|
{ |
|
"best_metric": 1.3603260517120361, |
|
"best_model_checkpoint": "./interact_output/checkpoint-914", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 914, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00015968553632342872, |
|
"loss": 1.8187, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00031937107264685743, |
|
"loss": 1.7865, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00047905660897028615, |
|
"loss": 1.9059, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0006387421452937149, |
|
"loss": 1.9266, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.9969, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 2.0468, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.9863, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.8926, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.8434, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.8316, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.7679, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.7136, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.8007, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.7397, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.7168, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.7507, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.5584, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.7085, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.6188, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.5501, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.6778, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.6112, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.5693, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.5671, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.5477, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.5861, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.6772, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.5901, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.5628, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.5902, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.4775, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.5247, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.5076, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.483, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.5376, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.4295, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.4517, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.5043, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.3862, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.4554, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.417, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.4428, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.4553, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.4517, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.4568, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 1.5652484893798828, |
|
"eval_runtime": 208.8087, |
|
"eval_samples_per_second": 12.902, |
|
"eval_steps_per_second": 3.228, |
|
"step": 457 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.3963, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.3257, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2477, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.283, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2559, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.3981, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.3224, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.3697, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2984, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2361, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2341, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2852, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2903, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.3681, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2503, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.3659, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2709, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.261, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2984, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2224, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.3484, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2559, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2761, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2682, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.164, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2756, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.193, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.176, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2107, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.1533, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2375, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.163, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.1706, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2231, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2927, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.1889, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.1449, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.212, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.1961, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.1678, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.1994, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.1694, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 1.93, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.0776, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.1641, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 1.97, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.0907, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 0.0007984276816171436, |
|
"loss": 1.2174, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 1.3603260517120361, |
|
"eval_runtime": 208.2857, |
|
"eval_samples_per_second": 12.934, |
|
"eval_steps_per_second": 3.236, |
|
"step": 914 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 914, |
|
"num_train_epochs": 2, |
|
"save_steps": 500, |
|
"total_flos": 5.844435036099379e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|