5.697278911564626e-06, |
|
"loss": 0.0008, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 11.43, |
|
"learning_rate": 4.846938775510204e-06, |
|
"loss": 0.0008, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 11.53, |
|
"learning_rate": 3.996598639455783e-06, |
|
"loss": 0.0008, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 11.63, |
|
"learning_rate": 3.146258503401361e-06, |
|
"loss": 0.0008, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 11.73, |
|
"learning_rate": 2.295918367346939e-06, |
|
"loss": 0.0008, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 11.84, |
|
"learning_rate": 1.4455782312925172e-06, |
|
"loss": 0.0008, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 11.94, |
|
"learning_rate": 5.952380952380952e-07, |
|
"loss": 0.0008, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 12.0, |
|
"step": 1176, |
|
"total_flos": 1.4460005262082867e+18, |
|
"train_loss": 0.013737765663116536, |
|
"train_runtime": 2175.34, |
|
"train_samples_per_second": 8.578, |
|
"train_steps_per_second": 0.541 |
|
} |
|
], |
|
"max_steps": 1176, |
|
"num_train_epochs": 12, |
|
"total_flos": 1.4460005262082867e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|