| { | |
| "best_metric": 1.634265422821045, | |
| "best_model_checkpoint": "./results/checkpoint-5800", | |
| "epoch": 0.2142434988179669, | |
| "global_step": 5800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019996, | |
| "loss": 4.2732, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019992000000000002, | |
| "loss": 3.4267, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019988, | |
| "loss": 3.1308, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019984, | |
| "loss": 2.9584, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001998, | |
| "loss": 2.8321, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019976000000000003, | |
| "loss": 2.8353, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019972000000000002, | |
| "loss": 2.7275, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019968, | |
| "loss": 2.7678, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019964, | |
| "loss": 2.6752, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001996, | |
| "loss": 2.7207, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_accuracy": 0.6036520746718839, | |
| "eval_loss": 2.011291980743408, | |
| "eval_runtime": 48.3273, | |
| "eval_samples_per_second": 8.753, | |
| "eval_steps_per_second": 1.097, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019956000000000002, | |
| "loss": 2.6655, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019952000000000001, | |
| "loss": 2.5982, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019948, | |
| "loss": 2.5936, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019944, | |
| "loss": 2.625, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019940000000000002, | |
| "loss": 2.6117, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019936000000000002, | |
| "loss": 2.5167, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019932, | |
| "loss": 2.4674, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019928, | |
| "loss": 2.5246, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019924, | |
| "loss": 2.5045, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019920000000000002, | |
| "loss": 2.5222, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.5987609032363251, | |
| "eval_loss": 2.0005741119384766, | |
| "eval_runtime": 47.4839, | |
| "eval_samples_per_second": 8.908, | |
| "eval_steps_per_second": 1.116, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019916, | |
| "loss": 2.5048, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019912, | |
| "loss": 2.4859, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019908, | |
| "loss": 2.439, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019904, | |
| "loss": 2.489, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.000199, | |
| "loss": 2.5181, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019896, | |
| "loss": 2.4656, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019892000000000003, | |
| "loss": 2.4849, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019888, | |
| "loss": 2.4934, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019884000000000001, | |
| "loss": 2.4359, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001988, | |
| "loss": 2.4123, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.6184886280264124, | |
| "eval_loss": 1.9406265020370483, | |
| "eval_runtime": 50.1664, | |
| "eval_samples_per_second": 8.432, | |
| "eval_steps_per_second": 1.056, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019876, | |
| "loss": 2.4585, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019872000000000002, | |
| "loss": 2.436, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019868, | |
| "loss": 2.4361, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019864, | |
| "loss": 2.4193, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001986, | |
| "loss": 2.4404, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019856000000000002, | |
| "loss": 2.4109, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019852000000000002, | |
| "loss": 2.4257, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019848, | |
| "loss": 2.423, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019844, | |
| "loss": 2.3701, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001984, | |
| "loss": 2.4469, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.6204450966006358, | |
| "eval_loss": 1.9681750535964966, | |
| "eval_runtime": 47.2918, | |
| "eval_samples_per_second": 8.944, | |
| "eval_steps_per_second": 1.121, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019836000000000002, | |
| "loss": 2.3953, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019832, | |
| "loss": 2.3848, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019828, | |
| "loss": 2.3802, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019824, | |
| "loss": 2.4174, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019820000000000002, | |
| "loss": 2.4125, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019816000000000001, | |
| "loss": 2.387, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019812, | |
| "loss": 2.3491, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019808, | |
| "loss": 2.3997, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019804, | |
| "loss": 2.3107, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019800000000000002, | |
| "loss": 2.3367, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.6377272356729436, | |
| "eval_loss": 1.8571785688400269, | |
| "eval_runtime": 47.2012, | |
| "eval_samples_per_second": 8.962, | |
| "eval_steps_per_second": 1.123, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019796, | |
| "loss": 2.3571, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019792000000000003, | |
| "loss": 2.325, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019788, | |
| "loss": 2.39, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019784, | |
| "loss": 2.3508, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001978, | |
| "loss": 2.3736, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019776, | |
| "loss": 2.2891, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019772000000000002, | |
| "loss": 2.3026, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019768, | |
| "loss": 2.2965, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019764, | |
| "loss": 2.3467, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001976, | |
| "loss": 2.2691, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.6315317518545692, | |
| "eval_loss": 1.8730525970458984, | |
| "eval_runtime": 46.6226, | |
| "eval_samples_per_second": 9.073, | |
| "eval_steps_per_second": 1.137, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019756, | |
| "loss": 2.3046, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019752000000000002, | |
| "loss": 2.2575, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019748, | |
| "loss": 2.2895, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019744, | |
| "loss": 2.2699, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001974, | |
| "loss": 2.2235, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019736000000000002, | |
| "loss": 2.2322, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019732000000000001, | |
| "loss": 2.2743, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019728, | |
| "loss": 2.2625, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019724, | |
| "loss": 2.2843, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001972, | |
| "loss": 2.2715, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.632428466617755, | |
| "eval_loss": 1.8891419172286987, | |
| "eval_runtime": 47.1404, | |
| "eval_samples_per_second": 8.973, | |
| "eval_steps_per_second": 1.124, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019716000000000002, | |
| "loss": 2.2755, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019712, | |
| "loss": 2.2597, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019708000000000003, | |
| "loss": 2.2185, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019704, | |
| "loss": 2.3046, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019700000000000002, | |
| "loss": 2.3451, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019696, | |
| "loss": 2.2956, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019692, | |
| "loss": 2.2371, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019688000000000003, | |
| "loss": 2.2705, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019684, | |
| "loss": 2.2141, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001968, | |
| "loss": 2.2344, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.6379717942447216, | |
| "eval_loss": 1.8463128805160522, | |
| "eval_runtime": 47.4067, | |
| "eval_samples_per_second": 8.923, | |
| "eval_steps_per_second": 1.118, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019676, | |
| "loss": 2.221, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019672000000000003, | |
| "loss": 2.3338, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019668000000000002, | |
| "loss": 2.1978, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019664000000000001, | |
| "loss": 2.2532, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001966, | |
| "loss": 2.2765, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019656, | |
| "loss": 2.2643, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019652000000000002, | |
| "loss": 2.2794, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019648000000000002, | |
| "loss": 2.2269, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019644, | |
| "loss": 2.2576, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001964, | |
| "loss": 2.2234, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.632183908045977, | |
| "eval_loss": 1.866058588027954, | |
| "eval_runtime": 46.4721, | |
| "eval_samples_per_second": 9.102, | |
| "eval_steps_per_second": 1.14, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019636000000000002, | |
| "loss": 2.2282, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019632000000000002, | |
| "loss": 2.2236, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019628, | |
| "loss": 2.2008, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019624, | |
| "loss": 2.2731, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001962, | |
| "loss": 2.2424, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019616000000000002, | |
| "loss": 2.1774, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019612, | |
| "loss": 2.1652, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019608, | |
| "loss": 2.1703, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019604, | |
| "loss": 2.185, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.000196, | |
| "loss": 2.1818, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.6382163528164996, | |
| "eval_loss": 1.81806218624115, | |
| "eval_runtime": 60.7049, | |
| "eval_samples_per_second": 6.968, | |
| "eval_steps_per_second": 0.873, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019596000000000001, | |
| "loss": 2.1961, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019592, | |
| "loss": 2.1806, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019588000000000003, | |
| "loss": 2.1523, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019584, | |
| "loss": 2.1305, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019580000000000002, | |
| "loss": 2.1467, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019576, | |
| "loss": 2.1324, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019572, | |
| "loss": 2.211, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019568000000000002, | |
| "loss": 2.1626, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019564, | |
| "loss": 2.1327, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001956, | |
| "loss": 2.1808, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.6419662509170947, | |
| "eval_loss": 1.838297724723816, | |
| "eval_runtime": 61.0821, | |
| "eval_samples_per_second": 6.925, | |
| "eval_steps_per_second": 0.868, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019556, | |
| "loss": 2.2277, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019552000000000003, | |
| "loss": 2.1227, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019548000000000002, | |
| "loss": 2.2336, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019544, | |
| "loss": 2.1708, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001954, | |
| "loss": 2.1549, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019536, | |
| "loss": 2.1776, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019532000000000002, | |
| "loss": 2.1634, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019528000000000001, | |
| "loss": 2.1891, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019524, | |
| "loss": 2.2221, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001952, | |
| "loss": 2.1885, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.6440857585391702, | |
| "eval_loss": 1.8327720165252686, | |
| "eval_runtime": 61.1648, | |
| "eval_samples_per_second": 6.916, | |
| "eval_steps_per_second": 0.867, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019516000000000002, | |
| "loss": 2.1854, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019512000000000002, | |
| "loss": 2.1554, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019508, | |
| "loss": 2.1365, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019504, | |
| "loss": 2.1783, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.000195, | |
| "loss": 2.1918, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019496000000000002, | |
| "loss": 2.2186, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019492, | |
| "loss": 2.1508, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019488000000000003, | |
| "loss": 2.1997, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019484, | |
| "loss": 2.0978, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001948, | |
| "loss": 2.1547, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.648650851879025, | |
| "eval_loss": 1.7967556715011597, | |
| "eval_runtime": 60.331, | |
| "eval_samples_per_second": 7.011, | |
| "eval_steps_per_second": 0.878, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019476, | |
| "loss": 2.1202, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019472, | |
| "loss": 2.1406, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019468000000000003, | |
| "loss": 2.149, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019464, | |
| "loss": 2.1915, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019460000000000001, | |
| "loss": 2.1721, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019456, | |
| "loss": 2.1155, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019452, | |
| "loss": 2.138, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019448000000000002, | |
| "loss": 2.0946, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019444, | |
| "loss": 2.1564, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001944, | |
| "loss": 2.1261, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.6471835004483574, | |
| "eval_loss": 1.8035624027252197, | |
| "eval_runtime": 59.6014, | |
| "eval_samples_per_second": 7.097, | |
| "eval_steps_per_second": 0.889, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019436, | |
| "loss": 2.1554, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019432000000000002, | |
| "loss": 2.1857, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019428000000000002, | |
| "loss": 2.1381, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019424, | |
| "loss": 2.1638, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001942, | |
| "loss": 2.1491, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019416, | |
| "loss": 2.209, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019412000000000002, | |
| "loss": 2.2035, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019408, | |
| "loss": 2.079, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019404, | |
| "loss": 2.1535, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.000194, | |
| "loss": 2.1074, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.6522377109317682, | |
| "eval_loss": 1.7710509300231934, | |
| "eval_runtime": 45.8627, | |
| "eval_samples_per_second": 9.223, | |
| "eval_steps_per_second": 1.156, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019396000000000002, | |
| "loss": 2.0692, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019392000000000001, | |
| "loss": 2.106, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019388, | |
| "loss": 2.133, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019384, | |
| "loss": 2.0844, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001938, | |
| "loss": 2.0839, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019376000000000002, | |
| "loss": 2.1023, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019372, | |
| "loss": 2.124, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019368000000000003, | |
| "loss": 2.1142, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019364, | |
| "loss": 2.0142, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019360000000000002, | |
| "loss": 2.1537, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.6504442814053966, | |
| "eval_loss": 1.7606570720672607, | |
| "eval_runtime": 46.4971, | |
| "eval_samples_per_second": 9.097, | |
| "eval_steps_per_second": 1.14, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019356, | |
| "loss": 2.0624, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019352, | |
| "loss": 2.1308, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019348000000000002, | |
| "loss": 2.0587, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019344, | |
| "loss": 2.1031, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001934, | |
| "loss": 2.0765, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019336, | |
| "loss": 2.0972, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019332, | |
| "loss": 2.0875, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019328000000000002, | |
| "loss": 2.1277, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019323999999999999, | |
| "loss": 2.088, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001932, | |
| "loss": 2.1085, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.6466943833048014, | |
| "eval_loss": 1.7533295154571533, | |
| "eval_runtime": 45.9496, | |
| "eval_samples_per_second": 9.206, | |
| "eval_steps_per_second": 1.153, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019316, | |
| "loss": 2.159, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019312000000000002, | |
| "loss": 2.0808, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019308000000000001, | |
| "loss": 2.1481, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019304, | |
| "loss": 2.0853, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.000193, | |
| "loss": 2.0692, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019296, | |
| "loss": 2.2094, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019292000000000002, | |
| "loss": 2.0793, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019288, | |
| "loss": 2.0469, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019284, | |
| "loss": 2.1105, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001928, | |
| "loss": 2.1268, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.6550093747452514, | |
| "eval_loss": 1.7450594902038574, | |
| "eval_runtime": 46.1382, | |
| "eval_samples_per_second": 9.168, | |
| "eval_steps_per_second": 1.149, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019276000000000002, | |
| "loss": 2.0895, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019272, | |
| "loss": 2.1127, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019268, | |
| "loss": 2.0435, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019264, | |
| "loss": 2.0799, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001926, | |
| "loss": 2.0886, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019256, | |
| "loss": 2.0726, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019252, | |
| "loss": 2.1095, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019248000000000003, | |
| "loss": 2.0732, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019244000000000002, | |
| "loss": 2.0577, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019240000000000001, | |
| "loss": 2.0991, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.6504442814053966, | |
| "eval_loss": 1.7744449377059937, | |
| "eval_runtime": 46.1319, | |
| "eval_samples_per_second": 9.169, | |
| "eval_steps_per_second": 1.149, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019236, | |
| "loss": 2.113, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019232, | |
| "loss": 2.0054, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019228000000000002, | |
| "loss": 2.0531, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019224000000000002, | |
| "loss": 2.0268, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001922, | |
| "loss": 2.0703, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019216, | |
| "loss": 2.0101, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019212000000000002, | |
| "loss": 2.0598, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019208000000000002, | |
| "loss": 2.0731, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019204, | |
| "loss": 2.0695, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.000192, | |
| "loss": 2.0982, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.6515855547403603, | |
| "eval_loss": 1.738739252090454, | |
| "eval_runtime": 45.7921, | |
| "eval_samples_per_second": 9.237, | |
| "eval_steps_per_second": 1.157, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019196, | |
| "loss": 2.0565, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019192000000000002, | |
| "loss": 2.0358, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019188, | |
| "loss": 2.0407, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019184, | |
| "loss": 2.0584, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001918, | |
| "loss": 2.0313, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019176, | |
| "loss": 2.0852, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019172000000000001, | |
| "loss": 2.1305, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019168, | |
| "loss": 2.8885, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019164000000000003, | |
| "loss": 5.2587, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001916, | |
| "loss": 5.5295, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.31556207711746964, | |
| "eval_loss": 4.5144548416137695, | |
| "eval_runtime": 46.4657, | |
| "eval_samples_per_second": 9.103, | |
| "eval_steps_per_second": 1.141, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019156000000000002, | |
| "loss": 4.2499, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019152, | |
| "loss": 2.2078, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019148, | |
| "loss": 2.1916, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019144000000000002, | |
| "loss": 2.1247, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001914, | |
| "loss": 2.0517, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019136, | |
| "loss": 2.1537, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019132, | |
| "loss": 2.1611, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019128000000000003, | |
| "loss": 2.1015, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019124000000000002, | |
| "loss": 2.191, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001912, | |
| "loss": 2.0354, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.652645308551398, | |
| "eval_loss": 1.74555242061615, | |
| "eval_runtime": 45.8199, | |
| "eval_samples_per_second": 9.232, | |
| "eval_steps_per_second": 1.157, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019116, | |
| "loss": 2.0853, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019112, | |
| "loss": 2.0091, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019108000000000002, | |
| "loss": 2.093, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019104000000000001, | |
| "loss": 1.9993, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.000191, | |
| "loss": 2.0933, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019096, | |
| "loss": 2.0847, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019092000000000002, | |
| "loss": 2.1092, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019088000000000002, | |
| "loss": 2.1634, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019084, | |
| "loss": 2.048, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001908, | |
| "loss": 2.0382, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.6545202576016956, | |
| "eval_loss": 1.7376079559326172, | |
| "eval_runtime": 46.305, | |
| "eval_samples_per_second": 9.135, | |
| "eval_steps_per_second": 1.145, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019076, | |
| "loss": 2.0105, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019072000000000002, | |
| "loss": 1.9905, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019068, | |
| "loss": 2.1397, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019064000000000003, | |
| "loss": 1.9861, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001906, | |
| "loss": 2.0603, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019056000000000002, | |
| "loss": 2.0137, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019052, | |
| "loss": 2.0223, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019048, | |
| "loss": 2.0917, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019044000000000003, | |
| "loss": 2.0426, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001904, | |
| "loss": 2.0427, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_accuracy": 0.6534605037906579, | |
| "eval_loss": 1.7286646366119385, | |
| "eval_runtime": 46.0656, | |
| "eval_samples_per_second": 9.183, | |
| "eval_steps_per_second": 1.151, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019036000000000001, | |
| "loss": 1.9983, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019032, | |
| "loss": 2.0404, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019028, | |
| "loss": 2.0165, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019024000000000002, | |
| "loss": 2.0585, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001902, | |
| "loss": 2.0517, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019016, | |
| "loss": 2.041, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019012, | |
| "loss": 1.9899, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019008000000000002, | |
| "loss": 1.9965, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019004000000000002, | |
| "loss": 2.0312, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019, | |
| "loss": 1.9543, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_accuracy": 0.6536235428385099, | |
| "eval_loss": 1.7141377925872803, | |
| "eval_runtime": 46.1754, | |
| "eval_samples_per_second": 9.161, | |
| "eval_steps_per_second": 1.148, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00018996, | |
| "loss": 2.0157, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00018992, | |
| "loss": 2.0398, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00018988000000000002, | |
| "loss": 2.0151, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00018984, | |
| "loss": 2.0104, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001898, | |
| "loss": 2.1258, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00018976, | |
| "loss": 2.0673, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00018972000000000002, | |
| "loss": 1.9949, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018968, | |
| "loss": 2.0162, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018964, | |
| "loss": 2.065, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001896, | |
| "loss": 1.9798, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.6568843237955491, | |
| "eval_loss": 1.7275162935256958, | |
| "eval_runtime": 46.0053, | |
| "eval_samples_per_second": 9.195, | |
| "eval_steps_per_second": 1.152, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018956, | |
| "loss": 2.0334, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018952000000000002, | |
| "loss": 2.0242, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018948, | |
| "loss": 2.0321, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018944000000000003, | |
| "loss": 2.0455, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001894, | |
| "loss": 2.0152, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018936000000000002, | |
| "loss": 2.0764, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018932, | |
| "loss": 2.0572, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018928, | |
| "loss": 1.9985, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018924000000000002, | |
| "loss": 2.0185, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001892, | |
| "loss": 2.0054, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.6598190266568843, | |
| "eval_loss": 1.6908519268035889, | |
| "eval_runtime": 45.7104, | |
| "eval_samples_per_second": 9.254, | |
| "eval_steps_per_second": 1.159, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018916, | |
| "loss": 2.0133, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018912, | |
| "loss": 2.0096, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018908000000000003, | |
| "loss": 2.0126, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018904000000000002, | |
| "loss": 1.9772, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018899999999999999, | |
| "loss": 2.0467, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018896, | |
| "loss": 1.9178, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018892, | |
| "loss": 2.0297, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018888000000000002, | |
| "loss": 2.0253, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018884000000000001, | |
| "loss": 1.9633, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001888, | |
| "loss": 2.0391, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.657128882367327, | |
| "eval_loss": 1.7396591901779175, | |
| "eval_runtime": 46.5669, | |
| "eval_samples_per_second": 9.084, | |
| "eval_steps_per_second": 1.138, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018876, | |
| "loss": 2.0096, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018872, | |
| "loss": 1.9861, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018868000000000002, | |
| "loss": 1.9337, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018864, | |
| "loss": 2.0316, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001886, | |
| "loss": 2.0544, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018856, | |
| "loss": 1.9592, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018852000000000002, | |
| "loss": 1.9677, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018848, | |
| "loss": 2.0595, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018844, | |
| "loss": 1.9924, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001884, | |
| "loss": 1.988, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.6597375071329583, | |
| "eval_loss": 1.7008874416351318, | |
| "eval_runtime": 46.6514, | |
| "eval_samples_per_second": 9.067, | |
| "eval_steps_per_second": 1.136, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018836, | |
| "loss": 2.0202, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018832, | |
| "loss": 1.9864, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018828, | |
| "loss": 1.9831, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018824000000000003, | |
| "loss": 1.9967, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001882, | |
| "loss": 1.9784, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018816000000000001, | |
| "loss": 1.9662, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018812, | |
| "loss": 1.9302, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018808, | |
| "loss": 2.0279, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018804000000000002, | |
| "loss": 2.0217, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.000188, | |
| "loss": 2.0044, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.6644656395206652, | |
| "eval_loss": 1.6991885900497437, | |
| "eval_runtime": 45.8483, | |
| "eval_samples_per_second": 9.226, | |
| "eval_steps_per_second": 1.156, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018796, | |
| "loss": 2.0481, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018792, | |
| "loss": 1.9341, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018788000000000002, | |
| "loss": 1.9922, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018784000000000002, | |
| "loss": 1.9681, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001878, | |
| "loss": 1.97, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018776, | |
| "loss": 1.9463, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018772, | |
| "loss": 1.9919, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018768000000000002, | |
| "loss": 1.9762, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018764, | |
| "loss": 1.9491, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001876, | |
| "loss": 2.0099, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.6629167685660716, | |
| "eval_loss": 1.6818691492080688, | |
| "eval_runtime": 47.0155, | |
| "eval_samples_per_second": 8.997, | |
| "eval_steps_per_second": 1.127, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018756, | |
| "loss": 1.9804, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018752, | |
| "loss": 1.9109, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018748000000000001, | |
| "loss": 1.9892, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018744, | |
| "loss": 1.9546, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018740000000000003, | |
| "loss": 1.9803, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018736, | |
| "loss": 1.9629, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018732000000000002, | |
| "loss": 1.9725, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018728, | |
| "loss": 2.0243, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018724, | |
| "loss": 2.0426, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018720000000000002, | |
| "loss": 1.9622, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.6634058857096274, | |
| "eval_loss": 1.6796367168426514, | |
| "eval_runtime": 45.6554, | |
| "eval_samples_per_second": 9.265, | |
| "eval_steps_per_second": 1.161, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018716, | |
| "loss": 2.0019, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018712, | |
| "loss": 1.9587, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018708, | |
| "loss": 1.9816, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018704000000000003, | |
| "loss": 1.9877, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018700000000000002, | |
| "loss": 2.0077, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018696, | |
| "loss": 2.043, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018692, | |
| "loss": 1.9861, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018688, | |
| "loss": 1.9399, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018684000000000002, | |
| "loss": 1.9473, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018680000000000001, | |
| "loss": 1.9716, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.657128882367327, | |
| "eval_loss": 1.7205617427825928, | |
| "eval_runtime": 46.0038, | |
| "eval_samples_per_second": 9.195, | |
| "eval_steps_per_second": 1.152, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018676, | |
| "loss": 1.9388, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018672, | |
| "loss": 1.9062, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018668000000000002, | |
| "loss": 2.0283, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018664000000000002, | |
| "loss": 1.9347, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001866, | |
| "loss": 1.9422, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018656, | |
| "loss": 1.935, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018652, | |
| "loss": 1.9642, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018648000000000002, | |
| "loss": 1.9179, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018644, | |
| "loss": 1.9948, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018640000000000003, | |
| "loss": 1.9136, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.6654438738077769, | |
| "eval_loss": 1.6819649934768677, | |
| "eval_runtime": 45.6304, | |
| "eval_samples_per_second": 9.27, | |
| "eval_steps_per_second": 1.162, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018636, | |
| "loss": 1.8923, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018632000000000002, | |
| "loss": 1.9587, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018628, | |
| "loss": 1.9211, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018624, | |
| "loss": 1.9302, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018620000000000003, | |
| "loss": 1.9764, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018616, | |
| "loss": 1.9956, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018612000000000001, | |
| "loss": 1.9196, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018608, | |
| "loss": 1.955, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018604, | |
| "loss": 1.9914, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018600000000000002, | |
| "loss": 1.9277, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.6650362761881471, | |
| "eval_loss": 1.6978471279144287, | |
| "eval_runtime": 45.6548, | |
| "eval_samples_per_second": 9.265, | |
| "eval_steps_per_second": 1.161, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018596, | |
| "loss": 1.949, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018592, | |
| "loss": 1.927, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018588, | |
| "loss": 2.0058, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018584000000000002, | |
| "loss": 1.9854, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018580000000000002, | |
| "loss": 1.9646, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018576, | |
| "loss": 1.9517, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018572, | |
| "loss": 2.0103, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018568, | |
| "loss": 1.9367, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018564000000000002, | |
| "loss": 1.9968, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001856, | |
| "loss": 1.9727, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.6593299095133285, | |
| "eval_loss": 1.6777493953704834, | |
| "eval_runtime": 60.7874, | |
| "eval_samples_per_second": 6.959, | |
| "eval_steps_per_second": 0.872, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018556, | |
| "loss": 1.9233, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018552, | |
| "loss": 1.926, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018548000000000002, | |
| "loss": 1.9538, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018544, | |
| "loss": 1.9795, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001854, | |
| "loss": 1.9675, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018536, | |
| "loss": 1.8831, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018532, | |
| "loss": 1.9082, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018528000000000001, | |
| "loss": 1.9514, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018524, | |
| "loss": 1.9714, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018520000000000003, | |
| "loss": 2.0391, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.6623461318985897, | |
| "eval_loss": 1.6935285329818726, | |
| "eval_runtime": 59.3856, | |
| "eval_samples_per_second": 7.123, | |
| "eval_steps_per_second": 0.892, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018516, | |
| "loss": 1.9065, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018512000000000002, | |
| "loss": 1.9062, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018508, | |
| "loss": 1.9187, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018504, | |
| "loss": 1.9407, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018500000000000002, | |
| "loss": 1.9684, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018496, | |
| "loss": 1.9124, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018492, | |
| "loss": 1.9626, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018488, | |
| "loss": 1.8665, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018484000000000003, | |
| "loss": 1.9432, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018480000000000002, | |
| "loss": 1.9367, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.6560691285562892, | |
| "eval_loss": 1.7309006452560425, | |
| "eval_runtime": 61.2631, | |
| "eval_samples_per_second": 6.905, | |
| "eval_steps_per_second": 0.865, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018476, | |
| "loss": 1.9483, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018472, | |
| "loss": 1.9067, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018468, | |
| "loss": 1.9485, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018464000000000002, | |
| "loss": 1.9529, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018460000000000001, | |
| "loss": 1.9463, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018456, | |
| "loss": 2.0001, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018452, | |
| "loss": 1.8994, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018448, | |
| "loss": 1.8648, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018444000000000002, | |
| "loss": 1.9028, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001844, | |
| "loss": 1.9146, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.6616939757071819, | |
| "eval_loss": 1.7054038047790527, | |
| "eval_runtime": 60.7176, | |
| "eval_samples_per_second": 6.967, | |
| "eval_steps_per_second": 0.873, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018436, | |
| "loss": 1.945, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018432, | |
| "loss": 1.9027, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018428000000000002, | |
| "loss": 1.959, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018424, | |
| "loss": 1.9469, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001842, | |
| "loss": 1.9149, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018416, | |
| "loss": 1.9151, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018412, | |
| "loss": 1.9054, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018408, | |
| "loss": 1.8939, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018404, | |
| "loss": 1.9331, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018400000000000003, | |
| "loss": 1.957, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.6670742642862966, | |
| "eval_loss": 1.6463383436203003, | |
| "eval_runtime": 46.0232, | |
| "eval_samples_per_second": 9.191, | |
| "eval_steps_per_second": 1.152, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018396, | |
| "loss": 1.9497, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018392000000000001, | |
| "loss": 1.9271, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018388, | |
| "loss": 1.9087, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018384, | |
| "loss": 1.9161, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018380000000000002, | |
| "loss": 1.9423, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018376, | |
| "loss": 1.8995, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018372, | |
| "loss": 1.9421, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018368, | |
| "loss": 1.9013, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018364000000000002, | |
| "loss": 1.9092, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018360000000000002, | |
| "loss": 1.882, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.6641395614249613, | |
| "eval_loss": 1.6783875226974487, | |
| "eval_runtime": 47.0079, | |
| "eval_samples_per_second": 8.998, | |
| "eval_steps_per_second": 1.127, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018356, | |
| "loss": 1.9424, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018352, | |
| "loss": 1.9477, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018348, | |
| "loss": 1.9255, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018344000000000002, | |
| "loss": 1.9456, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001834, | |
| "loss": 1.9288, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018336, | |
| "loss": 1.9088, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018332, | |
| "loss": 1.959, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018328000000000002, | |
| "loss": 1.9619, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018324000000000001, | |
| "loss": 1.9511, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0001832, | |
| "loss": 1.9489, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.6603081438004402, | |
| "eval_loss": 1.676958680152893, | |
| "eval_runtime": 46.3451, | |
| "eval_samples_per_second": 9.127, | |
| "eval_steps_per_second": 1.144, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018316, | |
| "loss": 1.8862, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018312, | |
| "loss": 1.8631, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018308000000000002, | |
| "loss": 1.9649, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018304, | |
| "loss": 1.9592, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.000183, | |
| "loss": 1.9317, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018296, | |
| "loss": 1.9138, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018292, | |
| "loss": 1.8876, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018288, | |
| "loss": 1.859, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018284, | |
| "loss": 1.9496, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018280000000000003, | |
| "loss": 1.9407, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.669601369528002, | |
| "eval_loss": 1.641465187072754, | |
| "eval_runtime": 46.8321, | |
| "eval_samples_per_second": 9.032, | |
| "eval_steps_per_second": 1.132, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018276, | |
| "loss": 1.9654, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018272, | |
| "loss": 1.9223, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018268, | |
| "loss": 1.9163, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018264, | |
| "loss": 1.9175, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018260000000000002, | |
| "loss": 1.9255, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018256, | |
| "loss": 1.8736, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018252, | |
| "loss": 1.8851, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018248, | |
| "loss": 1.9125, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018244000000000002, | |
| "loss": 1.888, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018240000000000002, | |
| "loss": 1.9402, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.6654438738077769, | |
| "eval_loss": 1.681833267211914, | |
| "eval_runtime": 46.6168, | |
| "eval_samples_per_second": 9.074, | |
| "eval_steps_per_second": 1.137, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018236, | |
| "loss": 1.8771, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018232, | |
| "loss": 1.9207, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018228, | |
| "loss": 1.8753, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018224000000000002, | |
| "loss": 1.8738, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0001822, | |
| "loss": 1.9238, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018216000000000003, | |
| "loss": 1.8845, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018212, | |
| "loss": 1.9076, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018208000000000002, | |
| "loss": 1.9064, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018204, | |
| "loss": 1.9555, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.000182, | |
| "loss": 1.894, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.6659329909513328, | |
| "eval_loss": 1.664554476737976, | |
| "eval_runtime": 46.5128, | |
| "eval_samples_per_second": 9.094, | |
| "eval_steps_per_second": 1.139, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018196000000000003, | |
| "loss": 1.9158, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018192, | |
| "loss": 1.9474, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018188000000000001, | |
| "loss": 1.9463, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018184, | |
| "loss": 1.8755, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018180000000000003, | |
| "loss": 1.9637, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018176000000000002, | |
| "loss": 1.9052, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018172, | |
| "loss": 1.9231, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018168, | |
| "loss": 1.9216, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018164, | |
| "loss": 1.8753, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018160000000000002, | |
| "loss": 1.9149, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.6674818619059265, | |
| "eval_loss": 1.6451318264007568, | |
| "eval_runtime": 46.9277, | |
| "eval_samples_per_second": 9.014, | |
| "eval_steps_per_second": 1.129, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018156000000000002, | |
| "loss": 1.8871, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018152, | |
| "loss": 1.9246, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018148, | |
| "loss": 1.9086, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018144, | |
| "loss": 1.9105, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018140000000000002, | |
| "loss": 1.9686, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018136, | |
| "loss": 1.8944, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018132, | |
| "loss": 1.8953, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018128, | |
| "loss": 1.898, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018124000000000002, | |
| "loss": 1.934, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0001812, | |
| "loss": 1.8868, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.6653623542838509, | |
| "eval_loss": 1.6440030336380005, | |
| "eval_runtime": 47.0909, | |
| "eval_samples_per_second": 8.983, | |
| "eval_steps_per_second": 1.125, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018116, | |
| "loss": 1.8573, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018112, | |
| "loss": 1.8907, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018108, | |
| "loss": 1.8429, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018104000000000001, | |
| "loss": 1.8393, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.000181, | |
| "loss": 2.0048, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018096000000000003, | |
| "loss": 1.8358, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018092, | |
| "loss": 1.9148, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018088000000000002, | |
| "loss": 1.8835, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018084, | |
| "loss": 1.8832, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0001808, | |
| "loss": 1.9157, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.6643841199967392, | |
| "eval_loss": 1.6713789701461792, | |
| "eval_runtime": 47.3501, | |
| "eval_samples_per_second": 8.933, | |
| "eval_steps_per_second": 1.119, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018076000000000002, | |
| "loss": 1.9131, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018072, | |
| "loss": 1.8841, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018068, | |
| "loss": 1.9479, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018064, | |
| "loss": 1.9109, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018060000000000003, | |
| "loss": 1.9122, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018056000000000002, | |
| "loss": 1.867, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018052, | |
| "loss": 1.9297, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018048, | |
| "loss": 1.8987, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018044, | |
| "loss": 1.8791, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018040000000000002, | |
| "loss": 1.884, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.669764408575854, | |
| "eval_loss": 1.6372376680374146, | |
| "eval_runtime": 45.8594, | |
| "eval_samples_per_second": 9.224, | |
| "eval_steps_per_second": 1.156, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018036000000000001, | |
| "loss": 1.9257, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018032, | |
| "loss": 1.8184, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018028, | |
| "loss": 1.9063, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018024, | |
| "loss": 1.9058, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018020000000000002, | |
| "loss": 1.8876, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018016, | |
| "loss": 1.8873, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018012, | |
| "loss": 1.8623, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018008, | |
| "loss": 1.8649, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018004000000000002, | |
| "loss": 1.9113, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018, | |
| "loss": 1.861, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.6632428466617755, | |
| "eval_loss": 1.6630749702453613, | |
| "eval_runtime": 46.3295, | |
| "eval_samples_per_second": 9.13, | |
| "eval_steps_per_second": 1.144, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017996, | |
| "loss": 1.95, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017992, | |
| "loss": 1.8517, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017988, | |
| "loss": 1.8582, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017984, | |
| "loss": 1.8658, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0001798, | |
| "loss": 1.9111, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017976000000000003, | |
| "loss": 1.8874, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017972, | |
| "loss": 1.8853, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017968000000000001, | |
| "loss": 1.8797, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017964, | |
| "loss": 1.8727, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0001796, | |
| "loss": 1.9064, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.6621015733268117, | |
| "eval_loss": 1.689902424812317, | |
| "eval_runtime": 47.432, | |
| "eval_samples_per_second": 8.918, | |
| "eval_steps_per_second": 1.117, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017956000000000002, | |
| "loss": 1.8958, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017952, | |
| "loss": 1.8912, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017948, | |
| "loss": 1.8342, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017944, | |
| "loss": 1.864, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017940000000000002, | |
| "loss": 1.8842, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017936000000000002, | |
| "loss": 1.8981, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017932, | |
| "loss": 1.8746, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017928, | |
| "loss": 1.8151, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017924, | |
| "loss": 1.8965, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017920000000000002, | |
| "loss": 1.9178, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.669682889051928, | |
| "eval_loss": 1.654188632965088, | |
| "eval_runtime": 47.2488, | |
| "eval_samples_per_second": 8.953, | |
| "eval_steps_per_second": 1.122, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017916, | |
| "loss": 1.8615, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017912, | |
| "loss": 1.8374, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017908, | |
| "loss": 1.9621, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017904000000000002, | |
| "loss": 1.8499, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017900000000000001, | |
| "loss": 1.8441, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017896, | |
| "loss": 1.9126, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00017892, | |
| "loss": 1.874, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017888, | |
| "loss": 1.9262, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017884000000000002, | |
| "loss": 1.8436, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001788, | |
| "loss": 1.9086, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.6702535257194098, | |
| "eval_loss": 1.6423653364181519, | |
| "eval_runtime": 47.3319, | |
| "eval_samples_per_second": 8.937, | |
| "eval_steps_per_second": 1.12, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017876, | |
| "loss": 1.9283, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017872, | |
| "loss": 1.8879, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017868, | |
| "loss": 1.9249, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017864, | |
| "loss": 1.866, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001786, | |
| "loss": 1.8631, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017856000000000003, | |
| "loss": 1.8883, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017852, | |
| "loss": 1.9085, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017848, | |
| "loss": 1.9506, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017844, | |
| "loss": 1.894, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001784, | |
| "loss": 1.9128, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.6704165647672617, | |
| "eval_loss": 1.65791916847229, | |
| "eval_runtime": 46.7984, | |
| "eval_samples_per_second": 9.039, | |
| "eval_steps_per_second": 1.133, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017836000000000002, | |
| "loss": 1.8842, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017832, | |
| "loss": 1.8935, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017828, | |
| "loss": 1.84, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017824, | |
| "loss": 1.8379, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017820000000000002, | |
| "loss": 1.8661, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017816000000000002, | |
| "loss": 1.8418, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017812, | |
| "loss": 1.8773, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017808, | |
| "loss": 1.939, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017804, | |
| "loss": 1.911, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017800000000000002, | |
| "loss": 1.8751, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.6681340180973343, | |
| "eval_loss": 1.6451387405395508, | |
| "eval_runtime": 46.943, | |
| "eval_samples_per_second": 9.011, | |
| "eval_steps_per_second": 1.129, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017796, | |
| "loss": 1.8385, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017792, | |
| "loss": 1.9321, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017788, | |
| "loss": 1.8533, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017784000000000002, | |
| "loss": 1.8428, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001778, | |
| "loss": 1.8833, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017776, | |
| "loss": 1.8387, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017772, | |
| "loss": 1.8742, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017768, | |
| "loss": 1.8835, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017764000000000001, | |
| "loss": 1.9084, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001776, | |
| "loss": 1.8289, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.6712317600065215, | |
| "eval_loss": 1.649842619895935, | |
| "eval_runtime": 47.4408, | |
| "eval_samples_per_second": 8.916, | |
| "eval_steps_per_second": 1.117, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017756000000000003, | |
| "loss": 1.9069, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017752, | |
| "loss": 1.8689, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017748000000000002, | |
| "loss": 1.8327, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017744, | |
| "loss": 1.8061, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001774, | |
| "loss": 1.8382, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017736000000000002, | |
| "loss": 1.8691, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017732000000000002, | |
| "loss": 1.8348, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017728, | |
| "loss": 1.8645, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017724, | |
| "loss": 1.9094, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001772, | |
| "loss": 1.8597, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.669601369528002, | |
| "eval_loss": 1.6287590265274048, | |
| "eval_runtime": 46.725, | |
| "eval_samples_per_second": 9.053, | |
| "eval_steps_per_second": 1.134, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017716000000000002, | |
| "loss": 1.8063, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017712, | |
| "loss": 1.8771, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017708, | |
| "loss": 1.9203, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017704, | |
| "loss": 1.9039, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017700000000000002, | |
| "loss": 1.8713, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017696, | |
| "loss": 1.8446, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017692, | |
| "loss": 1.8771, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017688, | |
| "loss": 1.8959, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017684, | |
| "loss": 1.915, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017680000000000001, | |
| "loss": 1.8873, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.6718023966740034, | |
| "eval_loss": 1.634265422821045, | |
| "eval_runtime": 47.1163, | |
| "eval_samples_per_second": 8.978, | |
| "eval_steps_per_second": 1.125, | |
| "step": 5800 | |
| } | |
| ], | |
| "max_steps": 50000, | |
| "num_train_epochs": 2, | |
| "total_flos": 1.066306262532096e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |