|
{ |
|
"best_metric": 0.3841711956521739, |
|
"best_model_checkpoint": "sew-mid-100k-ft-common-language/checkpoint-1730", |
|
"epoch": 9.997118155619596, |
|
"global_step": 1730, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 1.7341040462427746e-06, |
|
"loss": 3.8107, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 3.468208092485549e-06, |
|
"loss": 3.8051, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 5.202312138728324e-06, |
|
"loss": 3.8032, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 6.936416184971098e-06, |
|
"loss": 3.8053, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 8.670520231213873e-06, |
|
"loss": 3.7986, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 1.0404624277456647e-05, |
|
"loss": 3.8013, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 1.2138728323699422e-05, |
|
"loss": 3.7976, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 1.3872832369942197e-05, |
|
"loss": 3.7859, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 1.560693641618497e-05, |
|
"loss": 3.7734, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 1.7341040462427746e-05, |
|
"loss": 3.7613, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 1.9075144508670522e-05, |
|
"loss": 3.7491, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 2.0809248554913295e-05, |
|
"loss": 3.7382, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 2.2543352601156068e-05, |
|
"loss": 3.7225, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 2.4277456647398844e-05, |
|
"loss": 3.7054, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 2.601156069364162e-05, |
|
"loss": 3.6827, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 2.7745664739884393e-05, |
|
"loss": 3.6427, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 2.9479768786127166e-05, |
|
"loss": 3.608, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.05400815217391304, |
|
"eval_loss": 3.7265617847442627, |
|
"eval_runtime": 288.7689, |
|
"eval_samples_per_second": 20.39, |
|
"eval_steps_per_second": 5.098, |
|
"step": 173 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 2.9865125240847786e-05, |
|
"loss": 3.7665, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 2.9672447013487474e-05, |
|
"loss": 3.5552, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 2.9479768786127166e-05, |
|
"loss": 3.5012, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 2.928709055876686e-05, |
|
"loss": 3.4901, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 2.9094412331406553e-05, |
|
"loss": 3.4814, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 2.8901734104046242e-05, |
|
"loss": 3.4583, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 2.8709055876685934e-05, |
|
"loss": 3.4, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 2.8516377649325626e-05, |
|
"loss": 3.403, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 2.832369942196532e-05, |
|
"loss": 3.3906, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 2.813102119460501e-05, |
|
"loss": 3.3555, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 2.79383429672447e-05, |
|
"loss": 3.3101, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 2.7745664739884393e-05, |
|
"loss": 3.2952, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 2.7552986512524085e-05, |
|
"loss": 3.2715, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 2.7360308285163777e-05, |
|
"loss": 3.2484, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 1.85, |
|
"learning_rate": 2.716763005780347e-05, |
|
"loss": 3.2045, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 2.697495183044316e-05, |
|
"loss": 3.1758, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 2.6782273603082853e-05, |
|
"loss": 3.1298, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.16542119565217392, |
|
