|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.4842801241397923, |
|
"global_step": 11000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 1.798561151079137e-08, |
|
"loss": 1.4162, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 1.7985611510791368e-07, |
|
"loss": 1.435, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 3.5971223021582736e-07, |
|
"loss": 1.3193, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 5.39568345323741e-07, |
|
"loss": 1.6894, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 7.194244604316547e-07, |
|
"loss": 1.4606, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 8.992805755395684e-07, |
|
"loss": 1.5644, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"eval_loss": 1.9273985624313354, |
|
"eval_runtime": 12.8282, |
|
"eval_samples_per_second": 3.898, |
|
"eval_steps_per_second": 0.702, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.079136690647482e-06, |
|
"loss": 1.4742, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.2589928057553958e-06, |
|
"loss": 1.5418, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.4388489208633094e-06, |
|
"loss": 1.5507, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.618705035971223e-06, |
|
"loss": 1.3559, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.7985611510791368e-06, |
|
"loss": 1.4528, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"eval_loss": 1.925382137298584, |
|
"eval_runtime": 11.0984, |
|
"eval_samples_per_second": 4.505, |
|
"eval_steps_per_second": 0.811, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.9784172661870504e-06, |
|
"loss": 1.3953, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2.158273381294964e-06, |
|
"loss": 1.4271, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2.3381294964028776e-06, |
|
"loss": 1.4686, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2.5179856115107916e-06, |
|
"loss": 1.5426, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2.6978417266187052e-06, |
|
"loss": 1.3592, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"eval_loss": 1.9067959785461426, |
|
"eval_runtime": 11.1021, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2.877697841726619e-06, |
|
"loss": 1.4361, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 3.0575539568345324e-06, |
|
"loss": 1.4785, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 3.237410071942446e-06, |
|
"loss": 1.5655, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 3.4172661870503596e-06, |
|
"loss": 1.5012, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 3.5971223021582737e-06, |
|
"loss": 1.4161, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"eval_loss": 1.8503543138504028, |
|
"eval_runtime": 11.1033, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 3.7769784172661873e-06, |
|
"loss": 1.4231, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 3.956834532374101e-06, |
|
"loss": 1.3788, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 4.1366906474820145e-06, |
|
"loss": 1.373, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 4.316546762589928e-06, |
|
"loss": 1.4563, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 4.496402877697842e-06, |
|
"loss": 1.4898, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"eval_loss": 1.7314453125, |
|
"eval_runtime": 11.1042, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 4.676258992805755e-06, |
|
"loss": 1.3677, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 4.856115107913669e-06, |
|
"loss": 1.3327, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 5.035971223021583e-06, |
|
"loss": 1.2178, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 5.215827338129497e-06, |
|
"loss": 1.2909, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 5.3956834532374105e-06, |
|
"loss": 1.2929, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"eval_loss": 1.6855679750442505, |
|
"eval_runtime": 11.1082, |
|
"eval_samples_per_second": 4.501, |
|
"eval_steps_per_second": 0.81, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 5.575539568345324e-06, |
|
"loss": 1.3906, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 5.755395683453238e-06, |
|
"loss": 1.2595, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 5.935251798561151e-06, |
|
"loss": 1.4313, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 6.115107913669065e-06, |
|
"loss": 1.3019, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 6.2949640287769785e-06, |
|
"loss": 1.3041, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"eval_loss": 1.666140079498291, |
|
"eval_runtime": 11.1071, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 6.474820143884892e-06, |
|
"loss": 1.4346, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 6.654676258992806e-06, |
|
"loss": 1.3273, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 6.834532374100719e-06, |
|
"loss": 1.3503, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 7.014388489208634e-06, |
|
"loss": 1.3207, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 7.194244604316547e-06, |
|
"loss": 1.277, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"eval_loss": 1.6458452939987183, |
|
"eval_runtime": 11.1063, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 7.374100719424461e-06, |
|
"loss": 1.3067, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 7.5539568345323745e-06, |
|
"loss": 1.256, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 7.733812949640287e-06, |
|
"loss": 1.3186, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 7.913669064748202e-06, |
|
"loss": 1.3726, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 8.093525179856116e-06, |
|
"loss": 1.3915, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"eval_loss": 1.6347131729125977, |
|
"eval_runtime": 11.1051, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 8.273381294964029e-06, |
|
"loss": 1.2421, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 8.453237410071943e-06, |
|
"loss": 1.3915, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 8.633093525179856e-06, |
|
"loss": 1.2908, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 8.81294964028777e-06, |
|
"loss": 1.2557, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 8.992805755395683e-06, |
|
"loss": 1.2435, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"eval_loss": 1.6252355575561523, |
|
"eval_runtime": 11.102, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 9.172661870503598e-06, |
|
"loss": 1.3302, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 9.35251798561151e-06, |
|
"loss": 1.2328, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 9.532374100719425e-06, |
|
"loss": 1.3634, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 9.712230215827338e-06, |
|
"loss": 1.3094, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 9.892086330935252e-06, |
|
"loss": 1.2865, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"eval_loss": 1.6192078590393066, |
|
"eval_runtime": 11.1021, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.0071942446043167e-05, |
|
"loss": 1.432, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.0251798561151081e-05, |
|
"loss": 1.3137, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.0431654676258994e-05, |
|
"loss": 1.2526, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.0611510791366908e-05, |
|
"loss": 1.3433, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.0791366906474821e-05, |
|
"loss": 1.248, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"eval_loss": 1.6136677265167236, |
|
"eval_runtime": 11.1069, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.0971223021582735e-05, |
|
"loss": 1.5206, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.1151079136690648e-05, |
|
"loss": 1.3567, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.1330935251798563e-05, |
|
"loss": 1.4259, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.1510791366906475e-05, |
|
"loss": 1.2143, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.169064748201439e-05, |
|
"loss": 1.3078, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"eval_loss": 1.6037765741348267, |
|
"eval_runtime": 11.1043, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.1870503597122303e-05, |
|
"loss": 1.2581, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.2050359712230217e-05, |
|
"loss": 1.4021, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.223021582733813e-05, |
|
"loss": 1.1775, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.2410071942446044e-05, |
|
"loss": 1.1826, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.2589928057553957e-05, |
|
"loss": 1.1848, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"eval_loss": 1.5975204706192017, |
|
"eval_runtime": 11.1004, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1.2769784172661871e-05, |
|
"loss": 1.187, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1.2949640287769784e-05, |
|
"loss": 1.4702, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1.3129496402877699e-05, |
|
"loss": 1.2803, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1.3309352517985611e-05, |
|
"loss": 1.283, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1.3489208633093528e-05, |
|
"loss": 1.3394, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"eval_loss": 1.5950754880905151, |
|
"eval_runtime": 11.1052, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1.3669064748201439e-05, |
|
"loss": 1.1917, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1.3848920863309355e-05, |
|
"loss": 1.2019, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 1.4028776978417267e-05, |
|
"loss": 1.3595, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 1.4208633093525182e-05, |
|
"loss": 1.2742, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 1.4388489208633095e-05, |
|
"loss": 1.315, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"eval_loss": 1.5922518968582153, |
|
"eval_runtime": 11.1036, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 1.4568345323741009e-05, |
|
"loss": 1.2763, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 1.4748201438848922e-05, |
|
"loss": 1.2882, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 1.4928057553956836e-05, |
|
"loss": 1.2767, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 1.5107913669064749e-05, |
|
"loss": 1.3224, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 1.5287769784172665e-05, |
|
"loss": 1.1904, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"eval_loss": 1.5853155851364136, |
|
"eval_runtime": 11.1052, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 1.5467625899280575e-05, |
|
"loss": 1.2289, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 1.564748201438849e-05, |
|
"loss": 1.3167, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 1.5827338129496403e-05, |
|
"loss": 1.1872, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 1.600719424460432e-05, |
|
"loss": 1.3754, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 1.6187050359712232e-05, |
|
"loss": 1.2981, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"eval_loss": 1.5827200412750244, |
|
"eval_runtime": 11.1053, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 1.6366906474820145e-05, |
|
"loss": 1.3075, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 1.6546762589928058e-05, |
|
"loss": 1.2083, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 1.6726618705035974e-05, |
|
"loss": 1.3377, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 1.6906474820143887e-05, |
|
"loss": 1.3093, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 1.70863309352518e-05, |
|
"loss": 1.1896, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"eval_loss": 1.5787382125854492, |
|
"eval_runtime": 11.1062, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 1.7266187050359712e-05, |
|
"loss": 1.299, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 1.744604316546763e-05, |
|
"loss": 1.2352, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 1.762589928057554e-05, |
|
"loss": 1.3166, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 1.7805755395683454e-05, |
|
"loss": 1.3052, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 1.7985611510791367e-05, |
|
"loss": 1.2637, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"eval_loss": 1.5716426372528076, |
|
"eval_runtime": 11.098, |
|
"eval_samples_per_second": 4.505, |
|
"eval_steps_per_second": 0.811, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 1.8165467625899283e-05, |
|
"loss": 1.4615, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 1.8345323741007196e-05, |
|
"loss": 1.3223, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 1.8525179856115108e-05, |
|
"loss": 1.3151, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 1.870503597122302e-05, |
|
"loss": 1.2515, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 1.8884892086330937e-05, |
|
"loss": 1.2682, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"eval_loss": 1.569790244102478, |
|
"eval_runtime": 11.1047, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 1.906474820143885e-05, |
|
"loss": 1.435, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 1.9244604316546766e-05, |
|
"loss": 1.2376, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 1.9424460431654675e-05, |
|
"loss": 1.1425, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 1.960431654676259e-05, |
|
"loss": 1.3304, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 1.9784172661870504e-05, |
|
"loss": 1.3652, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"eval_loss": 1.5699230432510376, |
|
"eval_runtime": 11.1088, |
|
"eval_samples_per_second": 4.501, |
|
"eval_steps_per_second": 0.81, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 1.996402877697842e-05, |
|
"loss": 1.3223, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 1.9992424601107903e-05, |
|
"loss": 1.2706, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 1.998295535249278e-05, |
|
"loss": 1.2794, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 1.997348610387766e-05, |
|
"loss": 1.3047, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 1.9964016855262534e-05, |
|
"loss": 1.3269, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"eval_loss": 1.5647709369659424, |
|
"eval_runtime": 11.103, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 1.9954547606647415e-05, |
|
"loss": 1.2458, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 1.9945078358032292e-05, |
|
"loss": 1.2427, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 1.993560910941717e-05, |
|
"loss": 1.2674, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 1.9926139860802046e-05, |
|
"loss": 1.2655, |
|
"step": 1190 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 1.9916670612186923e-05, |
|
"loss": 1.3241, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"eval_loss": 1.5619537830352783, |
|
"eval_runtime": 11.1009, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 1.99072013635718e-05, |
|
"loss": 1.1897, |
|
"step": 1210 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 1.989773211495668e-05, |
|
"loss": 1.256, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 1.9888262866341558e-05, |
|
"loss": 1.2662, |
|
"step": 1230 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 1.9878793617726435e-05, |
|
"loss": 1.3108, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 1.9869324369111312e-05, |
|
"loss": 1.2627, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"eval_loss": 1.562312364578247, |
|
"eval_runtime": 11.1042, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 1.985985512049619e-05, |
|
"loss": 1.3572, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 1.985038587188107e-05, |
|
"loss": 1.2936, |
|
"step": 1270 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 1.9840916623265944e-05, |
|
"loss": 1.325, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 1.9831447374650824e-05, |
|
"loss": 1.3195, |
|
"step": 1290 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 1.98219781260357e-05, |
|
"loss": 1.2739, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"eval_loss": 1.5584262609481812, |
|
"eval_runtime": 11.1066, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 1.981250887742058e-05, |
|
"loss": 1.3748, |
|
"step": 1310 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 1.9803039628805456e-05, |
|
"loss": 1.4155, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 1.9793570380190336e-05, |
|
"loss": 1.2637, |
|
"step": 1330 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 1.978410113157521e-05, |
|
"loss": 1.2464, |
|
"step": 1340 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 1.977463188296009e-05, |
|
"loss": 1.1356, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"eval_loss": 1.5577096939086914, |
|
"eval_runtime": 11.1059, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 1.9765162634344964e-05, |
|
"loss": 1.3106, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 1.9755693385729845e-05, |
|
"loss": 1.2345, |
|
"step": 1370 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 1.9746224137114722e-05, |
|
"loss": 1.3584, |
|
"step": 1380 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 1.97367548884996e-05, |
|
"loss": 1.1978, |
|
"step": 1390 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 1.9727285639884476e-05, |
|
"loss": 1.4418, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"eval_loss": 1.5582587718963623, |
|
"eval_runtime": 11.0929, |
|
"eval_samples_per_second": 4.507, |
|
"eval_steps_per_second": 0.811, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 1.9717816391269357e-05, |
|
"loss": 1.3675, |
|
"step": 1410 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 1.970834714265423e-05, |
|
"loss": 1.3266, |
|
"step": 1420 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 1.969887789403911e-05, |
|
"loss": 1.3274, |
|
"step": 1430 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 1.9689408645423985e-05, |
|
"loss": 1.2459, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 1.9679939396808865e-05, |
|
"loss": 1.2634, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"eval_loss": 1.5625778436660767, |
|
"eval_runtime": 11.0786, |
|
"eval_samples_per_second": 4.513, |
|
"eval_steps_per_second": 0.812, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 1.9670470148193742e-05, |
|
"loss": 1.3589, |
|
"step": 1460 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 1.966100089957862e-05, |
|
"loss": 1.2044, |
|
"step": 1470 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 1.9651531650963497e-05, |
|
"loss": 1.2195, |
|
"step": 1480 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 1.9642062402348377e-05, |
|
"loss": 1.2452, |
|
"step": 1490 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 1.963259315373325e-05, |
|
"loss": 1.3395, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"eval_loss": 1.558931589126587, |
|
"eval_runtime": 11.0917, |
|
"eval_samples_per_second": 4.508, |
|
"eval_steps_per_second": 0.811, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 1.962312390511813e-05, |
|
"loss": 1.1856, |
|
"step": 1510 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 1.961365465650301e-05, |
|
"loss": 1.1571, |
|
"step": 1520 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 1.9604185407887886e-05, |
|
"loss": 1.2529, |
|
"step": 1530 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 1.9594716159272763e-05, |
|
"loss": 1.36, |
|
"step": 1540 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 1.958524691065764e-05, |
|
"loss": 1.3754, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"eval_loss": 1.562566876411438, |
|
"eval_runtime": 11.095, |
|
"eval_samples_per_second": 4.507, |
|
"eval_steps_per_second": 0.811, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 1.9575777662042517e-05, |
|
"loss": 1.4214, |
|
"step": 1560 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 1.9566308413427394e-05, |
|
"loss": 1.2369, |
|
"step": 1570 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 1.9556839164812275e-05, |
|
"loss": 1.2888, |
|
"step": 1580 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 1.9547369916197152e-05, |
|
"loss": 1.2645, |
|
"step": 1590 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 1.953790066758203e-05, |
|
"loss": 1.2399, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"eval_loss": 1.559140920639038, |
|
"eval_runtime": 11.0952, |
|
"eval_samples_per_second": 4.506, |
|
"eval_steps_per_second": 0.811, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 1.9528431418966906e-05, |
|
"loss": 1.1996, |
|
"step": 1610 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 1.9518962170351787e-05, |
|
"loss": 1.2092, |
|
"step": 1620 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 1.950949292173666e-05, |
|
"loss": 1.2746, |
|
"step": 1630 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 1.950002367312154e-05, |
|
"loss": 1.3702, |
|
"step": 1640 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 1.9490554424506415e-05, |
|
"loss": 1.1975, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"eval_loss": 1.5604815483093262, |
|
"eval_runtime": 11.0721, |
|
"eval_samples_per_second": 4.516, |
|
"eval_steps_per_second": 0.813, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 1.9481085175891295e-05, |
|
"loss": 1.1648, |
|
"step": 1660 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 1.9471615927276172e-05, |
|
"loss": 1.2779, |
|
"step": 1670 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 1.946214667866105e-05, |
|
"loss": 1.3638, |
|
"step": 1680 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 1.9452677430045927e-05, |
|
"loss": 1.2806, |
|
"step": 1690 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 1.9443208181430807e-05, |
|
"loss": 1.0964, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"eval_loss": 1.5594099760055542, |
|
"eval_runtime": 11.0873, |
|
"eval_samples_per_second": 4.51, |
|
"eval_steps_per_second": 0.812, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 1.943373893281568e-05, |
|
"loss": 1.2534, |
|
"step": 1710 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 1.942426968420056e-05, |
|
"loss": 1.2076, |
|
"step": 1720 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 1.9414800435585435e-05, |
|
"loss": 1.2185, |
|
"step": 1730 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 1.9405331186970316e-05, |
|
"loss": 1.2927, |
|
"step": 1740 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 1.9395861938355193e-05, |
|
"loss": 1.1294, |
|
"step": 1750 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"eval_loss": 1.559138298034668, |
|
"eval_runtime": 11.0979, |
|
"eval_samples_per_second": 4.505, |
|
"eval_steps_per_second": 0.811, |
|
"step": 1750 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 1.938639268974007e-05, |
|
"loss": 1.2764, |
|
"step": 1760 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 1.9376923441124947e-05, |
|
"loss": 1.2627, |
|
"step": 1770 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 1.9367454192509828e-05, |
|
"loss": 1.1362, |
|
"step": 1780 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 1.93579849438947e-05, |
|
"loss": 1.2727, |
|
"step": 1790 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 1.9348515695279582e-05, |
|
"loss": 1.3091, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"eval_loss": 1.5538157224655151, |
|
"eval_runtime": 11.07, |
|
"eval_samples_per_second": 4.517, |
|
"eval_steps_per_second": 0.813, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 1.933904644666446e-05, |
|
"loss": 1.2502, |
|
"step": 1810 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 1.9329577198049336e-05, |
|
"loss": 1.2181, |
|
"step": 1820 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 1.9320107949434213e-05, |
|
"loss": 1.0665, |
|
"step": 1830 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 1.931063870081909e-05, |
|
"loss": 1.304, |
|
"step": 1840 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 1.9301169452203968e-05, |
|
"loss": 1.2126, |
|
"step": 1850 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"eval_loss": 1.5541281700134277, |
|
"eval_runtime": 11.0885, |
|
"eval_samples_per_second": 4.509, |
|
"eval_steps_per_second": 0.812, |
|
"step": 1850 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 1.9291700203588848e-05, |
|
"loss": 1.2797, |
|
"step": 1860 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 1.9282230954973725e-05, |
|
"loss": 1.3164, |
|
"step": 1870 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 1.9272761706358603e-05, |
|
"loss": 1.225, |
|
"step": 1880 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 1.926329245774348e-05, |
|
"loss": 1.3071, |
|
"step": 1890 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 1.9253823209128357e-05, |
|
"loss": 1.3443, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"eval_loss": 1.5548361539840698, |
|
"eval_runtime": 11.0945, |
|
"eval_samples_per_second": 4.507, |
|
"eval_steps_per_second": 0.811, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 1.9244353960513234e-05, |
|
"loss": 1.2114, |
|
"step": 1910 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 1.923488471189811e-05, |
|
"loss": 1.37, |
|
"step": 1920 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 1.922541546328299e-05, |
|
"loss": 1.2907, |
|
"step": 1930 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 1.9215946214667865e-05, |
|
"loss": 1.2308, |
|
"step": 1940 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 1.9206476966052746e-05, |
|
"loss": 1.189, |
|
"step": 1950 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"eval_loss": 1.555216670036316, |
|
"eval_runtime": 11.092, |
|
"eval_samples_per_second": 4.508, |
|
"eval_steps_per_second": 0.811, |
|
"step": 1950 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 1.9197007717437623e-05, |
|
"loss": 1.1163, |
|
"step": 1960 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 1.91875384688225e-05, |
|
"loss": 1.2462, |
|
"step": 1970 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 1.9178069220207377e-05, |
|
"loss": 1.2087, |
|
"step": 1980 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 1.9168599971592258e-05, |
|
"loss": 1.1235, |
|
"step": 1990 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 1.915913072297713e-05, |
|
"loss": 1.2699, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"eval_loss": 1.5495699644088745, |
|
"eval_runtime": 11.094, |
|
"eval_samples_per_second": 4.507, |
|
"eval_steps_per_second": 0.811, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 1.9149661474362012e-05, |
|
"loss": 1.1534, |
|
"step": 2010 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 1.9140192225746886e-05, |
|
"loss": 1.3177, |
|
"step": 2020 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 1.9130722977131766e-05, |
|
"loss": 1.3197, |
|
"step": 2030 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 1.9121253728516644e-05, |
|
"loss": 1.32, |
|
"step": 2040 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 1.911178447990152e-05, |
|
"loss": 1.2205, |
|
"step": 2050 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"eval_loss": 1.5571376085281372, |
|
"eval_runtime": 11.0867, |
|
"eval_samples_per_second": 4.51, |
|
"eval_steps_per_second": 0.812, |
|
"step": 2050 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 1.9102315231286398e-05, |
|
"loss": 1.2431, |
|
"step": 2060 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 1.909284598267128e-05, |
|
"loss": 1.2597, |
|
"step": 2070 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 1.9083376734056152e-05, |
|
"loss": 1.3475, |
|
"step": 2080 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 1.9073907485441033e-05, |
|
"loss": 1.1992, |
|
"step": 2090 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 1.906443823682591e-05, |
|
"loss": 1.3392, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"eval_loss": 1.5473936796188354, |
|
"eval_runtime": 11.0581, |
|
"eval_samples_per_second": 4.522, |
|
"eval_steps_per_second": 0.814, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 1.9054968988210787e-05, |
|
"loss": 1.2667, |
|
"step": 2110 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 1.9045499739595664e-05, |
|
"loss": 1.2713, |
|
"step": 2120 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 1.903603049098054e-05, |
|
"loss": 1.2829, |
|
"step": 2130 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 1.902656124236542e-05, |
|
"loss": 1.3188, |
|
"step": 2140 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 1.90170919937503e-05, |
|
"loss": 1.2527, |
|
"step": 2150 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"eval_loss": 1.5466290712356567, |
|
"eval_runtime": 11.0839, |
|
"eval_samples_per_second": 4.511, |
|
"eval_steps_per_second": 0.812, |
|
"step": 2150 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 1.9007622745135176e-05, |
|
"loss": 1.2058, |
|
"step": 2160 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 1.8998153496520053e-05, |
|
"loss": 1.1532, |
|
"step": 2170 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 1.898868424790493e-05, |
|
"loss": 1.2386, |
|
"step": 2180 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 1.8979214999289807e-05, |
|
"loss": 1.368, |
|
"step": 2190 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 1.8969745750674685e-05, |
|
"loss": 1.1199, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"eval_loss": 1.5490005016326904, |
|
"eval_runtime": 11.0981, |
|
"eval_samples_per_second": 4.505, |
|
"eval_steps_per_second": 0.811, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 1.8960276502059562e-05, |
|
"loss": 1.1525, |
|
"step": 2210 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 1.8950807253444442e-05, |
|
"loss": 1.2627, |
|
"step": 2220 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 1.894133800482932e-05, |
|
"loss": 1.2216, |
|
"step": 2230 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 1.8931868756214197e-05, |
|
"loss": 1.2338, |
|
"step": 2240 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 1.8922399507599074e-05, |
|
"loss": 1.2449, |
|
"step": 2250 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"eval_loss": 1.5468719005584717, |
|
"eval_runtime": 11.0854, |
|
"eval_samples_per_second": 4.51, |
|
"eval_steps_per_second": 0.812, |
|
"step": 2250 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 1.891293025898395e-05, |
|
"loss": 1.2012, |
|
"step": 2260 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 1.8903461010368828e-05, |
|
"loss": 1.2574, |
|
"step": 2270 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 1.889399176175371e-05, |
|
"loss": 1.3283, |
|
"step": 2280 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 1.8884522513138582e-05, |
|
"loss": 1.3271, |
|
"step": 2290 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 1.8875053264523463e-05, |
|
"loss": 1.2611, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"eval_loss": 1.5451312065124512, |
|
"eval_runtime": 11.1073, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 1.886558401590834e-05, |
|
"loss": 1.1503, |
|
"step": 2310 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 1.8856114767293217e-05, |
|
"loss": 1.2082, |
|
"step": 2320 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 1.8846645518678094e-05, |
|
"loss": 1.2867, |
|
"step": 2330 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 1.883717627006297e-05, |
|
"loss": 1.4018, |
|
"step": 2340 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 1.882770702144785e-05, |
|
"loss": 1.1838, |
|
"step": 2350 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"eval_loss": 1.5499719381332397, |
|
"eval_runtime": 11.0832, |
|
"eval_samples_per_second": 4.511, |
|
"eval_steps_per_second": 0.812, |
|
"step": 2350 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 1.881823777283273e-05, |
|
"loss": 1.3283, |
|
"step": 2360 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 1.8808768524217603e-05, |
|
"loss": 1.3347, |
|
"step": 2370 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 1.8799299275602483e-05, |
|
"loss": 1.2319, |
|
"step": 2380 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 1.878983002698736e-05, |
|
"loss": 1.2472, |
|
"step": 2390 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 1.8780360778372238e-05, |
|
"loss": 1.3411, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"eval_loss": 1.5518121719360352, |
|
"eval_runtime": 11.0753, |
|
"eval_samples_per_second": 4.515, |
|
"eval_steps_per_second": 0.813, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 1.8770891529757115e-05, |
|
"loss": 1.1978, |
|
"step": 2410 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 1.8761422281141992e-05, |
|
"loss": 1.3477, |
|
"step": 2420 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 1.875195303252687e-05, |
|
"loss": 1.2406, |
|
"step": 2430 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 1.874248378391175e-05, |
|
"loss": 1.2655, |
|
"step": 2440 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 1.8733014535296627e-05, |
|
"loss": 1.2212, |
|
"step": 2450 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"eval_loss": 1.5567797422409058, |
|
"eval_runtime": 11.0918, |
|
"eval_samples_per_second": 4.508, |
|
"eval_steps_per_second": 0.811, |
|
"step": 2450 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 1.8723545286681504e-05, |
|
"loss": 1.2983, |
|
"step": 2460 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 1.871407603806638e-05, |
|
"loss": 1.1739, |
|
"step": 2470 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 1.8704606789451258e-05, |
|
"loss": 1.3639, |
|
"step": 2480 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 1.8695137540836135e-05, |
|
"loss": 1.2984, |
|
"step": 2490 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 1.8685668292221012e-05, |
|
"loss": 1.1452, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"eval_loss": 1.549959659576416, |
|
"eval_runtime": 11.0857, |
|
"eval_samples_per_second": 4.51, |
|
"eval_steps_per_second": 0.812, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 1.8676199043605893e-05, |
|
"loss": 1.1432, |
|
"step": 2510 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 1.866672979499077e-05, |
|
"loss": 1.1934, |
|
"step": 2520 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 1.8657260546375647e-05, |
|
"loss": 1.3292, |
|
"step": 2530 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 1.8647791297760524e-05, |
|
"loss": 1.3077, |
|
"step": 2540 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 1.86383220491454e-05, |
|
"loss": 1.3401, |
|
"step": 2550 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"eval_loss": 1.5510776042938232, |
|
"eval_runtime": 11.0939, |
|
"eval_samples_per_second": 4.507, |
|
"eval_steps_per_second": 0.811, |
|
"step": 2550 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 1.862885280053028e-05, |
|
"loss": 1.2091, |
|
"step": 2560 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 1.861938355191516e-05, |
|
"loss": 1.2314, |
|
"step": 2570 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 1.8609914303300033e-05, |
|
"loss": 1.2826, |
|
"step": 2580 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 1.8600445054684913e-05, |
|
"loss": 1.2705, |
|
"step": 2590 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 1.859097580606979e-05, |
|
"loss": 1.2282, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"eval_loss": 1.5423473119735718, |
|
"eval_runtime": 11.0897, |
|
"eval_samples_per_second": 4.509, |
|
"eval_steps_per_second": 0.812, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 1.8581506557454668e-05, |
|
"loss": 1.1069, |
|
"step": 2610 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 1.8572037308839545e-05, |
|
"loss": 1.3244, |
|
"step": 2620 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 1.8562568060224422e-05, |
|
"loss": 1.3847, |
|
"step": 2630 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 1.85530988116093e-05, |
|
"loss": 1.3832, |
|
"step": 2640 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 1.854362956299418e-05, |
|
"loss": 1.1572, |
|
"step": 2650 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"eval_loss": 1.5443249940872192, |
|
"eval_runtime": 11.0831, |
|
"eval_samples_per_second": 4.511, |
|
"eval_steps_per_second": 0.812, |
|
"step": 2650 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 1.8534160314379053e-05, |
|
"loss": 1.4245, |
|
"step": 2660 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 1.8524691065763934e-05, |
|
"loss": 1.2769, |
|
"step": 2670 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 1.851522181714881e-05, |
|
"loss": 1.2666, |
|
"step": 2680 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 1.8505752568533688e-05, |
|
"loss": 1.1944, |
|
"step": 2690 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 1.8496283319918565e-05, |
|
"loss": 1.2227, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"eval_loss": 1.5426236391067505, |
|
"eval_runtime": 11.0953, |
|
"eval_samples_per_second": 4.506, |
|
"eval_steps_per_second": 0.811, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 1.8486814071303442e-05, |
|
"loss": 1.2548, |
|
"step": 2710 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 1.847734482268832e-05, |
|
"loss": 1.308, |
|
"step": 2720 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 1.84678755740732e-05, |
|
"loss": 1.1477, |
|
"step": 2730 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 1.8458406325458077e-05, |
|
"loss": 1.1652, |
|
"step": 2740 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 1.8448937076842954e-05, |
|
"loss": 1.2477, |
|
"step": 2750 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"eval_loss": 1.5413143634796143, |
|
"eval_runtime": 11.0957, |
|
"eval_samples_per_second": 4.506, |
|
"eval_steps_per_second": 0.811, |
|
"step": 2750 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 1.843946782822783e-05, |
|
"loss": 1.2161, |
|
"step": 2760 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 1.842999857961271e-05, |
|
"loss": 1.395, |
|
"step": 2770 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 1.8420529330997586e-05, |
|
"loss": 1.1865, |
|
"step": 2780 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 1.8411060082382463e-05, |
|
"loss": 1.1924, |
|
"step": 2790 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 1.8401590833767343e-05, |
|
"loss": 1.3288, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"eval_loss": 1.5420317649841309, |
|
"eval_runtime": 11.0909, |
|
"eval_samples_per_second": 4.508, |
|
"eval_steps_per_second": 0.811, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 1.839212158515222e-05, |
|
"loss": 1.3175, |
|
"step": 2810 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 1.8382652336537098e-05, |
|
"loss": 1.2126, |
|
"step": 2820 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 1.8373183087921975e-05, |
|
"loss": 1.1571, |
|
"step": 2830 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 1.8363713839306852e-05, |
|
"loss": 1.2233, |
|
"step": 2840 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 1.835424459069173e-05, |
|
"loss": 1.1253, |
|
"step": 2850 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"eval_loss": 1.5390185117721558, |
|
"eval_runtime": 11.0954, |
|
"eval_samples_per_second": 4.506, |
|
"eval_steps_per_second": 0.811, |
|
"step": 2850 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 1.834477534207661e-05, |
|
"loss": 1.2053, |
|
"step": 2860 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 1.8335306093461483e-05, |
|
"loss": 1.2967, |
|
"step": 2870 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 1.8325836844846364e-05, |
|
"loss": 1.2482, |
|
"step": 2880 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 1.831636759623124e-05, |
|
"loss": 1.2903, |
|
"step": 2890 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 1.8306898347616118e-05, |
|
"loss": 1.3044, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"eval_loss": 1.5437415838241577, |
|
"eval_runtime": 11.0961, |
|
"eval_samples_per_second": 4.506, |
|
"eval_steps_per_second": 0.811, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 1.8297429099000995e-05, |
|
"loss": 1.2236, |
|
"step": 2910 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 1.8287959850385873e-05, |
|
"loss": 1.1983, |
|
"step": 2920 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 1.827849060177075e-05, |
|
"loss": 1.2438, |
|
"step": 2930 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 1.826902135315563e-05, |
|
"loss": 1.3013, |
|
"step": 2940 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 1.8259552104540504e-05, |
|
"loss": 1.2744, |
|
"step": 2950 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"eval_loss": 1.5418683290481567, |
|
"eval_runtime": 11.0955, |
|
"eval_samples_per_second": 4.506, |
|
"eval_steps_per_second": 0.811, |
|
"step": 2950 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 1.8250082855925384e-05, |
|
"loss": 1.1765, |
|
"step": 2960 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 1.824061360731026e-05, |
|
"loss": 1.2315, |
|
"step": 2970 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 1.823114435869514e-05, |
|
"loss": 1.1893, |
|
"step": 2980 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 1.8221675110080016e-05, |
|
"loss": 1.2625, |
|
"step": 2990 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 1.8212205861464893e-05, |
|
"loss": 1.3359, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"eval_loss": 1.5347923040390015, |
|
"eval_runtime": 11.09, |
|
"eval_samples_per_second": 4.509, |
|
"eval_steps_per_second": 0.812, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 1.820273661284977e-05, |
|
"loss": 1.2463, |
|
"step": 3010 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 1.819326736423465e-05, |
|
"loss": 1.2462, |
|
"step": 3020 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 1.8183798115619528e-05, |
|
"loss": 1.2767, |
|
"step": 3030 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 1.8174328867004405e-05, |
|
"loss": 1.3475, |
|
"step": 3040 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 1.8164859618389282e-05, |
|
"loss": 1.1512, |
|
"step": 3050 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"eval_loss": 1.5366531610488892, |
|
"eval_runtime": 11.092, |
|
"eval_samples_per_second": 4.508, |
|
"eval_steps_per_second": 0.811, |
|
"step": 3050 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 1.815539036977416e-05, |
|
"loss": 1.3212, |
|
"step": 3060 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 1.8145921121159036e-05, |
|
"loss": 1.2214, |
|
"step": 3070 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 1.8136451872543914e-05, |
|
"loss": 1.3595, |
|
"step": 3080 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 1.8126982623928794e-05, |
|
"loss": 1.264, |
|
"step": 3090 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 1.811751337531367e-05, |
|
"loss": 1.2112, |
|
"step": 3100 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"eval_loss": 1.5352517366409302, |
|
"eval_runtime": 11.0986, |
|
"eval_samples_per_second": 4.505, |
|
"eval_steps_per_second": 0.811, |
|
"step": 3100 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 1.810804412669855e-05, |
|
"loss": 1.2866, |
|
"step": 3110 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 1.8098574878083426e-05, |
|
"loss": 1.3223, |
|
"step": 3120 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 1.8089105629468303e-05, |
|
"loss": 1.263, |
|
"step": 3130 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 1.807963638085318e-05, |
|
"loss": 1.2206, |
|
"step": 3140 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 1.807016713223806e-05, |
|
"loss": 1.3491, |
|
"step": 3150 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"eval_loss": 1.5364201068878174, |
|
"eval_runtime": 11.0993, |
|
"eval_samples_per_second": 4.505, |
|
"eval_steps_per_second": 0.811, |
|
"step": 3150 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 1.8060697883622934e-05, |
|
"loss": 1.1581, |
|
"step": 3160 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 1.8051228635007815e-05, |
|
"loss": 1.2461, |
|
"step": 3170 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 1.8041759386392692e-05, |
|
"loss": 1.3326, |
|
"step": 3180 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 1.803229013777757e-05, |
|
"loss": 1.3156, |
|
"step": 3190 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 1.8022820889162446e-05, |
|
"loss": 1.197, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"eval_loss": 1.5414470434188843, |
|
"eval_runtime": 11.0931, |
|
"eval_samples_per_second": 4.507, |
|
"eval_steps_per_second": 0.811, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 1.8013351640547323e-05, |
|
"loss": 1.1757, |
|
"step": 3210 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 1.80038823919322e-05, |
|
"loss": 1.0882, |
|
"step": 3220 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 1.799441314331708e-05, |
|
"loss": 1.2738, |
|
"step": 3230 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 1.7984943894701955e-05, |
|
"loss": 1.1026, |
|
"step": 3240 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 1.7975474646086835e-05, |
|
"loss": 1.1574, |
|
"step": 3250 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"eval_loss": 1.5383353233337402, |
|
"eval_runtime": 11.0973, |
|
"eval_samples_per_second": 4.506, |
|
"eval_steps_per_second": 0.811, |
|
"step": 3250 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 1.7966005397471712e-05, |
|
"loss": 1.2176, |
|
"step": 3260 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 1.795653614885659e-05, |
|
"loss": 1.2055, |
|
"step": 3270 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 1.7947066900241467e-05, |
|
"loss": 1.2525, |
|
"step": 3280 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 1.7937597651626344e-05, |
|
"loss": 1.1751, |
|
"step": 3290 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 1.792812840301122e-05, |
|
"loss": 1.2693, |
|
"step": 3300 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"eval_loss": 1.531793475151062, |
|
"eval_runtime": 11.0749, |
|
"eval_samples_per_second": 4.515, |
|
"eval_steps_per_second": 0.813, |
|
"step": 3300 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 1.79186591543961e-05, |
|
"loss": 1.2349, |
|
"step": 3310 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 1.790918990578098e-05, |
|
"loss": 1.2574, |
|
"step": 3320 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 1.7899720657165856e-05, |
|
"loss": 1.3471, |
|
"step": 3330 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 1.7890251408550733e-05, |
|
"loss": 1.1868, |
|
"step": 3340 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 1.788078215993561e-05, |
|
"loss": 1.3677, |
|
"step": 3350 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"eval_loss": 1.5286340713500977, |
|
"eval_runtime": 11.0983, |
|
"eval_samples_per_second": 4.505, |
|
"eval_steps_per_second": 0.811, |
|
"step": 3350 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 1.7871312911320487e-05, |
|
"loss": 1.1813, |
|
"step": 3360 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 1.7861843662705364e-05, |
|
"loss": 1.2539, |
|
"step": 3370 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 1.7852374414090245e-05, |
|
"loss": 1.1783, |
|
"step": 3380 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 1.7842905165475122e-05, |
|
"loss": 1.212, |
|
"step": 3390 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 1.783343591686e-05, |
|
"loss": 1.2042, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"eval_loss": 1.5318104028701782, |
|
"eval_runtime": 11.0848, |
|
"eval_samples_per_second": 4.511, |
|
"eval_steps_per_second": 0.812, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 1.7823966668244876e-05, |
|
"loss": 1.2871, |
|
"step": 3410 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 1.7814497419629753e-05, |
|
"loss": 1.2545, |
|
"step": 3420 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 1.780502817101463e-05, |
|
"loss": 1.2271, |
|
"step": 3430 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 1.779555892239951e-05, |
|
"loss": 1.2238, |
|
"step": 3440 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 1.7786089673784385e-05, |
|
"loss": 1.2981, |
|
"step": 3450 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"eval_loss": 1.5240731239318848, |
|
"eval_runtime": 11.0943, |
|
"eval_samples_per_second": 4.507, |
|
"eval_steps_per_second": 0.811, |
|
"step": 3450 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 1.7776620425169265e-05, |
|
"loss": 1.2105, |
|
"step": 3460 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 1.7767151176554142e-05, |
|
"loss": 1.1707, |
|
"step": 3470 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 1.775768192793902e-05, |
|
"loss": 1.3166, |
|
"step": 3480 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 1.7748212679323897e-05, |
|
"loss": 1.3341, |
|
"step": 3490 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 1.7738743430708777e-05, |
|
"loss": 1.1713, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"eval_loss": 1.5264086723327637, |
|
"eval_runtime": 11.1079, |
|
"eval_samples_per_second": 4.501, |
|
"eval_steps_per_second": 0.81, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 1.772927418209365e-05, |
|
"loss": 1.3466, |
|
"step": 3510 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 1.771980493347853e-05, |
|
"loss": 1.1068, |
|
"step": 3520 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 1.7710335684863405e-05, |
|
"loss": 1.3368, |
|
"step": 3530 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 1.7700866436248286e-05, |
|
"loss": 1.3165, |
|
"step": 3540 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 1.7691397187633163e-05, |
|
"loss": 1.3923, |
|
"step": 3550 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"eval_loss": 1.5312632322311401, |
|
"eval_runtime": 11.1093, |
|
"eval_samples_per_second": 4.501, |
|
"eval_steps_per_second": 0.81, |
|
"step": 3550 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 1.768192793901804e-05, |
|
"loss": 1.2229, |
|
"step": 3560 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 1.7672458690402917e-05, |
|
"loss": 1.2425, |
|
"step": 3570 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 1.7662989441787794e-05, |
|
"loss": 1.2989, |
|
"step": 3580 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 1.765352019317267e-05, |
|
"loss": 1.3637, |
|
"step": 3590 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 1.7644050944557552e-05, |
|
"loss": 1.1649, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"eval_loss": 1.534061312675476, |
|
"eval_runtime": 11.1069, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 1.763458169594243e-05, |
|
"loss": 1.1419, |
|
"step": 3610 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 1.7625112447327306e-05, |
|
"loss": 1.3447, |
|
"step": 3620 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 1.7615643198712183e-05, |
|
"loss": 1.1675, |
|
"step": 3630 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 1.760617395009706e-05, |
|
"loss": 1.2257, |
|
"step": 3640 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 1.7596704701481938e-05, |
|
"loss": 1.2124, |
|
"step": 3650 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"eval_loss": 1.5254734754562378, |
|
"eval_runtime": 11.1058, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 3650 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 1.7587235452866815e-05, |
|
"loss": 1.2073, |
|
"step": 3660 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 1.7577766204251695e-05, |
|
"loss": 1.3199, |
|
"step": 3670 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 1.7568296955636572e-05, |
|
"loss": 1.3155, |
|
"step": 3680 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 1.755882770702145e-05, |
|
"loss": 1.3671, |
|
"step": 3690 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 1.7549358458406327e-05, |
|
"loss": 1.2166, |
|
"step": 3700 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"eval_loss": 1.5198516845703125, |
|
"eval_runtime": 11.1069, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 3700 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 1.7539889209791204e-05, |
|
"loss": 1.2918, |
|
"step": 3710 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 1.753041996117608e-05, |
|
"loss": 1.2558, |
|
"step": 3720 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 1.752095071256096e-05, |
|
"loss": 1.2687, |
|
"step": 3730 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 1.7511481463945835e-05, |
|
"loss": 1.1233, |
|
"step": 3740 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 1.7502012215330716e-05, |
|
"loss": 1.2028, |
|
"step": 3750 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"eval_loss": 1.523787498474121, |
|
"eval_runtime": 11.1042, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 3750 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 1.7492542966715593e-05, |
|
"loss": 1.2669, |
|
"step": 3760 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 1.748307371810047e-05, |
|
"loss": 1.2598, |
|
"step": 3770 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 1.7473604469485347e-05, |
|
"loss": 1.1636, |
|
"step": 3780 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 1.7464135220870228e-05, |
|
"loss": 1.2503, |
|
"step": 3790 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 1.74546659722551e-05, |
|
"loss": 1.2415, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"eval_loss": 1.5229607820510864, |
|
"eval_runtime": 11.1048, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 1.7445196723639982e-05, |
|
"loss": 1.3325, |
|
"step": 3810 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 1.7435727475024856e-05, |
|
"loss": 1.2579, |
|
"step": 3820 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 1.7426258226409736e-05, |
|
"loss": 1.2484, |
|
"step": 3830 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 1.7416788977794613e-05, |
|
"loss": 1.2481, |
|
"step": 3840 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 1.740731972917949e-05, |
|
"loss": 1.2949, |
|
"step": 3850 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"eval_loss": 1.5247286558151245, |
|
"eval_runtime": 11.1066, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 3850 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 1.7397850480564368e-05, |
|
"loss": 1.2384, |
|
"step": 3860 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 1.7388381231949248e-05, |
|
"loss": 1.2287, |
|
"step": 3870 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 1.7378911983334122e-05, |
|
"loss": 1.1437, |
|
"step": 3880 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 1.7369442734719003e-05, |
|
"loss": 1.2303, |
|
"step": 3890 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 1.735997348610388e-05, |
|
"loss": 1.2003, |
|
"step": 3900 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"eval_loss": 1.5227136611938477, |
|
"eval_runtime": 11.1063, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 3900 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 1.7350504237488757e-05, |
|
"loss": 1.2468, |
|
"step": 3910 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 1.7341034988873634e-05, |
|
"loss": 1.3642, |
|
"step": 3920 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 1.733156574025851e-05, |
|
"loss": 1.2299, |
|
"step": 3930 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 1.7322096491643388e-05, |
|
"loss": 1.3061, |
|
"step": 3940 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 1.7312627243028265e-05, |
|
"loss": 1.3448, |
|
"step": 3950 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"eval_loss": 1.5217057466506958, |
|
"eval_runtime": 11.1039, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 3950 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 1.7303157994413146e-05, |
|
"loss": 1.2401, |
|
"step": 3960 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 1.7293688745798023e-05, |
|
"loss": 1.2839, |
|
"step": 3970 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 1.72842194971829e-05, |
|
"loss": 1.201, |
|
"step": 3980 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 1.7274750248567777e-05, |
|
"loss": 1.281, |
|
"step": 3990 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 1.7265280999952654e-05, |
|
"loss": 1.4095, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"eval_loss": 1.5256649255752563, |
|
"eval_runtime": 11.1022, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 1.725581175133753e-05, |
|
"loss": 1.2993, |
|
"step": 4010 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 1.7246342502722412e-05, |
|
"loss": 1.2284, |
|
"step": 4020 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 1.7236873254107286e-05, |
|
"loss": 1.2987, |
|
"step": 4030 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 1.7227404005492166e-05, |
|
"loss": 1.3806, |
|
"step": 4040 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 1.7217934756877044e-05, |
|
"loss": 1.239, |
|
"step": 4050 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"eval_loss": 1.5235711336135864, |
|
"eval_runtime": 11.1069, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 4050 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 1.720846550826192e-05, |
|
"loss": 1.2513, |
|
"step": 4060 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 1.7198996259646798e-05, |
|
"loss": 1.2192, |
|
"step": 4070 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 1.718952701103168e-05, |
|
"loss": 1.2173, |
|
"step": 4080 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 1.7180057762416552e-05, |
|
"loss": 1.1926, |
|
"step": 4090 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 1.7170588513801433e-05, |
|
"loss": 1.3603, |
|
"step": 4100 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"eval_loss": 1.5220037698745728, |
|
"eval_runtime": 11.1023, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 4100 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 1.7161119265186306e-05, |
|
"loss": 1.1728, |
|
"step": 4110 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 1.7151650016571187e-05, |
|
"loss": 1.3196, |
|
"step": 4120 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 1.7142180767956064e-05, |
|
"loss": 1.2191, |
|
"step": 4130 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 1.713271151934094e-05, |
|
"loss": 1.2309, |
|
"step": 4140 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 1.712324227072582e-05, |
|
"loss": 1.3678, |
|
"step": 4150 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"eval_loss": 1.520238995552063, |
|
"eval_runtime": 11.1019, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 4150 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 1.71137730221107e-05, |
|
"loss": 1.2266, |
|
"step": 4160 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 1.7104303773495573e-05, |
|
"loss": 1.0984, |
|
"step": 4170 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 1.7094834524880453e-05, |
|
"loss": 1.2464, |
|
"step": 4180 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 1.708536527626533e-05, |
|
"loss": 1.1769, |
|
"step": 4190 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 1.7075896027650207e-05, |
|
"loss": 1.2518, |
|
"step": 4200 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"eval_loss": 1.5198990106582642, |
|
"eval_runtime": 11.1027, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 4200 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 1.7066426779035085e-05, |
|
"loss": 1.3594, |
|
"step": 4210 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 1.7056957530419962e-05, |
|
"loss": 1.2111, |
|
"step": 4220 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 1.704748828180484e-05, |
|
"loss": 1.3119, |
|
"step": 4230 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 1.703801903318972e-05, |
|
"loss": 1.1639, |
|
"step": 4240 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 1.7028549784574597e-05, |
|
"loss": 1.2872, |
|
"step": 4250 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"eval_loss": 1.5232974290847778, |
|
"eval_runtime": 11.1045, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 4250 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 1.7019080535959474e-05, |
|
"loss": 1.3735, |
|
"step": 4260 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 1.700961128734435e-05, |
|
"loss": 1.1299, |
|
"step": 4270 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 1.7000142038729228e-05, |
|
"loss": 1.2638, |
|
"step": 4280 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 1.6990672790114105e-05, |
|
"loss": 1.193, |
|
"step": 4290 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 1.6981203541498982e-05, |
|
"loss": 1.1182, |
|
"step": 4300 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"eval_loss": 1.5242395401000977, |
|
"eval_runtime": 11.1021, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 4300 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 1.6971734292883863e-05, |
|
"loss": 1.1725, |
|
"step": 4310 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 1.696226504426874e-05, |
|
"loss": 1.2596, |
|
"step": 4320 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 1.6952795795653617e-05, |
|
"loss": 1.2494, |
|
"step": 4330 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 1.6943326547038494e-05, |
|
"loss": 1.3007, |
|
"step": 4340 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 1.693385729842337e-05, |
|
"loss": 1.2895, |
|
"step": 4350 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"eval_loss": 1.5165597200393677, |
|
"eval_runtime": 11.1019, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 4350 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 1.692438804980825e-05, |
|
"loss": 1.2721, |
|
"step": 4360 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 1.691491880119313e-05, |
|
"loss": 1.2299, |
|
"step": 4370 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 1.6905449552578003e-05, |
|
"loss": 1.2702, |
|
"step": 4380 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 1.6895980303962883e-05, |
|
"loss": 1.325, |
|
"step": 4390 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 1.6886511055347757e-05, |
|
"loss": 1.161, |
|
"step": 4400 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"eval_loss": 1.520088791847229, |
|
"eval_runtime": 11.1034, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 4400 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 1.6877041806732638e-05, |
|
"loss": 1.3316, |
|
"step": 4410 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 1.6867572558117515e-05, |
|
"loss": 1.247, |
|
"step": 4420 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 1.6858103309502392e-05, |
|
"loss": 1.1956, |
|
"step": 4430 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 1.684863406088727e-05, |
|
"loss": 1.2836, |
|
"step": 4440 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 1.683916481227215e-05, |
|
"loss": 1.1809, |
|
"step": 4450 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"eval_loss": 1.5176990032196045, |
|
"eval_runtime": 11.1043, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 4450 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 1.6829695563657023e-05, |
|
"loss": 1.2991, |
|
"step": 4460 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 1.6820226315041904e-05, |
|
"loss": 1.1781, |
|
"step": 4470 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 1.681075706642678e-05, |
|
"loss": 1.1916, |
|
"step": 4480 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 1.6801287817811658e-05, |
|
"loss": 1.1718, |
|
"step": 4490 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 1.6791818569196535e-05, |
|
"loss": 1.2404, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"eval_loss": 1.5177475214004517, |
|
"eval_runtime": 11.1062, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 1.6782349320581412e-05, |
|
"loss": 1.3288, |
|
"step": 4510 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 1.677288007196629e-05, |
|
"loss": 1.2509, |
|
"step": 4520 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 1.676341082335117e-05, |
|
"loss": 1.3311, |
|
"step": 4530 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 1.6753941574736047e-05, |
|
"loss": 1.311, |
|
"step": 4540 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 1.6744472326120924e-05, |
|
"loss": 1.1809, |
|
"step": 4550 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"eval_loss": 1.5181995630264282, |
|
"eval_runtime": 11.1033, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 4550 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 1.67350030775058e-05, |
|
"loss": 1.2478, |
|
"step": 4560 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 1.672553382889068e-05, |
|
"loss": 1.1652, |
|
"step": 4570 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 1.6716064580275556e-05, |
|
"loss": 1.2703, |
|
"step": 4580 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 1.6706595331660433e-05, |
|
"loss": 1.2417, |
|
"step": 4590 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 1.6697126083045313e-05, |
|
"loss": 1.233, |
|
"step": 4600 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"eval_loss": 1.5219452381134033, |
|
"eval_runtime": 11.1032, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 4600 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 1.668765683443019e-05, |
|
"loss": 1.3557, |
|
"step": 4610 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 1.6678187585815068e-05, |
|
"loss": 1.301, |
|
"step": 4620 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 1.6668718337199945e-05, |
|
"loss": 1.2805, |
|
"step": 4630 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 1.6659249088584822e-05, |
|
"loss": 1.2429, |
|
"step": 4640 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 1.66497798399697e-05, |
|
"loss": 1.2803, |
|
"step": 4650 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"eval_loss": 1.513237714767456, |
|
"eval_runtime": 11.1006, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 4650 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 1.664031059135458e-05, |
|
"loss": 1.1772, |
|
"step": 4660 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 1.6630841342739453e-05, |
|
"loss": 1.2872, |
|
"step": 4670 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 1.6621372094124334e-05, |
|
"loss": 1.1889, |
|
"step": 4680 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 1.661190284550921e-05, |
|
"loss": 1.2534, |
|
"step": 4690 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 1.6602433596894088e-05, |
|
"loss": 1.1332, |
|
"step": 4700 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"eval_loss": 1.5165932178497314, |
|
"eval_runtime": 11.1077, |
|
"eval_samples_per_second": 4.501, |
|
"eval_steps_per_second": 0.81, |
|
"step": 4700 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 1.6592964348278965e-05, |
|
"loss": 1.3659, |
|
"step": 4710 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 1.6583495099663842e-05, |
|
"loss": 1.352, |
|
"step": 4720 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 1.657402585104872e-05, |
|
"loss": 1.3012, |
|
"step": 4730 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 1.65645566024336e-05, |
|
"loss": 1.2812, |
|
"step": 4740 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 1.6555087353818474e-05, |
|
"loss": 1.1912, |
|
"step": 4750 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"eval_loss": 1.5160266160964966, |
|
"eval_runtime": 11.1044, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 4750 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 1.6545618105203354e-05, |
|
"loss": 1.3031, |
|
"step": 4760 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 1.653614885658823e-05, |
|
"loss": 1.2716, |
|
"step": 4770 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 1.652667960797311e-05, |
|
"loss": 1.3176, |
|
"step": 4780 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 1.6517210359357986e-05, |
|
"loss": 1.1763, |
|
"step": 4790 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 1.6507741110742863e-05, |
|
"loss": 1.2525, |
|
"step": 4800 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"eval_loss": 1.517958402633667, |
|
"eval_runtime": 11.1053, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 4800 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 1.649827186212774e-05, |
|
"loss": 1.3948, |
|
"step": 4810 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 1.648880261351262e-05, |
|
"loss": 1.2808, |
|
"step": 4820 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 1.6479333364897498e-05, |
|
"loss": 1.3338, |
|
"step": 4830 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 1.6469864116282375e-05, |
|
"loss": 1.2254, |
|
"step": 4840 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 1.6460394867667252e-05, |
|
"loss": 1.1729, |
|
"step": 4850 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"eval_loss": 1.5148005485534668, |
|
"eval_runtime": 11.1012, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 4850 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 1.645092561905213e-05, |
|
"loss": 1.226, |
|
"step": 4860 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 1.6441456370437006e-05, |
|
"loss": 1.2996, |
|
"step": 4870 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 1.6431987121821883e-05, |
|
"loss": 1.2236, |
|
"step": 4880 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 1.6422517873206764e-05, |
|
"loss": 1.3025, |
|
"step": 4890 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 1.641304862459164e-05, |
|
"loss": 1.2055, |
|
"step": 4900 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"eval_loss": 1.5157992839813232, |
|
"eval_runtime": 11.1039, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 4900 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 1.6403579375976518e-05, |
|
"loss": 1.2806, |
|
"step": 4910 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 1.6394110127361395e-05, |
|
"loss": 1.2757, |
|
"step": 4920 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 1.6384640878746273e-05, |
|
"loss": 1.1912, |
|
"step": 4930 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 1.637517163013115e-05, |
|
"loss": 1.2241, |
|
"step": 4940 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 1.636570238151603e-05, |
|
"loss": 1.284, |
|
"step": 4950 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"eval_loss": 1.5186959505081177, |
|
"eval_runtime": 11.1049, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 4950 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 1.6356233132900904e-05, |
|
"loss": 1.3592, |
|
"step": 4960 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 1.6346763884285784e-05, |
|
"loss": 1.1724, |
|
"step": 4970 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 1.633729463567066e-05, |
|
"loss": 1.3508, |
|
"step": 4980 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 1.632782538705554e-05, |
|
"loss": 1.2638, |
|
"step": 4990 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 1.6318356138440416e-05, |
|
"loss": 1.2677, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"eval_loss": 1.5210458040237427, |
|
"eval_runtime": 11.1096, |
|
"eval_samples_per_second": 4.501, |
|
"eval_steps_per_second": 0.81, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 1.6308886889825293e-05, |
|
"loss": 1.2117, |
|
"step": 5010 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 1.629941764121017e-05, |
|
"loss": 1.1808, |
|
"step": 5020 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 1.628994839259505e-05, |
|
"loss": 1.2331, |
|
"step": 5030 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 1.6280479143979924e-05, |
|
"loss": 1.2229, |
|
"step": 5040 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 1.6271009895364805e-05, |
|
"loss": 1.2391, |
|
"step": 5050 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"eval_loss": 1.5157711505889893, |
|
"eval_runtime": 11.1076, |
|
"eval_samples_per_second": 4.501, |
|
"eval_steps_per_second": 0.81, |
|
"step": 5050 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 1.6261540646749682e-05, |
|
"loss": 1.1916, |
|
"step": 5060 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 1.625207139813456e-05, |
|
"loss": 1.2191, |
|
"step": 5070 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 1.6242602149519436e-05, |
|
"loss": 1.1622, |
|
"step": 5080 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 1.6233132900904314e-05, |
|
"loss": 1.1589, |
|
"step": 5090 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 1.622366365228919e-05, |
|
"loss": 1.084, |
|
"step": 5100 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"eval_loss": 1.515824556350708, |
|
"eval_runtime": 11.1049, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 5100 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 1.621419440367407e-05, |
|
"loss": 1.2266, |
|
"step": 5110 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 1.620472515505895e-05, |
|
"loss": 1.2264, |
|
"step": 5120 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 1.6195255906443825e-05, |
|
"loss": 1.3164, |
|
"step": 5130 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 1.6185786657828703e-05, |
|
"loss": 1.1653, |
|
"step": 5140 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 1.617631740921358e-05, |
|
"loss": 1.1668, |
|
"step": 5150 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"eval_loss": 1.5181384086608887, |
|
"eval_runtime": 11.1063, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 5150 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 1.6166848160598457e-05, |
|
"loss": 1.1629, |
|
"step": 5160 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 1.6157378911983334e-05, |
|
"loss": 1.1143, |
|
"step": 5170 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 1.6147909663368215e-05, |
|
"loss": 1.2293, |
|
"step": 5180 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 1.6138440414753092e-05, |
|
"loss": 1.1529, |
|
"step": 5190 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 1.612897116613797e-05, |
|
"loss": 1.245, |
|
"step": 5200 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"eval_loss": 1.5197851657867432, |
|
"eval_runtime": 11.1042, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 5200 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 1.6119501917522846e-05, |
|
"loss": 1.2817, |
|
"step": 5210 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 1.6110032668907723e-05, |
|
"loss": 1.1912, |
|
"step": 5220 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 1.61005634202926e-05, |
|
"loss": 1.2802, |
|
"step": 5230 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 1.609109417167748e-05, |
|
"loss": 1.1844, |
|
"step": 5240 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 1.6081624923062355e-05, |
|
"loss": 1.2329, |
|
"step": 5250 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"eval_loss": 1.5154054164886475, |
|
"eval_runtime": 11.1041, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 5250 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 1.6072155674447235e-05, |
|
"loss": 1.222, |
|
"step": 5260 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 1.6062686425832112e-05, |
|
"loss": 1.348, |
|
"step": 5270 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 1.605321717721699e-05, |
|
"loss": 1.2904, |
|
"step": 5280 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 1.6043747928601866e-05, |
|
"loss": 1.1723, |
|
"step": 5290 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 1.6034278679986744e-05, |
|
"loss": 1.3371, |
|
"step": 5300 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"eval_loss": 1.5103570222854614, |
|
"eval_runtime": 11.1043, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 5300 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 1.602480943137162e-05, |
|
"loss": 1.273, |
|
"step": 5310 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 1.60153401827565e-05, |
|
"loss": 1.266, |
|
"step": 5320 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 1.6005870934141375e-05, |
|
"loss": 1.2384, |
|
"step": 5330 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 1.5996401685526256e-05, |
|
"loss": 1.2663, |
|
"step": 5340 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 1.5986932436911133e-05, |
|
"loss": 1.2807, |
|
"step": 5350 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"eval_loss": 1.5090947151184082, |
|
"eval_runtime": 11.105, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 5350 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 1.597746318829601e-05, |
|
"loss": 1.2242, |
|
"step": 5360 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 1.5967993939680887e-05, |
|
"loss": 1.1769, |
|
"step": 5370 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 1.5958524691065764e-05, |
|
"loss": 1.3302, |
|
"step": 5380 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 1.594905544245064e-05, |
|
"loss": 1.3161, |
|
"step": 5390 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 1.5939586193835522e-05, |
|
"loss": 1.2054, |
|
"step": 5400 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"eval_loss": 1.5138897895812988, |
|
"eval_runtime": 11.1063, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 5400 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 1.59301169452204e-05, |
|
"loss": 1.2348, |
|
"step": 5410 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 1.5920647696605276e-05, |
|
"loss": 1.1776, |
|
"step": 5420 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 1.5911178447990153e-05, |
|
"loss": 1.1116, |
|
"step": 5430 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 1.590170919937503e-05, |
|
"loss": 1.0925, |
|
"step": 5440 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 1.5892239950759907e-05, |
|
"loss": 1.1619, |
|
"step": 5450 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"eval_loss": 1.5155420303344727, |
|
"eval_runtime": 11.1052, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 5450 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 1.5882770702144785e-05, |
|
"loss": 1.3392, |
|
"step": 5460 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 1.5873301453529665e-05, |
|
"loss": 1.195, |
|
"step": 5470 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 1.5863832204914542e-05, |
|
"loss": 1.2003, |
|
"step": 5480 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 1.585436295629942e-05, |
|
"loss": 1.1116, |
|
"step": 5490 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 1.5844893707684297e-05, |
|
"loss": 1.2471, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"eval_loss": 1.5145519971847534, |
|
"eval_runtime": 11.1049, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 1.5835424459069174e-05, |
|
"loss": 1.2846, |
|
"step": 5510 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 1.582595521045405e-05, |
|
"loss": 1.1335, |
|
"step": 5520 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 1.581648596183893e-05, |
|
"loss": 1.2422, |
|
"step": 5530 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 1.5807016713223805e-05, |
|
"loss": 1.132, |
|
"step": 5540 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 1.5797547464608686e-05, |
|
"loss": 1.3086, |
|
"step": 5550 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"eval_loss": 1.5202538967132568, |
|
"eval_runtime": 11.1071, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 5550 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 1.5788078215993563e-05, |
|
"loss": 1.2456, |
|
"step": 5560 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 1.577860896737844e-05, |
|
"loss": 1.0758, |
|
"step": 5570 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 1.5769139718763317e-05, |
|
"loss": 1.2522, |
|
"step": 5580 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 1.5759670470148194e-05, |
|
"loss": 1.261, |
|
"step": 5590 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 1.575020122153307e-05, |
|
"loss": 1.1948, |
|
"step": 5600 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"eval_loss": 1.5124799013137817, |
|
"eval_runtime": 11.1051, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 5600 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 1.5740731972917952e-05, |
|
"loss": 1.2618, |
|
"step": 5610 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 1.5731262724302826e-05, |
|
"loss": 1.2332, |
|
"step": 5620 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 1.5721793475687706e-05, |
|
"loss": 1.3488, |
|
"step": 5630 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 1.5712324227072583e-05, |
|
"loss": 1.2281, |
|
"step": 5640 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 1.570285497845746e-05, |
|
"loss": 1.1638, |
|
"step": 5650 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"eval_loss": 1.5104706287384033, |
|
"eval_runtime": 11.1019, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 5650 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 1.5693385729842338e-05, |
|
"loss": 1.2206, |
|
"step": 5660 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 1.5683916481227215e-05, |
|
"loss": 1.3591, |
|
"step": 5670 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 1.5674447232612092e-05, |
|
"loss": 1.1348, |
|
"step": 5680 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 1.5664977983996972e-05, |
|
"loss": 1.3598, |
|
"step": 5690 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 1.565550873538185e-05, |
|
"loss": 1.3163, |
|
"step": 5700 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"eval_loss": 1.511236310005188, |
|
"eval_runtime": 11.1003, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 5700 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 1.5646039486766727e-05, |
|
"loss": 1.2545, |
|
"step": 5710 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 1.5636570238151604e-05, |
|
"loss": 1.2293, |
|
"step": 5720 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 1.562710098953648e-05, |
|
"loss": 1.2216, |
|
"step": 5730 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 1.5617631740921358e-05, |
|
"loss": 1.1821, |
|
"step": 5740 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 1.5608162492306235e-05, |
|
"loss": 1.12, |
|
"step": 5750 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"eval_loss": 1.512481689453125, |
|
"eval_runtime": 11.103, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 5750 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 1.5598693243691116e-05, |
|
"loss": 1.2154, |
|
"step": 5760 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 1.5589223995075993e-05, |
|
"loss": 1.1624, |
|
"step": 5770 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 1.557975474646087e-05, |
|
"loss": 1.2371, |
|
"step": 5780 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 1.5570285497845747e-05, |
|
"loss": 1.2578, |
|
"step": 5790 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 1.5560816249230624e-05, |
|
"loss": 1.2715, |
|
"step": 5800 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"eval_loss": 1.5152621269226074, |
|
"eval_runtime": 11.1064, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 5800 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 1.55513470006155e-05, |
|
"loss": 1.1459, |
|
"step": 5810 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 1.5541877752000382e-05, |
|
"loss": 1.2057, |
|
"step": 5820 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 1.5532408503385256e-05, |
|
"loss": 1.185, |
|
"step": 5830 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 1.5522939254770136e-05, |
|
"loss": 1.2215, |
|
"step": 5840 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 1.5513470006155013e-05, |
|
"loss": 1.1208, |
|
"step": 5850 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"eval_loss": 1.5129001140594482, |
|
"eval_runtime": 11.0993, |
|
"eval_samples_per_second": 4.505, |
|
"eval_steps_per_second": 0.811, |
|
"step": 5850 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 1.550400075753989e-05, |
|
"loss": 1.312, |
|
"step": 5860 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 1.5494531508924768e-05, |
|
"loss": 1.2249, |
|
"step": 5870 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 1.5485062260309648e-05, |
|
"loss": 1.1926, |
|
"step": 5880 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 1.5475593011694522e-05, |
|
"loss": 1.2302, |
|
"step": 5890 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 1.5466123763079403e-05, |
|
"loss": 1.1741, |
|
"step": 5900 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"eval_loss": 1.5075663328170776, |
|
"eval_runtime": 11.1006, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 5900 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 1.5456654514464276e-05, |
|
"loss": 1.1996, |
|
"step": 5910 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 1.5447185265849157e-05, |
|
"loss": 1.3027, |
|
"step": 5920 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 1.5437716017234034e-05, |
|
"loss": 1.1912, |
|
"step": 5930 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 1.542824676861891e-05, |
|
"loss": 1.3958, |
|
"step": 5940 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 1.5418777520003788e-05, |
|
"loss": 1.1752, |
|
"step": 5950 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"eval_loss": 1.5051928758621216, |
|
"eval_runtime": 11.1064, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 5950 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 1.5409308271388665e-05, |
|
"loss": 1.3754, |
|
"step": 5960 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 1.5399839022773542e-05, |
|
"loss": 1.2321, |
|
"step": 5970 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 1.5390369774158423e-05, |
|
"loss": 1.314, |
|
"step": 5980 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 1.53809005255433e-05, |
|
"loss": 1.3009, |
|
"step": 5990 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 1.5371431276928177e-05, |
|
"loss": 1.2459, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"eval_loss": 1.5049835443496704, |
|
"eval_runtime": 11.1018, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 1.5361962028313054e-05, |
|
"loss": 1.2519, |
|
"step": 6010 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 1.535249277969793e-05, |
|
"loss": 1.3748, |
|
"step": 6020 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 1.534302353108281e-05, |
|
"loss": 1.2095, |
|
"step": 6030 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 1.5333554282467686e-05, |
|
"loss": 1.2699, |
|
"step": 6040 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 1.5324085033852566e-05, |
|
"loss": 1.1617, |
|
"step": 6050 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"eval_loss": 1.504417896270752, |
|
"eval_runtime": 11.1079, |
|
"eval_samples_per_second": 4.501, |
|
"eval_steps_per_second": 0.81, |
|
"step": 6050 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 1.5314615785237444e-05, |
|
"loss": 1.3861, |
|
"step": 6060 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 1.530514653662232e-05, |
|
"loss": 1.283, |
|
"step": 6070 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 1.5295677288007198e-05, |
|
"loss": 1.1709, |
|
"step": 6080 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 1.5286208039392075e-05, |
|
"loss": 1.2969, |
|
"step": 6090 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 1.5276738790776952e-05, |
|
"loss": 1.086, |
|
"step": 6100 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"eval_loss": 1.5073156356811523, |
|
"eval_runtime": 11.1005, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 6100 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 1.5267269542161833e-05, |
|
"loss": 1.2764, |
|
"step": 6110 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 1.5257800293546708e-05, |
|
"loss": 1.0797, |
|
"step": 6120 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 1.5248331044931585e-05, |
|
"loss": 1.3044, |
|
"step": 6130 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 1.5238861796316464e-05, |
|
"loss": 1.2231, |
|
"step": 6140 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 1.5229392547701341e-05, |
|
"loss": 1.2299, |
|
"step": 6150 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"eval_loss": 1.5081892013549805, |
|
"eval_runtime": 11.1036, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 6150 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 1.5219923299086218e-05, |
|
"loss": 1.2737, |
|
"step": 6160 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 1.5210454050471097e-05, |
|
"loss": 1.1765, |
|
"step": 6170 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 1.5200984801855974e-05, |
|
"loss": 1.1904, |
|
"step": 6180 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 1.5191515553240851e-05, |
|
"loss": 1.0931, |
|
"step": 6190 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 1.5182046304625729e-05, |
|
"loss": 1.2914, |
|
"step": 6200 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"eval_loss": 1.5075067281723022, |
|
"eval_runtime": 11.1007, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 6200 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 1.5172577056010607e-05, |
|
"loss": 1.3305, |
|
"step": 6210 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 1.5163107807395485e-05, |
|
"loss": 1.2824, |
|
"step": 6220 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 1.5153638558780362e-05, |
|
"loss": 1.2876, |
|
"step": 6230 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 1.514416931016524e-05, |
|
"loss": 1.2809, |
|
"step": 6240 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 1.5134700061550118e-05, |
|
"loss": 1.1877, |
|
"step": 6250 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"eval_loss": 1.5066986083984375, |
|
"eval_runtime": 11.102, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 6250 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 1.5125230812934995e-05, |
|
"loss": 1.3303, |
|
"step": 6260 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 1.5115761564319874e-05, |
|
"loss": 1.3187, |
|
"step": 6270 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 1.5106292315704749e-05, |
|
"loss": 1.3596, |
|
"step": 6280 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 1.5096823067089628e-05, |
|
"loss": 1.3987, |
|
"step": 6290 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 1.5087353818474507e-05, |
|
"loss": 1.2172, |
|
"step": 6300 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"eval_loss": 1.510190725326538, |
|
"eval_runtime": 11.1023, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 6300 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 1.5077884569859382e-05, |
|
"loss": 1.217, |
|
"step": 6310 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 1.5068415321244261e-05, |
|
"loss": 1.2176, |
|
"step": 6320 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 1.505894607262914e-05, |
|
"loss": 1.2746, |
|
"step": 6330 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 1.5049476824014015e-05, |
|
"loss": 1.1446, |
|
"step": 6340 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 1.5040007575398894e-05, |
|
"loss": 1.2467, |
|
"step": 6350 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"eval_loss": 1.5058343410491943, |
|
"eval_runtime": 11.1052, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 6350 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 1.503053832678377e-05, |
|
"loss": 1.3396, |
|
"step": 6360 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 1.5021069078168648e-05, |
|
"loss": 1.137, |
|
"step": 6370 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 1.5011599829553527e-05, |
|
"loss": 1.2044, |
|
"step": 6380 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 1.5002130580938403e-05, |
|
"loss": 1.2227, |
|
"step": 6390 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 1.4992661332323282e-05, |
|
"loss": 1.1355, |
|
"step": 6400 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"eval_loss": 1.5088095664978027, |
|
"eval_runtime": 11.1058, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 6400 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 1.4983192083708159e-05, |
|
"loss": 1.3279, |
|
"step": 6410 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 1.4973722835093036e-05, |
|
"loss": 1.1854, |
|
"step": 6420 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 1.4964253586477915e-05, |
|
"loss": 1.2564, |
|
"step": 6430 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 1.4954784337862792e-05, |
|
"loss": 1.2211, |
|
"step": 6440 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 1.4945315089247669e-05, |
|
"loss": 1.1585, |
|
"step": 6450 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"eval_loss": 1.513198733329773, |
|
"eval_runtime": 11.1037, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 6450 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 1.4935845840632548e-05, |
|
"loss": 1.2025, |
|
"step": 6460 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 1.4926376592017425e-05, |
|
"loss": 1.272, |
|
"step": 6470 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 1.4916907343402302e-05, |
|
"loss": 1.2619, |
|
"step": 6480 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 1.490743809478718e-05, |
|
"loss": 1.2126, |
|
"step": 6490 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 1.4897968846172058e-05, |
|
"loss": 1.3286, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"eval_loss": 1.511282205581665, |
|
"eval_runtime": 11.106, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 1.4888499597556935e-05, |
|
"loss": 1.2994, |
|
"step": 6510 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 1.4879030348941812e-05, |
|
"loss": 1.2734, |
|
"step": 6520 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 1.4869561100326691e-05, |
|
"loss": 1.2995, |
|
"step": 6530 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 1.4860091851711568e-05, |
|
"loss": 1.2612, |
|
"step": 6540 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 1.4850622603096445e-05, |
|
"loss": 1.266, |
|
"step": 6550 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"eval_loss": 1.504214882850647, |
|
"eval_runtime": 11.1029, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 6550 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 1.4841153354481324e-05, |
|
"loss": 1.1321, |
|
"step": 6560 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 1.48316841058662e-05, |
|
"loss": 1.1749, |
|
"step": 6570 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 1.4822214857251079e-05, |
|
"loss": 1.2184, |
|
"step": 6580 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 1.4812745608635957e-05, |
|
"loss": 1.3397, |
|
"step": 6590 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 1.4803276360020833e-05, |
|
"loss": 1.2433, |
|
"step": 6600 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"eval_loss": 1.5029431581497192, |
|
"eval_runtime": 11.1036, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 6600 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 1.4793807111405712e-05, |
|
"loss": 1.2198, |
|
"step": 6610 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 1.478433786279059e-05, |
|
"loss": 1.2595, |
|
"step": 6620 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 1.4774868614175466e-05, |
|
"loss": 1.2659, |
|
"step": 6630 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 1.4765399365560345e-05, |
|
"loss": 1.3481, |
|
"step": 6640 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 1.475593011694522e-05, |
|
"loss": 1.3093, |
|
"step": 6650 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"eval_loss": 1.5089229345321655, |
|
"eval_runtime": 11.1039, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 6650 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 1.4746460868330099e-05, |
|
"loss": 1.3988, |
|
"step": 6660 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 1.4736991619714978e-05, |
|
"loss": 1.3019, |
|
"step": 6670 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 1.4727522371099853e-05, |
|
"loss": 1.2533, |
|
"step": 6680 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 1.4718053122484732e-05, |
|
"loss": 1.2778, |
|
"step": 6690 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 1.4708583873869611e-05, |
|
"loss": 1.3292, |
|
"step": 6700 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"eval_loss": 1.5095062255859375, |
|
"eval_runtime": 11.1052, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 6700 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 1.4699114625254486e-05, |
|
"loss": 1.2946, |
|
"step": 6710 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 1.4689645376639365e-05, |
|
"loss": 1.1201, |
|
"step": 6720 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 1.4680176128024242e-05, |
|
"loss": 1.1428, |
|
"step": 6730 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 1.467070687940912e-05, |
|
"loss": 1.2471, |
|
"step": 6740 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 1.4661237630793998e-05, |
|
"loss": 1.0705, |
|
"step": 6750 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"eval_loss": 1.5066548585891724, |
|
"eval_runtime": 11.1042, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 6750 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 1.4651768382178875e-05, |
|
"loss": 1.2586, |
|
"step": 6760 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 1.4642299133563753e-05, |
|
"loss": 1.3162, |
|
"step": 6770 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 1.463282988494863e-05, |
|
"loss": 1.2276, |
|
"step": 6780 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 1.4623360636333509e-05, |
|
"loss": 1.1835, |
|
"step": 6790 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 1.4613891387718386e-05, |
|
"loss": 1.3087, |
|
"step": 6800 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"eval_loss": 1.5072882175445557, |
|
"eval_runtime": 11.1057, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 6800 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 1.4604422139103263e-05, |
|
"loss": 1.2367, |
|
"step": 6810 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 1.4594952890488142e-05, |
|
"loss": 1.3441, |
|
"step": 6820 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 1.4585483641873019e-05, |
|
"loss": 1.3857, |
|
"step": 6830 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 1.4576014393257896e-05, |
|
"loss": 1.2358, |
|
"step": 6840 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 1.4566545144642775e-05, |
|
"loss": 1.2483, |
|
"step": 6850 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"eval_loss": 1.510798692703247, |
|
"eval_runtime": 11.1094, |
|
"eval_samples_per_second": 4.501, |
|
"eval_steps_per_second": 0.81, |
|
"step": 6850 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 1.455707589602765e-05, |
|
"loss": 1.2633, |
|
"step": 6860 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 1.4547606647412529e-05, |
|
"loss": 1.2781, |
|
"step": 6870 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 1.4538137398797408e-05, |
|
"loss": 1.2922, |
|
"step": 6880 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 1.4528668150182283e-05, |
|
"loss": 1.0341, |
|
"step": 6890 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 1.4519198901567162e-05, |
|
"loss": 1.2376, |
|
"step": 6900 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"eval_loss": 1.512637972831726, |
|
"eval_runtime": 11.1062, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 6900 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 1.4509729652952041e-05, |
|
"loss": 1.2153, |
|
"step": 6910 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 1.4500260404336917e-05, |
|
"loss": 1.1935, |
|
"step": 6920 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 1.4490791155721795e-05, |
|
"loss": 1.2562, |
|
"step": 6930 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 1.448132190710667e-05, |
|
"loss": 1.2303, |
|
"step": 6940 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 1.447185265849155e-05, |
|
"loss": 1.2746, |
|
"step": 6950 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"eval_loss": 1.5068856477737427, |
|
"eval_runtime": 11.1031, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 6950 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 1.4462383409876428e-05, |
|
"loss": 1.1869, |
|
"step": 6960 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 1.4452914161261304e-05, |
|
"loss": 1.135, |
|
"step": 6970 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 1.4443444912646183e-05, |
|
"loss": 1.3105, |
|
"step": 6980 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 1.4433975664031062e-05, |
|
"loss": 1.1795, |
|
"step": 6990 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 1.4424506415415937e-05, |
|
"loss": 1.1047, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"eval_loss": 1.5093187093734741, |
|
"eval_runtime": 11.1049, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 1.4415037166800816e-05, |
|
"loss": 1.2075, |
|
"step": 7010 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 1.4405567918185693e-05, |
|
"loss": 1.283, |
|
"step": 7020 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 1.439609866957057e-05, |
|
"loss": 1.158, |
|
"step": 7030 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 1.4386629420955449e-05, |
|
"loss": 1.3239, |
|
"step": 7040 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 1.4377160172340326e-05, |
|
"loss": 1.31, |
|
"step": 7050 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"eval_loss": 1.511340618133545, |
|
"eval_runtime": 11.1039, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 7050 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 1.4367690923725203e-05, |
|
"loss": 1.2312, |
|
"step": 7060 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 1.4358221675110082e-05, |
|
"loss": 1.2874, |
|
"step": 7070 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 1.434875242649496e-05, |
|
"loss": 1.2393, |
|
"step": 7080 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 1.4339283177879836e-05, |
|
"loss": 1.2232, |
|
"step": 7090 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 1.4329813929264713e-05, |
|
"loss": 1.229, |
|
"step": 7100 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"eval_loss": 1.5077365636825562, |
|
"eval_runtime": 11.1044, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 7100 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 1.4320344680649592e-05, |
|
"loss": 1.168, |
|
"step": 7110 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 1.431087543203447e-05, |
|
"loss": 1.1784, |
|
"step": 7120 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 1.4301406183419347e-05, |
|
"loss": 1.1674, |
|
"step": 7130 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 1.4291936934804225e-05, |
|
"loss": 1.1466, |
|
"step": 7140 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 1.4282467686189101e-05, |
|
"loss": 1.2445, |
|
"step": 7150 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"eval_loss": 1.506815791130066, |
|
"eval_runtime": 11.1061, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 7150 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 1.427299843757398e-05, |
|
"loss": 1.2658, |
|
"step": 7160 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 1.4263529188958859e-05, |
|
"loss": 1.1542, |
|
"step": 7170 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 1.4254059940343734e-05, |
|
"loss": 1.2335, |
|
"step": 7180 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 1.4244590691728613e-05, |
|
"loss": 1.2308, |
|
"step": 7190 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 1.4235121443113492e-05, |
|
"loss": 1.2248, |
|
"step": 7200 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"eval_loss": 1.5059149265289307, |
|
"eval_runtime": 11.1042, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 7200 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 1.4225652194498367e-05, |
|
"loss": 1.1548, |
|
"step": 7210 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 1.4216182945883246e-05, |
|
"loss": 1.2057, |
|
"step": 7220 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 1.4206713697268121e-05, |
|
"loss": 1.2195, |
|
"step": 7230 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 1.4197244448653e-05, |
|
"loss": 1.2445, |
|
"step": 7240 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 1.4187775200037879e-05, |
|
"loss": 1.2574, |
|
"step": 7250 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"eval_loss": 1.5033655166625977, |
|
"eval_runtime": 11.1057, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 7250 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 1.4178305951422755e-05, |
|
"loss": 1.3211, |
|
"step": 7260 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 1.4168836702807633e-05, |
|
"loss": 1.1291, |
|
"step": 7270 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 1.4159367454192512e-05, |
|
"loss": 1.2883, |
|
"step": 7280 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 1.4149898205577388e-05, |
|
"loss": 1.2826, |
|
"step": 7290 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 1.4140428956962266e-05, |
|
"loss": 1.1146, |
|
"step": 7300 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"eval_loss": 1.5009595155715942, |
|
"eval_runtime": 11.1074, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 7300 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 1.4130959708347144e-05, |
|
"loss": 1.2304, |
|
"step": 7310 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 1.412149045973202e-05, |
|
"loss": 1.2728, |
|
"step": 7320 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 1.41120212111169e-05, |
|
"loss": 1.2091, |
|
"step": 7330 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 1.4102551962501777e-05, |
|
"loss": 1.2483, |
|
"step": 7340 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 1.4093082713886654e-05, |
|
"loss": 1.1942, |
|
"step": 7350 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"eval_loss": 1.4991462230682373, |
|
"eval_runtime": 11.1057, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 7350 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 1.4083613465271533e-05, |
|
"loss": 1.2849, |
|
"step": 7360 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 1.407414421665641e-05, |
|
"loss": 1.3465, |
|
"step": 7370 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.4064674968041287e-05, |
|
"loss": 1.0644, |
|
"step": 7380 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.4055205719426164e-05, |
|
"loss": 1.2192, |
|
"step": 7390 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.4045736470811043e-05, |
|
"loss": 1.3069, |
|
"step": 7400 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 1.4969042539596558, |
|
"eval_runtime": 11.1026, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 7400 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.403626722219592e-05, |
|
"loss": 1.2998, |
|
"step": 7410 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.4026797973580797e-05, |
|
"loss": 1.2498, |
|
"step": 7420 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.4017328724965676e-05, |
|
"loss": 1.3216, |
|
"step": 7430 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.4007859476350553e-05, |
|
"loss": 1.232, |
|
"step": 7440 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.399839022773543e-05, |
|
"loss": 1.1652, |
|
"step": 7450 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"eval_loss": 1.5023287534713745, |
|
"eval_runtime": 11.1049, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 7450 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.398892097912031e-05, |
|
"loss": 1.1882, |
|
"step": 7460 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.3979451730505185e-05, |
|
"loss": 1.2465, |
|
"step": 7470 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.3969982481890063e-05, |
|
"loss": 1.1823, |
|
"step": 7480 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.3960513233274942e-05, |
|
"loss": 1.1694, |
|
"step": 7490 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.3951043984659818e-05, |
|
"loss": 1.1586, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"eval_loss": 1.5061203241348267, |
|
"eval_runtime": 11.1053, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.3941574736044697e-05, |
|
"loss": 1.164, |
|
"step": 7510 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.3932105487429575e-05, |
|
"loss": 1.2655, |
|
"step": 7520 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 1.392263623881445e-05, |
|
"loss": 1.1802, |
|
"step": 7530 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 1.391316699019933e-05, |
|
"loss": 1.2329, |
|
"step": 7540 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 1.3903697741584205e-05, |
|
"loss": 1.1656, |
|
"step": 7550 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"eval_loss": 1.5041453838348389, |
|
"eval_runtime": 11.1041, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 7550 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 1.3894228492969084e-05, |
|
"loss": 1.1235, |
|
"step": 7560 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 1.3884759244353963e-05, |
|
"loss": 1.3264, |
|
"step": 7570 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 1.3875289995738838e-05, |
|
"loss": 1.2418, |
|
"step": 7580 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 1.3865820747123717e-05, |
|
"loss": 1.2587, |
|
"step": 7590 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 1.3856351498508594e-05, |
|
"loss": 1.1193, |
|
"step": 7600 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"eval_loss": 1.5012603998184204, |
|
"eval_runtime": 11.1043, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 7600 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 1.3846882249893471e-05, |
|
"loss": 1.1465, |
|
"step": 7610 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 1.383741300127835e-05, |
|
"loss": 1.147, |
|
"step": 7620 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 1.3827943752663227e-05, |
|
"loss": 1.132, |
|
"step": 7630 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 1.3818474504048104e-05, |
|
"loss": 1.18, |
|
"step": 7640 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 1.3809005255432983e-05, |
|
"loss": 1.2027, |
|
"step": 7650 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"eval_loss": 1.4945385456085205, |
|
"eval_runtime": 11.1041, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 7650 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 1.379953600681786e-05, |
|
"loss": 1.0908, |
|
"step": 7660 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 1.3790066758202738e-05, |
|
"loss": 1.1802, |
|
"step": 7670 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 1.3780597509587615e-05, |
|
"loss": 1.144, |
|
"step": 7680 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 1.3771128260972494e-05, |
|
"loss": 1.2644, |
|
"step": 7690 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 1.376165901235737e-05, |
|
"loss": 1.2341, |
|
"step": 7700 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"eval_loss": 1.4995837211608887, |
|
"eval_runtime": 11.1056, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 7700 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 1.3752189763742248e-05, |
|
"loss": 1.253, |
|
"step": 7710 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 1.3742720515127127e-05, |
|
"loss": 1.1352, |
|
"step": 7720 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 1.3733251266512004e-05, |
|
"loss": 1.1979, |
|
"step": 7730 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 1.3723782017896881e-05, |
|
"loss": 1.1743, |
|
"step": 7740 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 1.371431276928176e-05, |
|
"loss": 1.212, |
|
"step": 7750 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"eval_loss": 1.5030674934387207, |
|
"eval_runtime": 11.1044, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 7750 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 1.3704843520666635e-05, |
|
"loss": 1.3377, |
|
"step": 7760 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 1.3695374272051514e-05, |
|
"loss": 1.2612, |
|
"step": 7770 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 1.3685905023436393e-05, |
|
"loss": 1.2462, |
|
"step": 7780 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 1.3676435774821268e-05, |
|
"loss": 1.2551, |
|
"step": 7790 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 1.3666966526206147e-05, |
|
"loss": 1.2369, |
|
"step": 7800 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"eval_loss": 1.5058186054229736, |
|
"eval_runtime": 11.1057, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 7800 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 1.3657497277591026e-05, |
|
"loss": 1.2729, |
|
"step": 7810 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 1.3648028028975901e-05, |
|
"loss": 1.131, |
|
"step": 7820 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 1.363855878036078e-05, |
|
"loss": 1.1414, |
|
"step": 7830 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 1.3629089531745656e-05, |
|
"loss": 1.2636, |
|
"step": 7840 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 1.3619620283130535e-05, |
|
"loss": 1.2231, |
|
"step": 7850 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"eval_loss": 1.5046865940093994, |
|
"eval_runtime": 11.1051, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 7850 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 1.3610151034515413e-05, |
|
"loss": 1.2191, |
|
"step": 7860 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 1.3600681785900289e-05, |
|
"loss": 1.2249, |
|
"step": 7870 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 1.3591212537285168e-05, |
|
"loss": 1.121, |
|
"step": 7880 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 1.3581743288670047e-05, |
|
"loss": 1.2831, |
|
"step": 7890 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 1.3572274040054922e-05, |
|
"loss": 1.2337, |
|
"step": 7900 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"eval_loss": 1.4996365308761597, |
|
"eval_runtime": 11.1054, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 7900 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 1.35628047914398e-05, |
|
"loss": 1.2264, |
|
"step": 7910 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 1.3553335542824678e-05, |
|
"loss": 1.3452, |
|
"step": 7920 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 1.3543866294209555e-05, |
|
"loss": 1.3059, |
|
"step": 7930 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 1.3534397045594434e-05, |
|
"loss": 1.2351, |
|
"step": 7940 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 1.3524927796979311e-05, |
|
"loss": 1.2084, |
|
"step": 7950 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"eval_loss": 1.5007269382476807, |
|
"eval_runtime": 11.1064, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 7950 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 1.3515458548364188e-05, |
|
"loss": 1.0782, |
|
"step": 7960 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 1.3505989299749065e-05, |
|
"loss": 1.1822, |
|
"step": 7970 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 1.3496520051133944e-05, |
|
"loss": 1.272, |
|
"step": 7980 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 1.3487050802518821e-05, |
|
"loss": 1.1824, |
|
"step": 7990 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 1.3477581553903698e-05, |
|
"loss": 1.2639, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"eval_loss": 1.503584861755371, |
|
"eval_runtime": 11.1071, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 1.3468112305288577e-05, |
|
"loss": 1.2726, |
|
"step": 8010 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 1.3458643056673454e-05, |
|
"loss": 1.1866, |
|
"step": 8020 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 1.3449173808058332e-05, |
|
"loss": 1.2273, |
|
"step": 8030 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 1.343970455944321e-05, |
|
"loss": 1.2627, |
|
"step": 8040 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 1.3430235310828086e-05, |
|
"loss": 1.349, |
|
"step": 8050 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"eval_loss": 1.5049268007278442, |
|
"eval_runtime": 11.1051, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 8050 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 1.3420766062212965e-05, |
|
"loss": 1.2318, |
|
"step": 8060 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 1.3411296813597843e-05, |
|
"loss": 1.162, |
|
"step": 8070 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 1.3401827564982719e-05, |
|
"loss": 1.1136, |
|
"step": 8080 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 1.3392358316367598e-05, |
|
"loss": 1.1852, |
|
"step": 8090 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 1.3382889067752477e-05, |
|
"loss": 1.0928, |
|
"step": 8100 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"eval_loss": 1.500166654586792, |
|
"eval_runtime": 11.102, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 8100 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 1.3373419819137352e-05, |
|
"loss": 1.3376, |
|
"step": 8110 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 1.3363950570522231e-05, |
|
"loss": 1.1933, |
|
"step": 8120 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 1.3354481321907106e-05, |
|
"loss": 1.1219, |
|
"step": 8130 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 1.3345012073291985e-05, |
|
"loss": 1.2579, |
|
"step": 8140 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 1.3335542824676864e-05, |
|
"loss": 1.2191, |
|
"step": 8150 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"eval_loss": 1.497385859489441, |
|
"eval_runtime": 11.1035, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 8150 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 1.332607357606174e-05, |
|
"loss": 1.1932, |
|
"step": 8160 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 1.3316604327446618e-05, |
|
"loss": 1.154, |
|
"step": 8170 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 1.3307135078831497e-05, |
|
"loss": 1.1659, |
|
"step": 8180 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 1.3297665830216373e-05, |
|
"loss": 1.2568, |
|
"step": 8190 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 1.3288196581601251e-05, |
|
"loss": 1.1628, |
|
"step": 8200 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"eval_loss": 1.49826979637146, |
|
"eval_runtime": 11.1051, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 8200 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 1.3278727332986129e-05, |
|
"loss": 1.2736, |
|
"step": 8210 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 1.3269258084371006e-05, |
|
"loss": 1.295, |
|
"step": 8220 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 1.3259788835755885e-05, |
|
"loss": 1.247, |
|
"step": 8230 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 1.3250319587140762e-05, |
|
"loss": 1.301, |
|
"step": 8240 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 1.3240850338525639e-05, |
|
"loss": 1.2123, |
|
"step": 8250 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"eval_loss": 1.500402808189392, |
|
"eval_runtime": 11.1046, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 8250 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 1.3231381089910518e-05, |
|
"loss": 1.1853, |
|
"step": 8260 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 1.3221911841295395e-05, |
|
"loss": 1.1187, |
|
"step": 8270 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 1.3212442592680272e-05, |
|
"loss": 1.1464, |
|
"step": 8280 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 1.3202973344065149e-05, |
|
"loss": 1.1428, |
|
"step": 8290 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 1.3193504095450028e-05, |
|
"loss": 1.0356, |
|
"step": 8300 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"eval_loss": 1.4997183084487915, |
|
"eval_runtime": 11.1013, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 8300 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 1.3184034846834905e-05, |
|
"loss": 1.2164, |
|
"step": 8310 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 1.3174565598219782e-05, |
|
"loss": 1.1335, |
|
"step": 8320 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 1.3165096349604661e-05, |
|
"loss": 1.1911, |
|
"step": 8330 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 1.3155627100989538e-05, |
|
"loss": 1.1012, |
|
"step": 8340 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 1.3146157852374415e-05, |
|
"loss": 1.1377, |
|
"step": 8350 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"eval_loss": 1.5025912523269653, |
|
"eval_runtime": 11.1058, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 8350 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 1.3136688603759294e-05, |
|
"loss": 1.2557, |
|
"step": 8360 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 1.312721935514417e-05, |
|
"loss": 1.3335, |
|
"step": 8370 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 1.3117750106529048e-05, |
|
"loss": 1.2009, |
|
"step": 8380 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 1.3108280857913927e-05, |
|
"loss": 1.3195, |
|
"step": 8390 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 1.3098811609298803e-05, |
|
"loss": 1.1416, |
|
"step": 8400 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"eval_loss": 1.5021483898162842, |
|
"eval_runtime": 11.1035, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 8400 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 1.3089342360683681e-05, |
|
"loss": 1.1472, |
|
"step": 8410 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 1.3079873112068557e-05, |
|
"loss": 1.1732, |
|
"step": 8420 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 1.3070403863453436e-05, |
|
"loss": 1.1937, |
|
"step": 8430 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 1.3060934614838315e-05, |
|
"loss": 1.1634, |
|
"step": 8440 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 1.305146536622319e-05, |
|
"loss": 1.2493, |
|
"step": 8450 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"eval_loss": 1.5071872472763062, |
|
"eval_runtime": 11.1052, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 8450 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 1.3041996117608069e-05, |
|
"loss": 1.1491, |
|
"step": 8460 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 1.3032526868992948e-05, |
|
"loss": 1.2118, |
|
"step": 8470 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 1.3023057620377823e-05, |
|
"loss": 1.2603, |
|
"step": 8480 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 1.3013588371762702e-05, |
|
"loss": 1.3036, |
|
"step": 8490 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 1.3004119123147579e-05, |
|
"loss": 1.3555, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"eval_loss": 1.5028959512710571, |
|
"eval_runtime": 11.105, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 1.2994649874532456e-05, |
|
"loss": 1.2036, |
|
"step": 8510 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 1.2985180625917335e-05, |
|
"loss": 1.2552, |
|
"step": 8520 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 1.2975711377302212e-05, |
|
"loss": 1.245, |
|
"step": 8530 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 1.296624212868709e-05, |
|
"loss": 1.1665, |
|
"step": 8540 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 1.2956772880071968e-05, |
|
"loss": 1.1542, |
|
"step": 8550 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"eval_loss": 1.5009123086929321, |
|
"eval_runtime": 11.1108, |
|
"eval_samples_per_second": 4.5, |
|
"eval_steps_per_second": 0.81, |
|
"step": 8550 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 1.2947303631456845e-05, |
|
"loss": 1.2537, |
|
"step": 8560 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 1.2937834382841723e-05, |
|
"loss": 1.2248, |
|
"step": 8570 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 1.29283651342266e-05, |
|
"loss": 1.1921, |
|
"step": 8580 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 1.2918895885611478e-05, |
|
"loss": 1.2343, |
|
"step": 8590 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 1.2909426636996356e-05, |
|
"loss": 1.31, |
|
"step": 8600 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"eval_loss": 1.5027575492858887, |
|
"eval_runtime": 11.1054, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 8600 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 1.2899957388381233e-05, |
|
"loss": 1.2096, |
|
"step": 8610 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 1.2890488139766112e-05, |
|
"loss": 1.2578, |
|
"step": 8620 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 1.2881018891150989e-05, |
|
"loss": 1.1952, |
|
"step": 8630 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 1.2871549642535866e-05, |
|
"loss": 1.2778, |
|
"step": 8640 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 1.2862080393920745e-05, |
|
"loss": 1.3398, |
|
"step": 8650 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"eval_loss": 1.5001126527786255, |
|
"eval_runtime": 11.1055, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 8650 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 1.285261114530562e-05, |
|
"loss": 1.1276, |
|
"step": 8660 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 1.2843141896690499e-05, |
|
"loss": 1.2726, |
|
"step": 8670 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 1.2833672648075378e-05, |
|
"loss": 1.2657, |
|
"step": 8680 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 1.2824203399460253e-05, |
|
"loss": 1.2946, |
|
"step": 8690 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 1.2814734150845132e-05, |
|
"loss": 1.2216, |
|
"step": 8700 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"eval_loss": 1.4962161779403687, |
|
"eval_runtime": 11.1085, |
|
"eval_samples_per_second": 4.501, |
|
"eval_steps_per_second": 0.81, |
|
"step": 8700 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 1.2805264902230011e-05, |
|
"loss": 1.1626, |
|
"step": 8710 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 1.2795795653614886e-05, |
|
"loss": 1.2394, |
|
"step": 8720 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 1.2786326404999765e-05, |
|
"loss": 1.1959, |
|
"step": 8730 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 1.277685715638464e-05, |
|
"loss": 1.1766, |
|
"step": 8740 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 1.276738790776952e-05, |
|
"loss": 1.2031, |
|
"step": 8750 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"eval_loss": 1.497706651687622, |
|
"eval_runtime": 11.1045, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 8750 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 1.2757918659154398e-05, |
|
"loss": 1.2987, |
|
"step": 8760 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 1.2748449410539274e-05, |
|
"loss": 1.0638, |
|
"step": 8770 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 1.2738980161924153e-05, |
|
"loss": 1.2433, |
|
"step": 8780 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 1.2729510913309028e-05, |
|
"loss": 1.2129, |
|
"step": 8790 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 1.2720041664693907e-05, |
|
"loss": 1.2169, |
|
"step": 8800 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"eval_loss": 1.4974638223648071, |
|
"eval_runtime": 11.1076, |
|
"eval_samples_per_second": 4.501, |
|
"eval_steps_per_second": 0.81, |
|
"step": 8800 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 1.2710572416078786e-05, |
|
"loss": 1.1254, |
|
"step": 8810 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 1.2701103167463663e-05, |
|
"loss": 1.2459, |
|
"step": 8820 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 1.269163391884854e-05, |
|
"loss": 1.3157, |
|
"step": 8830 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 1.2682164670233419e-05, |
|
"loss": 1.1901, |
|
"step": 8840 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 1.2672695421618296e-05, |
|
"loss": 1.1491, |
|
"step": 8850 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"eval_loss": 1.4996168613433838, |
|
"eval_runtime": 11.106, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 8850 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 1.2663226173003173e-05, |
|
"loss": 1.1652, |
|
"step": 8860 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 1.265375692438805e-05, |
|
"loss": 1.2947, |
|
"step": 8870 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 1.2644287675772929e-05, |
|
"loss": 1.1284, |
|
"step": 8880 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 1.2634818427157806e-05, |
|
"loss": 1.326, |
|
"step": 8890 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 1.2625349178542683e-05, |
|
"loss": 1.122, |
|
"step": 8900 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"eval_loss": 1.500783085823059, |
|
"eval_runtime": 11.1072, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 8900 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 1.2615879929927562e-05, |
|
"loss": 1.28, |
|
"step": 8910 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 1.260641068131244e-05, |
|
"loss": 1.0614, |
|
"step": 8920 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 1.2596941432697316e-05, |
|
"loss": 1.3181, |
|
"step": 8930 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 1.2587472184082195e-05, |
|
"loss": 1.1707, |
|
"step": 8940 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 1.257800293546707e-05, |
|
"loss": 1.2613, |
|
"step": 8950 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"eval_loss": 1.4987977743148804, |
|
"eval_runtime": 11.1041, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 8950 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 1.256853368685195e-05, |
|
"loss": 1.1348, |
|
"step": 8960 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 1.2559064438236828e-05, |
|
"loss": 1.1257, |
|
"step": 8970 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 1.2549595189621704e-05, |
|
"loss": 1.2609, |
|
"step": 8980 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 1.2540125941006583e-05, |
|
"loss": 1.2296, |
|
"step": 8990 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 1.2530656692391462e-05, |
|
"loss": 1.3267, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"eval_loss": 1.4968334436416626, |
|
"eval_runtime": 11.1061, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 1.2521187443776337e-05, |
|
"loss": 1.2284, |
|
"step": 9010 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 1.2511718195161216e-05, |
|
"loss": 1.131, |
|
"step": 9020 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 1.2502248946546091e-05, |
|
"loss": 1.2651, |
|
"step": 9030 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 1.249277969793097e-05, |
|
"loss": 1.0726, |
|
"step": 9040 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 1.2483310449315849e-05, |
|
"loss": 1.1794, |
|
"step": 9050 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"eval_loss": 1.5011943578720093, |
|
"eval_runtime": 11.104, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 9050 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 1.2473841200700724e-05, |
|
"loss": 1.3531, |
|
"step": 9060 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 1.2464371952085603e-05, |
|
"loss": 1.2325, |
|
"step": 9070 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 1.2454902703470482e-05, |
|
"loss": 1.2638, |
|
"step": 9080 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 1.2445433454855357e-05, |
|
"loss": 1.1835, |
|
"step": 9090 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 1.2435964206240236e-05, |
|
"loss": 1.1467, |
|
"step": 9100 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"eval_loss": 1.5005993843078613, |
|
"eval_runtime": 11.1107, |
|
"eval_samples_per_second": 4.5, |
|
"eval_steps_per_second": 0.81, |
|
"step": 9100 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 1.2426494957625112e-05, |
|
"loss": 1.2982, |
|
"step": 9110 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 1.241702570900999e-05, |
|
"loss": 1.1999, |
|
"step": 9120 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 1.240755646039487e-05, |
|
"loss": 1.2807, |
|
"step": 9130 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 1.2398087211779745e-05, |
|
"loss": 1.3007, |
|
"step": 9140 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 1.2388617963164624e-05, |
|
"loss": 1.0927, |
|
"step": 9150 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"eval_loss": 1.4971923828125, |
|
"eval_runtime": 11.1041, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 9150 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 1.2379148714549501e-05, |
|
"loss": 1.2092, |
|
"step": 9160 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 1.236967946593438e-05, |
|
"loss": 1.2927, |
|
"step": 9170 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 1.2360210217319257e-05, |
|
"loss": 1.2985, |
|
"step": 9180 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 1.2350740968704134e-05, |
|
"loss": 1.2565, |
|
"step": 9190 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 1.2341271720089013e-05, |
|
"loss": 1.2903, |
|
"step": 9200 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"eval_loss": 1.4994169473648071, |
|
"eval_runtime": 11.1033, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 9200 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 1.233180247147389e-05, |
|
"loss": 1.184, |
|
"step": 9210 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 1.2322333222858767e-05, |
|
"loss": 1.3997, |
|
"step": 9220 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 1.2312863974243646e-05, |
|
"loss": 1.1375, |
|
"step": 9230 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 1.2303394725628521e-05, |
|
"loss": 1.2227, |
|
"step": 9240 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 1.22939254770134e-05, |
|
"loss": 1.1936, |
|
"step": 9250 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"eval_loss": 1.498415231704712, |
|
"eval_runtime": 11.104, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 9250 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 1.2284456228398279e-05, |
|
"loss": 1.1391, |
|
"step": 9260 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 1.2274986979783154e-05, |
|
"loss": 1.1804, |
|
"step": 9270 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 1.2265517731168033e-05, |
|
"loss": 1.2283, |
|
"step": 9280 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 1.2256048482552912e-05, |
|
"loss": 1.2479, |
|
"step": 9290 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 1.2246579233937788e-05, |
|
"loss": 1.1884, |
|
"step": 9300 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"eval_loss": 1.4984921216964722, |
|
"eval_runtime": 11.1049, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 9300 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 1.2237109985322666e-05, |
|
"loss": 1.0943, |
|
"step": 9310 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 1.2227640736707542e-05, |
|
"loss": 1.2415, |
|
"step": 9320 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 1.221817148809242e-05, |
|
"loss": 1.193, |
|
"step": 9330 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 1.22087022394773e-05, |
|
"loss": 1.0568, |
|
"step": 9340 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 1.2199232990862175e-05, |
|
"loss": 1.1973, |
|
"step": 9350 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"eval_loss": 1.4990426301956177, |
|
"eval_runtime": 11.1011, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 9350 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 1.2189763742247054e-05, |
|
"loss": 1.1434, |
|
"step": 9360 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 1.2180294493631933e-05, |
|
"loss": 1.0584, |
|
"step": 9370 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 1.2170825245016808e-05, |
|
"loss": 1.1557, |
|
"step": 9380 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 1.2161355996401687e-05, |
|
"loss": 1.2876, |
|
"step": 9390 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 1.2151886747786562e-05, |
|
"loss": 1.3124, |
|
"step": 9400 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"eval_loss": 1.5030548572540283, |
|
"eval_runtime": 11.1086, |
|
"eval_samples_per_second": 4.501, |
|
"eval_steps_per_second": 0.81, |
|
"step": 9400 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 1.2142417499171441e-05, |
|
"loss": 1.1234, |
|
"step": 9410 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 1.213294825055632e-05, |
|
"loss": 1.2868, |
|
"step": 9420 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 1.2123479001941195e-05, |
|
"loss": 1.2206, |
|
"step": 9430 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 1.2114009753326074e-05, |
|
"loss": 1.3098, |
|
"step": 9440 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 1.2104540504710953e-05, |
|
"loss": 1.2046, |
|
"step": 9450 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"eval_loss": 1.504317045211792, |
|
"eval_runtime": 11.1044, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 9450 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 1.2095071256095829e-05, |
|
"loss": 1.2261, |
|
"step": 9460 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 1.2085602007480707e-05, |
|
"loss": 1.1417, |
|
"step": 9470 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 1.2076132758865585e-05, |
|
"loss": 1.1539, |
|
"step": 9480 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 1.2066663510250463e-05, |
|
"loss": 1.1226, |
|
"step": 9490 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 1.205719426163534e-05, |
|
"loss": 1.2216, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"eval_loss": 1.5054816007614136, |
|
"eval_runtime": 11.1054, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 1.2047725013020218e-05, |
|
"loss": 1.3712, |
|
"step": 9510 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 1.2038255764405097e-05, |
|
"loss": 1.3036, |
|
"step": 9520 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 1.2028786515789974e-05, |
|
"loss": 1.1537, |
|
"step": 9530 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 1.201931726717485e-05, |
|
"loss": 1.2094, |
|
"step": 9540 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 1.200984801855973e-05, |
|
"loss": 1.2712, |
|
"step": 9550 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"eval_loss": 1.501383662223816, |
|
"eval_runtime": 11.1031, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 9550 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 1.2000378769944605e-05, |
|
"loss": 1.2945, |
|
"step": 9560 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 1.1990909521329484e-05, |
|
"loss": 1.165, |
|
"step": 9570 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 1.1981440272714363e-05, |
|
"loss": 1.202, |
|
"step": 9580 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 1.1971971024099238e-05, |
|
"loss": 1.2035, |
|
"step": 9590 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 1.1962501775484117e-05, |
|
"loss": 1.1685, |
|
"step": 9600 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"eval_loss": 1.4993391036987305, |
|
"eval_runtime": 11.1038, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 9600 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 1.1953032526868992e-05, |
|
"loss": 1.1555, |
|
"step": 9610 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 1.1943563278253871e-05, |
|
"loss": 1.2787, |
|
"step": 9620 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 1.193409402963875e-05, |
|
"loss": 1.269, |
|
"step": 9630 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 1.1924624781023626e-05, |
|
"loss": 1.2747, |
|
"step": 9640 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 1.1915155532408504e-05, |
|
"loss": 1.2206, |
|
"step": 9650 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"eval_loss": 1.4982408285140991, |
|
"eval_runtime": 11.104, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 9650 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 1.1905686283793383e-05, |
|
"loss": 1.0871, |
|
"step": 9660 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 1.1896217035178259e-05, |
|
"loss": 1.1652, |
|
"step": 9670 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 1.1886747786563138e-05, |
|
"loss": 1.1739, |
|
"step": 9680 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 1.1877278537948013e-05, |
|
"loss": 1.1879, |
|
"step": 9690 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 1.1867809289332892e-05, |
|
"loss": 1.1715, |
|
"step": 9700 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"eval_loss": 1.5000805854797363, |
|
"eval_runtime": 11.1049, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 9700 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 1.185834004071777e-05, |
|
"loss": 1.271, |
|
"step": 9710 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 1.1848870792102646e-05, |
|
"loss": 1.2943, |
|
"step": 9720 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 1.1839401543487525e-05, |
|
"loss": 1.211, |
|
"step": 9730 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 1.1829932294872404e-05, |
|
"loss": 1.178, |
|
"step": 9740 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 1.182046304625728e-05, |
|
"loss": 1.1787, |
|
"step": 9750 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"eval_loss": 1.4938322305679321, |
|
"eval_runtime": 11.1048, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.81, |
|
"step": 9750 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 1.1810993797642158e-05, |
|
"loss": 1.2527, |
|
"step": 9760 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 1.1801524549027035e-05, |
|
"loss": 1.1938, |
|
"step": 9770 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 1.1792055300411912e-05, |
|
"loss": 1.1182, |
|
"step": 9780 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 1.1782586051796791e-05, |
|
"loss": 1.1768, |
|
"step": 9790 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 1.1773116803181668e-05, |
|
"loss": 1.1797, |
|
"step": 9800 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"eval_loss": 1.4941012859344482, |
|
"eval_runtime": 11.1035, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 9800 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 1.1763647554566545e-05, |
|
"loss": 1.1728, |
|
"step": 9810 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 1.1754178305951424e-05, |
|
"loss": 1.1153, |
|
"step": 9820 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 1.1744709057336301e-05, |
|
"loss": 1.2773, |
|
"step": 9830 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 1.173523980872118e-05, |
|
"loss": 1.2117, |
|
"step": 9840 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 1.1725770560106056e-05, |
|
"loss": 1.1998, |
|
"step": 9850 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"eval_loss": 1.4989956617355347, |
|
"eval_runtime": 11.1065, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 9850 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 1.1716301311490935e-05, |
|
"loss": 1.2257, |
|
"step": 9860 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 1.1706832062875813e-05, |
|
"loss": 1.1184, |
|
"step": 9870 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 1.1697362814260689e-05, |
|
"loss": 1.2419, |
|
"step": 9880 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 1.1687893565645568e-05, |
|
"loss": 1.1835, |
|
"step": 9890 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 1.1678424317030446e-05, |
|
"loss": 1.2686, |
|
"step": 9900 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"eval_loss": 1.4995183944702148, |
|
"eval_runtime": 11.1063, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 9900 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 1.1668955068415322e-05, |
|
"loss": 1.0722, |
|
"step": 9910 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 1.16594858198002e-05, |
|
"loss": 1.2028, |
|
"step": 9920 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 1.1650016571185076e-05, |
|
"loss": 1.1951, |
|
"step": 9930 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 1.1640547322569955e-05, |
|
"loss": 0.9592, |
|
"step": 9940 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 1.1631078073954834e-05, |
|
"loss": 1.3403, |
|
"step": 9950 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"eval_loss": 1.4991717338562012, |
|
"eval_runtime": 11.1013, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 9950 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 1.162160882533971e-05, |
|
"loss": 1.1653, |
|
"step": 9960 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 1.1612139576724588e-05, |
|
"loss": 1.1255, |
|
"step": 9970 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 1.1602670328109464e-05, |
|
"loss": 1.2377, |
|
"step": 9980 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 1.1593201079494342e-05, |
|
"loss": 1.2345, |
|
"step": 9990 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 1.1583731830879221e-05, |
|
"loss": 1.2628, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"eval_loss": 1.4981472492218018, |
|
"eval_runtime": 11.104, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 1.1574262582264097e-05, |
|
"loss": 1.249, |
|
"step": 10010 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 1.1564793333648976e-05, |
|
"loss": 1.2288, |
|
"step": 10020 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 1.1555324085033854e-05, |
|
"loss": 1.2307, |
|
"step": 10030 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 1.154585483641873e-05, |
|
"loss": 1.1996, |
|
"step": 10040 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 1.1536385587803609e-05, |
|
"loss": 1.1284, |
|
"step": 10050 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"eval_loss": 1.498414158821106, |
|
"eval_runtime": 11.1073, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 10050 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 1.1526916339188486e-05, |
|
"loss": 1.1537, |
|
"step": 10060 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 1.1517447090573363e-05, |
|
"loss": 1.1017, |
|
"step": 10070 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 1.1507977841958242e-05, |
|
"loss": 1.2225, |
|
"step": 10080 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 1.1498508593343119e-05, |
|
"loss": 1.1123, |
|
"step": 10090 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 1.1489039344727996e-05, |
|
"loss": 1.2427, |
|
"step": 10100 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"eval_loss": 1.4983925819396973, |
|
"eval_runtime": 11.1057, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 10100 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 1.1479570096112875e-05, |
|
"loss": 1.2844, |
|
"step": 10110 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 1.1470100847497752e-05, |
|
"loss": 1.1989, |
|
"step": 10120 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 1.146063159888263e-05, |
|
"loss": 1.2221, |
|
"step": 10130 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 1.1451162350267506e-05, |
|
"loss": 1.0411, |
|
"step": 10140 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 1.1441693101652385e-05, |
|
"loss": 1.2759, |
|
"step": 10150 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"eval_loss": 1.501205325126648, |
|
"eval_runtime": 11.1052, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 10150 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 1.1432223853037264e-05, |
|
"loss": 1.286, |
|
"step": 10160 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 1.142275460442214e-05, |
|
"loss": 1.1442, |
|
"step": 10170 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 1.1413285355807018e-05, |
|
"loss": 1.3772, |
|
"step": 10180 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 1.1403816107191897e-05, |
|
"loss": 1.145, |
|
"step": 10190 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 1.1394346858576773e-05, |
|
"loss": 1.2953, |
|
"step": 10200 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"eval_loss": 1.4993594884872437, |
|
"eval_runtime": 11.1056, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 10200 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 1.1384877609961651e-05, |
|
"loss": 1.3081, |
|
"step": 10210 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 1.1375408361346527e-05, |
|
"loss": 1.1653, |
|
"step": 10220 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 1.1365939112731406e-05, |
|
"loss": 1.3389, |
|
"step": 10230 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 1.1356469864116284e-05, |
|
"loss": 1.2352, |
|
"step": 10240 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 1.134700061550116e-05, |
|
"loss": 1.1326, |
|
"step": 10250 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"eval_loss": 1.494726300239563, |
|
"eval_runtime": 11.1039, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 10250 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 1.1337531366886039e-05, |
|
"loss": 1.1964, |
|
"step": 10260 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 1.1328062118270918e-05, |
|
"loss": 1.2965, |
|
"step": 10270 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 1.1318592869655793e-05, |
|
"loss": 1.2474, |
|
"step": 10280 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 1.1309123621040672e-05, |
|
"loss": 1.2471, |
|
"step": 10290 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 1.1299654372425547e-05, |
|
"loss": 1.1328, |
|
"step": 10300 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"eval_loss": 1.4975593090057373, |
|
"eval_runtime": 11.1037, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 10300 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 1.1290185123810426e-05, |
|
"loss": 1.2449, |
|
"step": 10310 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 1.1280715875195305e-05, |
|
"loss": 1.3382, |
|
"step": 10320 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 1.127124662658018e-05, |
|
"loss": 1.3434, |
|
"step": 10330 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 1.126177737796506e-05, |
|
"loss": 1.2958, |
|
"step": 10340 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 1.1252308129349938e-05, |
|
"loss": 1.2466, |
|
"step": 10350 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"eval_loss": 1.4972091913223267, |
|
"eval_runtime": 11.1029, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 10350 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 1.1242838880734814e-05, |
|
"loss": 1.0627, |
|
"step": 10360 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 1.1233369632119692e-05, |
|
"loss": 1.2592, |
|
"step": 10370 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 1.122390038350457e-05, |
|
"loss": 1.1844, |
|
"step": 10380 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 1.1214431134889447e-05, |
|
"loss": 1.0547, |
|
"step": 10390 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 1.1204961886274325e-05, |
|
"loss": 1.2899, |
|
"step": 10400 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"eval_loss": 1.4961121082305908, |
|
"eval_runtime": 11.106, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 10400 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 1.1195492637659203e-05, |
|
"loss": 1.1759, |
|
"step": 10410 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 1.118602338904408e-05, |
|
"loss": 1.2786, |
|
"step": 10420 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 1.1176554140428957e-05, |
|
"loss": 1.2085, |
|
"step": 10430 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 1.1167084891813836e-05, |
|
"loss": 1.2988, |
|
"step": 10440 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 1.1157615643198713e-05, |
|
"loss": 1.2133, |
|
"step": 10450 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"eval_loss": 1.496193528175354, |
|
"eval_runtime": 11.104, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 10450 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 1.114814639458359e-05, |
|
"loss": 1.1956, |
|
"step": 10460 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 1.1138677145968469e-05, |
|
"loss": 1.1478, |
|
"step": 10470 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 1.1129207897353346e-05, |
|
"loss": 1.1807, |
|
"step": 10480 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 1.1119738648738223e-05, |
|
"loss": 1.2844, |
|
"step": 10490 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 1.1110269400123102e-05, |
|
"loss": 1.2622, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"eval_loss": 1.4945733547210693, |
|
"eval_runtime": 11.1062, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 1.1100800151507977e-05, |
|
"loss": 1.1661, |
|
"step": 10510 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 1.1091330902892856e-05, |
|
"loss": 1.2303, |
|
"step": 10520 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 1.1081861654277735e-05, |
|
"loss": 1.2216, |
|
"step": 10530 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 1.107239240566261e-05, |
|
"loss": 1.1493, |
|
"step": 10540 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 1.106292315704749e-05, |
|
"loss": 1.2547, |
|
"step": 10550 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"eval_loss": 1.4970910549163818, |
|
"eval_runtime": 11.1058, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 10550 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 1.1053453908432368e-05, |
|
"loss": 1.1844, |
|
"step": 10560 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 1.1043984659817244e-05, |
|
"loss": 1.1935, |
|
"step": 10570 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 1.1034515411202122e-05, |
|
"loss": 1.2762, |
|
"step": 10580 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 1.1025046162586998e-05, |
|
"loss": 1.2441, |
|
"step": 10590 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 1.1015576913971877e-05, |
|
"loss": 1.2323, |
|
"step": 10600 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"eval_loss": 1.4969464540481567, |
|
"eval_runtime": 11.1017, |
|
"eval_samples_per_second": 4.504, |
|
"eval_steps_per_second": 0.811, |
|
"step": 10600 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 1.1006107665356756e-05, |
|
"loss": 1.1749, |
|
"step": 10610 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 1.0996638416741631e-05, |
|
"loss": 1.2465, |
|
"step": 10620 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 1.098716916812651e-05, |
|
"loss": 1.2322, |
|
"step": 10630 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 1.0977699919511389e-05, |
|
"loss": 1.2006, |
|
"step": 10640 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 1.0968230670896264e-05, |
|
"loss": 1.1752, |
|
"step": 10650 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"eval_loss": 1.4951092004776, |
|
"eval_runtime": 11.1039, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 10650 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 1.0958761422281143e-05, |
|
"loss": 1.1563, |
|
"step": 10660 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 1.094929217366602e-05, |
|
"loss": 1.1753, |
|
"step": 10670 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 1.0939822925050897e-05, |
|
"loss": 1.2939, |
|
"step": 10680 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 1.0930353676435776e-05, |
|
"loss": 1.2794, |
|
"step": 10690 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 1.0920884427820653e-05, |
|
"loss": 1.273, |
|
"step": 10700 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"eval_loss": 1.496578574180603, |
|
"eval_runtime": 11.1039, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 10700 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 1.091141517920553e-05, |
|
"loss": 1.1265, |
|
"step": 10710 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 1.090194593059041e-05, |
|
"loss": 1.2651, |
|
"step": 10720 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 1.0892476681975286e-05, |
|
"loss": 1.3407, |
|
"step": 10730 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 1.0883007433360163e-05, |
|
"loss": 1.2431, |
|
"step": 10740 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 1.087353818474504e-05, |
|
"loss": 1.2744, |
|
"step": 10750 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"eval_loss": 1.4938522577285767, |
|
"eval_runtime": 11.1063, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 10750 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 1.086406893612992e-05, |
|
"loss": 1.2722, |
|
"step": 10760 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 1.0854599687514797e-05, |
|
"loss": 1.203, |
|
"step": 10770 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 1.0845130438899674e-05, |
|
"loss": 1.2182, |
|
"step": 10780 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 1.0835661190284553e-05, |
|
"loss": 1.2944, |
|
"step": 10790 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 1.0826191941669428e-05, |
|
"loss": 1.1419, |
|
"step": 10800 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"eval_loss": 1.4927809238433838, |
|
"eval_runtime": 11.1071, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 10800 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 1.0816722693054307e-05, |
|
"loss": 1.1867, |
|
"step": 10810 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 1.0807253444439186e-05, |
|
"loss": 1.1679, |
|
"step": 10820 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 1.0797784195824061e-05, |
|
"loss": 1.2571, |
|
"step": 10830 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 1.078831494720894e-05, |
|
"loss": 1.2425, |
|
"step": 10840 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 1.0778845698593819e-05, |
|
"loss": 1.1358, |
|
"step": 10850 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"eval_loss": 1.496710181236267, |
|
"eval_runtime": 11.1039, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 10850 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 1.0769376449978694e-05, |
|
"loss": 1.3063, |
|
"step": 10860 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 1.0759907201363573e-05, |
|
"loss": 1.1349, |
|
"step": 10870 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 1.0750437952748449e-05, |
|
"loss": 1.2385, |
|
"step": 10880 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 1.0740968704133327e-05, |
|
"loss": 1.1966, |
|
"step": 10890 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 1.0731499455518206e-05, |
|
"loss": 1.2486, |
|
"step": 10900 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"eval_loss": 1.4948495626449585, |
|
"eval_runtime": 11.1041, |
|
"eval_samples_per_second": 4.503, |
|
"eval_steps_per_second": 0.811, |
|
"step": 10900 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 1.0722030206903082e-05, |
|
"loss": 1.1464, |
|
"step": 10910 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 1.071256095828796e-05, |
|
"loss": 1.2395, |
|
"step": 10920 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 1.070309170967284e-05, |
|
"loss": 1.1445, |
|
"step": 10930 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 1.0693622461057715e-05, |
|
"loss": 1.1211, |
|
"step": 10940 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 1.0684153212442594e-05, |
|
"loss": 1.1491, |
|
"step": 10950 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"eval_loss": 1.4967584609985352, |
|
"eval_runtime": 11.1053, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 10950 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 1.067468396382747e-05, |
|
"loss": 1.266, |
|
"step": 10960 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 1.0665214715212348e-05, |
|
"loss": 1.3896, |
|
"step": 10970 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 1.0655745466597227e-05, |
|
"loss": 1.2138, |
|
"step": 10980 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 1.0646276217982104e-05, |
|
"loss": 1.2608, |
|
"step": 10990 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 1.0636806969366981e-05, |
|
"loss": 1.3209, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"eval_loss": 1.4953837394714355, |
|
"eval_runtime": 11.1068, |
|
"eval_samples_per_second": 4.502, |
|
"eval_steps_per_second": 0.81, |
|
"step": 11000 |
|
} |
|
], |
|
"max_steps": 22233, |
|
"num_train_epochs": 3, |
|
"total_flos": 3.1977073388195676e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|