| { | |
| "best_metric": 3.4388856887817383, | |
| "best_model_checkpoint": "./exper4_mesum5/checkpoint-1700", | |
| "epoch": 4.0, | |
| "global_step": 1720, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.988372093023256e-05, | |
| "loss": 3.3647, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9767441860465116e-05, | |
| "loss": 3.2445, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9651162790697676e-05, | |
| "loss": 3.3278, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.9534883720930235e-05, | |
| "loss": 3.297, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.941860465116279e-05, | |
| "loss": 3.3401, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.9302325581395353e-05, | |
| "loss": 3.2323, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.918604651162791e-05, | |
| "loss": 3.315, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.9069767441860468e-05, | |
| "loss": 3.248, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.8953488372093027e-05, | |
| "loss": 3.4069, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.8837209302325582e-05, | |
| "loss": 3.3793, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_accuracy": 0.13076923076923078, | |
| "eval_loss": 3.4527063369750977, | |
| "eval_runtime": 22.7969, | |
| "eval_samples_per_second": 74.133, | |
| "eval_steps_per_second": 9.3, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.872093023255814e-05, | |
| "loss": 3.2854, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.86046511627907e-05, | |
| "loss": 3.3025, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.8488372093023256e-05, | |
| "loss": 3.1857, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.8372093023255815e-05, | |
| "loss": 3.2973, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.825581395348837e-05, | |
| "loss": 3.4285, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.813953488372093e-05, | |
| "loss": 3.1757, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.802325581395349e-05, | |
| "loss": 3.3628, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.790697674418605e-05, | |
| "loss": 3.2249, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.7790697674418608e-05, | |
| "loss": 3.3497, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.7674418604651163e-05, | |
| "loss": 3.2492, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_accuracy": 0.13313609467455623, | |
| "eval_loss": 3.4500620365142822, | |
| "eval_runtime": 23.5821, | |
| "eval_samples_per_second": 71.664, | |
| "eval_steps_per_second": 8.99, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.7558139534883722e-05, | |
| "loss": 3.355, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.744186046511628e-05, | |
| "loss": 3.312, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.7325581395348837e-05, | |
| "loss": 3.2116, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1.7209302325581396e-05, | |
| "loss": 3.3501, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.7093023255813955e-05, | |
| "loss": 3.2442, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.697674418604651e-05, | |
| "loss": 3.2724, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.6860465116279073e-05, | |
| "loss": 3.2776, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.6755813953488372e-05, | |
| "loss": 3.4586, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.663953488372093e-05, | |
| "loss": 3.3761, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.652325581395349e-05, | |
| "loss": 3.3847, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_accuracy": 0.12721893491124261, | |
| "eval_loss": 3.4499523639678955, | |
| "eval_runtime": 22.8602, | |
| "eval_samples_per_second": 73.928, | |
| "eval_steps_per_second": 9.274, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.6406976744186046e-05, | |
| "loss": 3.4276, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.6290697674418605e-05, | |
| "loss": 3.3264, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.6174418604651164e-05, | |
| "loss": 3.4018, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.6058139534883723e-05, | |
| "loss": 3.3421, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.5941860465116282e-05, | |
| "loss": 3.2895, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.5825581395348838e-05, | |
| "loss": 3.2749, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.5709302325581397e-05, | |
| "loss": 3.3534, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.5593023255813956e-05, | |
| "loss": 3.4288, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.5476744186046512e-05, | |
| "loss": 3.189, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.536046511627907e-05, | |
| "loss": 3.3739, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.1319526627218935, | |
| "eval_loss": 3.4503750801086426, | |
| "eval_runtime": 23.6647, | |
| "eval_samples_per_second": 71.414, | |
| "eval_steps_per_second": 8.958, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.5244186046511628e-05, | |
| "loss": 3.3453, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.5127906976744187e-05, | |
| "loss": 3.2949, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.5011627906976745e-05, | |
| "loss": 3.3634, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.4895348837209302e-05, | |
| "loss": 3.3534, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.4779069767441863e-05, | |
| "loss": 3.1066, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.466279069767442e-05, | |
| "loss": 3.3086, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 1.4546511627906978e-05, | |
| "loss": 3.3534, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.4430232558139537e-05, | |
| "loss": 3.2703, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.4313953488372094e-05, | |
| "loss": 3.3116, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1.4197674418604652e-05, | |
| "loss": 3.4181, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_accuracy": 0.1319526627218935, | |
| "eval_loss": 3.4451892375946045, | |
| "eval_runtime": 23.0049, | |
| "eval_samples_per_second": 73.463, | |
| "eval_steps_per_second": 9.215, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.408139534883721e-05, | |
| "loss": 3.1991, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.3965116279069768e-05, | |
| "loss": 3.1958, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.3848837209302326e-05, | |
| "loss": 3.3147, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.3732558139534885e-05, | |
| "loss": 3.0998, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.3616279069767444e-05, | |
| "loss": 3.1957, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.3500000000000001e-05, | |
| "loss": 3.2075, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.338372093023256e-05, | |
| "loss": 3.3422, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.3267441860465118e-05, | |
| "loss": 3.3129, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.3151162790697675e-05, | |
| "loss": 3.1976, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.3034883720930234e-05, | |
| "loss": 3.214, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_accuracy": 0.1319526627218935, | |
| "eval_loss": 3.4503166675567627, | |
| "eval_runtime": 22.9971, | |
| "eval_samples_per_second": 73.487, | |
| "eval_steps_per_second": 9.219, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.2918604651162792e-05, | |
| "loss": 3.4408, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.2802325581395349e-05, | |
| "loss": 3.3097, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.2686046511627908e-05, | |
| "loss": 3.2481, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.2569767441860465e-05, | |
| "loss": 3.3651, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 1.2453488372093023e-05, | |
| "loss": 3.3526, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 1.2337209302325584e-05, | |
| "loss": 3.2383, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 1.2220930232558141e-05, | |
| "loss": 3.2768, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 1.2104651162790698e-05, | |
| "loss": 3.4161, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.1988372093023258e-05, | |
| "loss": 3.317, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 1.1872093023255815e-05, | |
| "loss": 3.282, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_accuracy": 0.13254437869822486, | |
| "eval_loss": 3.4444165229797363, | |
| "eval_runtime": 20.4538, | |
| "eval_samples_per_second": 82.625, | |
| "eval_steps_per_second": 10.365, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 1.1755813953488372e-05, | |
| "loss": 3.379, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 1.1639534883720931e-05, | |
| "loss": 3.2142, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 1.1523255813953489e-05, | |
| "loss": 3.3683, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 1.1406976744186046e-05, | |
| "loss": 3.3712, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 1.1290697674418605e-05, | |
| "loss": 3.3247, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 1.1174418604651163e-05, | |
| "loss": 3.3054, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.1058139534883724e-05, | |
| "loss": 3.3486, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.0941860465116281e-05, | |
| "loss": 3.1514, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.0825581395348838e-05, | |
| "loss": 3.3587, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.0709302325581396e-05, | |
| "loss": 3.5308, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_accuracy": 0.13372781065088757, | |
| "eval_loss": 3.447305202484131, | |
| "eval_runtime": 20.3628, | |
| "eval_samples_per_second": 82.995, | |
| "eval_steps_per_second": 10.411, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.0593023255813955e-05, | |
| "loss": 3.2896, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.0476744186046512e-05, | |
| "loss": 3.3485, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.036046511627907e-05, | |
| "loss": 3.3358, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.0255813953488373e-05, | |
| "loss": 3.2554, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.0139534883720932e-05, | |
| "loss": 3.4244, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.002325581395349e-05, | |
| "loss": 3.2821, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.906976744186047e-06, | |
| "loss": 3.3164, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.790697674418606e-06, | |
| "loss": 3.0955, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.674418604651164e-06, | |
| "loss": 3.3709, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.558139534883721e-06, | |
| "loss": 3.2251, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_accuracy": 0.13609467455621302, | |
| "eval_loss": 3.441458225250244, | |
| "eval_runtime": 19.9721, | |
| "eval_samples_per_second": 84.618, | |
| "eval_steps_per_second": 10.615, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 9.44186046511628e-06, | |
| "loss": 3.3381, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 9.32558139534884e-06, | |
| "loss": 3.3983, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 9.209302325581397e-06, | |
| "loss": 3.2623, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 9.093023255813954e-06, | |
| "loss": 3.3421, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 8.976744186046511e-06, | |
| "loss": 3.2618, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 8.86046511627907e-06, | |
| "loss": 3.2084, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 8.74418604651163e-06, | |
| "loss": 3.3887, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 8.627906976744187e-06, | |
| "loss": 3.2029, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 8.511627906976744e-06, | |
| "loss": 3.3352, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 8.395348837209303e-06, | |
| "loss": 3.4385, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_accuracy": 0.13431952662721894, | |
| "eval_loss": 3.4407730102539062, | |
| "eval_runtime": 20.4215, | |
| "eval_samples_per_second": 82.756, | |
| "eval_steps_per_second": 10.381, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 8.279069767441861e-06, | |
| "loss": 3.2518, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 8.16279069767442e-06, | |
| "loss": 3.3835, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 8.046511627906977e-06, | |
| "loss": 3.3427, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 7.930232558139536e-06, | |
| "loss": 3.3436, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 7.813953488372094e-06, | |
| "loss": 3.367, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.697674418604651e-06, | |
| "loss": 3.2828, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 7.5813953488372095e-06, | |
| "loss": 3.2326, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 7.465116279069769e-06, | |
| "loss": 3.25, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 7.348837209302326e-06, | |
| "loss": 3.2834, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.232558139534884e-06, | |
| "loss": 3.3702, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_accuracy": 0.13254437869822486, | |
| "eval_loss": 3.440593719482422, | |
| "eval_runtime": 19.9682, | |
| "eval_samples_per_second": 84.634, | |
| "eval_steps_per_second": 10.617, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.1162790697674425e-06, | |
| "loss": 3.2484, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7e-06, | |
| "loss": 3.4709, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.883720930232559e-06, | |
| "loss": 3.2633, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 6.767441860465117e-06, | |
| "loss": 3.1647, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 6.651162790697675e-06, | |
| "loss": 3.281, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 6.534883720930233e-06, | |
| "loss": 3.3152, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 6.418604651162791e-06, | |
| "loss": 3.2492, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 6.30232558139535e-06, | |
| "loss": 3.1767, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 6.186046511627908e-06, | |
| "loss": 3.2237, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 6.069767441860466e-06, | |
| "loss": 3.366, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_accuracy": 0.13550295857988165, | |
| "eval_loss": 3.4410951137542725, | |
| "eval_runtime": 20.8884, | |
| "eval_samples_per_second": 80.906, | |
| "eval_steps_per_second": 10.149, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 5.953488372093023e-06, | |
| "loss": 3.1916, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 5.8372093023255815e-06, | |
| "loss": 3.2141, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 5.72093023255814e-06, | |
| "loss": 3.2327, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 5.604651162790699e-06, | |
| "loss": 3.2471, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 5.488372093023256e-06, | |
| "loss": 3.352, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 5.3720930232558145e-06, | |
| "loss": 3.2829, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 5.255813953488372e-06, | |
| "loss": 3.286, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 5.13953488372093e-06, | |
| "loss": 3.2855, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 5.023255813953489e-06, | |
| "loss": 3.3314, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 4.906976744186047e-06, | |
| "loss": 3.2022, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "eval_accuracy": 0.13076923076923078, | |
| "eval_loss": 3.4403278827667236, | |
| "eval_runtime": 20.3251, | |
| "eval_samples_per_second": 83.148, | |
| "eval_steps_per_second": 10.43, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 4.790697674418605e-06, | |
| "loss": 3.2433, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 4.674418604651163e-06, | |
| "loss": 3.2373, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 4.558139534883721e-06, | |
| "loss": 3.3887, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 4.44186046511628e-06, | |
| "loss": 3.4096, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 4.325581395348837e-06, | |
| "loss": 3.2076, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 4.209302325581396e-06, | |
| "loss": 3.2343, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 4.0930232558139536e-06, | |
| "loss": 3.2599, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 3.976744186046512e-06, | |
| "loss": 3.4099, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 3.86046511627907e-06, | |
| "loss": 3.2749, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 3.744186046511628e-06, | |
| "loss": 3.2768, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "eval_accuracy": 0.1319526627218935, | |
| "eval_loss": 3.439352512359619, | |
| "eval_runtime": 20.0924, | |
| "eval_samples_per_second": 84.112, | |
| "eval_steps_per_second": 10.551, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 3.6279069767441866e-06, | |
| "loss": 3.2065, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 3.5116279069767444e-06, | |
| "loss": 3.199, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 3.3953488372093026e-06, | |
| "loss": 3.2538, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 3.279069767441861e-06, | |
| "loss": 3.2025, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 3.1627906976744187e-06, | |
| "loss": 3.3367, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 3.046511627906977e-06, | |
| "loss": 3.3147, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 2.930232558139535e-06, | |
| "loss": 3.3351, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 2.813953488372093e-06, | |
| "loss": 3.4559, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 2.6976744186046517e-06, | |
| "loss": 3.2375, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 2.5813953488372095e-06, | |
| "loss": 3.3444, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "eval_accuracy": 0.13136094674556212, | |
| "eval_loss": 3.4394140243530273, | |
| "eval_runtime": 20.2508, | |
| "eval_samples_per_second": 83.454, | |
| "eval_steps_per_second": 10.469, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 2.4651162790697678e-06, | |
| "loss": 3.157, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 2.3488372093023256e-06, | |
| "loss": 3.351, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 2.232558139534884e-06, | |
| "loss": 3.1032, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 2.116279069767442e-06, | |
| "loss": 3.3519, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 3.2095, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 1.8837209302325582e-06, | |
| "loss": 3.1797, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 1.7674418604651164e-06, | |
| "loss": 3.3945, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1.6511627906976747e-06, | |
| "loss": 3.3156, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 1.534883720930233e-06, | |
| "loss": 3.262, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 1.4186046511627907e-06, | |
| "loss": 3.2981, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "eval_accuracy": 0.13313609467455623, | |
| "eval_loss": 3.4391462802886963, | |
| "eval_runtime": 20.148, | |
| "eval_samples_per_second": 83.879, | |
| "eval_steps_per_second": 10.522, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 1.302325581395349e-06, | |
| "loss": 3.3013, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 1.1860465116279072e-06, | |
| "loss": 3.3263, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1.0697674418604653e-06, | |
| "loss": 3.2171, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 9.534883720930234e-07, | |
| "loss": 3.2686, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 8.372093023255814e-07, | |
| "loss": 3.3712, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 7.209302325581397e-07, | |
| "loss": 3.3263, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 6.046511627906977e-07, | |
| "loss": 3.2806, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 4.883720930232559e-07, | |
| "loss": 3.2469, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 3.7209302325581396e-07, | |
| "loss": 3.3294, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 2.558139534883721e-07, | |
| "loss": 3.3349, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "eval_accuracy": 0.13313609467455623, | |
| "eval_loss": 3.4388856887817383, | |
| "eval_runtime": 20.2692, | |
| "eval_samples_per_second": 83.378, | |
| "eval_steps_per_second": 10.459, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 1.3953488372093024e-07, | |
| "loss": 3.2635, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 2.3255813953488372e-08, | |
| "loss": 3.2729, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 1720, | |
| "total_flos": 2.1353892586861363e+18, | |
| "train_loss": 3.298098830289619, | |
| "train_runtime": 1059.013, | |
| "train_samples_per_second": 25.986, | |
| "train_steps_per_second": 1.624 | |
| } | |
| ], | |
| "max_steps": 1720, | |
| "num_train_epochs": 4, | |
| "total_flos": 2.1353892586861363e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |