| { | |
| "best_metric": 0.8733333333333333, | |
| "best_model_checkpoint": "bit-50-skin-lesions\\checkpoint-1062", | |
| "epoch": 33.984, | |
| "global_step": 1062, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.225806451612903e-06, | |
| "loss": 1.2002, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 6.451612903225806e-06, | |
| "loss": 0.9773, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.67741935483871e-06, | |
| "loss": 0.8102, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.5333333333333333, | |
| "eval_loss": 0.968501091003418, | |
| "eval_runtime": 21.6336, | |
| "eval_samples_per_second": 6.934, | |
| "eval_steps_per_second": 0.462, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.2903225806451613e-05, | |
| "loss": 0.699, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.7167, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.935483870967742e-05, | |
| "loss": 0.5819, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_accuracy": 0.74, | |
| "eval_loss": 0.6370717287063599, | |
| "eval_runtime": 20.2966, | |
| "eval_samples_per_second": 7.39, | |
| "eval_steps_per_second": 0.493, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 2.258064516129032e-05, | |
| "loss": 0.5839, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2.5806451612903226e-05, | |
| "loss": 0.547, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.9032258064516133e-05, | |
| "loss": 0.5664, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.6208174824714661, | |
| "eval_runtime": 20.1891, | |
| "eval_samples_per_second": 7.43, | |
| "eval_steps_per_second": 0.495, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.5493, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 3.548387096774194e-05, | |
| "loss": 0.5026, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 3.870967741935484e-05, | |
| "loss": 0.552, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7466666666666667, | |
| "eval_loss": 0.6024346947669983, | |
| "eval_runtime": 20.2094, | |
| "eval_samples_per_second": 7.422, | |
| "eval_steps_per_second": 0.495, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 4.1935483870967746e-05, | |
| "loss": 0.4447, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 4.516129032258064e-05, | |
| "loss": 0.5273, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.4998, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.76, | |
| "eval_loss": 0.5782171487808228, | |
| "eval_runtime": 19.9613, | |
| "eval_samples_per_second": 7.515, | |
| "eval_steps_per_second": 0.501, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 4.982078853046595e-05, | |
| "loss": 0.5239, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 4.9462365591397855e-05, | |
| "loss": 0.4935, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 4.910394265232976e-05, | |
| "loss": 0.4417, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "eval_accuracy": 0.78, | |
| "eval_loss": 0.504960298538208, | |
| "eval_runtime": 20.0953, | |
| "eval_samples_per_second": 7.464, | |
| "eval_steps_per_second": 0.498, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 4.874551971326165e-05, | |
| "loss": 0.428, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.4105, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 4.802867383512545e-05, | |
| "loss": 0.4161, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "eval_accuracy": 0.7666666666666667, | |
| "eval_loss": 0.6188395619392395, | |
| "eval_runtime": 20.1038, | |
| "eval_samples_per_second": 7.461, | |
| "eval_steps_per_second": 0.497, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 4.767025089605735e-05, | |
| "loss": 0.4169, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 4.731182795698925e-05, | |
| "loss": 0.306, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 4.695340501792115e-05, | |
| "loss": 0.3994, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.659498207885305e-05, | |
| "loss": 0.4077, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.630321741104126, | |
| "eval_runtime": 20.0628, | |
| "eval_samples_per_second": 7.477, | |
| "eval_steps_per_second": 0.498, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 4.6236559139784944e-05, | |
| "loss": 0.3623, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 4.5878136200716846e-05, | |
| "loss": 0.3911, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 4.551971326164875e-05, | |
| "loss": 0.4163, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.7933333333333333, | |
| "eval_loss": 0.548830509185791, | |
| "eval_runtime": 20.0908, | |
| "eval_samples_per_second": 7.466, | |
| "eval_steps_per_second": 0.498, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 4.516129032258064e-05, | |
| "loss": 0.319, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 4.4802867383512545e-05, | |
| "loss": 0.332, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.367, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "eval_accuracy": 0.8066666666666666, | |
| "eval_loss": 0.5251256227493286, | |
| "eval_runtime": 20.2039, | |
| "eval_samples_per_second": 7.424, | |
| "eval_steps_per_second": 0.495, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 4.408602150537635e-05, | |
| "loss": 0.4215, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 4.372759856630825e-05, | |
| "loss": 0.3571, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 4.3369175627240145e-05, | |
| "loss": 0.3391, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "eval_accuracy": 0.78, | |
| "eval_loss": 0.5417120456695557, | |
| "eval_runtime": 20.1843, | |
| "eval_samples_per_second": 7.432, | |
| "eval_steps_per_second": 0.495, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.3091, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 4.265232974910394e-05, | |
| "loss": 0.2611, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 4.2293906810035844e-05, | |
| "loss": 0.3298, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7933333333333333, | |
| "eval_loss": 0.4787960946559906, | |
| "eval_runtime": 20.0289, | |
| "eval_samples_per_second": 7.489, | |
| "eval_steps_per_second": 0.499, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 4.1935483870967746e-05, | |
| "loss": 0.2416, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 4.157706093189964e-05, | |
| "loss": 0.2494, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 4.121863799283154e-05, | |
| "loss": 0.3133, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.7733333333333333, | |
| "eval_loss": 0.6023210883140564, | |
| "eval_runtime": 19.8848, | |
| "eval_samples_per_second": 7.543, | |
| "eval_steps_per_second": 0.503, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 4.0860215053763444e-05, | |
| "loss": 0.2826, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 4.050179211469534e-05, | |
| "loss": 0.2571, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 4.014336917562724e-05, | |
| "loss": 0.2916, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "eval_accuracy": 0.76, | |
| "eval_loss": 0.5615163445472717, | |
| "eval_runtime": 19.8565, | |
| "eval_samples_per_second": 7.554, | |
| "eval_steps_per_second": 0.504, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 3.978494623655914e-05, | |
| "loss": 0.3033, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 3.9426523297491045e-05, | |
| "loss": 0.2611, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 3.906810035842295e-05, | |
| "loss": 0.2491, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "eval_accuracy": 0.84, | |
| "eval_loss": 0.4784340560436249, | |
| "eval_runtime": 20.1708, | |
| "eval_samples_per_second": 7.437, | |
| "eval_steps_per_second": 0.496, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 3.870967741935484e-05, | |
| "loss": 0.1961, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 3.8351254480286743e-05, | |
| "loss": 0.2239, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 3.799283154121864e-05, | |
| "loss": 0.2206, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.2213, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.5498819351196289, | |
| "eval_runtime": 20.1376, | |
| "eval_samples_per_second": 7.449, | |
| "eval_steps_per_second": 0.497, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 3.727598566308244e-05, | |
| "loss": 0.2294, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 3.691756272401434e-05, | |
| "loss": 0.228, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 3.655913978494624e-05, | |
| "loss": 0.2334, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.8133333333333334, | |
| "eval_loss": 0.5679303407669067, | |
| "eval_runtime": 19.8409, | |
| "eval_samples_per_second": 7.56, | |
| "eval_steps_per_second": 0.504, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 3.6200716845878134e-05, | |
| "loss": 0.1944, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 3.5842293906810036e-05, | |
| "loss": 0.1782, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 3.548387096774194e-05, | |
| "loss": 0.1882, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 17.98, | |
| "eval_accuracy": 0.82, | |
| "eval_loss": 0.5990158319473267, | |
| "eval_runtime": 19.6405, | |
| "eval_samples_per_second": 7.637, | |
| "eval_steps_per_second": 0.509, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 3.512544802867383e-05, | |
| "loss": 0.1918, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 3.4767025089605734e-05, | |
| "loss": 0.208, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 3.4408602150537636e-05, | |
| "loss": 0.2121, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 18.98, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.4990116357803345, | |
| "eval_runtime": 20.1236, | |
| "eval_samples_per_second": 7.454, | |
| "eval_steps_per_second": 0.497, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 3.405017921146954e-05, | |
| "loss": 0.1591, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 3.369175627240144e-05, | |
| "loss": 0.1472, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1456, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8066666666666666, | |
| "eval_loss": 0.7644553184509277, | |
| "eval_runtime": 19.8391, | |
| "eval_samples_per_second": 7.561, | |
| "eval_steps_per_second": 0.504, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 20.16, | |
| "learning_rate": 3.297491039426524e-05, | |
| "loss": 0.1569, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 3.261648745519714e-05, | |
| "loss": 0.1653, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.1938, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.8266666666666667, | |
| "eval_loss": 0.579462468624115, | |
| "eval_runtime": 19.9203, | |
| "eval_samples_per_second": 7.53, | |
| "eval_steps_per_second": 0.502, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 3.1899641577060935e-05, | |
| "loss": 0.1467, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 3.154121863799283e-05, | |
| "loss": 0.1463, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 3.118279569892473e-05, | |
| "loss": 0.1489, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 21.98, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.4865401089191437, | |
| "eval_runtime": 20.1519, | |
| "eval_samples_per_second": 7.443, | |
| "eval_steps_per_second": 0.496, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 3.0824372759856634e-05, | |
| "loss": 0.1771, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 3.046594982078853e-05, | |
| "loss": 0.1178, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 3.010752688172043e-05, | |
| "loss": 0.1887, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 22.98, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.641372561454773, | |
| "eval_runtime": 20.0159, | |
| "eval_samples_per_second": 7.494, | |
| "eval_steps_per_second": 0.5, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 23.04, | |
| "learning_rate": 2.974910394265233e-05, | |
| "loss": 0.1736, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 2.939068100358423e-05, | |
| "loss": 0.1307, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 2.9032258064516133e-05, | |
| "loss": 0.1716, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 2.8673835125448028e-05, | |
| "loss": 0.1713, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.84, | |
