| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.6470588235294117, | |
| "global_step": 1120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.4948500216800934e-06, | |
| "loss": 0.6941, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5.730640178391189e-06, | |
| "loss": 0.5573, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 6.90105620855803e-06, | |
| "loss": 0.5586, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 7.657394585211274e-06, | |
| "loss": 0.5574, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 8.217263382430936e-06, | |
| "loss": 0.5588, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.661968799114844e-06, | |
| "loss": 0.5516, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.030899869919434e-06, | |
| "loss": 0.5443, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.346158598654881e-06, | |
| "loss": 0.5404, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.621396430309407e-06, | |
| "loss": 0.5439, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.865639267998493e-06, | |
| "loss": 0.5335, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5398, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5516, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5362, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5447, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5404, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5402, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1e-05, | |
| "loss": 0.53, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5221, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5306, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5335, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5428, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5282, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5374, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1e-05, | |
| "loss": 0.535, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5187, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1e-05, | |
| "loss": 0.525, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5341, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5326, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5321, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5209, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5253, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5175, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5299, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5225, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5239, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1e-05, | |
| "loss": 0.528, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5219, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5152, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5011, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5155, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5152, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5204, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5122, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5144, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5167, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5061, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5327, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5233, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5192, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5052, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5191, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5246, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5121, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5094, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5108, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5124, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5159, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5095, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5181, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1e-05, | |
| "loss": 0.517, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1e-05, | |
| "loss": 0.492, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5101, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5058, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5045, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5077, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1e-05, | |
| "loss": 0.51, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5128, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5118, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3543, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3402, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3482, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3442, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3329, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3335, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3448, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3451, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3354, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3412, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1e-05, | |
| "loss": 0.343, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3463, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3661, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3378, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3375, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3402, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3529, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3499, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3454, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3444, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3424, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3508, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3458, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3442, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3456, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3437, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3477, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3514, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3394, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3499, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3474, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3549, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3483, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3503, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3493, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 1e-05, | |
| "loss": 0.349, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3487, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3472, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1e-05, | |
| "loss": 0.349, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 1e-05, | |
| "loss": 0.356, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3484, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3471, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3517, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3445, | |
| "step": 1120 | |
| } | |
| ], | |
| "max_steps": 3400, | |
| "num_train_epochs": 5, | |
| "total_flos": 1456488892334080.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |