|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 7.246376811594203, |
|
"eval_steps": 500, |
|
"global_step": 1000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00019800000000000002, |
|
"loss": 3.3296, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.000196, |
|
"loss": 2.5227, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.000194, |
|
"loss": 2.0348, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.000192, |
|
"loss": 1.9388, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.00019, |
|
"loss": 1.9197, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 0.000188, |
|
"loss": 1.814, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.00018600000000000002, |
|
"loss": 1.5649, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 0.00018400000000000003, |
|
"loss": 1.6691, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 0.000182, |
|
"loss": 1.6885, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 0.00018, |
|
"loss": 1.6748, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 0.00017800000000000002, |
|
"loss": 1.6405, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 0.00017600000000000002, |
|
"loss": 1.5524, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 0.000174, |
|
"loss": 1.374, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 0.000172, |
|
"loss": 1.4287, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 0.00017, |
|
"loss": 1.228, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 0.000168, |
|
"loss": 1.3442, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 0.000166, |
|
"loss": 1.3386, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 0.000164, |
|
"loss": 1.2911, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 0.000162, |
|
"loss": 1.2203, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 0.00016, |
|
"loss": 1.1671, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 0.00015800000000000002, |
|
"loss": 1.4117, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 0.00015600000000000002, |
|
"loss": 1.1522, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 0.000154, |
|
"loss": 1.3722, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 0.000152, |
|
"loss": 1.3268, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 0.00015000000000000001, |
|
"loss": 1.1648, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 0.000148, |
|
"loss": 1.2187, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 0.000146, |
|
"loss": 1.2501, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 0.000144, |
|
"loss": 1.0928, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"learning_rate": 0.000142, |
|
"loss": 0.8553, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 2.17, |
|
"learning_rate": 0.00014, |
|
"loss": 0.8745, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 2.25, |
|
"learning_rate": 0.000138, |
|
"loss": 0.9068, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"learning_rate": 0.00013600000000000003, |
|
"loss": 0.9783, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 2.39, |
|
"learning_rate": 0.000134, |
|
"loss": 0.9185, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 2.46, |
|
"learning_rate": 0.000132, |
|
"loss": 0.929, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 2.54, |
|
"learning_rate": 0.00013000000000000002, |
|
"loss": 0.9308, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 0.00012800000000000002, |
|
"loss": 0.929, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 2.68, |
|
"learning_rate": 0.000126, |
|
"loss": 1.0682, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"learning_rate": 0.000124, |
|
"loss": 0.9615, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 2.83, |
|
"learning_rate": 0.000122, |
|
"loss": 0.9984, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 2.9, |
|
"learning_rate": 0.00012, |
|
"loss": 0.9162, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 2.97, |
|
"learning_rate": 0.000118, |
|
"loss": 0.7737, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 3.04, |
|
"learning_rate": 0.000116, |
|
"loss": 0.8563, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 3.12, |
|
"learning_rate": 0.00011399999999999999, |
|
"loss": 0.5843, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 3.19, |
|
"learning_rate": 0.00011200000000000001, |
|
"loss": 0.6378, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 3.26, |
|
"learning_rate": 0.00011000000000000002, |
|
"loss": 0.5818, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 3.33, |
|
"learning_rate": 0.00010800000000000001, |
|
"loss": 0.6841, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 3.41, |
|
"learning_rate": 0.00010600000000000002, |
|
"loss": 0.6338, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 3.48, |
|
"learning_rate": 0.00010400000000000001, |
|
"loss": 0.6083, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 3.55, |
|
"learning_rate": 0.00010200000000000001, |
|
"loss": 0.6408, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 3.62, |
|
"learning_rate": 0.0001, |
|
"loss": 0.677, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 3.7, |
|
"learning_rate": 9.8e-05, |
|
"loss": 0.6878, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 3.77, |
|
"learning_rate": 9.6e-05, |
|
"loss": 0.5942, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 3.84, |
|
"learning_rate": 9.4e-05, |
|
"loss": 0.5855, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 3.91, |
|
"learning_rate": 9.200000000000001e-05, |
|
"loss": 0.6314, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 3.99, |
|
"learning_rate": 9e-05, |
|
"loss": 0.6157, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 4.06, |
|
"learning_rate": 8.800000000000001e-05, |
|
"loss": 0.399, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 4.13, |
|
"learning_rate": 8.6e-05, |
|
"loss": 0.3511, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 4.2, |
|
"learning_rate": 8.4e-05, |
|
"loss": 0.4271, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 4.28, |
|
"learning_rate": 8.2e-05, |
|
"loss": 0.4539, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 4.35, |
|
"learning_rate": 8e-05, |
|
"loss": 0.3656, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 4.42, |
|
"learning_rate": 7.800000000000001e-05, |
|
"loss": 0.4041, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 4.49, |
|
"learning_rate": 7.6e-05, |
|
"loss": 0.4036, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 4.57, |
|
"learning_rate": 7.4e-05, |
|
"loss": 0.3964, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 4.64, |
|
"learning_rate": 7.2e-05, |
|
"loss": 0.4016, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 4.71, |
|
"learning_rate": 7e-05, |
|
"loss": 0.3499, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 4.78, |
|
"learning_rate": 6.800000000000001e-05, |
|
"loss": 0.4193, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 4.86, |
|
"learning_rate": 6.6e-05, |
|
"loss": 0.3946, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 4.93, |
|
"learning_rate": 6.400000000000001e-05, |
|
"loss": 0.4058, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 6.2e-05, |
|
"loss": 0.4132, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 5.07, |
|
"learning_rate": 6e-05, |
|
"loss": 0.2782, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 5.14, |
|
"learning_rate": 5.8e-05, |
|
"loss": 0.2496, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 5.22, |
|
"learning_rate": 5.6000000000000006e-05, |
|
"loss": 0.259, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 5.29, |
|
"learning_rate": 5.4000000000000005e-05, |
|
"loss": 0.2572, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 5.36, |
|
"learning_rate": 5.2000000000000004e-05, |
|
"loss": 0.2885, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 5.43, |
|
"learning_rate": 5e-05, |
|
"loss": 0.2383, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 5.51, |
|
"learning_rate": 4.8e-05, |
|
"loss": 0.2976, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 5.58, |
|
"learning_rate": 4.600000000000001e-05, |
|
"loss": 0.287, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 5.65, |
|
"learning_rate": 4.4000000000000006e-05, |
|
"loss": 0.2737, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 5.72, |
|
"learning_rate": 4.2e-05, |
|
"loss": 0.2412, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 5.8, |
|
"learning_rate": 4e-05, |
|
"loss": 0.2736, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 5.87, |
|
"learning_rate": 3.8e-05, |
|
"loss": 0.278, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 5.94, |
|
"learning_rate": 3.6e-05, |
|
"loss": 0.2871, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 6.01, |
|
"learning_rate": 3.4000000000000007e-05, |
|
"loss": 0.243, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 6.09, |
|
"learning_rate": 3.2000000000000005e-05, |
|
"loss": 0.1926, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 6.16, |
|
"learning_rate": 3e-05, |
|
"loss": 0.2136, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 6.23, |
|
"learning_rate": 2.8000000000000003e-05, |
|
"loss": 0.2247, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 6.3, |
|
"learning_rate": 2.6000000000000002e-05, |
|
"loss": 0.2212, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 6.38, |
|
"learning_rate": 2.4e-05, |
|
"loss": 0.201, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 6.45, |
|
"learning_rate": 2.2000000000000003e-05, |
|
"loss": 0.2074, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 6.52, |
|
"learning_rate": 2e-05, |
|
"loss": 0.2087, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 6.59, |
|
"learning_rate": 1.8e-05, |
|
"loss": 0.1979, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 6.67, |
|
"learning_rate": 1.6000000000000003e-05, |
|
"loss": 0.2152, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 6.74, |
|
"learning_rate": 1.4000000000000001e-05, |
|
"loss": 0.2207, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 6.81, |
|
"learning_rate": 1.2e-05, |
|
"loss": 0.2088, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 6.88, |
|
"learning_rate": 1e-05, |
|
"loss": 0.2059, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 6.96, |
|
"learning_rate": 8.000000000000001e-06, |
|
"loss": 0.2092, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 7.03, |
|
"learning_rate": 6e-06, |
|
"loss": 0.1882, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 7.1, |
|
"learning_rate": 4.000000000000001e-06, |
|
"loss": 0.1814, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 7.17, |
|
"learning_rate": 2.0000000000000003e-06, |
|
"loss": 0.16, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 7.25, |
|
"learning_rate": 0.0, |
|
"loss": 0.1653, |
|
"step": 1000 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 1000, |
|
"num_train_epochs": 8, |
|
"save_steps": 500, |
|
"total_flos": 9570470597959680.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|