|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.9525691699604746, |
|
"eval_steps": 500, |
|
"global_step": 1000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 1.8e-05, |
|
"loss": 3.0593, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 3.6e-05, |
|
"loss": 1.6864, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 5.6000000000000006e-05, |
|
"loss": 1.098, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 7.6e-05, |
|
"loss": 0.7741, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 9.6e-05, |
|
"loss": 0.9582, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.0001, |
|
"loss": 1.0714, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.0001, |
|
"loss": 1.1548, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.0001, |
|
"loss": 0.8302, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.0001, |
|
"loss": 0.9465, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.0001, |
|
"loss": 0.8649, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 0.0001, |
|
"loss": 0.8821, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 0.0001, |
|
"loss": 0.9628, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.0001, |
|
"loss": 0.8706, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 0.0001, |
|
"loss": 0.669, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.6021, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 0.0001, |
|
"loss": 0.6725, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 0.0001, |
|
"loss": 0.6651, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 0.0001, |
|
"loss": 0.7534, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 0.0001, |
|
"loss": 0.7019, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 0.0001, |
|
"loss": 0.5879, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 0.0001, |
|
"loss": 0.5513, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 0.0001, |
|
"loss": 0.6116, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4817, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 0.0001, |
|
"loss": 0.6694, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 0.0001, |
|
"loss": 0.7335, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4327, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 0.0001, |
|
"loss": 0.5258, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2969, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4051, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3492, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 0.0001, |
|
"loss": 0.5444, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4339, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3432, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 0.0001, |
|
"loss": 0.5195, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4256, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4275, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 0.0001, |
|
"loss": 0.5108, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3536, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3049, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3325, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4221, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3514, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3613, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3535, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3633, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3954, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 0.0001, |
|
"loss": 0.288, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3639, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4876, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2981, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2474, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 2.06, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2725, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"learning_rate": 0.0001, |
|
"loss": 0.5512, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3865, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 2.17, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3104, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 2.21, |
|
"learning_rate": 0.0001, |
|
"loss": 0.381, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 2.25, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3347, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 2.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3222, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 2.33, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2435, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 2.37, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3606, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 2.41, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3137, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 2.45, |
|
"learning_rate": 0.0001, |
|
"loss": 0.243, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 2.49, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4017, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 2.53, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3375, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 2.57, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2959, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 0.0001, |
|
"loss": 0.31, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 2.65, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3298, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 2.69, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2462, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 2.73, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2599, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 2.77, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3736, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2408, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 2.85, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2684, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 2.89, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1603, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 2.92, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3044, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 2.96, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3166, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2564, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 3.04, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1702, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 3.08, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2165, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 3.12, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2071, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 3.16, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4326, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1978, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 3.24, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2628, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 3.28, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1515, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 3.32, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1968, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 3.36, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2305, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 3.4, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2085, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 3.44, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2006, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 3.48, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2685, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 3.52, |
|
"learning_rate": 0.0001, |
|
"loss": 0.192, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 3.56, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1993, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 3.6, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1312, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 3.64, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2326, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 3.68, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2676, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 3.72, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2519, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 3.75, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1722, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 3.79, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1649, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 3.83, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1923, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 3.87, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3485, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 3.91, |
|
"learning_rate": 0.0001, |
|
"loss": 0.15, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 3.95, |
|
"learning_rate": 0.0001, |
|
"loss": 0.258, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 3.95, |
|
"step": 1000, |
|
"total_flos": 5.6524204199809e+19, |
|
"train_loss": 0.4612073403596878, |
|
"train_runtime": 4968.0781, |
|
"train_samples_per_second": 6.441, |
|
"train_steps_per_second": 0.201 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 1000, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 4, |
|
"save_steps": 1000, |
|
"total_flos": 5.6524204199809e+19, |
|
"train_batch_size": 32, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|