"eval_loss": 3.21799898147583, |
|
"eval_runtime": 288.5015, |
|
"eval_samples_per_second": 20.409, |
|
"eval_steps_per_second": 5.102, |
|
"step": 346 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 2.658959537572254e-05, |
|
"loss": 3.2386, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 2.6396917148362237e-05, |
|
"loss": 3.1586, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 2.620423892100193e-05, |
|
"loss": 3.1117, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 2.2, |
|
"learning_rate": 2.601156069364162e-05, |
|
"loss": 3.0137, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 2.25, |
|
"learning_rate": 2.581888246628131e-05, |
|
"loss": 3.0632, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 2.31, |
|
"learning_rate": 2.5626204238921e-05, |
|
"loss": 2.9761, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 2.37, |
|
"learning_rate": 2.5433526011560693e-05, |
|
"loss": 2.9808, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 2.43, |
|
"learning_rate": 2.5240847784200388e-05, |
|
"loss": 2.9506, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 2.48, |
|
"learning_rate": 2.5048169556840077e-05, |
|
"loss": 2.9651, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 2.54, |
|
"learning_rate": 2.485549132947977e-05, |
|
"loss": 2.9751, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"learning_rate": 2.466281310211946e-05, |
|
"loss": 2.9642, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 2.66, |
|
"learning_rate": 2.4470134874759152e-05, |
|
"loss": 2.944, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 2.71, |
|
"learning_rate": 2.4277456647398844e-05, |
|
"loss": 2.9315, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 2.77, |
|
"learning_rate": 2.4084778420038536e-05, |
|
"loss": 2.905, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 2.83, |
|
"learning_rate": 2.3892100192678228e-05, |
|
"loss": 2.9028, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 2.89, |
|
"learning_rate": 2.369942196531792e-05, |
|
"loss": 2.8536, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.95, |
|
"learning_rate": 2.350674373795761e-05, |
|
"loss": 2.8481, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.20193614130434784, |
|
"eval_loss": 2.9270079135894775, |
|
"eval_runtime": 288.2515, |
|
"eval_samples_per_second": 20.427, |
|
"eval_steps_per_second": 5.107, |
|
"step": 519 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"learning_rate": 2.3314065510597304e-05, |
|
"loss": 3.0007, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 3.06, |
|
"learning_rate": 2.3121387283236996e-05, |
|
"loss": 2.8108, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 3.12, |
|
"learning_rate": 2.2928709055876687e-05, |
|
"loss": 2.7892, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 3.18, |
|
"learning_rate": 2.2736030828516376e-05, |
|
"loss": 2.7775, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 3.24, |
|
"learning_rate": 2.2543352601156068e-05, |
|
"loss": 2.7498, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 3.29, |
|
"learning_rate": 2.2350674373795763e-05, |
|
"loss": 2.7593, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 3.35, |
|
"learning_rate": 2.2157996146435455e-05, |
|
"loss": 2.7374, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 3.41, |
|
"learning_rate": 2.1965317919075144e-05, |
|
"loss": 2.7228, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 3.47, |
|
"learning_rate": 2.1772639691714835e-05, |
|
"loss": 2.7481, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 3.52, |
|
"learning_rate": 2.1579961464354527e-05, |
|
"loss": 2.6875, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 3.58, |
|
"learning_rate": 2.1387283236994223e-05, |
|
"loss": 2.7301, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 3.64, |
|
"learning_rate": 2.119460500963391e-05, |
|
"loss": 2.7506, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 3.7, |
|
"learning_rate": 2.1001926782273603e-05, |
|
"loss": 2.6264, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 3.76, |
|
"learning_rate": 2.0809248554913295e-05, |
|
"loss": 2.6626, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 3.81, |
|
"learning_rate": 2.0616570327552987e-05, |
|
"loss": 2.5905, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 3.87, |
|
"learning_rate": 2.042389210019268e-05, |
|
"loss": 2.6499, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 3.93, |
|
"learning_rate": 2.023121387283237e-05, |
|
"loss": 2.7104, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 3.99, |
|
"learning_rate": 2.0038535645472063e-05, |
|
"loss": 2.648, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.26188858695652173, |
|
"eval_loss": 2.6990630626678467, |
|
"eval_runtime": 287.8994, |
|
"eval_samples_per_second": 20.452, |
|
"eval_steps_per_second": 5.113, |
|
"step": 692 |
|
}, |
|
{ |
|
"epoch": 4.05, |
|
"learning_rate": 1.9845857418111754e-05, |
|
"loss": 2.7479, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 4.1, |
|
"learning_rate": 1.9653179190751443e-05, |
|
"loss": 2.6173, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 4.16, |
|
"learning_rate": 1.9460500963391135e-05, |
|
"loss": 2.5988, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 4.22, |
|
"learning_rate": 1.926782273603083e-05, |
|
"loss": 2.6025, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 4.28, |
|
"learning_rate": 1.9075144508670522e-05, |
|
"loss": 2.5247, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 4.33, |
|
"learning_rate": 1.888246628131021e-05, |
|
"loss": 2.5727, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 4.39, |
|
"learning_rate": 1.8689788053949903e-05, |
|
"loss": 2.6279, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 4.45, |
|
"learning_rate": 1.8497109826589594e-05, |
|
"loss": 2.5323, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 4.51, |
|
"learning_rate": 1.830443159922929e-05, |
|
"loss": 2.4919, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 4.56, |
|
"learning_rate": 1.8111753371868978e-05, |
|
"loss": 2.5477, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 4.62, |
|
"learning_rate": 1.791907514450867e-05, |
|
"loss": 2.5075, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 4.68, |
|
"learning_rate": 1.7726396917148362e-05, |
|
"loss": 2.4606, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 4.74, |
|
"learning_rate": 1.7533718689788054e-05, |
|
"loss": 2.5111, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 4.8, |
|
"learning_rate": 1.7341040462427746e-05, |
|
"loss": 2.5537, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 4.85, |
|
"learning_rate": 1.7148362235067438e-05, |
|
"loss": 2.4874, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 4.91, |
|
"learning_rate": 1.695568400770713e-05, |
|
"loss": 2.4619, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 4.97, |
|
"learning_rate": 1.676300578034682e-05, |
|
"loss": 2.5, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_accuracy": 0.30044157608695654, |
|
"eval_loss": 2.5235755443573, |
|
"eval_runtime": 288.083, |
|
"eval_samples_per_second": 20.439, |
|
"eval_steps_per_second": 5.11, |
|
"step": 865 |
|
}, |
|
{ |
|
"epoch": 5.03, |
|
"learning_rate": 1.657032755298651e-05, |
|
"loss": 2.6099, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 5.09, |
|
"learning_rate": 1.6377649325626205e-05, |
|
"loss": 2.4336, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 5.14, |
|
"learning_rate": 1.6184971098265897e-05, |
|
"loss": 2.4836, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 5.2, |
|
"learning_rate": 1.599229287090559e-05, |
|
"loss": 2.434, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 5.26, |
|
"learning_rate": 1.5799614643545278e-05, |
|
"loss": 2.3527, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 5.32, |
|
"learning_rate": 1.560693641618497e-05, |
|
"loss": 2.464, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 5.37, |
|
"learning_rate": 1.5414258188824665e-05, |
|
"loss": 2.4267, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 5.43, |
|
"learning_rate": 1.5221579961464355e-05, |
|
"loss": 2.4265, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 5.49, |
|
"learning_rate": 1.5028901734104047e-05, |
|
"loss": 2.3708, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 5.55, |
|
"learning_rate": 1.4836223506743737e-05, |
|
"loss": 2.3843, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 5.61, |
|
"learning_rate": 1.464354527938343e-05, |
|
"loss": 2.4064, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 5.66, |
|
"learning_rate": 1.4450867052023121e-05, |
|
"loss": 2.4072, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 5.72, |
|
"learning_rate": 1.4258188824662813e-05, |
|
"loss": 2.3964, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 5.78, |
|
"learning_rate": 1.4065510597302505e-05, |
|
"loss": 2.2824, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 5.84, |
|
"learning_rate": 1.3872832369942197e-05, |
|
"loss": 2.4044, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 5.89, |
|
"learning_rate": 1.3680154142581889e-05, |
|
"loss": 2.2942, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 5.95, |
|
"learning_rate": 1.348747591522158e-05, |
|
"loss": 2.2578, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_accuracy": 0.3211616847826087, |
|
"eval_loss": 2.401870012283325, |
|
"eval_runtime": 288.0444, |
|
"eval_samples_per_second": 20.441, |
|
"eval_steps_per_second": 5.11, |
|
"step": 1038 |
|
}, |
|
{ |
|
"epoch": 6.01, |
|
"learning_rate": 1.329479768786127e-05, |
|
"loss": 2.475, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 6.07, |
|
"learning_rate": 1.3102119460500964e-05, |
|
"loss": 2.3251, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 6.13, |
|
"learning_rate": 1.2909441233140654e-05, |
|
"loss": 2.3093, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 6.18, |
|
"learning_rate": 1.2716763005780346e-05, |
|
"loss": 2.3493, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 6.24, |
|
"learning_rate": 1.2524084778420038e-05, |
|
"loss": 2.3343, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 6.3, |
|
"learning_rate": 1.233140655105973e-05, |
|
"loss": 2.2668, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 6.36, |
|
"learning_rate": 1.2138728323699422e-05, |
|
"loss": 2.3182, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 6.41, |
|
"learning_rate": 1.1946050096339114e-05, |
|
"loss": 2.3879, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 6.47, |
|
"learning_rate": 1.1753371868978804e-05, |
|
"loss": 2.301, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 6.53, |
|
"learning_rate": 1.1560693641618498e-05, |
|
"loss": 2.1928, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 6.59, |
|
"learning_rate": 1.1368015414258188e-05, |
|
"loss": 2.3277, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 6.65, |
|
"learning_rate": 1.1175337186897882e-05, |
|
"loss": 2.3333, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 6.7, |
|
"learning_rate": 1.0982658959537572e-05, |
|
"loss": 2.3527, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 6.76, |
|
"learning_rate": 1.0789980732177264e-05, |
|
"loss": 2.3094, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 6.82, |
|
"learning_rate": 1.0597302504816956e-05, |
|
"loss": 2.2022, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 6.88, |
|
"learning_rate": 1.0404624277456647e-05, |
|
"loss": 2.1906, |
|
"step": 1190 |
|
}, |
|
{ |
|
"epoch": 6.93, |
|
"learning_rate": 1.021194605009634e-05, |
|
"loss": 2.2477, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 6.99, |
|
"learning_rate": 1.0019267822736031e-05, |
|
"loss": 2.2782, |
|
"step": 1210 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_accuracy": 0.3658288043478261, |
|
"eval_loss": 2.169760227203369, |
|
"eval_runtime": 289.07, |
|
"eval_samples_per_second": 20.369, |
|
"eval_steps_per_second": 5.092, |
|
"step": 1211 |
|
}, |
|
{ |
|
"epoch": 7.05, |
|
"learning_rate": 9.826589595375721e-06, |
|
"loss": 2.3796, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 7.11, |
|
"learning_rate": 9.633911368015415e-06, |
|
"loss": 2.2561, |
|
"step": 1230 |
|
}, |
|
{ |
|
"epoch": 7.17, |
|
"learning_rate": 9.441233140655105e-06, |
|
"loss": 2.2551, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 7.22, |
|
"learning_rate": 9.248554913294797e-06, |
|
"loss": 2.2132, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 7.28, |
|
"learning_rate": 9.055876685934489e-06, |
|
"loss": 2.2054, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 7.34, |
|
"learning_rate": 8.863198458574181e-06, |
|
"loss": 2.2528, |
|
"step": 1270 |
|
}, |
|
{ |
|
"epoch": 7.4, |
|
"learning_rate": 8.670520231213873e-06, |
|
"loss": 2.258, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 7.46, |
|
"learning_rate": 8.477842003853565e-06, |
|
"loss": 2.224, |
|
"step": 1290 |
|
}, |
|
{ |
|
"epoch": 7.51, |
|
"learning_rate": 8.285163776493255e-06, |
|
"loss": 2.1996, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 7.57, |
|
"learning_rate": 8.092485549132949e-06, |
|
"loss": 2.1924, |
|
"step": 1310 |
|
}, |
|
{ |
|
"epoch": 7.63, |
|
"learning_rate": 7.899807321772639e-06, |
|
"loss": 2.1949, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 7.69, |
|
"learning_rate": 7.707129094412332e-06, |
|
"loss": 2.1914, |
|
"step": 1330 |
|
}, |
|
{ |
|
"epoch": 7.74, |
|
"learning_rate": 7.5144508670520235e-06, |
|
"loss": 2.1401, |
|
"step": 1340 |
|
}, |
|
{ |
|
"epoch": 7.8, |
|
"learning_rate": 7.321772639691715e-06, |
|
"loss": 2.2643, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 7.86, |
|
"learning_rate": 7.129094412331406e-06, |
|
"loss": 2.1993, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 7.92, |
|
"learning_rate": 6.936416184971098e-06, |
|
"loss": 2.2727, |
|
"step": 1370 |
|
}, |
|
{ |
|
"epoch": 7.97, |
|
"learning_rate": 6.74373795761079e-06, |
|
"loss": 2.1665, |
|
"step": 1380 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_accuracy": 0.36311141304347827, |
|
"eval_loss": 2.1975557804107666, |
|
"eval_runtime": 288.65, |
|
"eval_samples_per_second": 20.398, |
|
"eval_steps_per_second": 5.1, |
|
"step": 1384 |
|
}, |
|
{ |
|
"epoch": 8.03, |
|
"learning_rate": 6.551059730250482e-06, |
|
"loss": 2.3102, |
|
"step": 1390 |
|
}, |
|
{ |
|
"epoch": 8.09, |
|
"learning_rate": 6.358381502890173e-06, |
|
"loss": 2.1722, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 8.15, |
|
"learning_rate": 6.165703275529865e-06, |
|
"loss": 2.1613, |
|
"step": 1410 |
|
}, |
|
{ |
|
"epoch": 8.21, |
|
"learning_rate": 5.973025048169557e-06, |
|
"loss": 2.2168, |
|
"step": 1420 |
|
}, |
|
{ |
|
"epoch": 8.27, |
|
"learning_rate": 5.780346820809249e-06, |
|
"loss": 2.1318, |
|
"step": 1430 |
|
}, |
|
{ |
|
"epoch": 8.32, |
|
"learning_rate": 5.587668593448941e-06, |
|
"loss": 2.179, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 8.38, |
|
"learning_rate": 5.394990366088632e-06, |
|
"loss": 2.1429, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 8.44, |
|
"learning_rate": 5.202312138728324e-06, |
|
"loss": 2.2007, |
|
"step": 1460 |
|
}, |
|
{ |
|
"epoch": 8.5, |
|
"learning_rate": 5.009633911368016e-06, |
|
"loss": 2.1911, |
|
"step": 1470 |
|
}, |
|
{ |
|
"epoch": 8.55, |
|
"learning_rate": 4.8169556840077075e-06, |
|
"loss": 2.1535, |
|
"step": 1480 |
|
}, |
|
{ |
|
"epoch": 8.61, |
|
"learning_rate": 4.624277456647399e-06, |
|
"loss": 2.114, |
|
"step": 1490 |
|
}, |
|
{ |
|
"epoch": 8.67, |
|
"learning_rate": 4.4315992292870905e-06, |
|
"loss": 2.1016, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 8.73, |
|
"learning_rate": 4.238921001926782e-06, |
|
"loss": 2.1631, |
|
"step": 1510 |
|
}, |
|
{ |
|
"epoch": 8.78, |
|
"learning_rate": 4.046242774566474e-06, |
|
"loss": 2.1449, |
|
"step": 1520 |
|
}, |
|
{ |
|
"epoch": 8.84, |
|
"learning_rate": 3.853564547206166e-06, |
|
"loss": 2.184, |
|
"step": 1530 |
|
}, |
|
{ |
|
"epoch": 8.9, |
|
"learning_rate": 3.6608863198458577e-06, |
|
"loss": 2.1418, |
|
"step": 1540 |
|
}, |
|
{ |
|
"epoch": 8.96, |
|
"learning_rate": 3.468208092485549e-06, |
|
"loss": 2.1626, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_accuracy": 0.37907608695652173, |
|
"eval_loss": 2.1473336219787598, |
|
"eval_runtime": 288.3051, |
|
"eval_samples_per_second": 20.423, |
|
"eval_steps_per_second": 5.106, |
|
"step": 1557 |
|
}, |
|
{ |
|
"epoch": 9.02, |
|
"learning_rate": 3.275529865125241e-06, |
|
"loss": 2.2924, |
|
"step": 1560 |
|
}, |
|
{ |
|
"epoch": 9.07, |
|
"learning_rate": 3.0828516377649325e-06, |
|
"loss": 2.1039, |
|
"step": 1570 |
|
}, |
|
{ |
|
"epoch": 9.13, |
|
"learning_rate": 2.8901734104046244e-06, |
|
"loss": 2.1386, |
|
"step": 1580 |
|
}, |
|
{ |
|
"epoch": 9.19, |
|
"learning_rate": 2.697495183044316e-06, |
|
"loss": 2.1226, |
|
"step": 1590 |
|
}, |
|
{ |
|
"epoch": 9.25, |
|
"learning_rate": 2.504816955684008e-06, |
|
"loss": 2.0778, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 9.31, |
|
"learning_rate": 2.3121387283236993e-06, |
|
"loss": 2.1477, |
|
"step": 1610 |
|
}, |
|
{ |
|
"epoch": 9.36, |
|
"learning_rate": 2.119460500963391e-06, |
|
"loss": 2.1617, |
|
"step": 1620 |
|
}, |
|
{ |
|
"epoch": 9.42, |
|
"learning_rate": 1.926782273603083e-06, |
|
"loss": 2.0862, |
|
"step": 1630 |
|
}, |
|
{ |
|
"epoch": 9.48, |
|
"learning_rate": 1.7341040462427746e-06, |
|
"loss": 2.2209, |
|
"step": 1640 |
|
}, |
|
{ |
|
"epoch": 9.54, |
|
"learning_rate": 1.5414258188824663e-06, |
|
"loss": 2.1223, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 9.59, |
|
"learning_rate": 1.348747591522158e-06, |
|
"loss": 2.1448, |
|
"step": 1660 |
|
}, |
|
{ |
|
"epoch": 9.65, |
|
"learning_rate": 1.1560693641618497e-06, |
|
"loss": 2.158, |
|
"step": 1670 |
|
}, |
|
{ |
|
"epoch": 9.71, |
|
"learning_rate": 9.633911368015416e-07, |
|
"loss": 2.1453, |
|
"step": 1680 |
|
}, |
|
{ |
|
"epoch": 9.77, |
|
"learning_rate": 7.707129094412331e-07, |
|
"loss": 2.1834, |
|
"step": 1690 |
|
}, |
|
{ |
|
"epoch": 9.82, |
|
"learning_rate": 5.780346820809248e-07, |
|
"loss": 2.1646, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 9.88, |
|
"learning_rate": 3.8535645472061657e-07, |
|
"loss": 2.1104, |
|
"step": 1710 |
|
}, |
|
{ |
|
"epoch": 9.94, |
|
"learning_rate": 1.9267822736030828e-07, |
|
"loss": 2.1577, |
|
"step": 1720 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 0.0, |
|
"loss": 2.1514, |
|
"step": 1730 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"eval_accuracy": 0.3841711956521739, |
|
"eval_loss": 2.1189279556274414, |
|
"eval_runtime": 288.75, |
|
"eval_samples_per_second": 20.391, |
|
"eval_steps_per_second": 5.098, |
|
"step": 1730 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"step": 1730, |
|
"total_flos": 3.403741533491613e+19, |
|
"train_loss": 2.660527980120885, |
|
"train_runtime": 5760.8603, |
|
"train_samples_per_second": 38.525, |
|
"train_steps_per_second": 0.3 |
|
} |
|
], |
|
"max_steps": 1730, |
|
"num_train_epochs": 10, |
|
"total_flos": 3.403741533491613e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|