hq_fer2013notestaugM / trainer_state.json
Piro17's picture
End of training
4f64c72
{
"best_metric": 0.6999146124635052,
"best_model_checkpoint": "hq_fer2013notestaugM/checkpoint-3177",
"epoch": 9.998585572842998,
"global_step": 3530,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 2.8328611898017e-07,
"loss": 1.9396,
"step": 10
},
{
"epoch": 0.06,
"learning_rate": 5.6657223796034e-07,
"loss": 1.9372,
"step": 20
},
{
"epoch": 0.08,
"learning_rate": 8.4985835694051e-07,
"loss": 1.9325,
"step": 30
},
{
"epoch": 0.11,
"learning_rate": 1.13314447592068e-06,
"loss": 1.9313,
"step": 40
},
{
"epoch": 0.14,
"learning_rate": 1.41643059490085e-06,
"loss": 1.9326,
"step": 50
},
{
"epoch": 0.17,
"learning_rate": 1.69971671388102e-06,
"loss": 1.9266,
"step": 60
},
{
"epoch": 0.2,
"learning_rate": 1.98300283286119e-06,
"loss": 1.9246,
"step": 70
},
{
"epoch": 0.23,
"learning_rate": 2.26628895184136e-06,
"loss": 1.9173,
"step": 80
},
{
"epoch": 0.25,
"learning_rate": 2.54957507082153e-06,
"loss": 1.9115,
"step": 90
},
{
"epoch": 0.28,
"learning_rate": 2.8328611898017e-06,
"loss": 1.9067,
"step": 100
},
{
"epoch": 0.31,
"learning_rate": 3.11614730878187e-06,
"loss": 1.8943,
"step": 110
},
{
"epoch": 0.34,
"learning_rate": 3.39943342776204e-06,
"loss": 1.8876,
"step": 120
},
{
"epoch": 0.37,
"learning_rate": 3.68271954674221e-06,
"loss": 1.8771,
"step": 130
},
{
"epoch": 0.4,
"learning_rate": 3.96600566572238e-06,
"loss": 1.8685,
"step": 140
},
{
"epoch": 0.42,
"learning_rate": 4.24929178470255e-06,
"loss": 1.8511,
"step": 150
},
{
"epoch": 0.45,
"learning_rate": 4.53257790368272e-06,
"loss": 1.8359,
"step": 160
},
{
"epoch": 0.48,
"learning_rate": 4.81586402266289e-06,
"loss": 1.8159,
"step": 170
},
{
"epoch": 0.51,
"learning_rate": 5.09915014164306e-06,
"loss": 1.7941,
"step": 180
},
{
"epoch": 0.54,
"learning_rate": 5.382436260623229e-06,
"loss": 1.7734,
"step": 190
},
{
"epoch": 0.57,
"learning_rate": 5.6657223796034e-06,
"loss": 1.7345,
"step": 200
},
{
"epoch": 0.59,
"learning_rate": 5.9490084985835695e-06,
"loss": 1.7244,
"step": 210
},
{
"epoch": 0.62,
"learning_rate": 6.23229461756374e-06,
"loss": 1.6518,
"step": 220
},
{
"epoch": 0.65,
"learning_rate": 6.51558073654391e-06,
"loss": 1.6384,
"step": 230
},
{
"epoch": 0.68,
"learning_rate": 6.79886685552408e-06,
"loss": 1.5812,
"step": 240
},
{
"epoch": 0.71,
"learning_rate": 7.082152974504249e-06,
"loss": 1.5845,
"step": 250
},
{
"epoch": 0.74,
"learning_rate": 7.36543909348442e-06,
"loss": 1.5438,
"step": 260
},
{
"epoch": 0.76,
"learning_rate": 7.64872521246459e-06,
"loss": 1.4838,
"step": 270
},
{
"epoch": 0.79,
"learning_rate": 7.93201133144476e-06,
"loss": 1.4631,
"step": 280
},
{
"epoch": 0.82,
"learning_rate": 8.215297450424929e-06,
"loss": 1.4308,
"step": 290
},
{
"epoch": 0.85,
"learning_rate": 8.4985835694051e-06,
"loss": 1.4088,
"step": 300
},
{
"epoch": 0.88,
"learning_rate": 8.78186968838527e-06,
"loss": 1.3938,
"step": 310
},
{
"epoch": 0.91,
"learning_rate": 9.06515580736544e-06,
"loss": 1.3423,
"step": 320
},
{
"epoch": 0.93,
"learning_rate": 9.34844192634561e-06,
"loss": 1.3211,
"step": 330
},
{
"epoch": 0.96,
"learning_rate": 9.63172804532578e-06,
"loss": 1.3197,
"step": 340
},
{
"epoch": 0.99,
"learning_rate": 9.91501416430595e-06,
"loss": 1.2858,
"step": 350
},
{
"epoch": 1.0,
"eval_accuracy": 0.5545237463518174,
"eval_f1": 0.5122245135719901,
"eval_loss": 1.2814059257507324,
"eval_precision": 0.5431752227356587,
"eval_recall": 0.5545237463518174,
"eval_runtime": 333.001,
"eval_samples_per_second": 33.955,
"eval_steps_per_second": 1.063,
"step": 353
},
{
"epoch": 1.02,
"learning_rate": 9.977966635190433e-06,
"loss": 1.3717,
"step": 360
},
{
"epoch": 1.05,
"learning_rate": 9.946490399748192e-06,
"loss": 1.2267,
"step": 370
},
{
"epoch": 1.08,
"learning_rate": 9.91501416430595e-06,
"loss": 1.2461,
"step": 380
},
{
"epoch": 1.1,
"learning_rate": 9.883537928863708e-06,
"loss": 1.2069,
"step": 390
},
{
"epoch": 1.13,
"learning_rate": 9.852061693421467e-06,
"loss": 1.2097,
"step": 400
},
{
"epoch": 1.16,
"learning_rate": 9.820585457979227e-06,
"loss": 1.2063,
"step": 410
},
{
"epoch": 1.19,
"learning_rate": 9.789109222536986e-06,
"loss": 1.1918,
"step": 420
},
{
"epoch": 1.22,
"learning_rate": 9.757632987094745e-06,
"loss": 1.1887,
"step": 430
},
{
"epoch": 1.25,
"learning_rate": 9.726156751652504e-06,
"loss": 1.1611,
"step": 440
},
{
"epoch": 1.27,
"learning_rate": 9.694680516210261e-06,
"loss": 1.1886,
"step": 450
},
{
"epoch": 1.3,
"learning_rate": 9.66320428076802e-06,
"loss": 1.1775,
"step": 460
},
{
"epoch": 1.33,
"learning_rate": 9.63172804532578e-06,
"loss": 1.1253,
"step": 470
},
{
"epoch": 1.36,
"learning_rate": 9.600251809883539e-06,
"loss": 1.1337,
"step": 480
},
{
"epoch": 1.39,
"learning_rate": 9.568775574441298e-06,
"loss": 1.1639,
"step": 490
},
{
"epoch": 1.42,
"learning_rate": 9.537299338999057e-06,
"loss": 1.151,
"step": 500
},
{
"epoch": 1.44,
"learning_rate": 9.505823103556814e-06,
"loss": 1.1099,
"step": 510
},
{
"epoch": 1.47,
"learning_rate": 9.474346868114575e-06,
"loss": 1.1148,
"step": 520
},
{
"epoch": 1.5,
"learning_rate": 9.442870632672332e-06,
"loss": 1.128,
"step": 530
},
{
"epoch": 1.53,
"learning_rate": 9.411394397230093e-06,
"loss": 1.1183,
"step": 540
},
{
"epoch": 1.56,
"learning_rate": 9.37991816178785e-06,
"loss": 1.0734,
"step": 550
},
{
"epoch": 1.59,
"learning_rate": 9.34844192634561e-06,
"loss": 1.1166,
"step": 560
},
{
"epoch": 1.61,
"learning_rate": 9.316965690903369e-06,
"loss": 1.0831,
"step": 570
},
{
"epoch": 1.64,
"learning_rate": 9.285489455461128e-06,
"loss": 1.0546,
"step": 580
},
{
"epoch": 1.67,
"learning_rate": 9.254013220018887e-06,
"loss": 1.0714,
"step": 590
},
{
"epoch": 1.7,
"learning_rate": 9.222536984576646e-06,
"loss": 1.0744,
"step": 600
},
{
"epoch": 1.73,
"learning_rate": 9.191060749134404e-06,
"loss": 1.0775,
"step": 610
},
{
"epoch": 1.76,
"learning_rate": 9.159584513692163e-06,
"loss": 1.1157,
"step": 620
},
{
"epoch": 1.78,
"learning_rate": 9.128108278249922e-06,
"loss": 1.0622,
"step": 630
},
{
"epoch": 1.81,
"learning_rate": 9.096632042807681e-06,
"loss": 1.0237,
"step": 640
},
{
"epoch": 1.84,
"learning_rate": 9.06515580736544e-06,
"loss": 1.0493,
"step": 650
},
{
"epoch": 1.87,
"learning_rate": 9.033679571923199e-06,
"loss": 1.0306,
"step": 660
},
{
"epoch": 1.9,
"learning_rate": 9.002203336480958e-06,
"loss": 1.0579,
"step": 670
},
{
"epoch": 1.93,
"learning_rate": 8.970727101038716e-06,
"loss": 1.0788,
"step": 680
},
{
"epoch": 1.95,
"learning_rate": 8.939250865596475e-06,
"loss": 1.0559,
"step": 690
},
{
"epoch": 1.98,
"learning_rate": 8.907774630154234e-06,
"loss": 1.0247,
"step": 700
},
{
"epoch": 2.0,
"eval_accuracy": 0.6288140090209605,
"eval_f1": 0.6135740404225875,
"eval_loss": 1.0342609882354736,
"eval_precision": 0.6235435699661211,
"eval_recall": 0.6288140090209605,
"eval_runtime": 326.0618,
"eval_samples_per_second": 34.677,
"eval_steps_per_second": 1.086,
"step": 706
},
{
"epoch": 2.01,
"learning_rate": 8.876298394711993e-06,
"loss": 1.0803,
"step": 710
},
{
"epoch": 2.04,
"learning_rate": 8.844822159269752e-06,
"loss": 1.0011,
"step": 720
},
{
"epoch": 2.07,
"learning_rate": 8.813345923827511e-06,
"loss": 0.9931,
"step": 730
},
{
"epoch": 2.1,
"learning_rate": 8.78186968838527e-06,
"loss": 0.9953,
"step": 740
},
{
"epoch": 2.12,
"learning_rate": 8.75039345294303e-06,
"loss": 0.9752,
"step": 750
},
{
"epoch": 2.15,
"learning_rate": 8.718917217500787e-06,
"loss": 1.0203,
"step": 760
},
{
"epoch": 2.18,
"learning_rate": 8.687440982058548e-06,
"loss": 1.0056,
"step": 770
},
{
"epoch": 2.21,
"learning_rate": 8.655964746616305e-06,
"loss": 0.9677,
"step": 780
},
{
"epoch": 2.24,
"learning_rate": 8.624488511174064e-06,
"loss": 1.0072,
"step": 790
},
{
"epoch": 2.27,
"learning_rate": 8.593012275731823e-06,
"loss": 0.9771,
"step": 800
},
{
"epoch": 2.29,
"learning_rate": 8.561536040289582e-06,
"loss": 1.0006,
"step": 810
},
{
"epoch": 2.32,
"learning_rate": 8.53005980484734e-06,
"loss": 0.9872,
"step": 820
},
{
"epoch": 2.35,
"learning_rate": 8.4985835694051e-06,
"loss": 1.0059,
"step": 830
},
{
"epoch": 2.38,
"learning_rate": 8.467107333962858e-06,
"loss": 0.9547,
"step": 840
},
{
"epoch": 2.41,
"learning_rate": 8.435631098520619e-06,
"loss": 0.9941,
"step": 850
},
{
"epoch": 2.44,
"learning_rate": 8.404154863078376e-06,
"loss": 0.9536,
"step": 860
},
{
"epoch": 2.46,
"learning_rate": 8.372678627636135e-06,
"loss": 1.0144,
"step": 870
},
{
"epoch": 2.49,
"learning_rate": 8.341202392193894e-06,
"loss": 0.9211,
"step": 880
},
{
"epoch": 2.52,
"learning_rate": 8.309726156751653e-06,
"loss": 0.9589,
"step": 890
},
{
"epoch": 2.55,
"learning_rate": 8.278249921309413e-06,
"loss": 0.9474,
"step": 900
},
{
"epoch": 2.58,
"learning_rate": 8.246773685867172e-06,
"loss": 0.9686,
"step": 910
},
{
"epoch": 2.61,
"learning_rate": 8.215297450424929e-06,
"loss": 0.9035,
"step": 920
},
{
"epoch": 2.63,
"learning_rate": 8.183821214982688e-06,
"loss": 0.9512,
"step": 930
},
{
"epoch": 2.66,
"learning_rate": 8.152344979540447e-06,
"loss": 0.9357,
"step": 940
},
{
"epoch": 2.69,
"learning_rate": 8.120868744098206e-06,
"loss": 0.9689,
"step": 950
},
{
"epoch": 2.72,
"learning_rate": 8.089392508655966e-06,
"loss": 0.9181,
"step": 960
},
{
"epoch": 2.75,
"learning_rate": 8.057916273213725e-06,
"loss": 0.9799,
"step": 970
},
{
"epoch": 2.78,
"learning_rate": 8.026440037771484e-06,
"loss": 0.9487,
"step": 980
},
{
"epoch": 2.8,
"learning_rate": 7.994963802329241e-06,
"loss": 0.9624,
"step": 990
},
{
"epoch": 2.83,
"learning_rate": 7.963487566887e-06,
"loss": 0.9725,
"step": 1000
},
{
"epoch": 2.86,
"learning_rate": 7.93201133144476e-06,
"loss": 0.9632,
"step": 1010
},
{
"epoch": 2.89,
"learning_rate": 7.900535096002518e-06,
"loss": 0.901,
"step": 1020
},
{
"epoch": 2.92,
"learning_rate": 7.869058860560278e-06,
"loss": 0.9307,
"step": 1030
},
{
"epoch": 2.94,
"learning_rate": 7.837582625118037e-06,
"loss": 0.9438,
"step": 1040
},
{
"epoch": 2.97,
"learning_rate": 7.806106389675794e-06,
"loss": 0.9403,
"step": 1050
},
{
"epoch": 3.0,
"eval_accuracy": 0.6606526930220218,
"eval_f1": 0.6522485946989532,
"eval_loss": 0.9499703049659729,
"eval_precision": 0.6591555259267519,
"eval_recall": 0.6606526930220218,
"eval_runtime": 326.9143,
"eval_samples_per_second": 34.587,
"eval_steps_per_second": 1.083,
"step": 1059
},
{
"epoch": 3.0,
"learning_rate": 7.774630154233555e-06,
"loss": 0.9586,
"step": 1060
},
{
"epoch": 3.03,
"learning_rate": 7.743153918791312e-06,
"loss": 0.9108,
"step": 1070
},
{
"epoch": 3.06,
"learning_rate": 7.711677683349073e-06,
"loss": 0.8975,
"step": 1080
},
{
"epoch": 3.09,
"learning_rate": 7.68020144790683e-06,
"loss": 0.8858,
"step": 1090
},
{
"epoch": 3.12,
"learning_rate": 7.64872521246459e-06,
"loss": 0.9063,
"step": 1100
},
{
"epoch": 3.14,
"learning_rate": 7.617248977022349e-06,
"loss": 0.9176,
"step": 1110
},
{
"epoch": 3.17,
"learning_rate": 7.585772741580108e-06,
"loss": 0.9077,
"step": 1120
},
{
"epoch": 3.2,
"learning_rate": 7.554296506137867e-06,
"loss": 0.8904,
"step": 1130
},
{
"epoch": 3.23,
"learning_rate": 7.522820270695625e-06,
"loss": 0.9058,
"step": 1140
},
{
"epoch": 3.26,
"learning_rate": 7.491344035253384e-06,
"loss": 0.891,
"step": 1150
},
{
"epoch": 3.29,
"learning_rate": 7.4598677998111434e-06,
"loss": 0.8987,
"step": 1160
},
{
"epoch": 3.31,
"learning_rate": 7.428391564368902e-06,
"loss": 0.8513,
"step": 1170
},
{
"epoch": 3.34,
"learning_rate": 7.396915328926662e-06,
"loss": 0.8618,
"step": 1180
},
{
"epoch": 3.37,
"learning_rate": 7.36543909348442e-06,
"loss": 0.9109,
"step": 1190
},
{
"epoch": 3.4,
"learning_rate": 7.333962858042178e-06,
"loss": 0.8657,
"step": 1200
},
{
"epoch": 3.43,
"learning_rate": 7.302486622599938e-06,
"loss": 0.8856,
"step": 1210
},
{
"epoch": 3.46,
"learning_rate": 7.271010387157696e-06,
"loss": 0.9221,
"step": 1220
},
{
"epoch": 3.48,
"learning_rate": 7.239534151715455e-06,
"loss": 0.8731,
"step": 1230
},
{
"epoch": 3.51,
"learning_rate": 7.208057916273215e-06,
"loss": 0.8531,
"step": 1240
},
{
"epoch": 3.54,
"learning_rate": 7.176581680830973e-06,
"loss": 0.8751,
"step": 1250
},
{
"epoch": 3.57,
"learning_rate": 7.145105445388733e-06,
"loss": 0.9432,
"step": 1260
},
{
"epoch": 3.6,
"learning_rate": 7.113629209946491e-06,
"loss": 0.8926,
"step": 1270
},
{
"epoch": 3.63,
"learning_rate": 7.082152974504249e-06,
"loss": 0.8456,
"step": 1280
},
{
"epoch": 3.65,
"learning_rate": 7.050676739062009e-06,
"loss": 0.8764,
"step": 1290
},
{
"epoch": 3.68,
"learning_rate": 7.0192005036197675e-06,
"loss": 0.8566,
"step": 1300
},
{
"epoch": 3.71,
"learning_rate": 6.987724268177527e-06,
"loss": 0.886,
"step": 1310
},
{
"epoch": 3.74,
"learning_rate": 6.956248032735286e-06,
"loss": 0.8618,
"step": 1320
},
{
"epoch": 3.77,
"learning_rate": 6.924771797293044e-06,
"loss": 0.8622,
"step": 1330
},
{
"epoch": 3.79,
"learning_rate": 6.893295561850803e-06,
"loss": 0.857,
"step": 1340
},
{
"epoch": 3.82,
"learning_rate": 6.861819326408562e-06,
"loss": 0.8449,
"step": 1350
},
{
"epoch": 3.85,
"learning_rate": 6.830343090966321e-06,
"loss": 0.8671,
"step": 1360
},
{
"epoch": 3.88,
"learning_rate": 6.79886685552408e-06,
"loss": 0.8534,
"step": 1370
},
{
"epoch": 3.91,
"learning_rate": 6.767390620081839e-06,
"loss": 0.8277,
"step": 1380
},
{
"epoch": 3.94,
"learning_rate": 6.735914384639598e-06,
"loss": 0.8816,
"step": 1390
},
{
"epoch": 3.96,
"learning_rate": 6.704438149197356e-06,
"loss": 0.8682,
"step": 1400
},
{
"epoch": 3.99,
"learning_rate": 6.672961913755115e-06,
"loss": 0.8501,
"step": 1410
},
{
"epoch": 4.0,
"eval_accuracy": 0.6802865481560095,
"eval_f1": 0.6760402772900678,
"eval_loss": 0.8971089124679565,
"eval_precision": 0.6760672912456882,
"eval_recall": 0.6802865481560095,
"eval_runtime": 327.0927,
"eval_samples_per_second": 34.568,
"eval_steps_per_second": 1.082,
"step": 1412
},
{
"epoch": 4.02,
"learning_rate": 6.641485678312874e-06,
"loss": 0.8996,
"step": 1420
},
{
"epoch": 4.05,
"learning_rate": 6.6100094428706325e-06,
"loss": 0.797,
"step": 1430
},
{
"epoch": 4.08,
"learning_rate": 6.5785332074283925e-06,
"loss": 0.8466,
"step": 1440
},
{
"epoch": 4.11,
"learning_rate": 6.547056971986151e-06,
"loss": 0.8575,
"step": 1450
},
{
"epoch": 4.14,
"learning_rate": 6.51558073654391e-06,
"loss": 0.8142,
"step": 1460
},
{
"epoch": 4.16,
"learning_rate": 6.484104501101669e-06,
"loss": 0.8328,
"step": 1470
},
{
"epoch": 4.19,
"learning_rate": 6.452628265659427e-06,
"loss": 0.8703,
"step": 1480
},
{
"epoch": 4.22,
"learning_rate": 6.421152030217187e-06,
"loss": 0.8141,
"step": 1490
},
{
"epoch": 4.25,
"learning_rate": 6.3896757947749454e-06,
"loss": 0.8101,
"step": 1500
},
{
"epoch": 4.28,
"learning_rate": 6.358199559332704e-06,
"loss": 0.8666,
"step": 1510
},
{
"epoch": 4.31,
"learning_rate": 6.326723323890464e-06,
"loss": 0.8095,
"step": 1520
},
{
"epoch": 4.33,
"learning_rate": 6.295247088448222e-06,
"loss": 0.8407,
"step": 1530
},
{
"epoch": 4.36,
"learning_rate": 6.263770853005982e-06,
"loss": 0.7865,
"step": 1540
},
{
"epoch": 4.39,
"learning_rate": 6.23229461756374e-06,
"loss": 0.8422,
"step": 1550
},
{
"epoch": 4.42,
"learning_rate": 6.200818382121498e-06,
"loss": 0.8377,
"step": 1560
},
{
"epoch": 4.45,
"learning_rate": 6.169342146679258e-06,
"loss": 0.8692,
"step": 1570
},
{
"epoch": 4.48,
"learning_rate": 6.137865911237017e-06,
"loss": 0.8257,
"step": 1580
},
{
"epoch": 4.5,
"learning_rate": 6.106389675794775e-06,
"loss": 0.7972,
"step": 1590
},
{
"epoch": 4.53,
"learning_rate": 6.074913440352535e-06,
"loss": 0.8064,
"step": 1600
},
{
"epoch": 4.56,
"learning_rate": 6.043437204910293e-06,
"loss": 0.8145,
"step": 1610
},
{
"epoch": 4.59,
"learning_rate": 6.011960969468052e-06,
"loss": 0.8655,
"step": 1620
},
{
"epoch": 4.62,
"learning_rate": 5.980484734025811e-06,
"loss": 0.8088,
"step": 1630
},
{
"epoch": 4.64,
"learning_rate": 5.9490084985835695e-06,
"loss": 0.7936,
"step": 1640
},
{
"epoch": 4.67,
"learning_rate": 5.917532263141329e-06,
"loss": 0.8018,
"step": 1650
},
{
"epoch": 4.7,
"learning_rate": 5.886056027699088e-06,
"loss": 0.7975,
"step": 1660
},
{
"epoch": 4.73,
"learning_rate": 5.854579792256847e-06,
"loss": 0.8434,
"step": 1670
},
{
"epoch": 4.76,
"learning_rate": 5.823103556814605e-06,
"loss": 0.8153,
"step": 1680
},
{
"epoch": 4.79,
"learning_rate": 5.791627321372364e-06,
"loss": 0.8244,
"step": 1690
},
{
"epoch": 4.81,
"learning_rate": 5.760151085930123e-06,
"loss": 0.81,
"step": 1700
},
{
"epoch": 4.84,
"learning_rate": 5.728674850487882e-06,
"loss": 0.8323,
"step": 1710
},
{
"epoch": 4.87,
"learning_rate": 5.6971986150456415e-06,
"loss": 0.7752,
"step": 1720
},
{
"epoch": 4.9,
"learning_rate": 5.6657223796034e-06,
"loss": 0.8074,
"step": 1730
},
{
"epoch": 4.93,
"learning_rate": 5.634246144161158e-06,
"loss": 0.7975,
"step": 1740
},
{
"epoch": 4.96,
"learning_rate": 5.602769908718918e-06,
"loss": 0.8391,
"step": 1750
},
{
"epoch": 4.98,
"learning_rate": 5.571293673276676e-06,
"loss": 0.8148,
"step": 1760
},
{
"epoch": 5.0,
"eval_accuracy": 0.6856814362784116,
"eval_f1": 0.685421574309762,
"eval_loss": 0.873296320438385,
"eval_precision": 0.6880833294843167,
"eval_recall": 0.6856814362784116,
"eval_runtime": 324.485,
"eval_samples_per_second": 34.846,
"eval_steps_per_second": 1.091,
"step": 1765
},
{
"epoch": 5.01,
"learning_rate": 5.5398174378344345e-06,
"loss": 0.8198,
"step": 1770
},
{
"epoch": 5.04,
"learning_rate": 5.5083412023921945e-06,
"loss": 0.7889,
"step": 1780
},
{
"epoch": 5.07,
"learning_rate": 5.476864966949953e-06,
"loss": 0.7909,
"step": 1790
},
{
"epoch": 5.1,
"learning_rate": 5.445388731507713e-06,
"loss": 0.7854,
"step": 1800
},
{
"epoch": 5.13,
"learning_rate": 5.413912496065471e-06,
"loss": 0.7871,
"step": 1810
},
{
"epoch": 5.16,
"learning_rate": 5.382436260623229e-06,
"loss": 0.7673,
"step": 1820
},
{
"epoch": 5.18,
"learning_rate": 5.350960025180989e-06,
"loss": 0.7493,
"step": 1830
},
{
"epoch": 5.21,
"learning_rate": 5.3194837897387474e-06,
"loss": 0.7953,
"step": 1840
},
{
"epoch": 5.24,
"learning_rate": 5.288007554296507e-06,
"loss": 0.831,
"step": 1850
},
{
"epoch": 5.27,
"learning_rate": 5.256531318854266e-06,
"loss": 0.7678,
"step": 1860
},
{
"epoch": 5.3,
"learning_rate": 5.225055083412024e-06,
"loss": 0.7809,
"step": 1870
},
{
"epoch": 5.33,
"learning_rate": 5.193578847969784e-06,
"loss": 0.8247,
"step": 1880
},
{
"epoch": 5.35,
"learning_rate": 5.162102612527542e-06,
"loss": 0.8201,
"step": 1890
},
{
"epoch": 5.38,
"learning_rate": 5.130626377085301e-06,
"loss": 0.7721,
"step": 1900
},
{
"epoch": 5.41,
"learning_rate": 5.09915014164306e-06,
"loss": 0.7709,
"step": 1910
},
{
"epoch": 5.44,
"learning_rate": 5.067673906200819e-06,
"loss": 0.7757,
"step": 1920
},
{
"epoch": 5.47,
"learning_rate": 5.036197670758578e-06,
"loss": 0.809,
"step": 1930
},
{
"epoch": 5.5,
"learning_rate": 5.004721435316337e-06,
"loss": 0.7553,
"step": 1940
},
{
"epoch": 5.52,
"learning_rate": 4.973245199874096e-06,
"loss": 0.8157,
"step": 1950
},
{
"epoch": 5.55,
"learning_rate": 4.941768964431854e-06,
"loss": 0.7409,
"step": 1960
},
{
"epoch": 5.58,
"learning_rate": 4.910292728989613e-06,
"loss": 0.7412,
"step": 1970
},
{
"epoch": 5.61,
"learning_rate": 4.878816493547372e-06,
"loss": 0.8036,
"step": 1980
},
{
"epoch": 5.64,
"learning_rate": 4.847340258105131e-06,
"loss": 0.8074,
"step": 1990
},
{
"epoch": 5.66,
"learning_rate": 4.81586402266289e-06,
"loss": 0.803,
"step": 2000
},
{
"epoch": 5.69,
"learning_rate": 4.784387787220649e-06,
"loss": 0.7577,
"step": 2010
},
{
"epoch": 5.72,
"learning_rate": 4.752911551778407e-06,
"loss": 0.7432,
"step": 2020
},
{
"epoch": 5.75,
"learning_rate": 4.721435316336166e-06,
"loss": 0.7096,
"step": 2030
},
{
"epoch": 5.78,
"learning_rate": 4.689959080893925e-06,
"loss": 0.7942,
"step": 2040
},
{
"epoch": 5.81,
"learning_rate": 4.6584828454516844e-06,
"loss": 0.7659,
"step": 2050
},
{
"epoch": 5.83,
"learning_rate": 4.6270066100094435e-06,
"loss": 0.7768,
"step": 2060
},
{
"epoch": 5.86,
"learning_rate": 4.595530374567202e-06,
"loss": 0.8028,
"step": 2070
},
{
"epoch": 5.89,
"learning_rate": 4.564054139124961e-06,
"loss": 0.81,
"step": 2080
},
{
"epoch": 5.92,
"learning_rate": 4.53257790368272e-06,
"loss": 0.7667,
"step": 2090
},
{
"epoch": 5.95,
"learning_rate": 4.501101668240479e-06,
"loss": 0.8109,
"step": 2100
},
{
"epoch": 5.98,
"learning_rate": 4.469625432798237e-06,
"loss": 0.7898,
"step": 2110
},
{
"epoch": 6.0,
"eval_accuracy": 0.6913416467674892,
"eval_f1": 0.6888127658536334,
"eval_loss": 0.8526361584663391,
"eval_precision": 0.6911291055014825,
"eval_recall": 0.6913416467674892,
"eval_runtime": 327.2319,
"eval_samples_per_second": 34.553,
"eval_steps_per_second": 1.082,
"step": 2118
},
{
"epoch": 6.01,
"learning_rate": 4.4381491973559965e-06,
"loss": 0.7771,
"step": 2120
},
{
"epoch": 6.03,
"learning_rate": 4.406672961913756e-06,
"loss": 0.7278,
"step": 2130
},
{
"epoch": 6.06,
"learning_rate": 4.375196726471515e-06,
"loss": 0.7372,
"step": 2140
},
{
"epoch": 6.09,
"learning_rate": 4.343720491029274e-06,
"loss": 0.7411,
"step": 2150
},
{
"epoch": 6.12,
"learning_rate": 4.312244255587032e-06,
"loss": 0.7973,
"step": 2160
},
{
"epoch": 6.15,
"learning_rate": 4.280768020144791e-06,
"loss": 0.7526,
"step": 2170
},
{
"epoch": 6.18,
"learning_rate": 4.24929178470255e-06,
"loss": 0.7706,
"step": 2180
},
{
"epoch": 6.2,
"learning_rate": 4.217815549260309e-06,
"loss": 0.7605,
"step": 2190
},
{
"epoch": 6.23,
"learning_rate": 4.186339313818068e-06,
"loss": 0.7216,
"step": 2200
},
{
"epoch": 6.26,
"learning_rate": 4.154863078375827e-06,
"loss": 0.7944,
"step": 2210
},
{
"epoch": 6.29,
"learning_rate": 4.123386842933586e-06,
"loss": 0.7374,
"step": 2220
},
{
"epoch": 6.32,
"learning_rate": 4.091910607491344e-06,
"loss": 0.7128,
"step": 2230
},
{
"epoch": 6.35,
"learning_rate": 4.060434372049103e-06,
"loss": 0.7644,
"step": 2240
},
{
"epoch": 6.37,
"learning_rate": 4.028958136606862e-06,
"loss": 0.7381,
"step": 2250
},
{
"epoch": 6.4,
"learning_rate": 3.997481901164621e-06,
"loss": 0.7309,
"step": 2260
},
{
"epoch": 6.43,
"learning_rate": 3.96600566572238e-06,
"loss": 0.7149,
"step": 2270
},
{
"epoch": 6.46,
"learning_rate": 3.934529430280139e-06,
"loss": 0.8118,
"step": 2280
},
{
"epoch": 6.49,
"learning_rate": 3.903053194837897e-06,
"loss": 0.7818,
"step": 2290
},
{
"epoch": 6.51,
"learning_rate": 3.871576959395656e-06,
"loss": 0.7372,
"step": 2300
},
{
"epoch": 6.54,
"learning_rate": 3.840100723953415e-06,
"loss": 0.7401,
"step": 2310
},
{
"epoch": 6.57,
"learning_rate": 3.8086244885111744e-06,
"loss": 0.7598,
"step": 2320
},
{
"epoch": 6.6,
"learning_rate": 3.7771482530689335e-06,
"loss": 0.7223,
"step": 2330
},
{
"epoch": 6.63,
"learning_rate": 3.745672017626692e-06,
"loss": 0.7462,
"step": 2340
},
{
"epoch": 6.66,
"learning_rate": 3.714195782184451e-06,
"loss": 0.7563,
"step": 2350
},
{
"epoch": 6.68,
"learning_rate": 3.68271954674221e-06,
"loss": 0.7643,
"step": 2360
},
{
"epoch": 6.71,
"learning_rate": 3.651243311299969e-06,
"loss": 0.7298,
"step": 2370
},
{
"epoch": 6.74,
"learning_rate": 3.6197670758577273e-06,
"loss": 0.7303,
"step": 2380
},
{
"epoch": 6.77,
"learning_rate": 3.5882908404154864e-06,
"loss": 0.7668,
"step": 2390
},
{
"epoch": 6.8,
"learning_rate": 3.5568146049732455e-06,
"loss": 0.7257,
"step": 2400
},
{
"epoch": 6.83,
"learning_rate": 3.5253383695310046e-06,
"loss": 0.7326,
"step": 2410
},
{
"epoch": 6.85,
"learning_rate": 3.4938621340887633e-06,
"loss": 0.7217,
"step": 2420
},
{
"epoch": 6.88,
"learning_rate": 3.462385898646522e-06,
"loss": 0.7941,
"step": 2430
},
{
"epoch": 6.91,
"learning_rate": 3.430909663204281e-06,
"loss": 0.7393,
"step": 2440
},
{
"epoch": 6.94,
"learning_rate": 3.39943342776204e-06,
"loss": 0.7542,
"step": 2450
},
{
"epoch": 6.97,
"learning_rate": 3.367957192319799e-06,
"loss": 0.7464,
"step": 2460
},
{
"epoch": 7.0,
"learning_rate": 3.3364809568775576e-06,
"loss": 0.7074,
"step": 2470
},
{
"epoch": 7.0,
"eval_accuracy": 0.6958521270009729,
"eval_f1": 0.6952840578720214,
"eval_loss": 0.840837836265564,
"eval_precision": 0.6971422528714606,
"eval_recall": 0.6958521270009729,
"eval_runtime": 325.4461,
"eval_samples_per_second": 34.743,
"eval_steps_per_second": 1.088,
"step": 2471
},
{
"epoch": 7.03,
"learning_rate": 3.3050047214353163e-06,
"loss": 0.7885,
"step": 2480
},
{
"epoch": 7.05,
"learning_rate": 3.2735284859930754e-06,
"loss": 0.7209,
"step": 2490
},
{
"epoch": 7.08,
"learning_rate": 3.2420522505508345e-06,
"loss": 0.7331,
"step": 2500
},
{
"epoch": 7.11,
"learning_rate": 3.2105760151085936e-06,
"loss": 0.7092,
"step": 2510
},
{
"epoch": 7.14,
"learning_rate": 3.179099779666352e-06,
"loss": 0.6885,
"step": 2520
},
{
"epoch": 7.17,
"learning_rate": 3.147623544224111e-06,
"loss": 0.7096,
"step": 2530
},
{
"epoch": 7.2,
"learning_rate": 3.11614730878187e-06,
"loss": 0.7398,
"step": 2540
},
{
"epoch": 7.22,
"learning_rate": 3.084671073339629e-06,
"loss": 0.6973,
"step": 2550
},
{
"epoch": 7.25,
"learning_rate": 3.0531948378973874e-06,
"loss": 0.7058,
"step": 2560
},
{
"epoch": 7.28,
"learning_rate": 3.0217186024551465e-06,
"loss": 0.7044,
"step": 2570
},
{
"epoch": 7.31,
"learning_rate": 2.9902423670129056e-06,
"loss": 0.7623,
"step": 2580
},
{
"epoch": 7.34,
"learning_rate": 2.9587661315706643e-06,
"loss": 0.7405,
"step": 2590
},
{
"epoch": 7.36,
"learning_rate": 2.9272898961284234e-06,
"loss": 0.7305,
"step": 2600
},
{
"epoch": 7.39,
"learning_rate": 2.895813660686182e-06,
"loss": 0.7685,
"step": 2610
},
{
"epoch": 7.42,
"learning_rate": 2.864337425243941e-06,
"loss": 0.7283,
"step": 2620
},
{
"epoch": 7.45,
"learning_rate": 2.8328611898017e-06,
"loss": 0.7408,
"step": 2630
},
{
"epoch": 7.48,
"learning_rate": 2.801384954359459e-06,
"loss": 0.7085,
"step": 2640
},
{
"epoch": 7.51,
"learning_rate": 2.7699087189172173e-06,
"loss": 0.6837,
"step": 2650
},
{
"epoch": 7.53,
"learning_rate": 2.7384324834749764e-06,
"loss": 0.6925,
"step": 2660
},
{
"epoch": 7.56,
"learning_rate": 2.7069562480327355e-06,
"loss": 0.7173,
"step": 2670
},
{
"epoch": 7.59,
"learning_rate": 2.6754800125904946e-06,
"loss": 0.704,
"step": 2680
},
{
"epoch": 7.62,
"learning_rate": 2.6440037771482537e-06,
"loss": 0.7445,
"step": 2690
},
{
"epoch": 7.65,
"learning_rate": 2.612527541706012e-06,
"loss": 0.7379,
"step": 2700
},
{
"epoch": 7.68,
"learning_rate": 2.581051306263771e-06,
"loss": 0.7597,
"step": 2710
},
{
"epoch": 7.7,
"learning_rate": 2.54957507082153e-06,
"loss": 0.6948,
"step": 2720
},
{
"epoch": 7.73,
"learning_rate": 2.518098835379289e-06,
"loss": 0.724,
"step": 2730
},
{
"epoch": 7.76,
"learning_rate": 2.486622599937048e-06,
"loss": 0.6875,
"step": 2740
},
{
"epoch": 7.79,
"learning_rate": 2.4551463644948066e-06,
"loss": 0.7314,
"step": 2750
},
{
"epoch": 7.82,
"learning_rate": 2.4236701290525653e-06,
"loss": 0.7149,
"step": 2760
},
{
"epoch": 7.85,
"learning_rate": 2.3921938936103244e-06,
"loss": 0.6907,
"step": 2770
},
{
"epoch": 7.87,
"learning_rate": 2.360717658168083e-06,
"loss": 0.7527,
"step": 2780
},
{
"epoch": 7.9,
"learning_rate": 2.3292414227258422e-06,
"loss": 0.7125,
"step": 2790
},
{
"epoch": 7.93,
"learning_rate": 2.297765187283601e-06,
"loss": 0.738,
"step": 2800
},
{
"epoch": 7.96,
"learning_rate": 2.26628895184136e-06,
"loss": 0.7524,
"step": 2810
},
{
"epoch": 7.99,
"learning_rate": 2.2348127163991187e-06,
"loss": 0.7273,
"step": 2820
},
{
"epoch": 8.0,
"eval_accuracy": 0.6979747059343769,
"eval_f1": 0.6949271443194357,
"eval_loss": 0.8360838294029236,
"eval_precision": 0.6970505008964258,
"eval_recall": 0.6979747059343769,
"eval_runtime": 326.7725,
"eval_samples_per_second": 34.602,
"eval_steps_per_second": 1.083,
"step": 2824
},
{
"epoch": 8.02,
"learning_rate": 2.203336480956878e-06,
"loss": 0.7467,
"step": 2830
},
{
"epoch": 8.05,
"learning_rate": 2.171860245514637e-06,
"loss": 0.7095,
"step": 2840
},
{
"epoch": 8.07,
"learning_rate": 2.1403840100723956e-06,
"loss": 0.7352,
"step": 2850
},
{
"epoch": 8.1,
"learning_rate": 2.1089077746301547e-06,
"loss": 0.6881,
"step": 2860
},
{
"epoch": 8.13,
"learning_rate": 2.0774315391879134e-06,
"loss": 0.7128,
"step": 2870
},
{
"epoch": 8.16,
"learning_rate": 2.045955303745672e-06,
"loss": 0.6996,
"step": 2880
},
{
"epoch": 8.19,
"learning_rate": 2.014479068303431e-06,
"loss": 0.6924,
"step": 2890
},
{
"epoch": 8.21,
"learning_rate": 1.98300283286119e-06,
"loss": 0.7192,
"step": 2900
},
{
"epoch": 8.24,
"learning_rate": 1.9515265974189485e-06,
"loss": 0.71,
"step": 2910
},
{
"epoch": 8.27,
"learning_rate": 1.9200503619767076e-06,
"loss": 0.6583,
"step": 2920
},
{
"epoch": 8.3,
"learning_rate": 1.8885741265344667e-06,
"loss": 0.688,
"step": 2930
},
{
"epoch": 8.33,
"learning_rate": 1.8570978910922254e-06,
"loss": 0.7189,
"step": 2940
},
{
"epoch": 8.36,
"learning_rate": 1.8256216556499845e-06,
"loss": 0.6788,
"step": 2950
},
{
"epoch": 8.38,
"learning_rate": 1.7941454202077432e-06,
"loss": 0.7478,
"step": 2960
},
{
"epoch": 8.41,
"learning_rate": 1.7626691847655023e-06,
"loss": 0.6639,
"step": 2970
},
{
"epoch": 8.44,
"learning_rate": 1.731192949323261e-06,
"loss": 0.6611,
"step": 2980
},
{
"epoch": 8.47,
"learning_rate": 1.69971671388102e-06,
"loss": 0.6962,
"step": 2990
},
{
"epoch": 8.5,
"learning_rate": 1.6682404784387788e-06,
"loss": 0.7243,
"step": 3000
},
{
"epoch": 8.53,
"learning_rate": 1.6367642429965377e-06,
"loss": 0.7055,
"step": 3010
},
{
"epoch": 8.55,
"learning_rate": 1.6052880075542968e-06,
"loss": 0.7012,
"step": 3020
},
{
"epoch": 8.58,
"learning_rate": 1.5738117721120555e-06,
"loss": 0.7254,
"step": 3030
},
{
"epoch": 8.61,
"learning_rate": 1.5423355366698146e-06,
"loss": 0.7331,
"step": 3040
},
{
"epoch": 8.64,
"learning_rate": 1.5108593012275733e-06,
"loss": 0.7232,
"step": 3050
},
{
"epoch": 8.67,
"learning_rate": 1.4793830657853322e-06,
"loss": 0.7048,
"step": 3060
},
{
"epoch": 8.7,
"learning_rate": 1.447906830343091e-06,
"loss": 0.6746,
"step": 3070
},
{
"epoch": 8.72,
"learning_rate": 1.41643059490085e-06,
"loss": 0.7003,
"step": 3080
},
{
"epoch": 8.75,
"learning_rate": 1.3849543594586086e-06,
"loss": 0.722,
"step": 3090
},
{
"epoch": 8.78,
"learning_rate": 1.3534781240163677e-06,
"loss": 0.6753,
"step": 3100
},
{
"epoch": 8.81,
"learning_rate": 1.3220018885741268e-06,
"loss": 0.7121,
"step": 3110
},
{
"epoch": 8.84,
"learning_rate": 1.2905256531318855e-06,
"loss": 0.7367,
"step": 3120
},
{
"epoch": 8.87,
"learning_rate": 1.2590494176896444e-06,
"loss": 0.6855,
"step": 3130
},
{
"epoch": 8.89,
"learning_rate": 1.2275731822474033e-06,
"loss": 0.6994,
"step": 3140
},
{
"epoch": 8.92,
"learning_rate": 1.1960969468051622e-06,
"loss": 0.7058,
"step": 3150
},
{
"epoch": 8.95,
"learning_rate": 1.1646207113629211e-06,
"loss": 0.6823,
"step": 3160
},
{
"epoch": 8.98,
"learning_rate": 1.13314447592068e-06,
"loss": 0.6982,
"step": 3170
},
{
"epoch": 9.0,
"eval_accuracy": 0.6998319625011055,
"eval_f1": 0.6999146124635052,
"eval_loss": 0.8297391533851624,
"eval_precision": 0.7022095243425648,
"eval_recall": 0.6998319625011055,
"eval_runtime": 327.3955,
"eval_samples_per_second": 34.536,
"eval_steps_per_second": 1.081,
"step": 3177
},
{
"epoch": 9.01,
"learning_rate": 1.101668240478439e-06,
"loss": 0.7032,
"step": 3180
},
{
"epoch": 9.04,
"learning_rate": 1.0701920050361978e-06,
"loss": 0.6451,
"step": 3190
},
{
"epoch": 9.07,
"learning_rate": 1.0387157695939567e-06,
"loss": 0.6803,
"step": 3200
},
{
"epoch": 9.09,
"learning_rate": 1.0072395341517156e-06,
"loss": 0.7201,
"step": 3210
},
{
"epoch": 9.12,
"learning_rate": 9.757632987094743e-07,
"loss": 0.6948,
"step": 3220
},
{
"epoch": 9.15,
"learning_rate": 9.442870632672334e-07,
"loss": 0.7006,
"step": 3230
},
{
"epoch": 9.18,
"learning_rate": 9.128108278249923e-07,
"loss": 0.7041,
"step": 3240
},
{
"epoch": 9.21,
"learning_rate": 8.813345923827512e-07,
"loss": 0.6986,
"step": 3250
},
{
"epoch": 9.23,
"learning_rate": 8.4985835694051e-07,
"loss": 0.7013,
"step": 3260
},
{
"epoch": 9.26,
"learning_rate": 8.183821214982688e-07,
"loss": 0.6856,
"step": 3270
},
{
"epoch": 9.29,
"learning_rate": 7.869058860560277e-07,
"loss": 0.6804,
"step": 3280
},
{
"epoch": 9.32,
"learning_rate": 7.554296506137866e-07,
"loss": 0.7148,
"step": 3290
},
{
"epoch": 9.35,
"learning_rate": 7.239534151715455e-07,
"loss": 0.6959,
"step": 3300
},
{
"epoch": 9.38,
"learning_rate": 6.924771797293043e-07,
"loss": 0.6655,
"step": 3310
},
{
"epoch": 9.4,
"learning_rate": 6.610009442870634e-07,
"loss": 0.6948,
"step": 3320
},
{
"epoch": 9.43,
"learning_rate": 6.295247088448222e-07,
"loss": 0.6935,
"step": 3330
},
{
"epoch": 9.46,
"learning_rate": 5.980484734025811e-07,
"loss": 0.6612,
"step": 3340
},
{
"epoch": 9.49,
"learning_rate": 5.6657223796034e-07,
"loss": 0.6648,
"step": 3350
},
{
"epoch": 9.52,
"learning_rate": 5.350960025180989e-07,
"loss": 0.6276,
"step": 3360
},
{
"epoch": 9.55,
"learning_rate": 5.036197670758578e-07,
"loss": 0.7007,
"step": 3370
},
{
"epoch": 9.57,
"learning_rate": 4.721435316336167e-07,
"loss": 0.726,
"step": 3380
},
{
"epoch": 9.6,
"learning_rate": 4.406672961913756e-07,
"loss": 0.6869,
"step": 3390
},
{
"epoch": 9.63,
"learning_rate": 4.091910607491344e-07,
"loss": 0.7359,
"step": 3400
},
{
"epoch": 9.66,
"learning_rate": 3.777148253068933e-07,
"loss": 0.7079,
"step": 3410
},
{
"epoch": 9.69,
"learning_rate": 3.4623858986465216e-07,
"loss": 0.6872,
"step": 3420
},
{
"epoch": 9.72,
"learning_rate": 3.147623544224111e-07,
"loss": 0.6855,
"step": 3430
},
{
"epoch": 9.74,
"learning_rate": 2.8328611898017e-07,
"loss": 0.6772,
"step": 3440
},
{
"epoch": 9.77,
"learning_rate": 2.518098835379289e-07,
"loss": 0.7006,
"step": 3450
},
{
"epoch": 9.8,
"learning_rate": 2.203336480956878e-07,
"loss": 0.7026,
"step": 3460
},
{
"epoch": 9.83,
"learning_rate": 1.8885741265344666e-07,
"loss": 0.6837,
"step": 3470
},
{
"epoch": 9.86,
"learning_rate": 1.5738117721120555e-07,
"loss": 0.6597,
"step": 3480
},
{
"epoch": 9.89,
"learning_rate": 1.2590494176896445e-07,
"loss": 0.6924,
"step": 3490
},
{
"epoch": 9.91,
"learning_rate": 9.442870632672333e-08,
"loss": 0.6952,
"step": 3500
},
{
"epoch": 9.94,
"learning_rate": 6.295247088448222e-08,
"loss": 0.7021,
"step": 3510
},
{
"epoch": 9.97,
"learning_rate": 3.147623544224111e-08,
"loss": 0.6631,
"step": 3520
},
{
"epoch": 10.0,
"learning_rate": 0.0,
"loss": 0.6994,
"step": 3530
},
{
"epoch": 10.0,
"eval_accuracy": 0.6998319625011055,
"eval_f1": 0.6991477606968214,
"eval_loss": 0.8286696076393127,
"eval_precision": 0.7002150749452164,
"eval_recall": 0.6998319625011055,
"eval_runtime": 329.1215,
"eval_samples_per_second": 34.355,
"eval_steps_per_second": 1.076,
"step": 3530
},
{
"epoch": 10.0,
"step": 3530,
"total_flos": 3.5044145509209285e+19,
"train_loss": 0.9149793551934002,
"train_runtime": 28607.4466,
"train_samples_per_second": 15.809,
"train_steps_per_second": 0.123
}
],
"max_steps": 3530,
"num_train_epochs": 10,
"total_flos": 3.5044145509209285e+19,
"trial_name": null,
"trial_params": null
}