mmomm25's picture
Training in progress, epoch 4
37a93ad verified
raw
history blame
36.6 kB
{
"best_metric": 0.1480465531349182,
"best_model_checkpoint": "swin-tiny-patch4-window7-224-crack-detectorMAIN50epochsFINAL\\checkpoint-2787",
"epoch": 4.999103139013453,
"eval_steps": 500,
"global_step": 2787,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 1.7953321364452426e-07,
"loss": 1.4257,
"step": 10
},
{
"epoch": 0.04,
"learning_rate": 3.590664272890485e-07,
"loss": 1.4227,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 5.385996409335728e-07,
"loss": 1.4112,
"step": 30
},
{
"epoch": 0.07,
"learning_rate": 7.18132854578097e-07,
"loss": 1.4052,
"step": 40
},
{
"epoch": 0.09,
"learning_rate": 8.976660682226213e-07,
"loss": 1.3954,
"step": 50
},
{
"epoch": 0.11,
"learning_rate": 1.0771992818671456e-06,
"loss": 1.3978,
"step": 60
},
{
"epoch": 0.13,
"learning_rate": 1.2567324955116697e-06,
"loss": 1.3862,
"step": 70
},
{
"epoch": 0.14,
"learning_rate": 1.436265709156194e-06,
"loss": 1.3651,
"step": 80
},
{
"epoch": 0.16,
"learning_rate": 1.6157989228007182e-06,
"loss": 1.359,
"step": 90
},
{
"epoch": 0.18,
"learning_rate": 1.7953321364452425e-06,
"loss": 1.3476,
"step": 100
},
{
"epoch": 0.2,
"learning_rate": 1.9748653500897667e-06,
"loss": 1.3303,
"step": 110
},
{
"epoch": 0.22,
"learning_rate": 2.1543985637342912e-06,
"loss": 1.3047,
"step": 120
},
{
"epoch": 0.23,
"learning_rate": 2.333931777378815e-06,
"loss": 1.2944,
"step": 130
},
{
"epoch": 0.25,
"learning_rate": 2.5134649910233395e-06,
"loss": 1.284,
"step": 140
},
{
"epoch": 0.27,
"learning_rate": 2.6929982046678636e-06,
"loss": 1.23,
"step": 150
},
{
"epoch": 0.29,
"learning_rate": 2.872531418312388e-06,
"loss": 1.2103,
"step": 160
},
{
"epoch": 0.3,
"learning_rate": 3.0520646319569123e-06,
"loss": 1.187,
"step": 170
},
{
"epoch": 0.32,
"learning_rate": 3.2315978456014364e-06,
"loss": 1.1591,
"step": 180
},
{
"epoch": 0.34,
"learning_rate": 3.411131059245961e-06,
"loss": 1.144,
"step": 190
},
{
"epoch": 0.36,
"learning_rate": 3.590664272890485e-06,
"loss": 1.0904,
"step": 200
},
{
"epoch": 0.38,
"learning_rate": 3.770197486535009e-06,
"loss": 1.0401,
"step": 210
},
{
"epoch": 0.39,
"learning_rate": 3.949730700179533e-06,
"loss": 1.0281,
"step": 220
},
{
"epoch": 0.41,
"learning_rate": 4.129263913824058e-06,
"loss": 0.9577,
"step": 230
},
{
"epoch": 0.43,
"learning_rate": 4.3087971274685824e-06,
"loss": 0.9251,
"step": 240
},
{
"epoch": 0.45,
"learning_rate": 4.488330341113106e-06,
"loss": 0.8964,
"step": 250
},
{
"epoch": 0.47,
"learning_rate": 4.66786355475763e-06,
"loss": 0.8897,
"step": 260
},
{
"epoch": 0.48,
"learning_rate": 4.847396768402154e-06,
"loss": 0.8481,
"step": 270
},
{
"epoch": 0.5,
"learning_rate": 5.026929982046679e-06,
"loss": 0.8048,
"step": 280
},
{
"epoch": 0.52,
"learning_rate": 5.206463195691203e-06,
"loss": 0.8014,
"step": 290
},
{
"epoch": 0.54,
"learning_rate": 5.385996409335727e-06,
"loss": 0.7511,
"step": 300
},
{
"epoch": 0.56,
"learning_rate": 5.565529622980251e-06,
"loss": 0.741,
"step": 310
},
{
"epoch": 0.57,
"learning_rate": 5.745062836624776e-06,
"loss": 0.7327,
"step": 320
},
{
"epoch": 0.59,
"learning_rate": 5.9245960502693004e-06,
"loss": 0.7492,
"step": 330
},
{
"epoch": 0.61,
"learning_rate": 6.1041292639138246e-06,
"loss": 0.7613,
"step": 340
},
{
"epoch": 0.63,
"learning_rate": 6.283662477558349e-06,
"loss": 0.6902,
"step": 350
},
{
"epoch": 0.65,
"learning_rate": 6.463195691202873e-06,
"loss": 0.6687,
"step": 360
},
{
"epoch": 0.66,
"learning_rate": 6.642728904847396e-06,
"loss": 0.6623,
"step": 370
},
{
"epoch": 0.68,
"learning_rate": 6.822262118491922e-06,
"loss": 0.6901,
"step": 380
},
{
"epoch": 0.7,
"learning_rate": 7.001795332136446e-06,
"loss": 0.6638,
"step": 390
},
{
"epoch": 0.72,
"learning_rate": 7.18132854578097e-06,
"loss": 0.6414,
"step": 400
},
{
"epoch": 0.74,
"learning_rate": 7.360861759425494e-06,
"loss": 0.6877,
"step": 410
},
{
"epoch": 0.75,
"learning_rate": 7.540394973070018e-06,
"loss": 0.6249,
"step": 420
},
{
"epoch": 0.77,
"learning_rate": 7.719928186714543e-06,
"loss": 0.6099,
"step": 430
},
{
"epoch": 0.79,
"learning_rate": 7.899461400359067e-06,
"loss": 0.6321,
"step": 440
},
{
"epoch": 0.81,
"learning_rate": 8.07899461400359e-06,
"loss": 0.6431,
"step": 450
},
{
"epoch": 0.83,
"learning_rate": 8.258527827648117e-06,
"loss": 0.6404,
"step": 460
},
{
"epoch": 0.84,
"learning_rate": 8.43806104129264e-06,
"loss": 0.6148,
"step": 470
},
{
"epoch": 0.86,
"learning_rate": 8.617594254937165e-06,
"loss": 0.5844,
"step": 480
},
{
"epoch": 0.88,
"learning_rate": 8.797127468581689e-06,
"loss": 0.6316,
"step": 490
},
{
"epoch": 0.9,
"learning_rate": 8.976660682226211e-06,
"loss": 0.6018,
"step": 500
},
{
"epoch": 0.91,
"learning_rate": 9.156193895870736e-06,
"loss": 0.5843,
"step": 510
},
{
"epoch": 0.93,
"learning_rate": 9.33572710951526e-06,
"loss": 0.5986,
"step": 520
},
{
"epoch": 0.95,
"learning_rate": 9.515260323159784e-06,
"loss": 0.5718,
"step": 530
},
{
"epoch": 0.97,
"learning_rate": 9.694793536804308e-06,
"loss": 0.5163,
"step": 540
},
{
"epoch": 0.99,
"learning_rate": 9.874326750448834e-06,
"loss": 0.5448,
"step": 550
},
{
"epoch": 1.0,
"eval_accuracy": {
"accuracy": 0.8387530836510428
},
"eval_f1": {
"f1": 0.8242528613153339
},
"eval_loss": 0.43474748730659485,
"eval_precision": {
"precision": 0.8238035334510331
},
"eval_recall": {
"recall": 0.8266051811271123
},
"eval_runtime": 171.551,
"eval_samples_per_second": 103.969,
"eval_steps_per_second": 3.253,
"step": 557
},
{
"epoch": 1.0,
"learning_rate": 1.0053859964093358e-05,
"loss": 0.58,
"step": 560
},
{
"epoch": 1.02,
"learning_rate": 1.0233393177737882e-05,
"loss": 0.5298,
"step": 570
},
{
"epoch": 1.04,
"learning_rate": 1.0412926391382406e-05,
"loss": 0.5592,
"step": 580
},
{
"epoch": 1.06,
"learning_rate": 1.059245960502693e-05,
"loss": 0.5352,
"step": 590
},
{
"epoch": 1.08,
"learning_rate": 1.0771992818671454e-05,
"loss": 0.5683,
"step": 600
},
{
"epoch": 1.09,
"learning_rate": 1.0951526032315979e-05,
"loss": 0.571,
"step": 610
},
{
"epoch": 1.11,
"learning_rate": 1.1131059245960503e-05,
"loss": 0.5603,
"step": 620
},
{
"epoch": 1.13,
"learning_rate": 1.1310592459605028e-05,
"loss": 0.5157,
"step": 630
},
{
"epoch": 1.15,
"learning_rate": 1.1490125673249553e-05,
"loss": 0.4885,
"step": 640
},
{
"epoch": 1.17,
"learning_rate": 1.1669658886894077e-05,
"loss": 0.5005,
"step": 650
},
{
"epoch": 1.18,
"learning_rate": 1.1849192100538601e-05,
"loss": 0.4951,
"step": 660
},
{
"epoch": 1.2,
"learning_rate": 1.2028725314183125e-05,
"loss": 0.5197,
"step": 670
},
{
"epoch": 1.22,
"learning_rate": 1.2208258527827649e-05,
"loss": 0.4746,
"step": 680
},
{
"epoch": 1.24,
"learning_rate": 1.2387791741472173e-05,
"loss": 0.486,
"step": 690
},
{
"epoch": 1.26,
"learning_rate": 1.2567324955116697e-05,
"loss": 0.4932,
"step": 700
},
{
"epoch": 1.27,
"learning_rate": 1.2746858168761221e-05,
"loss": 0.5222,
"step": 710
},
{
"epoch": 1.29,
"learning_rate": 1.2926391382405746e-05,
"loss": 0.434,
"step": 720
},
{
"epoch": 1.31,
"learning_rate": 1.310592459605027e-05,
"loss": 0.4817,
"step": 730
},
{
"epoch": 1.33,
"learning_rate": 1.3285457809694792e-05,
"loss": 0.487,
"step": 740
},
{
"epoch": 1.35,
"learning_rate": 1.3464991023339318e-05,
"loss": 0.4478,
"step": 750
},
{
"epoch": 1.36,
"learning_rate": 1.3644524236983844e-05,
"loss": 0.4564,
"step": 760
},
{
"epoch": 1.38,
"learning_rate": 1.3824057450628366e-05,
"loss": 0.4455,
"step": 770
},
{
"epoch": 1.4,
"learning_rate": 1.4003590664272892e-05,
"loss": 0.4701,
"step": 780
},
{
"epoch": 1.42,
"learning_rate": 1.4183123877917415e-05,
"loss": 0.4333,
"step": 790
},
{
"epoch": 1.43,
"learning_rate": 1.436265709156194e-05,
"loss": 0.4409,
"step": 800
},
{
"epoch": 1.45,
"learning_rate": 1.4542190305206463e-05,
"loss": 0.4639,
"step": 810
},
{
"epoch": 1.47,
"learning_rate": 1.4721723518850989e-05,
"loss": 0.4552,
"step": 820
},
{
"epoch": 1.49,
"learning_rate": 1.4901256732495511e-05,
"loss": 0.4759,
"step": 830
},
{
"epoch": 1.51,
"learning_rate": 1.5080789946140037e-05,
"loss": 0.4584,
"step": 840
},
{
"epoch": 1.52,
"learning_rate": 1.5260323159784563e-05,
"loss": 0.4502,
"step": 850
},
{
"epoch": 1.54,
"learning_rate": 1.5439856373429085e-05,
"loss": 0.4519,
"step": 860
},
{
"epoch": 1.56,
"learning_rate": 1.561938958707361e-05,
"loss": 0.4695,
"step": 870
},
{
"epoch": 1.58,
"learning_rate": 1.5798922800718133e-05,
"loss": 0.4466,
"step": 880
},
{
"epoch": 1.6,
"learning_rate": 1.597845601436266e-05,
"loss": 0.4531,
"step": 890
},
{
"epoch": 1.61,
"learning_rate": 1.615798922800718e-05,
"loss": 0.4674,
"step": 900
},
{
"epoch": 1.63,
"learning_rate": 1.6337522441651707e-05,
"loss": 0.4262,
"step": 910
},
{
"epoch": 1.65,
"learning_rate": 1.6517055655296233e-05,
"loss": 0.3945,
"step": 920
},
{
"epoch": 1.67,
"learning_rate": 1.6696588868940756e-05,
"loss": 0.4318,
"step": 930
},
{
"epoch": 1.69,
"learning_rate": 1.687612208258528e-05,
"loss": 0.439,
"step": 940
},
{
"epoch": 1.7,
"learning_rate": 1.7055655296229804e-05,
"loss": 0.4036,
"step": 950
},
{
"epoch": 1.72,
"learning_rate": 1.723518850987433e-05,
"loss": 0.422,
"step": 960
},
{
"epoch": 1.74,
"learning_rate": 1.7414721723518852e-05,
"loss": 0.4315,
"step": 970
},
{
"epoch": 1.76,
"learning_rate": 1.7594254937163378e-05,
"loss": 0.4516,
"step": 980
},
{
"epoch": 1.78,
"learning_rate": 1.77737881508079e-05,
"loss": 0.4092,
"step": 990
},
{
"epoch": 1.79,
"learning_rate": 1.7953321364452423e-05,
"loss": 0.4367,
"step": 1000
},
{
"epoch": 1.81,
"learning_rate": 1.813285457809695e-05,
"loss": 0.4321,
"step": 1010
},
{
"epoch": 1.83,
"learning_rate": 1.831238779174147e-05,
"loss": 0.3859,
"step": 1020
},
{
"epoch": 1.85,
"learning_rate": 1.8491921005385997e-05,
"loss": 0.415,
"step": 1030
},
{
"epoch": 1.87,
"learning_rate": 1.867145421903052e-05,
"loss": 0.4388,
"step": 1040
},
{
"epoch": 1.88,
"learning_rate": 1.8850987432675045e-05,
"loss": 0.3968,
"step": 1050
},
{
"epoch": 1.9,
"learning_rate": 1.9030520646319568e-05,
"loss": 0.4172,
"step": 1060
},
{
"epoch": 1.92,
"learning_rate": 1.9210053859964093e-05,
"loss": 0.4593,
"step": 1070
},
{
"epoch": 1.94,
"learning_rate": 1.9389587073608616e-05,
"loss": 0.3924,
"step": 1080
},
{
"epoch": 1.96,
"learning_rate": 1.9569120287253142e-05,
"loss": 0.4067,
"step": 1090
},
{
"epoch": 1.97,
"learning_rate": 1.9748653500897668e-05,
"loss": 0.3906,
"step": 1100
},
{
"epoch": 1.99,
"learning_rate": 1.992818671454219e-05,
"loss": 0.3915,
"step": 1110
},
{
"epoch": 2.0,
"eval_accuracy": {
"accuracy": 0.8952679973088137
},
"eval_f1": {
"f1": 0.8895212539619177
},
"eval_loss": 0.2781514525413513,
"eval_precision": {
"precision": 0.8895590270096669
},
"eval_recall": {
"recall": 0.892156947982043
},
"eval_runtime": 99.0662,
"eval_samples_per_second": 180.041,
"eval_steps_per_second": 5.633,
"step": 1115
},
{
"epoch": 2.01,
"learning_rate": 2.0107719928186716e-05,
"loss": 0.4099,
"step": 1120
},
{
"epoch": 2.03,
"learning_rate": 2.0287253141831238e-05,
"loss": 0.4165,
"step": 1130
},
{
"epoch": 2.04,
"learning_rate": 2.0466786355475764e-05,
"loss": 0.3958,
"step": 1140
},
{
"epoch": 2.06,
"learning_rate": 2.0646319569120286e-05,
"loss": 0.4353,
"step": 1150
},
{
"epoch": 2.08,
"learning_rate": 2.0825852782764812e-05,
"loss": 0.3832,
"step": 1160
},
{
"epoch": 2.1,
"learning_rate": 2.1005385996409338e-05,
"loss": 0.3967,
"step": 1170
},
{
"epoch": 2.12,
"learning_rate": 2.118491921005386e-05,
"loss": 0.3614,
"step": 1180
},
{
"epoch": 2.13,
"learning_rate": 2.1364452423698386e-05,
"loss": 0.3665,
"step": 1190
},
{
"epoch": 2.15,
"learning_rate": 2.154398563734291e-05,
"loss": 0.3871,
"step": 1200
},
{
"epoch": 2.17,
"learning_rate": 2.1723518850987435e-05,
"loss": 0.3748,
"step": 1210
},
{
"epoch": 2.19,
"learning_rate": 2.1903052064631957e-05,
"loss": 0.396,
"step": 1220
},
{
"epoch": 2.21,
"learning_rate": 2.2082585278276483e-05,
"loss": 0.374,
"step": 1230
},
{
"epoch": 2.22,
"learning_rate": 2.2262118491921005e-05,
"loss": 0.3735,
"step": 1240
},
{
"epoch": 2.24,
"learning_rate": 2.244165170556553e-05,
"loss": 0.3894,
"step": 1250
},
{
"epoch": 2.26,
"learning_rate": 2.2621184919210057e-05,
"loss": 0.3443,
"step": 1260
},
{
"epoch": 2.28,
"learning_rate": 2.280071813285458e-05,
"loss": 0.3402,
"step": 1270
},
{
"epoch": 2.3,
"learning_rate": 2.2980251346499105e-05,
"loss": 0.4164,
"step": 1280
},
{
"epoch": 2.31,
"learning_rate": 2.3159784560143628e-05,
"loss": 0.3879,
"step": 1290
},
{
"epoch": 2.33,
"learning_rate": 2.3339317773788153e-05,
"loss": 0.3719,
"step": 1300
},
{
"epoch": 2.35,
"learning_rate": 2.3518850987432676e-05,
"loss": 0.3477,
"step": 1310
},
{
"epoch": 2.37,
"learning_rate": 2.3698384201077202e-05,
"loss": 0.3744,
"step": 1320
},
{
"epoch": 2.39,
"learning_rate": 2.3877917414721724e-05,
"loss": 0.3833,
"step": 1330
},
{
"epoch": 2.4,
"learning_rate": 2.405745062836625e-05,
"loss": 0.398,
"step": 1340
},
{
"epoch": 2.42,
"learning_rate": 2.4236983842010776e-05,
"loss": 0.3562,
"step": 1350
},
{
"epoch": 2.44,
"learning_rate": 2.4416517055655298e-05,
"loss": 0.3614,
"step": 1360
},
{
"epoch": 2.46,
"learning_rate": 2.4596050269299824e-05,
"loss": 0.315,
"step": 1370
},
{
"epoch": 2.48,
"learning_rate": 2.4775583482944346e-05,
"loss": 0.3441,
"step": 1380
},
{
"epoch": 2.49,
"learning_rate": 2.495511669658887e-05,
"loss": 0.3589,
"step": 1390
},
{
"epoch": 2.51,
"learning_rate": 2.5134649910233395e-05,
"loss": 0.3418,
"step": 1400
},
{
"epoch": 2.53,
"learning_rate": 2.5314183123877917e-05,
"loss": 0.3696,
"step": 1410
},
{
"epoch": 2.55,
"learning_rate": 2.5493716337522443e-05,
"loss": 0.3606,
"step": 1420
},
{
"epoch": 2.57,
"learning_rate": 2.5673249551166965e-05,
"loss": 0.3389,
"step": 1430
},
{
"epoch": 2.58,
"learning_rate": 2.585278276481149e-05,
"loss": 0.3375,
"step": 1440
},
{
"epoch": 2.6,
"learning_rate": 2.6032315978456017e-05,
"loss": 0.3193,
"step": 1450
},
{
"epoch": 2.62,
"learning_rate": 2.621184919210054e-05,
"loss": 0.3683,
"step": 1460
},
{
"epoch": 2.64,
"learning_rate": 2.6391382405745062e-05,
"loss": 0.3203,
"step": 1470
},
{
"epoch": 2.65,
"learning_rate": 2.6570915619389584e-05,
"loss": 0.3792,
"step": 1480
},
{
"epoch": 2.67,
"learning_rate": 2.6750448833034114e-05,
"loss": 0.3343,
"step": 1490
},
{
"epoch": 2.69,
"learning_rate": 2.6929982046678636e-05,
"loss": 0.3671,
"step": 1500
},
{
"epoch": 2.71,
"learning_rate": 2.710951526032316e-05,
"loss": 0.4002,
"step": 1510
},
{
"epoch": 2.73,
"learning_rate": 2.7289048473967688e-05,
"loss": 0.3246,
"step": 1520
},
{
"epoch": 2.74,
"learning_rate": 2.746858168761221e-05,
"loss": 0.3731,
"step": 1530
},
{
"epoch": 2.76,
"learning_rate": 2.7648114901256732e-05,
"loss": 0.3652,
"step": 1540
},
{
"epoch": 2.78,
"learning_rate": 2.7827648114901255e-05,
"loss": 0.3767,
"step": 1550
},
{
"epoch": 2.8,
"learning_rate": 2.8007181328545784e-05,
"loss": 0.3135,
"step": 1560
},
{
"epoch": 2.82,
"learning_rate": 2.8186714542190307e-05,
"loss": 0.3303,
"step": 1570
},
{
"epoch": 2.83,
"learning_rate": 2.836624775583483e-05,
"loss": 0.3485,
"step": 1580
},
{
"epoch": 2.85,
"learning_rate": 2.8545780969479358e-05,
"loss": 0.3528,
"step": 1590
},
{
"epoch": 2.87,
"learning_rate": 2.872531418312388e-05,
"loss": 0.3205,
"step": 1600
},
{
"epoch": 2.89,
"learning_rate": 2.8904847396768403e-05,
"loss": 0.3047,
"step": 1610
},
{
"epoch": 2.91,
"learning_rate": 2.9084380610412926e-05,
"loss": 0.3656,
"step": 1620
},
{
"epoch": 2.92,
"learning_rate": 2.9263913824057455e-05,
"loss": 0.3317,
"step": 1630
},
{
"epoch": 2.94,
"learning_rate": 2.9443447037701977e-05,
"loss": 0.3318,
"step": 1640
},
{
"epoch": 2.96,
"learning_rate": 2.96229802513465e-05,
"loss": 0.365,
"step": 1650
},
{
"epoch": 2.98,
"learning_rate": 2.9802513464991022e-05,
"loss": 0.3273,
"step": 1660
},
{
"epoch": 3.0,
"learning_rate": 2.998204667863555e-05,
"loss": 0.3246,
"step": 1670
},
{
"epoch": 3.0,
"eval_accuracy": {
"accuracy": 0.9295245570755775
},
"eval_f1": {
"f1": 0.9243811536773696
},
"eval_loss": 0.19212597608566284,
"eval_precision": {
"precision": 0.9273415557649412
},
"eval_recall": {
"recall": 0.9219909309089409
},
"eval_runtime": 99.0388,
"eval_samples_per_second": 180.091,
"eval_steps_per_second": 5.634,
"step": 1672
},
{
"epoch": 3.01,
"learning_rate": 3.0161579892280074e-05,
"loss": 0.3135,
"step": 1680
},
{
"epoch": 3.03,
"learning_rate": 3.0341113105924596e-05,
"loss": 0.3145,
"step": 1690
},
{
"epoch": 3.05,
"learning_rate": 3.0520646319569125e-05,
"loss": 0.3395,
"step": 1700
},
{
"epoch": 3.07,
"learning_rate": 3.070017953321365e-05,
"loss": 0.2927,
"step": 1710
},
{
"epoch": 3.09,
"learning_rate": 3.087971274685817e-05,
"loss": 0.3363,
"step": 1720
},
{
"epoch": 3.1,
"learning_rate": 3.105924596050269e-05,
"loss": 0.3392,
"step": 1730
},
{
"epoch": 3.12,
"learning_rate": 3.123877917414722e-05,
"loss": 0.3279,
"step": 1740
},
{
"epoch": 3.14,
"learning_rate": 3.1418312387791744e-05,
"loss": 0.3194,
"step": 1750
},
{
"epoch": 3.16,
"learning_rate": 3.159784560143627e-05,
"loss": 0.3206,
"step": 1760
},
{
"epoch": 3.17,
"learning_rate": 3.1777378815080796e-05,
"loss": 0.3246,
"step": 1770
},
{
"epoch": 3.19,
"learning_rate": 3.195691202872532e-05,
"loss": 0.3155,
"step": 1780
},
{
"epoch": 3.21,
"learning_rate": 3.213644524236984e-05,
"loss": 0.301,
"step": 1790
},
{
"epoch": 3.23,
"learning_rate": 3.231597845601436e-05,
"loss": 0.3287,
"step": 1800
},
{
"epoch": 3.25,
"learning_rate": 3.249551166965889e-05,
"loss": 0.3282,
"step": 1810
},
{
"epoch": 3.26,
"learning_rate": 3.2675044883303415e-05,
"loss": 0.2872,
"step": 1820
},
{
"epoch": 3.28,
"learning_rate": 3.285457809694794e-05,
"loss": 0.3003,
"step": 1830
},
{
"epoch": 3.3,
"learning_rate": 3.3034111310592466e-05,
"loss": 0.3009,
"step": 1840
},
{
"epoch": 3.32,
"learning_rate": 3.321364452423699e-05,
"loss": 0.325,
"step": 1850
},
{
"epoch": 3.34,
"learning_rate": 3.339317773788151e-05,
"loss": 0.3308,
"step": 1860
},
{
"epoch": 3.35,
"learning_rate": 3.3572710951526034e-05,
"loss": 0.3175,
"step": 1870
},
{
"epoch": 3.37,
"learning_rate": 3.375224416517056e-05,
"loss": 0.291,
"step": 1880
},
{
"epoch": 3.39,
"learning_rate": 3.3931777378815085e-05,
"loss": 0.2936,
"step": 1890
},
{
"epoch": 3.41,
"learning_rate": 3.411131059245961e-05,
"loss": 0.3304,
"step": 1900
},
{
"epoch": 3.43,
"learning_rate": 3.429084380610413e-05,
"loss": 0.331,
"step": 1910
},
{
"epoch": 3.44,
"learning_rate": 3.447037701974866e-05,
"loss": 0.3158,
"step": 1920
},
{
"epoch": 3.46,
"learning_rate": 3.464991023339318e-05,
"loss": 0.3054,
"step": 1930
},
{
"epoch": 3.48,
"learning_rate": 3.4829443447037704e-05,
"loss": 0.3063,
"step": 1940
},
{
"epoch": 3.5,
"learning_rate": 3.500897666068223e-05,
"loss": 0.279,
"step": 1950
},
{
"epoch": 3.52,
"learning_rate": 3.5188509874326756e-05,
"loss": 0.2986,
"step": 1960
},
{
"epoch": 3.53,
"learning_rate": 3.536804308797128e-05,
"loss": 0.3184,
"step": 1970
},
{
"epoch": 3.55,
"learning_rate": 3.55475763016158e-05,
"loss": 0.3623,
"step": 1980
},
{
"epoch": 3.57,
"learning_rate": 3.572710951526032e-05,
"loss": 0.3178,
"step": 1990
},
{
"epoch": 3.59,
"learning_rate": 3.5906642728904846e-05,
"loss": 0.2553,
"step": 2000
},
{
"epoch": 3.61,
"learning_rate": 3.6086175942549375e-05,
"loss": 0.3116,
"step": 2010
},
{
"epoch": 3.62,
"learning_rate": 3.62657091561939e-05,
"loss": 0.3278,
"step": 2020
},
{
"epoch": 3.64,
"learning_rate": 3.644524236983842e-05,
"loss": 0.311,
"step": 2030
},
{
"epoch": 3.66,
"learning_rate": 3.662477558348294e-05,
"loss": 0.3116,
"step": 2040
},
{
"epoch": 3.68,
"learning_rate": 3.6804308797127465e-05,
"loss": 0.3087,
"step": 2050
},
{
"epoch": 3.7,
"learning_rate": 3.6983842010771994e-05,
"loss": 0.3091,
"step": 2060
},
{
"epoch": 3.71,
"learning_rate": 3.7163375224416516e-05,
"loss": 0.2855,
"step": 2070
},
{
"epoch": 3.73,
"learning_rate": 3.734290843806104e-05,
"loss": 0.313,
"step": 2080
},
{
"epoch": 3.75,
"learning_rate": 3.752244165170557e-05,
"loss": 0.2992,
"step": 2090
},
{
"epoch": 3.77,
"learning_rate": 3.770197486535009e-05,
"loss": 0.2946,
"step": 2100
},
{
"epoch": 3.78,
"learning_rate": 3.788150807899461e-05,
"loss": 0.3034,
"step": 2110
},
{
"epoch": 3.8,
"learning_rate": 3.8061041292639135e-05,
"loss": 0.2868,
"step": 2120
},
{
"epoch": 3.82,
"learning_rate": 3.8240574506283664e-05,
"loss": 0.2818,
"step": 2130
},
{
"epoch": 3.84,
"learning_rate": 3.842010771992819e-05,
"loss": 0.2943,
"step": 2140
},
{
"epoch": 3.86,
"learning_rate": 3.859964093357271e-05,
"loss": 0.3166,
"step": 2150
},
{
"epoch": 3.87,
"learning_rate": 3.877917414721723e-05,
"loss": 0.2947,
"step": 2160
},
{
"epoch": 3.89,
"learning_rate": 3.895870736086176e-05,
"loss": 0.2764,
"step": 2170
},
{
"epoch": 3.91,
"learning_rate": 3.9138240574506283e-05,
"loss": 0.278,
"step": 2180
},
{
"epoch": 3.93,
"learning_rate": 3.9317773788150806e-05,
"loss": 0.3091,
"step": 2190
},
{
"epoch": 3.95,
"learning_rate": 3.9497307001795335e-05,
"loss": 0.3336,
"step": 2200
},
{
"epoch": 3.96,
"learning_rate": 3.967684021543986e-05,
"loss": 0.3256,
"step": 2210
},
{
"epoch": 3.98,
"learning_rate": 3.985637342908438e-05,
"loss": 0.2664,
"step": 2220
},
{
"epoch": 4.0,
"learning_rate": 4.00359066427289e-05,
"loss": 0.2819,
"step": 2230
},
{
"epoch": 4.0,
"eval_accuracy": {
"accuracy": 0.9389437093518727
},
"eval_f1": {
"f1": 0.934636026587255
},
"eval_loss": 0.16309776902198792,
"eval_precision": {
"precision": 0.9384931858190604
},
"eval_recall": {
"recall": 0.9317771824858079
},
"eval_runtime": 98.5849,
"eval_samples_per_second": 180.92,
"eval_steps_per_second": 5.66,
"step": 2230
},
{
"epoch": 4.02,
"learning_rate": 4.021543985637343e-05,
"loss": 0.2725,
"step": 2240
},
{
"epoch": 4.04,
"learning_rate": 4.0394973070017954e-05,
"loss": 0.3239,
"step": 2250
},
{
"epoch": 4.05,
"learning_rate": 4.0574506283662476e-05,
"loss": 0.2761,
"step": 2260
},
{
"epoch": 4.07,
"learning_rate": 4.0754039497307006e-05,
"loss": 0.275,
"step": 2270
},
{
"epoch": 4.09,
"learning_rate": 4.093357271095153e-05,
"loss": 0.2789,
"step": 2280
},
{
"epoch": 4.11,
"learning_rate": 4.111310592459605e-05,
"loss": 0.2702,
"step": 2290
},
{
"epoch": 4.13,
"learning_rate": 4.129263913824057e-05,
"loss": 0.3244,
"step": 2300
},
{
"epoch": 4.14,
"learning_rate": 4.14721723518851e-05,
"loss": 0.3254,
"step": 2310
},
{
"epoch": 4.16,
"learning_rate": 4.1651705565529625e-05,
"loss": 0.2969,
"step": 2320
},
{
"epoch": 4.18,
"learning_rate": 4.183123877917415e-05,
"loss": 0.2545,
"step": 2330
},
{
"epoch": 4.2,
"learning_rate": 4.2010771992818676e-05,
"loss": 0.2307,
"step": 2340
},
{
"epoch": 4.22,
"learning_rate": 4.21903052064632e-05,
"loss": 0.3132,
"step": 2350
},
{
"epoch": 4.23,
"learning_rate": 4.236983842010772e-05,
"loss": 0.3017,
"step": 2360
},
{
"epoch": 4.25,
"learning_rate": 4.2549371633752244e-05,
"loss": 0.2885,
"step": 2370
},
{
"epoch": 4.27,
"learning_rate": 4.272890484739677e-05,
"loss": 0.3085,
"step": 2380
},
{
"epoch": 4.29,
"learning_rate": 4.2908438061041295e-05,
"loss": 0.3079,
"step": 2390
},
{
"epoch": 4.3,
"learning_rate": 4.308797127468582e-05,
"loss": 0.2749,
"step": 2400
},
{
"epoch": 4.32,
"learning_rate": 4.326750448833034e-05,
"loss": 0.2863,
"step": 2410
},
{
"epoch": 4.34,
"learning_rate": 4.344703770197487e-05,
"loss": 0.2523,
"step": 2420
},
{
"epoch": 4.36,
"learning_rate": 4.362657091561939e-05,
"loss": 0.2441,
"step": 2430
},
{
"epoch": 4.38,
"learning_rate": 4.3806104129263914e-05,
"loss": 0.3174,
"step": 2440
},
{
"epoch": 4.39,
"learning_rate": 4.398563734290844e-05,
"loss": 0.2938,
"step": 2450
},
{
"epoch": 4.41,
"learning_rate": 4.4165170556552966e-05,
"loss": 0.2632,
"step": 2460
},
{
"epoch": 4.43,
"learning_rate": 4.434470377019749e-05,
"loss": 0.2924,
"step": 2470
},
{
"epoch": 4.45,
"learning_rate": 4.452423698384201e-05,
"loss": 0.3018,
"step": 2480
},
{
"epoch": 4.47,
"learning_rate": 4.470377019748654e-05,
"loss": 0.2488,
"step": 2490
},
{
"epoch": 4.48,
"learning_rate": 4.488330341113106e-05,
"loss": 0.2659,
"step": 2500
},
{
"epoch": 4.5,
"learning_rate": 4.5062836624775585e-05,
"loss": 0.2689,
"step": 2510
},
{
"epoch": 4.52,
"learning_rate": 4.5242369838420114e-05,
"loss": 0.2702,
"step": 2520
},
{
"epoch": 4.54,
"learning_rate": 4.5421903052064636e-05,
"loss": 0.2695,
"step": 2530
},
{
"epoch": 4.56,
"learning_rate": 4.560143626570916e-05,
"loss": 0.2629,
"step": 2540
},
{
"epoch": 4.57,
"learning_rate": 4.578096947935368e-05,
"loss": 0.2931,
"step": 2550
},
{
"epoch": 4.59,
"learning_rate": 4.596050269299821e-05,
"loss": 0.2865,
"step": 2560
},
{
"epoch": 4.61,
"learning_rate": 4.614003590664273e-05,
"loss": 0.2751,
"step": 2570
},
{
"epoch": 4.63,
"learning_rate": 4.6319569120287255e-05,
"loss": 0.2565,
"step": 2580
},
{
"epoch": 4.65,
"learning_rate": 4.6499102333931784e-05,
"loss": 0.2589,
"step": 2590
},
{
"epoch": 4.66,
"learning_rate": 4.667863554757631e-05,
"loss": 0.2501,
"step": 2600
},
{
"epoch": 4.68,
"learning_rate": 4.685816876122083e-05,
"loss": 0.2524,
"step": 2610
},
{
"epoch": 4.7,
"learning_rate": 4.703770197486535e-05,
"loss": 0.2596,
"step": 2620
},
{
"epoch": 4.72,
"learning_rate": 4.721723518850988e-05,
"loss": 0.2567,
"step": 2630
},
{
"epoch": 4.74,
"learning_rate": 4.7396768402154403e-05,
"loss": 0.2886,
"step": 2640
},
{
"epoch": 4.75,
"learning_rate": 4.7576301615798926e-05,
"loss": 0.2879,
"step": 2650
},
{
"epoch": 4.77,
"learning_rate": 4.775583482944345e-05,
"loss": 0.2703,
"step": 2660
},
{
"epoch": 4.79,
"learning_rate": 4.793536804308798e-05,
"loss": 0.3013,
"step": 2670
},
{
"epoch": 4.81,
"learning_rate": 4.81149012567325e-05,
"loss": 0.2801,
"step": 2680
},
{
"epoch": 4.83,
"learning_rate": 4.829443447037702e-05,
"loss": 0.2886,
"step": 2690
},
{
"epoch": 4.84,
"learning_rate": 4.847396768402155e-05,
"loss": 0.3084,
"step": 2700
},
{
"epoch": 4.86,
"learning_rate": 4.8653500897666074e-05,
"loss": 0.2886,
"step": 2710
},
{
"epoch": 4.88,
"learning_rate": 4.8833034111310596e-05,
"loss": 0.2678,
"step": 2720
},
{
"epoch": 4.9,
"learning_rate": 4.901256732495512e-05,
"loss": 0.2628,
"step": 2730
},
{
"epoch": 4.91,
"learning_rate": 4.919210053859965e-05,
"loss": 0.2834,
"step": 2740
},
{
"epoch": 4.93,
"learning_rate": 4.937163375224417e-05,
"loss": 0.2775,
"step": 2750
},
{
"epoch": 4.95,
"learning_rate": 4.955116696588869e-05,
"loss": 0.2987,
"step": 2760
},
{
"epoch": 4.97,
"learning_rate": 4.9730700179533215e-05,
"loss": 0.2409,
"step": 2770
},
{
"epoch": 4.99,
"learning_rate": 4.991023339317774e-05,
"loss": 0.3022,
"step": 2780
},
{
"epoch": 5.0,
"eval_accuracy": {
"accuracy": 0.9471294012110338
},
"eval_f1": {
"f1": 0.944197644580418
},
"eval_loss": 0.1480465531349182,
"eval_precision": {
"precision": 0.9443621962369058
},
"eval_recall": {
"recall": 0.9440973623586151
},
"eval_runtime": 99.3848,
"eval_samples_per_second": 179.464,
"eval_steps_per_second": 5.615,
"step": 2787
}
],
"logging_steps": 10,
"max_steps": 27850,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"total_flos": 8.866626753374208e+18,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}