| "eval_loss": 0.5748192071914673, | |
| "eval_runtime": 20.2017, | |
| "eval_samples_per_second": 7.425, | |
| "eval_steps_per_second": 0.495, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "learning_rate": 2.831541218637993e-05, | |
| "loss": 0.1503, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 2.7956989247311828e-05, | |
| "loss": 0.1278, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 24.96, | |
| "learning_rate": 2.759856630824373e-05, | |
| "loss": 0.154, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.8266666666666667, | |
| "eval_loss": 0.5349760055541992, | |
| "eval_runtime": 20.1924, | |
| "eval_samples_per_second": 7.429, | |
| "eval_steps_per_second": 0.495, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 2.7240143369175632e-05, | |
| "loss": 0.0884, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 0.134, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 2.652329749103943e-05, | |
| "loss": 0.1232, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 25.98, | |
| "eval_accuracy": 0.8466666666666667, | |
| "eval_loss": 0.5574176907539368, | |
| "eval_runtime": 20.0038, | |
| "eval_samples_per_second": 7.499, | |
| "eval_steps_per_second": 0.5, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 2.616487455197133e-05, | |
| "loss": 0.1021, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 2.5806451612903226e-05, | |
| "loss": 0.1958, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 2.5448028673835127e-05, | |
| "loss": 0.1514, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 26.98, | |
| "eval_accuracy": 0.8666666666666667, | |
| "eval_loss": 0.4726710021495819, | |
| "eval_runtime": 20.1425, | |
| "eval_samples_per_second": 7.447, | |
| "eval_steps_per_second": 0.496, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 2.5089605734767026e-05, | |
| "loss": 0.1184, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 2.4731182795698928e-05, | |
| "loss": 0.1252, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 2.4372759856630826e-05, | |
| "loss": 0.0835, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8133333333333334, | |
| "eval_loss": 0.8025414943695068, | |
| "eval_runtime": 19.9723, | |
| "eval_samples_per_second": 7.51, | |
| "eval_steps_per_second": 0.501, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 28.16, | |
| "learning_rate": 2.4014336917562724e-05, | |
| "loss": 0.1916, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 28.48, | |
| "learning_rate": 2.3655913978494626e-05, | |
| "loss": 0.1547, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 2.3297491039426525e-05, | |
| "loss": 0.1012, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.8666666666666667, | |
| "eval_loss": 0.5923764705657959, | |
| "eval_runtime": 19.9464, | |
| "eval_samples_per_second": 7.52, | |
| "eval_steps_per_second": 0.501, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 29.12, | |
| "learning_rate": 2.2939068100358423e-05, | |
| "loss": 0.0884, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 2.258064516129032e-05, | |
| "loss": 0.0869, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.1328, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 29.98, | |
| "eval_accuracy": 0.86, | |
| "eval_loss": 0.5381821990013123, | |
| "eval_runtime": 20.537, | |
| "eval_samples_per_second": 7.304, | |
| "eval_steps_per_second": 0.487, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 30.08, | |
| "learning_rate": 2.1863799283154125e-05, | |
| "loss": 0.1074, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 30.4, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.1311, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 30.72, | |
| "learning_rate": 2.1146953405017922e-05, | |
| "loss": 0.1243, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 30.98, | |
| "eval_accuracy": 0.8466666666666667, | |
| "eval_loss": 0.5992811322212219, | |
| "eval_runtime": 19.7967, | |
| "eval_samples_per_second": 7.577, | |
| "eval_steps_per_second": 0.505, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 31.04, | |
| "learning_rate": 2.078853046594982e-05, | |
| "loss": 0.122, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 31.36, | |
| "learning_rate": 2.0430107526881722e-05, | |
| "loss": 0.0976, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 31.68, | |
| "learning_rate": 2.007168458781362e-05, | |
| "loss": 0.114, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 1.9713261648745522e-05, | |
| "loss": 0.0924, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8133333333333334, | |
| "eval_loss": 0.7414191961288452, | |
| "eval_runtime": 20.4518, | |
| "eval_samples_per_second": 7.334, | |
| "eval_steps_per_second": 0.489, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 32.32, | |
| "learning_rate": 1.935483870967742e-05, | |
| "loss": 0.117, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 32.64, | |
| "learning_rate": 1.899641577060932e-05, | |
| "loss": 0.1152, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 32.96, | |
| "learning_rate": 1.863799283154122e-05, | |
| "loss": 0.1101, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 32.99, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.7131091952323914, | |
| "eval_runtime": 20.5438, | |
| "eval_samples_per_second": 7.301, | |
| "eval_steps_per_second": 0.487, | |
| "step": 1031 | |
| }, | |
| { | |
| "epoch": 33.28, | |
| "learning_rate": 1.827956989247312e-05, | |
| "loss": 0.0776, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 33.6, | |
| "learning_rate": 1.7921146953405018e-05, | |
| "loss": 0.0753, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 33.92, | |
| "learning_rate": 1.7562724014336916e-05, | |
| "loss": 0.0785, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 33.98, | |
| "eval_accuracy": 0.8733333333333333, | |
| "eval_loss": 0.5796133279800415, | |
| "eval_runtime": 19.6695, | |
| "eval_samples_per_second": 7.626, | |
| "eval_steps_per_second": 0.508, | |
| "step": 1062 | |
| } | |
| ], | |
| "max_steps": 1550, | |
| "num_train_epochs": 50, | |
| "total_flos": 5.774646411362304e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |