| { | |
| "best_metric": 0.99, | |
| "best_model_checkpoint": "./Beit-LungCancerbeit2e-5/checkpoint-3297", | |
| "epoch": 30.0, | |
| "global_step": 4710, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.397027600849257e-07, | |
| "loss": 1.7055, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 7.643312101910829e-07, | |
| "loss": 1.7461, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.1889596602972401e-06, | |
| "loss": 1.5472, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.613588110403397e-06, | |
| "loss": 1.2834, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.0382165605095544e-06, | |
| "loss": 1.0778, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.4628450106157116e-06, | |
| "loss": 0.9111, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.8874734607218683e-06, | |
| "loss": 0.8629, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 3.3121019108280255e-06, | |
| "loss": 0.7923, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.7367303609341826e-06, | |
| "loss": 0.7736, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.16135881104034e-06, | |
| "loss": 0.6986, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.585987261146497e-06, | |
| "loss": 0.6813, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 5.0106157112526545e-06, | |
| "loss": 0.6384, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5.435244161358811e-06, | |
| "loss": 0.6333, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.859872611464969e-06, | |
| "loss": 0.5907, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 6.284501061571126e-06, | |
| "loss": 0.6305, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6375, | |
| "eval_loss": 0.718781590461731, | |
| "eval_runtime": 67.1207, | |
| "eval_samples_per_second": 5.959, | |
| "eval_steps_per_second": 0.745, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 6.709129511677282e-06, | |
| "loss": 0.6018, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 7.091295116772824e-06, | |
| "loss": 0.5399, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 7.515923566878982e-06, | |
| "loss": 0.5101, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 7.940552016985139e-06, | |
| "loss": 0.5172, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 8.365180467091297e-06, | |
| "loss": 0.5191, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 8.789808917197454e-06, | |
| "loss": 0.4911, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 9.21443736730361e-06, | |
| "loss": 0.511, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 9.639065817409767e-06, | |
| "loss": 0.4754, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 1.0063694267515924e-05, | |
| "loss": 0.4507, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 1.048832271762208e-05, | |
| "loss": 0.4725, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 1.0912951167728239e-05, | |
| "loss": 0.4585, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 1.1337579617834396e-05, | |
| "loss": 0.4159, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.1762208067940553e-05, | |
| "loss": 0.4225, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1.218683651804671e-05, | |
| "loss": 0.3766, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.2611464968152866e-05, | |
| "loss": 0.4066, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.3036093418259024e-05, | |
| "loss": 0.4162, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.87, | |
| "eval_loss": 0.339584082365036, | |
| "eval_runtime": 3.5366, | |
| "eval_samples_per_second": 113.104, | |
| "eval_steps_per_second": 14.138, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.3460721868365181e-05, | |
| "loss": 0.3861, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.3885350318471338e-05, | |
| "loss": 0.3062, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.4309978768577495e-05, | |
| "loss": 0.2826, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.4734607218683651e-05, | |
| "loss": 0.2979, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.5159235668789811e-05, | |
| "loss": 0.2812, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.5583864118895968e-05, | |
| "loss": 0.2323, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.6008492569002127e-05, | |
| "loss": 0.2541, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 1.643312101910828e-05, | |
| "loss": 0.229, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 1.685774946921444e-05, | |
| "loss": 0.2631, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 1.7282377919320595e-05, | |
| "loss": 0.2704, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 1.7707006369426754e-05, | |
| "loss": 0.2792, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.8131634819532912e-05, | |
| "loss": 0.2358, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.8556263269639067e-05, | |
| "loss": 0.248, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.8980891719745225e-05, | |
| "loss": 0.1844, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.940552016985138e-05, | |
| "loss": 0.2244, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.983014861995754e-05, | |
| "loss": 0.192, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.925, | |
| "eval_loss": 0.21070748567581177, | |
| "eval_runtime": 3.5552, | |
| "eval_samples_per_second": 112.511, | |
| "eval_steps_per_second": 14.064, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 1.9971691436659592e-05, | |
| "loss": 0.1972, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 1.9924510497758907e-05, | |
| "loss": 0.1875, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 1.9877329558858223e-05, | |
| "loss": 0.1261, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 1.983014861995754e-05, | |
| "loss": 0.1463, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 1.9782967681056855e-05, | |
| "loss": 0.1455, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 1.973578674215617e-05, | |
| "loss": 0.1335, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 1.9688605803255486e-05, | |
| "loss": 0.1754, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 1.9641424864354802e-05, | |
| "loss": 0.1456, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 1.9594243925454118e-05, | |
| "loss": 0.1693, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 1.9547062986553433e-05, | |
| "loss": 0.1019, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 1.949988204765275e-05, | |
| "loss": 0.1324, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 1.9452701108752065e-05, | |
| "loss": 0.1422, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 1.940552016985138e-05, | |
| "loss": 0.0882, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 1.9358339230950696e-05, | |
| "loss": 0.1039, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 1.9311158292050015e-05, | |
| "loss": 0.0832, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8925, | |
| "eval_loss": 0.31647127866744995, | |
| "eval_runtime": 3.9256, | |
| "eval_samples_per_second": 101.896, | |
| "eval_steps_per_second": 12.737, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 1.926397735314933e-05, | |
| "loss": 0.1326, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 1.9216796414248643e-05, | |
| "loss": 0.0947, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 1.916961547534796e-05, | |
| "loss": 0.0796, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 1.9122434536447275e-05, | |
| "loss": 0.1037, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 1.9075253597546594e-05, | |
| "loss": 0.0643, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 1.902807265864591e-05, | |
| "loss": 0.0983, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 1.8980891719745225e-05, | |
| "loss": 0.0984, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 1.893371078084454e-05, | |
| "loss": 0.0654, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 1.8886529841943857e-05, | |
| "loss": 0.0701, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 1.8839348903043173e-05, | |
| "loss": 0.0725, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 1.879216796414249e-05, | |
| "loss": 0.0336, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 1.8744987025241804e-05, | |
| "loss": 0.0597, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 1.869780608634112e-05, | |
| "loss": 0.0975, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 1.8650625147440436e-05, | |
| "loss": 0.0814, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 1.860344420853975e-05, | |
| "loss": 0.0812, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 1.8556263269639067e-05, | |
| "loss": 0.0589, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9825, | |
| "eval_loss": 0.05781665816903114, | |
| "eval_runtime": 3.5713, | |
| "eval_samples_per_second": 112.003, | |
| "eval_steps_per_second": 14.0, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 1.8509082330738383e-05, | |
| "loss": 0.0605, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 1.84619013918377e-05, | |
| "loss": 0.0455, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 1.8414720452937018e-05, | |
| "loss": 0.0443, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 1.836753951403633e-05, | |
| "loss": 0.0592, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 1.8320358575135646e-05, | |
| "loss": 0.0462, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 1.827317763623496e-05, | |
| "loss": 0.0535, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 1.8225996697334277e-05, | |
| "loss": 0.0905, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 1.8178815758433593e-05, | |
| "loss": 0.0432, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 1.8131634819532912e-05, | |
| "loss": 0.0576, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 1.8084453880632228e-05, | |
| "loss": 0.0209, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 1.8037272941731543e-05, | |
| "loss": 0.0587, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 1.7990092002830856e-05, | |
| "loss": 0.0327, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 1.794291106393017e-05, | |
| "loss": 0.0707, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 1.789573012502949e-05, | |
| "loss": 0.0613, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 1.7848549186128806e-05, | |
| "loss": 0.0772, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 1.7801368247228122e-05, | |
| "loss": 0.0243, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9875, | |
| "eval_loss": 0.0692724883556366, | |
| "eval_runtime": 3.5461, | |
| "eval_samples_per_second": 112.801, | |
| "eval_steps_per_second": 14.1, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 1.7754187308327438e-05, | |
| "loss": 0.0374, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 1.7707006369426754e-05, | |
| "loss": 0.0676, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 1.765982543052607e-05, | |
| "loss": 0.0218, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 1.7612644491625385e-05, | |
| "loss": 0.0356, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 1.75654635527247e-05, | |
| "loss": 0.0374, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 1.7518282613824017e-05, | |
| "loss": 0.027, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 1.7471101674923332e-05, | |
| "loss": 0.0303, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 1.7423920736022648e-05, | |
| "loss": 0.0197, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 1.738145789101203e-05, | |
| "loss": 0.0187, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 1.7334276952111347e-05, | |
| "loss": 0.052, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 1.7287096013210666e-05, | |
| "loss": 0.0256, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 1.7239915074309982e-05, | |
| "loss": 0.0608, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 1.7192734135409298e-05, | |
| "loss": 0.0361, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 1.714555319650861e-05, | |
| "loss": 0.0633, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 1.7098372257607926e-05, | |
| "loss": 0.0199, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.975, | |
| "eval_loss": 0.1500987559556961, | |
| "eval_runtime": 3.5476, | |
| "eval_samples_per_second": 112.752, | |
| "eval_steps_per_second": 14.094, | |
| "step": 1099 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 1.705119131870724e-05, | |
| "loss": 0.0324, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 1.700401037980656e-05, | |
| "loss": 0.0678, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 1.6956829440905876e-05, | |
| "loss": 0.0372, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 1.6909648502005192e-05, | |
| "loss": 0.0232, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 1.6862467563104508e-05, | |
| "loss": 0.0244, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 1.6815286624203824e-05, | |
| "loss": 0.0155, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 1.676810568530314e-05, | |
| "loss": 0.0114, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 1.6720924746402455e-05, | |
| "loss": 0.0367, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 1.667374380750177e-05, | |
| "loss": 0.0128, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 1.6626562868601087e-05, | |
| "loss": 0.0181, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 1.6579381929700402e-05, | |
| "loss": 0.025, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 1.6532200990799718e-05, | |
| "loss": 0.0456, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 1.6485020051899034e-05, | |
| "loss": 0.0291, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 1.643783911299835e-05, | |
| "loss": 0.0157, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 1.6390658174097665e-05, | |
| "loss": 0.0204, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 1.6343477235196984e-05, | |
| "loss": 0.0201, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.97, | |
| "eval_loss": 0.10987219214439392, | |
| "eval_runtime": 3.5493, | |
| "eval_samples_per_second": 112.697, | |
| "eval_steps_per_second": 14.087, | |
| "step": 1256 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 1.6296296296296297e-05, | |
| "loss": 0.0246, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 1.6249115357395612e-05, | |
| "loss": 0.0304, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 1.6201934418494928e-05, | |
| "loss": 0.0304, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 1.6154753479594244e-05, | |
| "loss": 0.0083, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 1.6107572540693563e-05, | |
| "loss": 0.0244, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 1.606039160179288e-05, | |
| "loss": 0.0252, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 1.6013210662892194e-05, | |
| "loss": 0.0153, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 1.596602972399151e-05, | |
| "loss": 0.0219, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "learning_rate": 1.5918848785090822e-05, | |
| "loss": 0.0198, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 1.5871667846190138e-05, | |
| "loss": 0.0144, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 1.5824486907289457e-05, | |
| "loss": 0.0165, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 1.5777305968388773e-05, | |
| "loss": 0.0113, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 1.573012502948809e-05, | |
| "loss": 0.0264, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 1.5682944090587405e-05, | |
| "loss": 0.0274, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 1.563576315168672e-05, | |
| "loss": 0.0079, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 1.5588582212786036e-05, | |
| "loss": 0.021, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9825, | |
| "eval_loss": 0.13185830414295197, | |
| "eval_runtime": 3.7445, | |
| "eval_samples_per_second": 106.822, | |
| "eval_steps_per_second": 13.353, | |
| "step": 1413 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 1.5541401273885352e-05, | |
| "loss": 0.0206, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 1.5494220334984667e-05, | |
| "loss": 0.0157, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 1.5447039396083983e-05, | |
| "loss": 0.0071, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 1.53998584571833e-05, | |
| "loss": 0.0225, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 1.5352677518282615e-05, | |
| "loss": 0.0262, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 1.530549657938193e-05, | |
| "loss": 0.0172, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 1.5258315640481248e-05, | |
| "loss": 0.0071, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 1.5211134701580564e-05, | |
| "loss": 0.0069, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 1.516395376267988e-05, | |
| "loss": 0.0035, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 1.5116772823779195e-05, | |
| "loss": 0.0186, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 1.5069591884878509e-05, | |
| "loss": 0.011, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 1.5022410945977825e-05, | |
| "loss": 0.0165, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "learning_rate": 1.4975230007077142e-05, | |
| "loss": 0.0118, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 9.87, | |
| "learning_rate": 1.4928049068176458e-05, | |
| "loss": 0.0395, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 1.4880868129275774e-05, | |
| "loss": 0.009, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 1.483368719037509e-05, | |
| "loss": 0.0139, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.96, | |
| "eval_loss": 0.17666393518447876, | |
| "eval_runtime": 3.6723, | |
| "eval_samples_per_second": 108.923, | |
| "eval_steps_per_second": 13.615, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 10.06, | |
| "learning_rate": 1.4786506251474407e-05, | |
| "loss": 0.0215, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 10.13, | |
| "learning_rate": 1.4739325312573723e-05, | |
| "loss": 0.0047, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 10.19, | |
| "learning_rate": 1.4692144373673037e-05, | |
| "loss": 0.0037, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 10.25, | |
| "learning_rate": 1.4644963434772352e-05, | |
| "loss": 0.0107, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 1.4597782495871668e-05, | |
| "loss": 0.0265, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 10.38, | |
| "learning_rate": 1.4550601556970985e-05, | |
| "loss": 0.0178, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 10.45, | |
| "learning_rate": 1.4503420618070301e-05, | |
| "loss": 0.021, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 10.51, | |
| "learning_rate": 1.4456239679169617e-05, | |
| "loss": 0.0102, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 10.57, | |
| "learning_rate": 1.4409058740268933e-05, | |
| "loss": 0.0347, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 10.64, | |
| "learning_rate": 1.4361877801368248e-05, | |
| "loss": 0.0063, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "learning_rate": 1.4314696862467566e-05, | |
| "loss": 0.0042, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "learning_rate": 1.426751592356688e-05, | |
| "loss": 0.0137, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 1.4220334984666196e-05, | |
| "loss": 0.008, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 10.89, | |
| "learning_rate": 1.4173154045765511e-05, | |
| "loss": 0.0022, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "learning_rate": 1.4125973106864827e-05, | |
| "loss": 0.016, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9775, | |
| "eval_loss": 0.0946773886680603, | |
| "eval_runtime": 3.6096, | |
| "eval_samples_per_second": 110.817, | |
| "eval_steps_per_second": 13.852, | |
| "step": 1727 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 1.4078792167964144e-05, | |
| "loss": 0.0124, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 11.08, | |
| "learning_rate": 1.403161122906346e-05, | |
| "loss": 0.0126, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 11.15, | |
| "learning_rate": 1.3984430290162776e-05, | |
| "loss": 0.0016, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 11.21, | |
| "learning_rate": 1.3937249351262092e-05, | |
| "loss": 0.0097, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 11.27, | |
| "learning_rate": 1.3890068412361409e-05, | |
| "loss": 0.0161, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 11.34, | |
| "learning_rate": 1.3842887473460721e-05, | |
| "loss": 0.0058, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 1.3795706534560039e-05, | |
| "loss": 0.0102, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 11.46, | |
| "learning_rate": 1.3748525595659355e-05, | |
| "loss": 0.0329, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 11.53, | |
| "learning_rate": 1.370134465675867e-05, | |
| "loss": 0.0223, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "learning_rate": 1.3654163717857986e-05, | |
| "loss": 0.0077, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 11.66, | |
| "learning_rate": 1.3606982778957303e-05, | |
| "loss": 0.0038, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 1.3559801840056619e-05, | |
| "loss": 0.0031, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 11.78, | |
| "learning_rate": 1.3512620901155935e-05, | |
| "loss": 0.0174, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 11.85, | |
| "learning_rate": 1.3465439962255249e-05, | |
| "loss": 0.0022, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "learning_rate": 1.3418259023354565e-05, | |
| "loss": 0.0032, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 11.97, | |
| "learning_rate": 1.3371078084453882e-05, | |
| "loss": 0.0077, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9625, | |
| "eval_loss": 0.1879103034734726, | |
| "eval_runtime": 3.6799, | |
| "eval_samples_per_second": 108.7, | |
| "eval_steps_per_second": 13.587, | |
| "step": 1884 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 1.3323897145553198e-05, | |
| "loss": 0.0413, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 1.3276716206652514e-05, | |
| "loss": 0.021, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 12.17, | |
| "learning_rate": 1.322953526775183e-05, | |
| "loss": 0.0053, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 12.23, | |
| "learning_rate": 1.3182354328851145e-05, | |
| "loss": 0.0008, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 12.29, | |
| "learning_rate": 1.3135173389950462e-05, | |
| "loss": 0.0109, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "learning_rate": 1.3087992451049778e-05, | |
| "loss": 0.0098, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 12.42, | |
| "learning_rate": 1.3040811512149092e-05, | |
| "loss": 0.0269, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 1.2993630573248408e-05, | |
| "loss": 0.0008, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 12.55, | |
| "learning_rate": 1.2946449634347724e-05, | |
| "loss": 0.0291, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 12.61, | |
| "learning_rate": 1.2899268695447041e-05, | |
| "loss": 0.0189, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 12.68, | |
| "learning_rate": 1.2852087756546357e-05, | |
| "loss": 0.0264, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 12.74, | |
| "learning_rate": 1.2804906817645673e-05, | |
| "loss": 0.0171, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 1.2757725878744988e-05, | |
| "loss": 0.0099, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 12.87, | |
| "learning_rate": 1.2710544939844304e-05, | |
| "loss": 0.0071, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "learning_rate": 1.2663364000943618e-05, | |
| "loss": 0.0034, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "learning_rate": 1.2616183062042935e-05, | |
| "loss": 0.0166, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9725, | |
| "eval_loss": 0.14901761710643768, | |
| "eval_runtime": 3.618, | |
| "eval_samples_per_second": 110.557, | |
| "eval_steps_per_second": 13.82, | |
| "step": 2041 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 1.2569002123142251e-05, | |
| "loss": 0.0092, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 1.2521821184241567e-05, | |
| "loss": 0.0117, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 13.18, | |
| "learning_rate": 1.2474640245340883e-05, | |
| "loss": 0.0096, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 13.25, | |
| "learning_rate": 1.24274593064402e-05, | |
| "loss": 0.0256, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 13.31, | |
| "learning_rate": 1.2380278367539516e-05, | |
| "loss": 0.0136, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 13.38, | |
| "learning_rate": 1.2333097428638832e-05, | |
| "loss": 0.0032, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 1.2285916489738147e-05, | |
| "loss": 0.0026, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "learning_rate": 1.2238735550837461e-05, | |
| "loss": 0.0085, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 13.57, | |
| "learning_rate": 1.2191554611936777e-05, | |
| "loss": 0.0113, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 13.63, | |
| "learning_rate": 1.2144373673036094e-05, | |
| "loss": 0.021, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 13.69, | |
| "learning_rate": 1.209719273413541e-05, | |
| "loss": 0.0179, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 1.2050011795234726e-05, | |
| "loss": 0.0063, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 1.2002830856334042e-05, | |
| "loss": 0.008, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "learning_rate": 1.1955649917433359e-05, | |
| "loss": 0.0044, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 13.95, | |
| "learning_rate": 1.1908468978532675e-05, | |
| "loss": 0.0111, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9875, | |
| "eval_loss": 0.06426624208688736, | |
| "eval_runtime": 3.8488, | |
| "eval_samples_per_second": 103.927, | |
| "eval_steps_per_second": 12.991, | |
| "step": 2198 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 1.186128803963199e-05, | |
| "loss": 0.0221, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 1.1814107100731305e-05, | |
| "loss": 0.0035, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 1.176692616183062e-05, | |
| "loss": 0.0171, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 14.2, | |
| "learning_rate": 1.1719745222929938e-05, | |
| "loss": 0.0139, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 14.27, | |
| "learning_rate": 1.1672564284029253e-05, | |
| "loss": 0.0025, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 14.33, | |
| "learning_rate": 1.162538334512857e-05, | |
| "loss": 0.0046, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 14.39, | |
| "learning_rate": 1.1578202406227885e-05, | |
| "loss": 0.0151, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 14.46, | |
| "learning_rate": 1.15310214673272e-05, | |
| "loss": 0.0092, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 14.52, | |
| "learning_rate": 1.1483840528426518e-05, | |
| "loss": 0.0037, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 14.59, | |
| "learning_rate": 1.1436659589525832e-05, | |
| "loss": 0.0014, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 14.65, | |
| "learning_rate": 1.1389478650625148e-05, | |
| "loss": 0.0103, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "learning_rate": 1.1342297711724464e-05, | |
| "loss": 0.021, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 14.78, | |
| "learning_rate": 1.129511677282378e-05, | |
| "loss": 0.0016, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 1.1247935833923097e-05, | |
| "loss": 0.0085, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 14.9, | |
| "learning_rate": 1.1200754895022412e-05, | |
| "loss": 0.0024, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 14.97, | |
| "learning_rate": 1.1153573956121728e-05, | |
| "loss": 0.0029, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9375, | |
| "eval_loss": 0.29853329062461853, | |
| "eval_runtime": 3.6432, | |
| "eval_samples_per_second": 109.794, | |
| "eval_steps_per_second": 13.724, | |
| "step": 2355 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 1.1106393017221044e-05, | |
| "loss": 0.0115, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 15.1, | |
| "learning_rate": 1.1059212078320361e-05, | |
| "loss": 0.0094, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "learning_rate": 1.1012031139419674e-05, | |
| "loss": 0.0122, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "learning_rate": 1.0964850200518991e-05, | |
| "loss": 0.0176, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 15.29, | |
| "learning_rate": 1.0917669261618307e-05, | |
| "loss": 0.0044, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 15.35, | |
| "learning_rate": 1.0870488322717623e-05, | |
| "loss": 0.0003, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 15.41, | |
| "learning_rate": 1.0823307383816938e-05, | |
| "loss": 0.0076, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 15.48, | |
| "learning_rate": 1.0776126444916256e-05, | |
| "loss": 0.0035, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 15.54, | |
| "learning_rate": 1.0728945506015571e-05, | |
| "loss": 0.0007, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 15.61, | |
| "learning_rate": 1.0681764567114887e-05, | |
| "loss": 0.0044, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 15.67, | |
| "learning_rate": 1.0634583628214203e-05, | |
| "loss": 0.0063, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 15.73, | |
| "learning_rate": 1.0587402689313517e-05, | |
| "loss": 0.0098, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 15.8, | |
| "learning_rate": 1.0540221750412833e-05, | |
| "loss": 0.0077, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "learning_rate": 1.049304081151215e-05, | |
| "loss": 0.0178, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 15.92, | |
| "learning_rate": 1.0445859872611466e-05, | |
| "loss": 0.0117, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "learning_rate": 1.0398678933710782e-05, | |
| "loss": 0.0015, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.98, | |
| "eval_loss": 0.10450205951929092, | |
| "eval_runtime": 3.6982, | |
| "eval_samples_per_second": 108.161, | |
| "eval_steps_per_second": 13.52, | |
| "step": 2512 | |
| }, | |
| { | |
| "epoch": 16.05, | |
| "learning_rate": 1.0351497994810097e-05, | |
| "loss": 0.0007, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 16.11, | |
| "learning_rate": 1.0304317055909415e-05, | |
| "loss": 0.0203, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 16.18, | |
| "learning_rate": 1.025713611700873e-05, | |
| "loss": 0.0022, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 16.24, | |
| "learning_rate": 1.0209955178108044e-05, | |
| "loss": 0.0118, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 16.31, | |
| "learning_rate": 1.016277423920736e-05, | |
| "loss": 0.0005, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 16.37, | |
| "learning_rate": 1.0115593300306676e-05, | |
| "loss": 0.0009, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 16.43, | |
| "learning_rate": 1.0068412361405993e-05, | |
| "loss": 0.0086, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 16.5, | |
| "learning_rate": 1.0021231422505309e-05, | |
| "loss": 0.0038, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 16.56, | |
| "learning_rate": 9.974050483604625e-06, | |
| "loss": 0.011, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 16.62, | |
| "learning_rate": 9.92686954470394e-06, | |
| "loss": 0.0166, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 16.69, | |
| "learning_rate": 9.879688605803256e-06, | |
| "loss": 0.0008, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 16.75, | |
| "learning_rate": 9.832507666902572e-06, | |
| "loss": 0.0085, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 16.82, | |
| "learning_rate": 9.785326728001888e-06, | |
| "loss": 0.0005, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 16.88, | |
| "learning_rate": 9.738145789101205e-06, | |
| "loss": 0.0062, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 16.94, | |
| "learning_rate": 9.69096485020052e-06, | |
| "loss": 0.0045, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.9825, | |
| "eval_loss": 0.0958116427063942, | |
| "eval_runtime": 3.613, | |
| "eval_samples_per_second": 110.713, | |
| "eval_steps_per_second": 13.839, | |
| "step": 2669 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 9.643783911299835e-06, | |
| "loss": 0.0003, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 17.07, | |
| "learning_rate": 9.596602972399152e-06, | |
| "loss": 0.0068, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 17.13, | |
| "learning_rate": 9.549422033498468e-06, | |
| "loss": 0.0087, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 17.2, | |
| "learning_rate": 9.502241094597782e-06, | |
| "loss": 0.009, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 17.26, | |
| "learning_rate": 9.4550601556971e-06, | |
| "loss": 0.0052, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 17.32, | |
| "learning_rate": 9.407879216796415e-06, | |
| "loss": 0.0004, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 17.39, | |
| "learning_rate": 9.360698277895731e-06, | |
| "loss": 0.0075, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 17.45, | |
| "learning_rate": 9.313517338995047e-06, | |
| "loss": 0.0072, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 17.52, | |
| "learning_rate": 9.266336400094362e-06, | |
| "loss": 0.011, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 17.58, | |
| "learning_rate": 9.219155461193678e-06, | |
| "loss": 0.0075, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 17.64, | |
| "learning_rate": 9.171974522292994e-06, | |
| "loss": 0.0078, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 17.71, | |
| "learning_rate": 9.124793583392311e-06, | |
| "loss": 0.0041, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 17.77, | |
| "learning_rate": 9.077612644491625e-06, | |
| "loss": 0.0071, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 17.83, | |
| "learning_rate": 9.030431705590941e-06, | |
| "loss": 0.0012, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 17.9, | |
| "learning_rate": 8.983250766690259e-06, | |
| "loss": 0.0016, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 17.96, | |
| "learning_rate": 8.936069827789574e-06, | |
| "loss": 0.0038, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.975, | |
| "eval_loss": 0.08133537322282791, | |
| "eval_runtime": 3.6605, | |
| "eval_samples_per_second": 109.274, | |
| "eval_steps_per_second": 13.659, | |
| "step": 2826 | |
| }, | |
| { | |
| "epoch": 18.03, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 0.0001, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 18.09, | |
| "learning_rate": 8.841707949988206e-06, | |
| "loss": 0.0005, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 18.15, | |
| "learning_rate": 8.794527011087521e-06, | |
| "loss": 0.0058, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 18.22, | |
| "learning_rate": 8.747346072186837e-06, | |
| "loss": 0.0003, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 18.28, | |
| "learning_rate": 8.700165133286153e-06, | |
| "loss": 0.006, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 18.34, | |
| "learning_rate": 8.652984194385469e-06, | |
| "loss": 0.005, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 18.41, | |
| "learning_rate": 8.605803255484784e-06, | |
| "loss": 0.0123, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 18.47, | |
| "learning_rate": 8.5586223165841e-06, | |
| "loss": 0.008, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 18.54, | |
| "learning_rate": 8.511441377683418e-06, | |
| "loss": 0.0133, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 18.6, | |
| "learning_rate": 8.464260438782732e-06, | |
| "loss": 0.0078, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 8.417079499882049e-06, | |
| "loss": 0.0139, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 18.73, | |
| "learning_rate": 8.369898560981365e-06, | |
| "loss": 0.0015, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 18.79, | |
| "learning_rate": 8.32271762208068e-06, | |
| "loss": 0.0171, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 18.85, | |
| "learning_rate": 8.275536683179996e-06, | |
| "loss": 0.0091, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "learning_rate": 8.228355744279312e-06, | |
| "loss": 0.0003, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 18.98, | |
| "learning_rate": 8.181174805378628e-06, | |
| "loss": 0.0412, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.9725, | |
| "eval_loss": 0.14458990097045898, | |
| "eval_runtime": 3.8861, | |
| "eval_samples_per_second": 102.93, | |
| "eval_steps_per_second": 12.866, | |
| "step": 2983 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 8.133993866477943e-06, | |
| "loss": 0.0091, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 19.11, | |
| "learning_rate": 8.08681292757726e-06, | |
| "loss": 0.001, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 19.17, | |
| "learning_rate": 8.039631988676575e-06, | |
| "loss": 0.0003, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 19.24, | |
| "learning_rate": 7.99245104977589e-06, | |
| "loss": 0.0061, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 19.3, | |
| "learning_rate": 7.945270110875208e-06, | |
| "loss": 0.0085, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 7.898089171974524e-06, | |
| "loss": 0.0011, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 19.43, | |
| "learning_rate": 7.850908233073838e-06, | |
| "loss": 0.0021, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 19.49, | |
| "learning_rate": 7.803727294173155e-06, | |
| "loss": 0.0001, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 19.55, | |
| "learning_rate": 7.756546355272471e-06, | |
| "loss": 0.0002, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 19.62, | |
| "learning_rate": 7.709365416371787e-06, | |
| "loss": 0.015, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 7.662184477471102e-06, | |
| "loss": 0.0008, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 19.75, | |
| "learning_rate": 7.615003538570418e-06, | |
| "loss": 0.005, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 19.81, | |
| "learning_rate": 7.567822599669734e-06, | |
| "loss": 0.0022, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 19.87, | |
| "learning_rate": 7.52064166076905e-06, | |
| "loss": 0.001, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 19.94, | |
| "learning_rate": 7.473460721868365e-06, | |
| "loss": 0.0178, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 7.426279782967681e-06, | |
| "loss": 0.0003, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.965, | |
| "eval_loss": 0.16244125366210938, | |
| "eval_runtime": 4.1384, | |
| "eval_samples_per_second": 96.656, | |
| "eval_steps_per_second": 12.082, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 20.06, | |
| "learning_rate": 7.379098844066998e-06, | |
| "loss": 0.0078, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 20.13, | |
| "learning_rate": 7.331917905166313e-06, | |
| "loss": 0.0003, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 20.19, | |
| "learning_rate": 7.28473696626563e-06, | |
| "loss": 0.0019, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 20.25, | |
| "learning_rate": 7.237556027364945e-06, | |
| "loss": 0.001, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 20.32, | |
| "learning_rate": 7.1903750884642605e-06, | |
| "loss": 0.0072, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 20.38, | |
| "learning_rate": 7.143194149563577e-06, | |
| "loss": 0.0077, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 20.45, | |
| "learning_rate": 7.096013210662893e-06, | |
| "loss": 0.0013, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 20.51, | |
| "learning_rate": 7.0488322717622086e-06, | |
| "loss": 0.0002, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 20.57, | |
| "learning_rate": 7.001651332861524e-06, | |
| "loss": 0.0, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 20.64, | |
| "learning_rate": 6.954470393960841e-06, | |
| "loss": 0.0115, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 20.7, | |
| "learning_rate": 6.907289455060157e-06, | |
| "loss": 0.0014, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 20.76, | |
| "learning_rate": 6.8601085161594715e-06, | |
| "loss": 0.0066, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 6.812927577258788e-06, | |
| "loss": 0.0049, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 20.89, | |
| "learning_rate": 6.765746638358104e-06, | |
| "loss": 0.0004, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 20.96, | |
| "learning_rate": 6.71856569945742e-06, | |
| "loss": 0.0007, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.99, | |
| "eval_loss": 0.06704743206501007, | |
| "eval_runtime": 3.8513, | |
| "eval_samples_per_second": 103.86, | |
| "eval_steps_per_second": 12.983, | |
| "step": 3297 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 6.671384760556736e-06, | |
| "loss": 0.0001, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 21.08, | |
| "learning_rate": 6.624203821656051e-06, | |
| "loss": 0.0006, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 21.15, | |
| "learning_rate": 6.5770228827553676e-06, | |
| "loss": 0.0003, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 21.21, | |
| "learning_rate": 6.529841943854683e-06, | |
| "loss": 0.0001, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 21.27, | |
| "learning_rate": 6.482661004954e-06, | |
| "loss": 0.0113, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 21.34, | |
| "learning_rate": 6.435480066053315e-06, | |
| "loss": 0.0006, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 21.4, | |
| "learning_rate": 6.3882991271526305e-06, | |
| "loss": 0.0071, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 21.46, | |
| "learning_rate": 6.341118188251947e-06, | |
| "loss": 0.002, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 21.53, | |
| "learning_rate": 6.293937249351263e-06, | |
| "loss": 0.0017, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 21.59, | |
| "learning_rate": 6.246756310450578e-06, | |
| "loss": 0.0045, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 21.66, | |
| "learning_rate": 6.199575371549894e-06, | |
| "loss": 0.0002, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 21.72, | |
| "learning_rate": 6.15239443264921e-06, | |
| "loss": 0.002, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 21.78, | |
| "learning_rate": 6.1052134937485265e-06, | |
| "loss": 0.0058, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 21.85, | |
| "learning_rate": 6.058032554847842e-06, | |
| "loss": 0.0199, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 21.91, | |
| "learning_rate": 6.010851615947157e-06, | |
| "loss": 0.0084, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 21.97, | |
| "learning_rate": 5.963670677046474e-06, | |
| "loss": 0.0001, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.985, | |
| "eval_loss": 0.08064628392457962, | |
| "eval_runtime": 3.6485, | |
| "eval_samples_per_second": 109.633, | |
| "eval_steps_per_second": 13.704, | |
| "step": 3454 | |
| }, | |
| { | |
| "epoch": 22.04, | |
| "learning_rate": 5.9164897381457895e-06, | |
| "loss": 0.0005, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 22.1, | |
| "learning_rate": 5.869308799245106e-06, | |
| "loss": 0.0005, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 22.17, | |
| "learning_rate": 5.822127860344421e-06, | |
| "loss": 0.0, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 22.23, | |
| "learning_rate": 5.774946921443737e-06, | |
| "loss": 0.0, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 22.29, | |
| "learning_rate": 5.727765982543053e-06, | |
| "loss": 0.0001, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 22.36, | |
| "learning_rate": 5.680585043642369e-06, | |
| "loss": 0.0002, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 22.42, | |
| "learning_rate": 5.633404104741685e-06, | |
| "loss": 0.0073, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 22.48, | |
| "learning_rate": 5.5862231658410004e-06, | |
| "loss": 0.0021, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 22.55, | |
| "learning_rate": 5.539042226940316e-06, | |
| "loss": 0.0, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 22.61, | |
| "learning_rate": 5.491861288039633e-06, | |
| "loss": 0.0028, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 22.68, | |
| "learning_rate": 5.4446803491389485e-06, | |
| "loss": 0.0024, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 22.74, | |
| "learning_rate": 5.397499410238264e-06, | |
| "loss": 0.0035, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 22.8, | |
| "learning_rate": 5.35031847133758e-06, | |
| "loss": 0.0002, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 22.87, | |
| "learning_rate": 5.3031375324368965e-06, | |
| "loss": 0.0, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 22.93, | |
| "learning_rate": 5.255956593536212e-06, | |
| "loss": 0.0015, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 22.99, | |
| "learning_rate": 5.208775654635527e-06, | |
| "loss": 0.0001, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.9825, | |
| "eval_loss": 0.09302221238613129, | |
| "eval_runtime": 4.8817, | |
| "eval_samples_per_second": 81.939, | |
| "eval_steps_per_second": 10.242, | |
| "step": 3611 | |
| }, | |
| { | |
| "epoch": 23.06, | |
| "learning_rate": 5.161594715734844e-06, | |
| "loss": 0.0015, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 23.12, | |
| "learning_rate": 5.1144137768341594e-06, | |
| "loss": 0.0003, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 23.18, | |
| "learning_rate": 5.067232837933476e-06, | |
| "loss": 0.0001, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 23.25, | |
| "learning_rate": 5.020051899032791e-06, | |
| "loss": 0.0001, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 23.31, | |
| "learning_rate": 4.972870960132107e-06, | |
| "loss": 0.0001, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 23.38, | |
| "learning_rate": 4.925690021231423e-06, | |
| "loss": 0.0001, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 23.44, | |
| "learning_rate": 4.878509082330739e-06, | |
| "loss": 0.0, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 23.5, | |
| "learning_rate": 4.831328143430055e-06, | |
| "loss": 0.0107, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 23.57, | |
| "learning_rate": 4.78414720452937e-06, | |
| "loss": 0.0001, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 23.63, | |
| "learning_rate": 4.736966265628686e-06, | |
| "loss": 0.0021, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 23.69, | |
| "learning_rate": 4.689785326728003e-06, | |
| "loss": 0.0021, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 23.76, | |
| "learning_rate": 4.642604387827318e-06, | |
| "loss": 0.0001, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 23.82, | |
| "learning_rate": 4.595423448926634e-06, | |
| "loss": 0.0074, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 23.89, | |
| "learning_rate": 4.54824251002595e-06, | |
| "loss": 0.0003, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 23.95, | |
| "learning_rate": 4.501061571125266e-06, | |
| "loss": 0.0037, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.9725, | |
| "eval_loss": 0.1421746164560318, | |
| "eval_runtime": 3.6108, | |
| "eval_samples_per_second": 110.78, | |
| "eval_steps_per_second": 13.847, | |
| "step": 3768 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 4.453880632224581e-06, | |
| "loss": 0.0, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 24.08, | |
| "learning_rate": 4.406699693323898e-06, | |
| "loss": 0.0002, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 24.14, | |
| "learning_rate": 4.359518754423213e-06, | |
| "loss": 0.0055, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 24.2, | |
| "learning_rate": 4.312337815522529e-06, | |
| "loss": 0.0037, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 24.27, | |
| "learning_rate": 4.265156876621845e-06, | |
| "loss": 0.0001, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 24.33, | |
| "learning_rate": 4.217975937721161e-06, | |
| "loss": 0.0006, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 24.39, | |
| "learning_rate": 4.170794998820477e-06, | |
| "loss": 0.0, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 24.46, | |
| "learning_rate": 4.123614059919792e-06, | |
| "loss": 0.0001, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 24.52, | |
| "learning_rate": 4.076433121019109e-06, | |
| "loss": 0.0, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 24.59, | |
| "learning_rate": 4.029252182118425e-06, | |
| "loss": 0.0001, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 24.65, | |
| "learning_rate": 3.98207124321774e-06, | |
| "loss": 0.0001, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 24.71, | |
| "learning_rate": 3.934890304317056e-06, | |
| "loss": 0.0004, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 24.78, | |
| "learning_rate": 3.887709365416373e-06, | |
| "loss": 0.0002, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 24.84, | |
| "learning_rate": 3.8405284265156875e-06, | |
| "loss": 0.0134, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 24.9, | |
| "learning_rate": 3.793347487615004e-06, | |
| "loss": 0.0029, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 24.97, | |
| "learning_rate": 3.7461665487143194e-06, | |
| "loss": 0.0001, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.99, | |
| "eval_loss": 0.05674205347895622, | |
| "eval_runtime": 4.1893, | |
| "eval_samples_per_second": 95.482, | |
| "eval_steps_per_second": 11.935, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 25.03, | |
| "learning_rate": 3.6989856098136356e-06, | |
| "loss": 0.0222, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 25.1, | |
| "learning_rate": 3.6518046709129513e-06, | |
| "loss": 0.0004, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 25.16, | |
| "learning_rate": 3.6046237320122675e-06, | |
| "loss": 0.0006, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 25.22, | |
| "learning_rate": 3.5574427931115836e-06, | |
| "loss": 0.0007, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 25.29, | |
| "learning_rate": 3.510261854210899e-06, | |
| "loss": 0.0219, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 25.35, | |
| "learning_rate": 3.463080915310215e-06, | |
| "loss": 0.0, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 25.41, | |
| "learning_rate": 3.415899976409531e-06, | |
| "loss": 0.0071, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 25.48, | |
| "learning_rate": 3.368719037508847e-06, | |
| "loss": 0.0003, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 25.54, | |
| "learning_rate": 3.3215380986081623e-06, | |
| "loss": 0.0, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 25.61, | |
| "learning_rate": 3.2743571597074784e-06, | |
| "loss": 0.0003, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 25.67, | |
| "learning_rate": 3.227176220806794e-06, | |
| "loss": 0.0047, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 25.73, | |
| "learning_rate": 3.1799952819061103e-06, | |
| "loss": 0.0002, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 25.8, | |
| "learning_rate": 3.132814343005426e-06, | |
| "loss": 0.0003, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 25.86, | |
| "learning_rate": 3.085633404104742e-06, | |
| "loss": 0.0001, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 3.0384524652040575e-06, | |
| "loss": 0.0003, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 25.99, | |
| "learning_rate": 2.9912715263033736e-06, | |
| "loss": 0.0057, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.99, | |
| "eval_loss": 0.061558231711387634, | |
| "eval_runtime": 3.688, | |
| "eval_samples_per_second": 108.459, | |
| "eval_steps_per_second": 13.557, | |
| "step": 4082 | |
| }, | |
| { | |
| "epoch": 26.05, | |
| "learning_rate": 2.94409058740269e-06, | |
| "loss": 0.0108, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 26.11, | |
| "learning_rate": 2.8969096485020055e-06, | |
| "loss": 0.0026, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 26.18, | |
| "learning_rate": 2.8497287096013217e-06, | |
| "loss": 0.0009, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 2.802547770700637e-06, | |
| "loss": 0.0, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 26.31, | |
| "learning_rate": 2.755366831799953e-06, | |
| "loss": 0.0, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 26.37, | |
| "learning_rate": 2.708185892899269e-06, | |
| "loss": 0.0001, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 26.43, | |
| "learning_rate": 2.661004953998585e-06, | |
| "loss": 0.0, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 26.5, | |
| "learning_rate": 2.6138240150979003e-06, | |
| "loss": 0.0029, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 2.5666430761972165e-06, | |
| "loss": 0.0056, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 26.62, | |
| "learning_rate": 2.519462137296532e-06, | |
| "loss": 0.0, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 26.69, | |
| "learning_rate": 2.4722811983958484e-06, | |
| "loss": 0.0001, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 26.75, | |
| "learning_rate": 2.425100259495164e-06, | |
| "loss": 0.0002, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 26.82, | |
| "learning_rate": 2.3779193205944802e-06, | |
| "loss": 0.0049, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 2.330738381693796e-06, | |
| "loss": 0.0006, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 26.94, | |
| "learning_rate": 2.2835574427931117e-06, | |
| "loss": 0.0, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.98, | |
| "eval_loss": 0.08436720073223114, | |
| "eval_runtime": 4.2248, | |
| "eval_samples_per_second": 94.68, | |
| "eval_steps_per_second": 11.835, | |
| "step": 4239 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 2.2363765038924274e-06, | |
| "loss": 0.0, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 27.07, | |
| "learning_rate": 2.1891955649917436e-06, | |
| "loss": 0.0003, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 27.13, | |
| "learning_rate": 2.1420146260910593e-06, | |
| "loss": 0.0127, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 2.094833687190375e-06, | |
| "loss": 0.0, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 27.26, | |
| "learning_rate": 2.047652748289691e-06, | |
| "loss": 0.0024, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 27.32, | |
| "learning_rate": 2.000471809389007e-06, | |
| "loss": 0.0, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 27.39, | |
| "learning_rate": 1.953290870488323e-06, | |
| "loss": 0.0043, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 27.45, | |
| "learning_rate": 1.9061099315876388e-06, | |
| "loss": 0.0027, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 1.8589289926869548e-06, | |
| "loss": 0.0, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 27.58, | |
| "learning_rate": 1.8117480537862705e-06, | |
| "loss": 0.0003, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 27.64, | |
| "learning_rate": 1.7645671148855864e-06, | |
| "loss": 0.0, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 27.71, | |
| "learning_rate": 1.7173861759849022e-06, | |
| "loss": 0.0058, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 27.77, | |
| "learning_rate": 1.6702052370842181e-06, | |
| "loss": 0.0003, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 27.83, | |
| "learning_rate": 1.623024298183534e-06, | |
| "loss": 0.0156, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 27.9, | |
| "learning_rate": 1.5758433592828498e-06, | |
| "loss": 0.0, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 27.96, | |
| "learning_rate": 1.5286624203821657e-06, | |
| "loss": 0.0022, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.99, | |
| "eval_loss": 0.06583850830793381, | |
| "eval_runtime": 4.0003, | |
| "eval_samples_per_second": 99.991, | |
| "eval_steps_per_second": 12.499, | |
| "step": 4396 | |
| }, | |
| { | |
| "epoch": 28.03, | |
| "learning_rate": 1.4814814814814815e-06, | |
| "loss": 0.0004, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 28.09, | |
| "learning_rate": 1.4343005425807974e-06, | |
| "loss": 0.0, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 28.15, | |
| "learning_rate": 1.3871196036801131e-06, | |
| "loss": 0.0001, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 28.22, | |
| "learning_rate": 1.3399386647794293e-06, | |
| "loss": 0.0008, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 28.28, | |
| "learning_rate": 1.2927577258787452e-06, | |
| "loss": 0.001, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 28.34, | |
| "learning_rate": 1.245576786978061e-06, | |
| "loss": 0.0001, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 28.41, | |
| "learning_rate": 1.1983958480773767e-06, | |
| "loss": 0.0072, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 28.47, | |
| "learning_rate": 1.1512149091766928e-06, | |
| "loss": 0.0, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 28.54, | |
| "learning_rate": 1.1040339702760086e-06, | |
| "loss": 0.0001, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 28.6, | |
| "learning_rate": 1.0568530313753245e-06, | |
| "loss": 0.0017, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 28.66, | |
| "learning_rate": 1.0096720924746402e-06, | |
| "loss": 0.0, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 28.73, | |
| "learning_rate": 9.624911535739562e-07, | |
| "loss": 0.0, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 28.79, | |
| "learning_rate": 9.15310214673272e-07, | |
| "loss": 0.0005, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 8.681292757725881e-07, | |
| "loss": 0.0001, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "learning_rate": 8.209483368719039e-07, | |
| "loss": 0.0, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 28.98, | |
| "learning_rate": 7.737673979712197e-07, | |
| "loss": 0.0, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.9825, | |
| "eval_loss": 0.07669363915920258, | |
| "eval_runtime": 3.7171, | |
| "eval_samples_per_second": 107.61, | |
| "eval_steps_per_second": 13.451, | |
| "step": 4553 | |
| }, | |
| { | |
| "epoch": 29.04, | |
| "learning_rate": 7.265864590705356e-07, | |
| "loss": 0.0, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 29.11, | |
| "learning_rate": 6.794055201698514e-07, | |
| "loss": 0.0036, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 29.17, | |
| "learning_rate": 6.322245812691672e-07, | |
| "loss": 0.0, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 29.24, | |
| "learning_rate": 5.850436423684832e-07, | |
| "loss": 0.0004, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 29.3, | |
| "learning_rate": 5.37862703467799e-07, | |
| "loss": 0.0, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 29.36, | |
| "learning_rate": 4.906817645671149e-07, | |
| "loss": 0.0, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 29.43, | |
| "learning_rate": 4.435008256664308e-07, | |
| "loss": 0.0001, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 29.49, | |
| "learning_rate": 3.963198867657467e-07, | |
| "loss": 0.0004, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 29.55, | |
| "learning_rate": 3.4913894786506253e-07, | |
| "loss": 0.0001, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 29.62, | |
| "learning_rate": 3.019580089643784e-07, | |
| "loss": 0.0, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 29.68, | |
| "learning_rate": 2.547770700636943e-07, | |
| "loss": 0.0026, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 29.75, | |
| "learning_rate": 2.0759613116301014e-07, | |
| "loss": 0.0001, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 29.81, | |
| "learning_rate": 1.6041519226232603e-07, | |
| "loss": 0.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 29.87, | |
| "learning_rate": 1.132342533616419e-07, | |
| "loss": 0.0002, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 29.94, | |
| "learning_rate": 6.605331446095778e-08, | |
| "loss": 0.001, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 1.887237556027365e-08, | |
| "loss": 0.0001, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.9875, | |
| "eval_loss": 0.07613274455070496, | |
| "eval_runtime": 4.211, | |
| "eval_samples_per_second": 94.99, | |
| "eval_steps_per_second": 11.874, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "step": 4710, | |
| "total_flos": 2.3238077313024e+19, | |
| "train_loss": 0.07197937404424458, | |
| "train_runtime": 7271.1721, | |
| "train_samples_per_second": 41.259, | |
| "train_steps_per_second": 0.648 | |
| } | |
| ], | |
| "max_steps": 4710, | |
| "num_train_epochs": 30, | |
| "total_flos": 2.3238077313024e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |