vit-Facial-Expression-Recognition / trainer_state.json
motheecreator's picture
End of training
ea3ea91 verified
raw
history blame contribute delete
No virus
82.4 kB
{
"best_metric": 0.7444126074498567,
"best_model_checkpoint": "vit-Facial-Expression-Recognition/checkpoint-1962",
"epoch": 9.9980894153611,
"eval_steps": 500,
"global_step": 6540,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 1.5290519877675841e-06,
"loss": 1.9371,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 3.0581039755351682e-06,
"loss": 1.8225,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 4.587155963302753e-06,
"loss": 1.4076,
"step": 30
},
{
"epoch": 0.06,
"learning_rate": 6.1162079510703365e-06,
"loss": 1.5662,
"step": 40
},
{
"epoch": 0.08,
"learning_rate": 7.645259938837921e-06,
"loss": 1.3985,
"step": 50
},
{
"epoch": 0.09,
"learning_rate": 9.174311926605506e-06,
"loss": 1.1727,
"step": 60
},
{
"epoch": 0.11,
"learning_rate": 1.070336391437309e-05,
"loss": 1.1874,
"step": 70
},
{
"epoch": 0.12,
"learning_rate": 1.2232415902140673e-05,
"loss": 1.1256,
"step": 80
},
{
"epoch": 0.14,
"learning_rate": 1.3761467889908258e-05,
"loss": 1.0438,
"step": 90
},
{
"epoch": 0.15,
"learning_rate": 1.5290519877675842e-05,
"loss": 1.1966,
"step": 100
},
{
"epoch": 0.17,
"learning_rate": 1.6819571865443427e-05,
"loss": 1.0475,
"step": 110
},
{
"epoch": 0.18,
"learning_rate": 1.834862385321101e-05,
"loss": 0.9658,
"step": 120
},
{
"epoch": 0.2,
"learning_rate": 1.9877675840978592e-05,
"loss": 0.959,
"step": 130
},
{
"epoch": 0.21,
"learning_rate": 2.140672782874618e-05,
"loss": 0.7963,
"step": 140
},
{
"epoch": 0.23,
"learning_rate": 2.2935779816513765e-05,
"loss": 0.9615,
"step": 150
},
{
"epoch": 0.24,
"learning_rate": 2.4464831804281346e-05,
"loss": 0.8296,
"step": 160
},
{
"epoch": 0.26,
"learning_rate": 2.5993883792048927e-05,
"loss": 0.8144,
"step": 170
},
{
"epoch": 0.28,
"learning_rate": 2.7522935779816515e-05,
"loss": 0.9023,
"step": 180
},
{
"epoch": 0.29,
"learning_rate": 2.90519877675841e-05,
"loss": 0.9142,
"step": 190
},
{
"epoch": 0.31,
"learning_rate": 3.0581039755351684e-05,
"loss": 0.9456,
"step": 200
},
{
"epoch": 0.32,
"learning_rate": 3.211009174311927e-05,
"loss": 0.8358,
"step": 210
},
{
"epoch": 0.34,
"learning_rate": 3.363914373088685e-05,
"loss": 0.7678,
"step": 220
},
{
"epoch": 0.35,
"learning_rate": 3.516819571865443e-05,
"loss": 0.8491,
"step": 230
},
{
"epoch": 0.37,
"learning_rate": 3.669724770642202e-05,
"loss": 0.7184,
"step": 240
},
{
"epoch": 0.38,
"learning_rate": 3.822629969418961e-05,
"loss": 0.767,
"step": 250
},
{
"epoch": 0.4,
"learning_rate": 3.9755351681957185e-05,
"loss": 0.7829,
"step": 260
},
{
"epoch": 0.41,
"learning_rate": 4.1284403669724776e-05,
"loss": 0.76,
"step": 270
},
{
"epoch": 0.43,
"learning_rate": 4.281345565749236e-05,
"loss": 0.8151,
"step": 280
},
{
"epoch": 0.44,
"learning_rate": 4.434250764525994e-05,
"loss": 0.7488,
"step": 290
},
{
"epoch": 0.46,
"learning_rate": 4.587155963302753e-05,
"loss": 0.6966,
"step": 300
},
{
"epoch": 0.47,
"learning_rate": 4.740061162079511e-05,
"loss": 0.9042,
"step": 310
},
{
"epoch": 0.49,
"learning_rate": 4.892966360856269e-05,
"loss": 0.7496,
"step": 320
},
{
"epoch": 0.5,
"learning_rate": 4.994903160040775e-05,
"loss": 0.7599,
"step": 330
},
{
"epoch": 0.52,
"learning_rate": 4.977913693510024e-05,
"loss": 0.8631,
"step": 340
},
{
"epoch": 0.53,
"learning_rate": 4.9609242269792734e-05,
"loss": 0.8586,
"step": 350
},
{
"epoch": 0.55,
"learning_rate": 4.943934760448522e-05,
"loss": 0.7269,
"step": 360
},
{
"epoch": 0.57,
"learning_rate": 4.926945293917771e-05,
"loss": 0.8573,
"step": 370
},
{
"epoch": 0.58,
"learning_rate": 4.9099558273870206e-05,
"loss": 0.7636,
"step": 380
},
{
"epoch": 0.6,
"learning_rate": 4.892966360856269e-05,
"loss": 0.7227,
"step": 390
},
{
"epoch": 0.61,
"learning_rate": 4.8759768943255185e-05,
"loss": 0.7689,
"step": 400
},
{
"epoch": 0.63,
"learning_rate": 4.858987427794767e-05,
"loss": 0.6832,
"step": 410
},
{
"epoch": 0.64,
"learning_rate": 4.8419979612640164e-05,
"loss": 0.7225,
"step": 420
},
{
"epoch": 0.66,
"learning_rate": 4.8250084947332657e-05,
"loss": 0.8064,
"step": 430
},
{
"epoch": 0.67,
"learning_rate": 4.808019028202514e-05,
"loss": 0.6557,
"step": 440
},
{
"epoch": 0.69,
"learning_rate": 4.7910295616717635e-05,
"loss": 0.7788,
"step": 450
},
{
"epoch": 0.7,
"learning_rate": 4.774040095141013e-05,
"loss": 0.7525,
"step": 460
},
{
"epoch": 0.72,
"learning_rate": 4.7570506286102614e-05,
"loss": 0.7951,
"step": 470
},
{
"epoch": 0.73,
"learning_rate": 4.740061162079511e-05,
"loss": 0.8923,
"step": 480
},
{
"epoch": 0.75,
"learning_rate": 4.72307169554876e-05,
"loss": 0.7103,
"step": 490
},
{
"epoch": 0.76,
"learning_rate": 4.706082229018009e-05,
"loss": 0.6821,
"step": 500
},
{
"epoch": 0.78,
"learning_rate": 4.6890927624872586e-05,
"loss": 0.7814,
"step": 510
},
{
"epoch": 0.79,
"learning_rate": 4.672103295956507e-05,
"loss": 0.7257,
"step": 520
},
{
"epoch": 0.81,
"learning_rate": 4.6551138294257565e-05,
"loss": 0.7441,
"step": 530
},
{
"epoch": 0.83,
"learning_rate": 4.638124362895006e-05,
"loss": 0.7044,
"step": 540
},
{
"epoch": 0.84,
"learning_rate": 4.6211348963642544e-05,
"loss": 0.779,
"step": 550
},
{
"epoch": 0.86,
"learning_rate": 4.604145429833504e-05,
"loss": 0.8438,
"step": 560
},
{
"epoch": 0.87,
"learning_rate": 4.587155963302753e-05,
"loss": 0.7342,
"step": 570
},
{
"epoch": 0.89,
"learning_rate": 4.5701664967720016e-05,
"loss": 0.6886,
"step": 580
},
{
"epoch": 0.9,
"learning_rate": 4.553177030241251e-05,
"loss": 0.7733,
"step": 590
},
{
"epoch": 0.92,
"learning_rate": 4.5361875637104995e-05,
"loss": 0.7655,
"step": 600
},
{
"epoch": 0.93,
"learning_rate": 4.519198097179749e-05,
"loss": 0.6929,
"step": 610
},
{
"epoch": 0.95,
"learning_rate": 4.502208630648998e-05,
"loss": 0.788,
"step": 620
},
{
"epoch": 0.96,
"learning_rate": 4.4852191641182466e-05,
"loss": 0.6691,
"step": 630
},
{
"epoch": 0.98,
"learning_rate": 4.468229697587496e-05,
"loss": 0.6881,
"step": 640
},
{
"epoch": 0.99,
"learning_rate": 4.451240231056745e-05,
"loss": 0.7175,
"step": 650
},
{
"epoch": 1.0,
"eval_accuracy": 0.7308500477554919,
"eval_loss": 0.7081200480461121,
"eval_runtime": 48.365,
"eval_samples_per_second": 108.24,
"eval_steps_per_second": 13.543,
"step": 654
},
{
"epoch": 1.01,
"learning_rate": 4.434250764525994e-05,
"loss": 0.6844,
"step": 660
},
{
"epoch": 1.02,
"learning_rate": 4.417261297995243e-05,
"loss": 0.7542,
"step": 670
},
{
"epoch": 1.04,
"learning_rate": 4.400271831464492e-05,
"loss": 0.6111,
"step": 680
},
{
"epoch": 1.05,
"learning_rate": 4.383282364933741e-05,
"loss": 0.6169,
"step": 690
},
{
"epoch": 1.07,
"learning_rate": 4.36629289840299e-05,
"loss": 0.7111,
"step": 700
},
{
"epoch": 1.09,
"learning_rate": 4.349303431872239e-05,
"loss": 0.732,
"step": 710
},
{
"epoch": 1.1,
"learning_rate": 4.332313965341488e-05,
"loss": 0.623,
"step": 720
},
{
"epoch": 1.12,
"learning_rate": 4.3153244988107375e-05,
"loss": 0.6272,
"step": 730
},
{
"epoch": 1.13,
"learning_rate": 4.298335032279987e-05,
"loss": 0.6331,
"step": 740
},
{
"epoch": 1.15,
"learning_rate": 4.281345565749236e-05,
"loss": 0.6036,
"step": 750
},
{
"epoch": 1.16,
"learning_rate": 4.264356099218485e-05,
"loss": 0.6559,
"step": 760
},
{
"epoch": 1.18,
"learning_rate": 4.247366632687734e-05,
"loss": 0.5873,
"step": 770
},
{
"epoch": 1.19,
"learning_rate": 4.230377166156983e-05,
"loss": 0.6016,
"step": 780
},
{
"epoch": 1.21,
"learning_rate": 4.213387699626232e-05,
"loss": 0.6399,
"step": 790
},
{
"epoch": 1.22,
"learning_rate": 4.196398233095481e-05,
"loss": 0.6719,
"step": 800
},
{
"epoch": 1.24,
"learning_rate": 4.1794087665647304e-05,
"loss": 0.5458,
"step": 810
},
{
"epoch": 1.25,
"learning_rate": 4.162419300033979e-05,
"loss": 0.6167,
"step": 820
},
{
"epoch": 1.27,
"learning_rate": 4.145429833503228e-05,
"loss": 0.6865,
"step": 830
},
{
"epoch": 1.28,
"learning_rate": 4.1284403669724776e-05,
"loss": 0.6527,
"step": 840
},
{
"epoch": 1.3,
"learning_rate": 4.111450900441726e-05,
"loss": 0.5855,
"step": 850
},
{
"epoch": 1.31,
"learning_rate": 4.0944614339109755e-05,
"loss": 0.5976,
"step": 860
},
{
"epoch": 1.33,
"learning_rate": 4.077471967380224e-05,
"loss": 0.6886,
"step": 870
},
{
"epoch": 1.35,
"learning_rate": 4.0604825008494734e-05,
"loss": 0.6992,
"step": 880
},
{
"epoch": 1.36,
"learning_rate": 4.043493034318723e-05,
"loss": 0.6413,
"step": 890
},
{
"epoch": 1.38,
"learning_rate": 4.026503567787971e-05,
"loss": 0.6227,
"step": 900
},
{
"epoch": 1.39,
"learning_rate": 4.0095141012572206e-05,
"loss": 0.611,
"step": 910
},
{
"epoch": 1.41,
"learning_rate": 3.99252463472647e-05,
"loss": 0.5908,
"step": 920
},
{
"epoch": 1.42,
"learning_rate": 3.9755351681957185e-05,
"loss": 0.6177,
"step": 930
},
{
"epoch": 1.44,
"learning_rate": 3.958545701664968e-05,
"loss": 0.6077,
"step": 940
},
{
"epoch": 1.45,
"learning_rate": 3.941556235134217e-05,
"loss": 0.6321,
"step": 950
},
{
"epoch": 1.47,
"learning_rate": 3.9245667686034656e-05,
"loss": 0.5838,
"step": 960
},
{
"epoch": 1.48,
"learning_rate": 3.907577302072715e-05,
"loss": 0.6619,
"step": 970
},
{
"epoch": 1.5,
"learning_rate": 3.890587835541964e-05,
"loss": 0.5823,
"step": 980
},
{
"epoch": 1.51,
"learning_rate": 3.8735983690112135e-05,
"loss": 0.5496,
"step": 990
},
{
"epoch": 1.53,
"learning_rate": 3.856608902480463e-05,
"loss": 0.6632,
"step": 1000
},
{
"epoch": 1.54,
"learning_rate": 3.8396194359497114e-05,
"loss": 0.5744,
"step": 1010
},
{
"epoch": 1.56,
"learning_rate": 3.822629969418961e-05,
"loss": 0.6259,
"step": 1020
},
{
"epoch": 1.57,
"learning_rate": 3.80564050288821e-05,
"loss": 0.6156,
"step": 1030
},
{
"epoch": 1.59,
"learning_rate": 3.7886510363574586e-05,
"loss": 0.5593,
"step": 1040
},
{
"epoch": 1.6,
"learning_rate": 3.771661569826708e-05,
"loss": 0.6951,
"step": 1050
},
{
"epoch": 1.62,
"learning_rate": 3.7546721032959565e-05,
"loss": 0.6099,
"step": 1060
},
{
"epoch": 1.64,
"learning_rate": 3.737682636765206e-05,
"loss": 0.6019,
"step": 1070
},
{
"epoch": 1.65,
"learning_rate": 3.720693170234455e-05,
"loss": 0.5226,
"step": 1080
},
{
"epoch": 1.67,
"learning_rate": 3.7037037037037037e-05,
"loss": 0.6539,
"step": 1090
},
{
"epoch": 1.68,
"learning_rate": 3.686714237172953e-05,
"loss": 0.6031,
"step": 1100
},
{
"epoch": 1.7,
"learning_rate": 3.669724770642202e-05,
"loss": 0.6356,
"step": 1110
},
{
"epoch": 1.71,
"learning_rate": 3.652735304111451e-05,
"loss": 0.6456,
"step": 1120
},
{
"epoch": 1.73,
"learning_rate": 3.6357458375807e-05,
"loss": 0.5222,
"step": 1130
},
{
"epoch": 1.74,
"learning_rate": 3.6187563710499494e-05,
"loss": 0.5715,
"step": 1140
},
{
"epoch": 1.76,
"learning_rate": 3.601766904519198e-05,
"loss": 0.6142,
"step": 1150
},
{
"epoch": 1.77,
"learning_rate": 3.584777437988447e-05,
"loss": 0.6794,
"step": 1160
},
{
"epoch": 1.79,
"learning_rate": 3.567787971457696e-05,
"loss": 0.7228,
"step": 1170
},
{
"epoch": 1.8,
"learning_rate": 3.550798504926945e-05,
"loss": 0.6374,
"step": 1180
},
{
"epoch": 1.82,
"learning_rate": 3.5338090383961945e-05,
"loss": 0.6078,
"step": 1190
},
{
"epoch": 1.83,
"learning_rate": 3.516819571865443e-05,
"loss": 0.6115,
"step": 1200
},
{
"epoch": 1.85,
"learning_rate": 3.4998301053346924e-05,
"loss": 0.6853,
"step": 1210
},
{
"epoch": 1.86,
"learning_rate": 3.482840638803942e-05,
"loss": 0.5883,
"step": 1220
},
{
"epoch": 1.88,
"learning_rate": 3.465851172273191e-05,
"loss": 0.6143,
"step": 1230
},
{
"epoch": 1.9,
"learning_rate": 3.44886170574244e-05,
"loss": 0.6067,
"step": 1240
},
{
"epoch": 1.91,
"learning_rate": 3.431872239211689e-05,
"loss": 0.64,
"step": 1250
},
{
"epoch": 1.93,
"learning_rate": 3.414882772680938e-05,
"loss": 0.6043,
"step": 1260
},
{
"epoch": 1.94,
"learning_rate": 3.3978933061501874e-05,
"loss": 0.5755,
"step": 1270
},
{
"epoch": 1.96,
"learning_rate": 3.380903839619436e-05,
"loss": 0.6534,
"step": 1280
},
{
"epoch": 1.97,
"learning_rate": 3.363914373088685e-05,
"loss": 0.5583,
"step": 1290
},
{
"epoch": 1.99,
"learning_rate": 3.3469249065579346e-05,
"loss": 0.6952,
"step": 1300
},
{
"epoch": 2.0,
"eval_accuracy": 0.7379178605539637,
"eval_loss": 0.6931169629096985,
"eval_runtime": 48.247,
"eval_samples_per_second": 108.504,
"eval_steps_per_second": 13.576,
"step": 1308
},
{
"epoch": 2.0,
"learning_rate": 3.329935440027183e-05,
"loss": 0.5479,
"step": 1310
},
{
"epoch": 2.02,
"learning_rate": 3.3129459734964325e-05,
"loss": 0.523,
"step": 1320
},
{
"epoch": 2.03,
"learning_rate": 3.295956506965682e-05,
"loss": 0.4421,
"step": 1330
},
{
"epoch": 2.05,
"learning_rate": 3.2789670404349304e-05,
"loss": 0.4887,
"step": 1340
},
{
"epoch": 2.06,
"learning_rate": 3.26197757390418e-05,
"loss": 0.4665,
"step": 1350
},
{
"epoch": 2.08,
"learning_rate": 3.244988107373428e-05,
"loss": 0.5767,
"step": 1360
},
{
"epoch": 2.09,
"learning_rate": 3.2279986408426776e-05,
"loss": 0.4944,
"step": 1370
},
{
"epoch": 2.11,
"learning_rate": 3.211009174311927e-05,
"loss": 0.4159,
"step": 1380
},
{
"epoch": 2.12,
"learning_rate": 3.1940197077811755e-05,
"loss": 0.3825,
"step": 1390
},
{
"epoch": 2.14,
"learning_rate": 3.177030241250425e-05,
"loss": 0.46,
"step": 1400
},
{
"epoch": 2.16,
"learning_rate": 3.160040774719674e-05,
"loss": 0.4904,
"step": 1410
},
{
"epoch": 2.17,
"learning_rate": 3.1430513081889227e-05,
"loss": 0.5993,
"step": 1420
},
{
"epoch": 2.19,
"learning_rate": 3.126061841658172e-05,
"loss": 0.5107,
"step": 1430
},
{
"epoch": 2.2,
"learning_rate": 3.1090723751274206e-05,
"loss": 0.4616,
"step": 1440
},
{
"epoch": 2.22,
"learning_rate": 3.09208290859667e-05,
"loss": 0.4318,
"step": 1450
},
{
"epoch": 2.23,
"learning_rate": 3.075093442065919e-05,
"loss": 0.4934,
"step": 1460
},
{
"epoch": 2.25,
"learning_rate": 3.0581039755351684e-05,
"loss": 0.4119,
"step": 1470
},
{
"epoch": 2.26,
"learning_rate": 3.0411145090044174e-05,
"loss": 0.5154,
"step": 1480
},
{
"epoch": 2.28,
"learning_rate": 3.0241250424736666e-05,
"loss": 0.5126,
"step": 1490
},
{
"epoch": 2.29,
"learning_rate": 3.0071355759429153e-05,
"loss": 0.429,
"step": 1500
},
{
"epoch": 2.31,
"learning_rate": 2.9901461094121645e-05,
"loss": 0.5008,
"step": 1510
},
{
"epoch": 2.32,
"learning_rate": 2.9731566428814138e-05,
"loss": 0.4074,
"step": 1520
},
{
"epoch": 2.34,
"learning_rate": 2.9561671763506628e-05,
"loss": 0.4563,
"step": 1530
},
{
"epoch": 2.35,
"learning_rate": 2.939177709819912e-05,
"loss": 0.5493,
"step": 1540
},
{
"epoch": 2.37,
"learning_rate": 2.9221882432891607e-05,
"loss": 0.5255,
"step": 1550
},
{
"epoch": 2.38,
"learning_rate": 2.90519877675841e-05,
"loss": 0.4812,
"step": 1560
},
{
"epoch": 2.4,
"learning_rate": 2.8882093102276592e-05,
"loss": 0.4576,
"step": 1570
},
{
"epoch": 2.41,
"learning_rate": 2.871219843696908e-05,
"loss": 0.5143,
"step": 1580
},
{
"epoch": 2.43,
"learning_rate": 2.854230377166157e-05,
"loss": 0.4439,
"step": 1590
},
{
"epoch": 2.45,
"learning_rate": 2.8372409106354064e-05,
"loss": 0.4637,
"step": 1600
},
{
"epoch": 2.46,
"learning_rate": 2.820251444104655e-05,
"loss": 0.4575,
"step": 1610
},
{
"epoch": 2.48,
"learning_rate": 2.8032619775739043e-05,
"loss": 0.4955,
"step": 1620
},
{
"epoch": 2.49,
"learning_rate": 2.7862725110431533e-05,
"loss": 0.446,
"step": 1630
},
{
"epoch": 2.51,
"learning_rate": 2.7692830445124026e-05,
"loss": 0.5241,
"step": 1640
},
{
"epoch": 2.52,
"learning_rate": 2.7522935779816515e-05,
"loss": 0.4872,
"step": 1650
},
{
"epoch": 2.54,
"learning_rate": 2.7353041114509004e-05,
"loss": 0.4526,
"step": 1660
},
{
"epoch": 2.55,
"learning_rate": 2.7183146449201497e-05,
"loss": 0.513,
"step": 1670
},
{
"epoch": 2.57,
"learning_rate": 2.701325178389399e-05,
"loss": 0.5036,
"step": 1680
},
{
"epoch": 2.58,
"learning_rate": 2.6843357118586476e-05,
"loss": 0.4714,
"step": 1690
},
{
"epoch": 2.6,
"learning_rate": 2.667346245327897e-05,
"loss": 0.4228,
"step": 1700
},
{
"epoch": 2.61,
"learning_rate": 2.6503567787971462e-05,
"loss": 0.4916,
"step": 1710
},
{
"epoch": 2.63,
"learning_rate": 2.6333673122663948e-05,
"loss": 0.5439,
"step": 1720
},
{
"epoch": 2.64,
"learning_rate": 2.616377845735644e-05,
"loss": 0.4702,
"step": 1730
},
{
"epoch": 2.66,
"learning_rate": 2.5993883792048927e-05,
"loss": 0.5041,
"step": 1740
},
{
"epoch": 2.67,
"learning_rate": 2.582398912674142e-05,
"loss": 0.4341,
"step": 1750
},
{
"epoch": 2.69,
"learning_rate": 2.5654094461433913e-05,
"loss": 0.4781,
"step": 1760
},
{
"epoch": 2.71,
"learning_rate": 2.5484199796126402e-05,
"loss": 0.4447,
"step": 1770
},
{
"epoch": 2.72,
"learning_rate": 2.5314305130818895e-05,
"loss": 0.424,
"step": 1780
},
{
"epoch": 2.74,
"learning_rate": 2.5144410465511388e-05,
"loss": 0.5021,
"step": 1790
},
{
"epoch": 2.75,
"learning_rate": 2.4974515800203874e-05,
"loss": 0.4491,
"step": 1800
},
{
"epoch": 2.77,
"learning_rate": 2.4804621134896367e-05,
"loss": 0.47,
"step": 1810
},
{
"epoch": 2.78,
"learning_rate": 2.4634726469588856e-05,
"loss": 0.4573,
"step": 1820
},
{
"epoch": 2.8,
"learning_rate": 2.4464831804281346e-05,
"loss": 0.4301,
"step": 1830
},
{
"epoch": 2.81,
"learning_rate": 2.4294937138973835e-05,
"loss": 0.5122,
"step": 1840
},
{
"epoch": 2.83,
"learning_rate": 2.4125042473666328e-05,
"loss": 0.4943,
"step": 1850
},
{
"epoch": 2.84,
"learning_rate": 2.3955147808358818e-05,
"loss": 0.4656,
"step": 1860
},
{
"epoch": 2.86,
"learning_rate": 2.3785253143051307e-05,
"loss": 0.4625,
"step": 1870
},
{
"epoch": 2.87,
"learning_rate": 2.36153584777438e-05,
"loss": 0.5568,
"step": 1880
},
{
"epoch": 2.89,
"learning_rate": 2.3445463812436293e-05,
"loss": 0.3586,
"step": 1890
},
{
"epoch": 2.9,
"learning_rate": 2.3275569147128782e-05,
"loss": 0.5519,
"step": 1900
},
{
"epoch": 2.92,
"learning_rate": 2.3105674481821272e-05,
"loss": 0.5399,
"step": 1910
},
{
"epoch": 2.93,
"learning_rate": 2.2935779816513765e-05,
"loss": 0.4763,
"step": 1920
},
{
"epoch": 2.95,
"learning_rate": 2.2765885151206254e-05,
"loss": 0.5894,
"step": 1930
},
{
"epoch": 2.97,
"learning_rate": 2.2595990485898744e-05,
"loss": 0.5012,
"step": 1940
},
{
"epoch": 2.98,
"learning_rate": 2.2426095820591233e-05,
"loss": 0.419,
"step": 1950
},
{
"epoch": 3.0,
"learning_rate": 2.2256201155283726e-05,
"loss": 0.5041,
"step": 1960
},
{
"epoch": 3.0,
"eval_accuracy": 0.7444126074498567,
"eval_loss": 0.7038247585296631,
"eval_runtime": 52.7062,
"eval_samples_per_second": 99.324,
"eval_steps_per_second": 12.427,
"step": 1962
},
{
"epoch": 3.01,
"learning_rate": 2.2086306489976216e-05,
"loss": 0.4415,
"step": 1970
},
{
"epoch": 3.03,
"learning_rate": 2.1916411824668705e-05,
"loss": 0.2787,
"step": 1980
},
{
"epoch": 3.04,
"learning_rate": 2.1746517159361194e-05,
"loss": 0.4013,
"step": 1990
},
{
"epoch": 3.06,
"learning_rate": 2.1576622494053687e-05,
"loss": 0.3279,
"step": 2000
},
{
"epoch": 3.07,
"learning_rate": 2.140672782874618e-05,
"loss": 0.3274,
"step": 2010
},
{
"epoch": 3.09,
"learning_rate": 2.123683316343867e-05,
"loss": 0.3664,
"step": 2020
},
{
"epoch": 3.1,
"learning_rate": 2.106693849813116e-05,
"loss": 0.3076,
"step": 2030
},
{
"epoch": 3.12,
"learning_rate": 2.0897043832823652e-05,
"loss": 0.4652,
"step": 2040
},
{
"epoch": 3.13,
"learning_rate": 2.072714916751614e-05,
"loss": 0.358,
"step": 2050
},
{
"epoch": 3.15,
"learning_rate": 2.055725450220863e-05,
"loss": 0.3003,
"step": 2060
},
{
"epoch": 3.16,
"learning_rate": 2.038735983690112e-05,
"loss": 0.3643,
"step": 2070
},
{
"epoch": 3.18,
"learning_rate": 2.0217465171593613e-05,
"loss": 0.3784,
"step": 2080
},
{
"epoch": 3.19,
"learning_rate": 2.0047570506286103e-05,
"loss": 0.3069,
"step": 2090
},
{
"epoch": 3.21,
"learning_rate": 1.9877675840978592e-05,
"loss": 0.3309,
"step": 2100
},
{
"epoch": 3.23,
"learning_rate": 1.9707781175671085e-05,
"loss": 0.3504,
"step": 2110
},
{
"epoch": 3.24,
"learning_rate": 1.9537886510363575e-05,
"loss": 0.3749,
"step": 2120
},
{
"epoch": 3.26,
"learning_rate": 1.9367991845056068e-05,
"loss": 0.3634,
"step": 2130
},
{
"epoch": 3.27,
"learning_rate": 1.9198097179748557e-05,
"loss": 0.3223,
"step": 2140
},
{
"epoch": 3.29,
"learning_rate": 1.902820251444105e-05,
"loss": 0.4309,
"step": 2150
},
{
"epoch": 3.3,
"learning_rate": 1.885830784913354e-05,
"loss": 0.3728,
"step": 2160
},
{
"epoch": 3.32,
"learning_rate": 1.868841318382603e-05,
"loss": 0.2607,
"step": 2170
},
{
"epoch": 3.33,
"learning_rate": 1.8518518518518518e-05,
"loss": 0.3335,
"step": 2180
},
{
"epoch": 3.35,
"learning_rate": 1.834862385321101e-05,
"loss": 0.2907,
"step": 2190
},
{
"epoch": 3.36,
"learning_rate": 1.81787291879035e-05,
"loss": 0.3103,
"step": 2200
},
{
"epoch": 3.38,
"learning_rate": 1.800883452259599e-05,
"loss": 0.3538,
"step": 2210
},
{
"epoch": 3.39,
"learning_rate": 1.783893985728848e-05,
"loss": 0.4066,
"step": 2220
},
{
"epoch": 3.41,
"learning_rate": 1.7669045191980972e-05,
"loss": 0.3397,
"step": 2230
},
{
"epoch": 3.42,
"learning_rate": 1.7499150526673462e-05,
"loss": 0.3611,
"step": 2240
},
{
"epoch": 3.44,
"learning_rate": 1.7329255861365955e-05,
"loss": 0.3621,
"step": 2250
},
{
"epoch": 3.45,
"learning_rate": 1.7159361196058444e-05,
"loss": 0.2716,
"step": 2260
},
{
"epoch": 3.47,
"learning_rate": 1.6989466530750937e-05,
"loss": 0.3324,
"step": 2270
},
{
"epoch": 3.48,
"learning_rate": 1.6819571865443427e-05,
"loss": 0.3249,
"step": 2280
},
{
"epoch": 3.5,
"learning_rate": 1.6649677200135916e-05,
"loss": 0.3113,
"step": 2290
},
{
"epoch": 3.52,
"learning_rate": 1.647978253482841e-05,
"loss": 0.2582,
"step": 2300
},
{
"epoch": 3.53,
"learning_rate": 1.63098878695209e-05,
"loss": 0.3834,
"step": 2310
},
{
"epoch": 3.55,
"learning_rate": 1.6139993204213388e-05,
"loss": 0.29,
"step": 2320
},
{
"epoch": 3.56,
"learning_rate": 1.5970098538905877e-05,
"loss": 0.3144,
"step": 2330
},
{
"epoch": 3.58,
"learning_rate": 1.580020387359837e-05,
"loss": 0.3653,
"step": 2340
},
{
"epoch": 3.59,
"learning_rate": 1.563030920829086e-05,
"loss": 0.3767,
"step": 2350
},
{
"epoch": 3.61,
"learning_rate": 1.546041454298335e-05,
"loss": 0.3475,
"step": 2360
},
{
"epoch": 3.62,
"learning_rate": 1.5290519877675842e-05,
"loss": 0.4123,
"step": 2370
},
{
"epoch": 3.64,
"learning_rate": 1.5120625212368333e-05,
"loss": 0.3363,
"step": 2380
},
{
"epoch": 3.65,
"learning_rate": 1.4950730547060823e-05,
"loss": 0.25,
"step": 2390
},
{
"epoch": 3.67,
"learning_rate": 1.4780835881753314e-05,
"loss": 0.2966,
"step": 2400
},
{
"epoch": 3.68,
"learning_rate": 1.4610941216445803e-05,
"loss": 0.3758,
"step": 2410
},
{
"epoch": 3.7,
"learning_rate": 1.4441046551138296e-05,
"loss": 0.3117,
"step": 2420
},
{
"epoch": 3.71,
"learning_rate": 1.4271151885830786e-05,
"loss": 0.305,
"step": 2430
},
{
"epoch": 3.73,
"learning_rate": 1.4101257220523275e-05,
"loss": 0.3168,
"step": 2440
},
{
"epoch": 3.74,
"learning_rate": 1.3931362555215766e-05,
"loss": 0.3642,
"step": 2450
},
{
"epoch": 3.76,
"learning_rate": 1.3761467889908258e-05,
"loss": 0.3745,
"step": 2460
},
{
"epoch": 3.78,
"learning_rate": 1.3591573224600749e-05,
"loss": 0.3162,
"step": 2470
},
{
"epoch": 3.79,
"learning_rate": 1.3421678559293238e-05,
"loss": 0.3817,
"step": 2480
},
{
"epoch": 3.81,
"learning_rate": 1.3251783893985731e-05,
"loss": 0.2568,
"step": 2490
},
{
"epoch": 3.82,
"learning_rate": 1.308188922867822e-05,
"loss": 0.3392,
"step": 2500
},
{
"epoch": 3.84,
"learning_rate": 1.291199456337071e-05,
"loss": 0.386,
"step": 2510
},
{
"epoch": 3.85,
"learning_rate": 1.2742099898063201e-05,
"loss": 0.392,
"step": 2520
},
{
"epoch": 3.87,
"learning_rate": 1.2572205232755694e-05,
"loss": 0.3166,
"step": 2530
},
{
"epoch": 3.88,
"learning_rate": 1.2402310567448183e-05,
"loss": 0.3222,
"step": 2540
},
{
"epoch": 3.9,
"learning_rate": 1.2232415902140673e-05,
"loss": 0.3122,
"step": 2550
},
{
"epoch": 3.91,
"learning_rate": 1.2062521236833164e-05,
"loss": 0.3275,
"step": 2560
},
{
"epoch": 3.93,
"learning_rate": 1.1892626571525654e-05,
"loss": 0.3268,
"step": 2570
},
{
"epoch": 3.94,
"learning_rate": 1.1722731906218146e-05,
"loss": 0.2926,
"step": 2580
},
{
"epoch": 3.96,
"learning_rate": 1.1552837240910636e-05,
"loss": 0.3422,
"step": 2590
},
{
"epoch": 3.97,
"learning_rate": 1.1382942575603127e-05,
"loss": 0.3107,
"step": 2600
},
{
"epoch": 3.99,
"learning_rate": 1.1213047910295617e-05,
"loss": 0.2461,
"step": 2610
},
{
"epoch": 4.0,
"eval_accuracy": 0.7392550143266475,
"eval_loss": 0.7843212485313416,
"eval_runtime": 48.1379,
"eval_samples_per_second": 108.75,
"eval_steps_per_second": 13.607,
"step": 2617
},
{
"epoch": 4.0,
"learning_rate": 1.1043153244988108e-05,
"loss": 0.2342,
"step": 2620
},
{
"epoch": 4.02,
"learning_rate": 1.0873258579680597e-05,
"loss": 0.2295,
"step": 2630
},
{
"epoch": 4.04,
"learning_rate": 1.070336391437309e-05,
"loss": 0.1964,
"step": 2640
},
{
"epoch": 4.05,
"learning_rate": 1.053346924906558e-05,
"loss": 0.2504,
"step": 2650
},
{
"epoch": 4.07,
"learning_rate": 1.036357458375807e-05,
"loss": 0.2676,
"step": 2660
},
{
"epoch": 4.08,
"learning_rate": 1.019367991845056e-05,
"loss": 0.2241,
"step": 2670
},
{
"epoch": 4.1,
"learning_rate": 1.0023785253143051e-05,
"loss": 0.189,
"step": 2680
},
{
"epoch": 4.11,
"learning_rate": 9.853890587835543e-06,
"loss": 0.263,
"step": 2690
},
{
"epoch": 4.13,
"learning_rate": 9.683995922528034e-06,
"loss": 0.2561,
"step": 2700
},
{
"epoch": 4.14,
"learning_rate": 9.514101257220525e-06,
"loss": 0.2154,
"step": 2710
},
{
"epoch": 4.16,
"learning_rate": 9.344206591913014e-06,
"loss": 0.2351,
"step": 2720
},
{
"epoch": 4.17,
"learning_rate": 9.174311926605506e-06,
"loss": 0.2281,
"step": 2730
},
{
"epoch": 4.19,
"learning_rate": 9.004417261297995e-06,
"loss": 0.1526,
"step": 2740
},
{
"epoch": 4.2,
"learning_rate": 8.834522595990486e-06,
"loss": 0.2612,
"step": 2750
},
{
"epoch": 4.22,
"learning_rate": 8.664627930682977e-06,
"loss": 0.2339,
"step": 2760
},
{
"epoch": 4.23,
"learning_rate": 8.494733265375469e-06,
"loss": 0.2484,
"step": 2770
},
{
"epoch": 4.25,
"learning_rate": 8.324838600067958e-06,
"loss": 0.2338,
"step": 2780
},
{
"epoch": 4.26,
"learning_rate": 8.15494393476045e-06,
"loss": 0.2062,
"step": 2790
},
{
"epoch": 4.28,
"learning_rate": 7.985049269452939e-06,
"loss": 0.2153,
"step": 2800
},
{
"epoch": 4.29,
"learning_rate": 7.81515460414543e-06,
"loss": 0.1661,
"step": 2810
},
{
"epoch": 4.31,
"learning_rate": 7.645259938837921e-06,
"loss": 0.2059,
"step": 2820
},
{
"epoch": 4.33,
"learning_rate": 7.475365273530411e-06,
"loss": 0.2611,
"step": 2830
},
{
"epoch": 4.34,
"learning_rate": 7.305470608222902e-06,
"loss": 0.2026,
"step": 2840
},
{
"epoch": 4.36,
"learning_rate": 7.135575942915393e-06,
"loss": 0.2194,
"step": 2850
},
{
"epoch": 4.37,
"learning_rate": 6.965681277607883e-06,
"loss": 0.1759,
"step": 2860
},
{
"epoch": 4.39,
"learning_rate": 6.795786612300374e-06,
"loss": 0.2087,
"step": 2870
},
{
"epoch": 4.4,
"learning_rate": 6.6258919469928655e-06,
"loss": 0.2105,
"step": 2880
},
{
"epoch": 4.42,
"learning_rate": 6.455997281685355e-06,
"loss": 0.2052,
"step": 2890
},
{
"epoch": 4.43,
"learning_rate": 6.286102616377847e-06,
"loss": 0.2395,
"step": 2900
},
{
"epoch": 4.45,
"learning_rate": 6.1162079510703365e-06,
"loss": 0.1953,
"step": 2910
},
{
"epoch": 4.46,
"learning_rate": 5.946313285762827e-06,
"loss": 0.1944,
"step": 2920
},
{
"epoch": 4.48,
"learning_rate": 5.776418620455318e-06,
"loss": 0.2784,
"step": 2930
},
{
"epoch": 4.49,
"learning_rate": 5.606523955147808e-06,
"loss": 0.1885,
"step": 2940
},
{
"epoch": 4.51,
"learning_rate": 5.436629289840299e-06,
"loss": 0.2575,
"step": 2950
},
{
"epoch": 4.52,
"learning_rate": 5.26673462453279e-06,
"loss": 0.1941,
"step": 2960
},
{
"epoch": 4.54,
"learning_rate": 5.09683995922528e-06,
"loss": 0.2795,
"step": 2970
},
{
"epoch": 4.55,
"learning_rate": 4.926945293917771e-06,
"loss": 0.1971,
"step": 2980
},
{
"epoch": 4.57,
"learning_rate": 4.7570506286102625e-06,
"loss": 0.224,
"step": 2990
},
{
"epoch": 4.59,
"learning_rate": 4.587155963302753e-06,
"loss": 0.2044,
"step": 3000
},
{
"epoch": 4.6,
"learning_rate": 4.417261297995243e-06,
"loss": 0.2073,
"step": 3010
},
{
"epoch": 4.62,
"learning_rate": 4.247366632687734e-06,
"loss": 0.2055,
"step": 3020
},
{
"epoch": 4.63,
"learning_rate": 4.077471967380225e-06,
"loss": 0.1936,
"step": 3030
},
{
"epoch": 4.65,
"learning_rate": 3.907577302072715e-06,
"loss": 0.219,
"step": 3040
},
{
"epoch": 4.66,
"learning_rate": 3.7376826367652057e-06,
"loss": 0.198,
"step": 3050
},
{
"epoch": 4.68,
"learning_rate": 3.5677879714576964e-06,
"loss": 0.242,
"step": 3060
},
{
"epoch": 4.69,
"learning_rate": 3.397893306150187e-06,
"loss": 0.2242,
"step": 3070
},
{
"epoch": 4.71,
"learning_rate": 3.2279986408426775e-06,
"loss": 0.2083,
"step": 3080
},
{
"epoch": 4.72,
"learning_rate": 3.0581039755351682e-06,
"loss": 0.2268,
"step": 3090
},
{
"epoch": 4.74,
"learning_rate": 2.888209310227659e-06,
"loss": 0.1819,
"step": 3100
},
{
"epoch": 4.75,
"learning_rate": 2.7183146449201493e-06,
"loss": 0.2127,
"step": 3110
},
{
"epoch": 4.77,
"learning_rate": 2.54841997961264e-06,
"loss": 0.1816,
"step": 3120
},
{
"epoch": 4.78,
"learning_rate": 2.3785253143051312e-06,
"loss": 0.187,
"step": 3130
},
{
"epoch": 4.8,
"learning_rate": 2.2086306489976216e-06,
"loss": 0.2482,
"step": 3140
},
{
"epoch": 4.81,
"learning_rate": 2.0387359836901123e-06,
"loss": 0.2161,
"step": 3150
},
{
"epoch": 4.83,
"learning_rate": 1.8688413183826028e-06,
"loss": 0.2413,
"step": 3160
},
{
"epoch": 4.85,
"learning_rate": 1.6989466530750936e-06,
"loss": 0.1959,
"step": 3170
},
{
"epoch": 4.86,
"learning_rate": 1.5290519877675841e-06,
"loss": 0.2644,
"step": 3180
},
{
"epoch": 4.88,
"learning_rate": 1.3591573224600747e-06,
"loss": 0.1793,
"step": 3190
},
{
"epoch": 4.89,
"learning_rate": 1.1892626571525656e-06,
"loss": 0.1869,
"step": 3200
},
{
"epoch": 4.91,
"learning_rate": 1.0193679918450562e-06,
"loss": 0.195,
"step": 3210
},
{
"epoch": 4.92,
"learning_rate": 8.494733265375468e-07,
"loss": 0.2474,
"step": 3220
},
{
"epoch": 4.94,
"learning_rate": 6.795786612300373e-07,
"loss": 0.2748,
"step": 3230
},
{
"epoch": 4.95,
"learning_rate": 5.096839959225281e-07,
"loss": 0.1932,
"step": 3240
},
{
"epoch": 4.97,
"learning_rate": 3.3978933061501866e-07,
"loss": 0.2393,
"step": 3250
},
{
"epoch": 4.98,
"learning_rate": 1.6989466530750933e-07,
"loss": 0.2547,
"step": 3260
},
{
"epoch": 5.0,
"learning_rate": 0.0,
"loss": 0.1846,
"step": 3270
},
{
"epoch": 5.0,
"eval_accuracy": 0.7390639923591213,
"eval_loss": 0.8219425082206726,
"eval_runtime": 48.049,
"eval_samples_per_second": 108.951,
"eval_steps_per_second": 13.632,
"step": 3270
},
{
"epoch": 5.02,
"learning_rate": 2.7692830445124026e-05,
"loss": 0.1929,
"step": 3280
},
{
"epoch": 5.03,
"learning_rate": 2.760788311247027e-05,
"loss": 0.1936,
"step": 3290
},
{
"epoch": 5.05,
"learning_rate": 2.7522935779816515e-05,
"loss": 0.1636,
"step": 3300
},
{
"epoch": 5.06,
"learning_rate": 2.743798844716276e-05,
"loss": 0.1827,
"step": 3310
},
{
"epoch": 5.08,
"learning_rate": 2.7353041114509004e-05,
"loss": 0.2437,
"step": 3320
},
{
"epoch": 5.09,
"learning_rate": 2.7268093781855254e-05,
"loss": 0.2142,
"step": 3330
},
{
"epoch": 5.11,
"learning_rate": 2.7183146449201497e-05,
"loss": 0.2637,
"step": 3340
},
{
"epoch": 5.12,
"learning_rate": 2.709819911654774e-05,
"loss": 0.213,
"step": 3350
},
{
"epoch": 5.14,
"learning_rate": 2.701325178389399e-05,
"loss": 0.2534,
"step": 3360
},
{
"epoch": 5.15,
"learning_rate": 2.6928304451240233e-05,
"loss": 0.2819,
"step": 3370
},
{
"epoch": 5.17,
"learning_rate": 2.6843357118586476e-05,
"loss": 0.2568,
"step": 3380
},
{
"epoch": 5.18,
"learning_rate": 2.6758409785932726e-05,
"loss": 0.2391,
"step": 3390
},
{
"epoch": 5.2,
"learning_rate": 2.667346245327897e-05,
"loss": 0.2604,
"step": 3400
},
{
"epoch": 5.21,
"learning_rate": 2.6588515120625212e-05,
"loss": 0.2849,
"step": 3410
},
{
"epoch": 5.23,
"learning_rate": 2.6503567787971462e-05,
"loss": 0.2233,
"step": 3420
},
{
"epoch": 5.24,
"learning_rate": 2.6418620455317705e-05,
"loss": 0.2154,
"step": 3430
},
{
"epoch": 5.26,
"learning_rate": 2.6333673122663948e-05,
"loss": 0.2891,
"step": 3440
},
{
"epoch": 5.28,
"learning_rate": 2.624872579001019e-05,
"loss": 0.217,
"step": 3450
},
{
"epoch": 5.29,
"learning_rate": 2.616377845735644e-05,
"loss": 0.2627,
"step": 3460
},
{
"epoch": 5.31,
"learning_rate": 2.6078831124702684e-05,
"loss": 0.2276,
"step": 3470
},
{
"epoch": 5.32,
"learning_rate": 2.5993883792048927e-05,
"loss": 0.2119,
"step": 3480
},
{
"epoch": 5.34,
"learning_rate": 2.5908936459395177e-05,
"loss": 0.2302,
"step": 3490
},
{
"epoch": 5.35,
"learning_rate": 2.582398912674142e-05,
"loss": 0.284,
"step": 3500
},
{
"epoch": 5.37,
"learning_rate": 2.5739041794087666e-05,
"loss": 0.2456,
"step": 3510
},
{
"epoch": 5.38,
"learning_rate": 2.5654094461433913e-05,
"loss": 0.2087,
"step": 3520
},
{
"epoch": 5.4,
"learning_rate": 2.556914712878016e-05,
"loss": 0.282,
"step": 3530
},
{
"epoch": 5.41,
"learning_rate": 2.5484199796126402e-05,
"loss": 0.213,
"step": 3540
},
{
"epoch": 5.43,
"learning_rate": 2.539925246347265e-05,
"loss": 0.207,
"step": 3550
},
{
"epoch": 5.44,
"learning_rate": 2.5314305130818895e-05,
"loss": 0.2326,
"step": 3560
},
{
"epoch": 5.46,
"learning_rate": 2.5229357798165138e-05,
"loss": 0.2557,
"step": 3570
},
{
"epoch": 5.47,
"learning_rate": 2.5144410465511388e-05,
"loss": 0.2524,
"step": 3580
},
{
"epoch": 5.49,
"learning_rate": 2.505946313285763e-05,
"loss": 0.3032,
"step": 3590
},
{
"epoch": 5.5,
"learning_rate": 2.4974515800203874e-05,
"loss": 0.3316,
"step": 3600
},
{
"epoch": 5.52,
"learning_rate": 2.488956846755012e-05,
"loss": 0.2447,
"step": 3610
},
{
"epoch": 5.53,
"learning_rate": 2.4804621134896367e-05,
"loss": 0.3041,
"step": 3620
},
{
"epoch": 5.55,
"learning_rate": 2.471967380224261e-05,
"loss": 0.1924,
"step": 3630
},
{
"epoch": 5.57,
"learning_rate": 2.4634726469588856e-05,
"loss": 0.2868,
"step": 3640
},
{
"epoch": 5.58,
"learning_rate": 2.4549779136935103e-05,
"loss": 0.2278,
"step": 3650
},
{
"epoch": 5.6,
"learning_rate": 2.4464831804281346e-05,
"loss": 0.3065,
"step": 3660
},
{
"epoch": 5.61,
"learning_rate": 2.4379884471627592e-05,
"loss": 0.2801,
"step": 3670
},
{
"epoch": 5.63,
"learning_rate": 2.4294937138973835e-05,
"loss": 0.2434,
"step": 3680
},
{
"epoch": 5.64,
"learning_rate": 2.4209989806320082e-05,
"loss": 0.2846,
"step": 3690
},
{
"epoch": 5.66,
"learning_rate": 2.4125042473666328e-05,
"loss": 0.2783,
"step": 3700
},
{
"epoch": 5.67,
"learning_rate": 2.404009514101257e-05,
"loss": 0.271,
"step": 3710
},
{
"epoch": 5.69,
"learning_rate": 2.3955147808358818e-05,
"loss": 0.1965,
"step": 3720
},
{
"epoch": 5.7,
"learning_rate": 2.3870200475705064e-05,
"loss": 0.2836,
"step": 3730
},
{
"epoch": 5.72,
"learning_rate": 2.3785253143051307e-05,
"loss": 0.2765,
"step": 3740
},
{
"epoch": 5.73,
"learning_rate": 2.3700305810397554e-05,
"loss": 0.267,
"step": 3750
},
{
"epoch": 5.75,
"learning_rate": 2.36153584777438e-05,
"loss": 0.2518,
"step": 3760
},
{
"epoch": 5.76,
"learning_rate": 2.3530411145090047e-05,
"loss": 0.3005,
"step": 3770
},
{
"epoch": 5.78,
"learning_rate": 2.3445463812436293e-05,
"loss": 0.2205,
"step": 3780
},
{
"epoch": 5.79,
"learning_rate": 2.3360516479782536e-05,
"loss": 0.2288,
"step": 3790
},
{
"epoch": 5.81,
"learning_rate": 2.3275569147128782e-05,
"loss": 0.2786,
"step": 3800
},
{
"epoch": 5.83,
"learning_rate": 2.319062181447503e-05,
"loss": 0.2371,
"step": 3810
},
{
"epoch": 5.84,
"learning_rate": 2.3105674481821272e-05,
"loss": 0.2495,
"step": 3820
},
{
"epoch": 5.86,
"learning_rate": 2.302072714916752e-05,
"loss": 0.3372,
"step": 3830
},
{
"epoch": 5.87,
"learning_rate": 2.2935779816513765e-05,
"loss": 0.286,
"step": 3840
},
{
"epoch": 5.89,
"learning_rate": 2.2850832483860008e-05,
"loss": 0.1617,
"step": 3850
},
{
"epoch": 5.9,
"learning_rate": 2.2765885151206254e-05,
"loss": 0.3336,
"step": 3860
},
{
"epoch": 5.92,
"learning_rate": 2.2680937818552497e-05,
"loss": 0.2747,
"step": 3870
},
{
"epoch": 5.93,
"learning_rate": 2.2595990485898744e-05,
"loss": 0.2783,
"step": 3880
},
{
"epoch": 5.95,
"learning_rate": 2.251104315324499e-05,
"loss": 0.2528,
"step": 3890
},
{
"epoch": 5.96,
"learning_rate": 2.2426095820591233e-05,
"loss": 0.2145,
"step": 3900
},
{
"epoch": 5.98,
"learning_rate": 2.234114848793748e-05,
"loss": 0.2747,
"step": 3910
},
{
"epoch": 5.99,
"learning_rate": 2.2256201155283726e-05,
"loss": 0.276,
"step": 3920
},
{
"epoch": 6.0,
"eval_accuracy": 0.7335243553008596,
"eval_loss": 0.8875630497932434,
"eval_runtime": 52.9673,
"eval_samples_per_second": 98.835,
"eval_steps_per_second": 12.366,
"step": 3924
},
{
"epoch": 6.01,
"learning_rate": 2.217125382262997e-05,
"loss": 0.2266,
"step": 3930
},
{
"epoch": 6.02,
"learning_rate": 2.2086306489976216e-05,
"loss": 0.1317,
"step": 3940
},
{
"epoch": 6.04,
"learning_rate": 2.200135915732246e-05,
"loss": 0.1782,
"step": 3950
},
{
"epoch": 6.05,
"learning_rate": 2.1916411824668705e-05,
"loss": 0.1682,
"step": 3960
},
{
"epoch": 6.07,
"learning_rate": 2.183146449201495e-05,
"loss": 0.136,
"step": 3970
},
{
"epoch": 6.09,
"learning_rate": 2.1746517159361194e-05,
"loss": 0.1868,
"step": 3980
},
{
"epoch": 6.1,
"learning_rate": 2.166156982670744e-05,
"loss": 0.2079,
"step": 3990
},
{
"epoch": 6.12,
"learning_rate": 2.1576622494053687e-05,
"loss": 0.1697,
"step": 4000
},
{
"epoch": 6.13,
"learning_rate": 2.1491675161399934e-05,
"loss": 0.1892,
"step": 4010
},
{
"epoch": 6.15,
"learning_rate": 2.140672782874618e-05,
"loss": 0.2033,
"step": 4020
},
{
"epoch": 6.16,
"learning_rate": 2.1321780496092427e-05,
"loss": 0.1372,
"step": 4030
},
{
"epoch": 6.18,
"learning_rate": 2.123683316343867e-05,
"loss": 0.199,
"step": 4040
},
{
"epoch": 6.19,
"learning_rate": 2.1151885830784916e-05,
"loss": 0.1655,
"step": 4050
},
{
"epoch": 6.21,
"learning_rate": 2.106693849813116e-05,
"loss": 0.1681,
"step": 4060
},
{
"epoch": 6.22,
"learning_rate": 2.0981991165477406e-05,
"loss": 0.2172,
"step": 4070
},
{
"epoch": 6.24,
"learning_rate": 2.0897043832823652e-05,
"loss": 0.1542,
"step": 4080
},
{
"epoch": 6.25,
"learning_rate": 2.0812096500169895e-05,
"loss": 0.1596,
"step": 4090
},
{
"epoch": 6.27,
"learning_rate": 2.072714916751614e-05,
"loss": 0.1871,
"step": 4100
},
{
"epoch": 6.28,
"learning_rate": 2.0642201834862388e-05,
"loss": 0.1852,
"step": 4110
},
{
"epoch": 6.3,
"learning_rate": 2.055725450220863e-05,
"loss": 0.2118,
"step": 4120
},
{
"epoch": 6.31,
"learning_rate": 2.0472307169554877e-05,
"loss": 0.1648,
"step": 4130
},
{
"epoch": 6.33,
"learning_rate": 2.038735983690112e-05,
"loss": 0.1759,
"step": 4140
},
{
"epoch": 6.35,
"learning_rate": 2.0302412504247367e-05,
"loss": 0.1385,
"step": 4150
},
{
"epoch": 6.36,
"learning_rate": 2.0217465171593613e-05,
"loss": 0.1848,
"step": 4160
},
{
"epoch": 6.38,
"learning_rate": 2.0132517838939856e-05,
"loss": 0.2324,
"step": 4170
},
{
"epoch": 6.39,
"learning_rate": 2.0047570506286103e-05,
"loss": 0.2223,
"step": 4180
},
{
"epoch": 6.41,
"learning_rate": 1.996262317363235e-05,
"loss": 0.1592,
"step": 4190
},
{
"epoch": 6.42,
"learning_rate": 1.9877675840978592e-05,
"loss": 0.1849,
"step": 4200
},
{
"epoch": 6.44,
"learning_rate": 1.979272850832484e-05,
"loss": 0.1592,
"step": 4210
},
{
"epoch": 6.45,
"learning_rate": 1.9707781175671085e-05,
"loss": 0.147,
"step": 4220
},
{
"epoch": 6.47,
"learning_rate": 1.9622833843017328e-05,
"loss": 0.2434,
"step": 4230
},
{
"epoch": 6.48,
"learning_rate": 1.9537886510363575e-05,
"loss": 0.1759,
"step": 4240
},
{
"epoch": 6.5,
"learning_rate": 1.945293917770982e-05,
"loss": 0.1086,
"step": 4250
},
{
"epoch": 6.51,
"learning_rate": 1.9367991845056068e-05,
"loss": 0.1473,
"step": 4260
},
{
"epoch": 6.53,
"learning_rate": 1.9283044512402314e-05,
"loss": 0.2267,
"step": 4270
},
{
"epoch": 6.54,
"learning_rate": 1.9198097179748557e-05,
"loss": 0.1617,
"step": 4280
},
{
"epoch": 6.56,
"learning_rate": 1.9113149847094803e-05,
"loss": 0.1352,
"step": 4290
},
{
"epoch": 6.57,
"learning_rate": 1.902820251444105e-05,
"loss": 0.1824,
"step": 4300
},
{
"epoch": 6.59,
"learning_rate": 1.8943255181787293e-05,
"loss": 0.2317,
"step": 4310
},
{
"epoch": 6.6,
"learning_rate": 1.885830784913354e-05,
"loss": 0.1288,
"step": 4320
},
{
"epoch": 6.62,
"learning_rate": 1.8773360516479782e-05,
"loss": 0.1705,
"step": 4330
},
{
"epoch": 6.64,
"learning_rate": 1.868841318382603e-05,
"loss": 0.1666,
"step": 4340
},
{
"epoch": 6.65,
"learning_rate": 1.8603465851172275e-05,
"loss": 0.1805,
"step": 4350
},
{
"epoch": 6.67,
"learning_rate": 1.8518518518518518e-05,
"loss": 0.1735,
"step": 4360
},
{
"epoch": 6.68,
"learning_rate": 1.8433571185864765e-05,
"loss": 0.1469,
"step": 4370
},
{
"epoch": 6.7,
"learning_rate": 1.834862385321101e-05,
"loss": 0.1741,
"step": 4380
},
{
"epoch": 6.71,
"learning_rate": 1.8263676520557254e-05,
"loss": 0.1928,
"step": 4390
},
{
"epoch": 6.73,
"learning_rate": 1.81787291879035e-05,
"loss": 0.1633,
"step": 4400
},
{
"epoch": 6.74,
"learning_rate": 1.8093781855249747e-05,
"loss": 0.171,
"step": 4410
},
{
"epoch": 6.76,
"learning_rate": 1.800883452259599e-05,
"loss": 0.1172,
"step": 4420
},
{
"epoch": 6.77,
"learning_rate": 1.7923887189942237e-05,
"loss": 0.1969,
"step": 4430
},
{
"epoch": 6.79,
"learning_rate": 1.783893985728848e-05,
"loss": 0.1892,
"step": 4440
},
{
"epoch": 6.8,
"learning_rate": 1.7753992524634726e-05,
"loss": 0.1663,
"step": 4450
},
{
"epoch": 6.82,
"learning_rate": 1.7669045191980972e-05,
"loss": 0.1804,
"step": 4460
},
{
"epoch": 6.83,
"learning_rate": 1.7584097859327215e-05,
"loss": 0.1847,
"step": 4470
},
{
"epoch": 6.85,
"learning_rate": 1.7499150526673462e-05,
"loss": 0.1542,
"step": 4480
},
{
"epoch": 6.86,
"learning_rate": 1.741420319401971e-05,
"loss": 0.2272,
"step": 4490
},
{
"epoch": 6.88,
"learning_rate": 1.7329255861365955e-05,
"loss": 0.2078,
"step": 4500
},
{
"epoch": 6.9,
"learning_rate": 1.72443085287122e-05,
"loss": 0.1508,
"step": 4510
},
{
"epoch": 6.91,
"learning_rate": 1.7159361196058444e-05,
"loss": 0.1619,
"step": 4520
},
{
"epoch": 6.93,
"learning_rate": 1.707441386340469e-05,
"loss": 0.147,
"step": 4530
},
{
"epoch": 6.94,
"learning_rate": 1.6989466530750937e-05,
"loss": 0.1696,
"step": 4540
},
{
"epoch": 6.96,
"learning_rate": 1.690451919809718e-05,
"loss": 0.1835,
"step": 4550
},
{
"epoch": 6.97,
"learning_rate": 1.6819571865443427e-05,
"loss": 0.2407,
"step": 4560
},
{
"epoch": 6.99,
"learning_rate": 1.6734624532789673e-05,
"loss": 0.2217,
"step": 4570
},
{
"epoch": 7.0,
"eval_accuracy": 0.7255014326647564,
"eval_loss": 0.975210428237915,
"eval_runtime": 48.2463,
"eval_samples_per_second": 108.506,
"eval_steps_per_second": 13.576,
"step": 4578
},
{
"epoch": 7.0,
"learning_rate": 1.6649677200135916e-05,
"loss": 0.1381,
"step": 4580
},
{
"epoch": 7.02,
"learning_rate": 1.6564729867482163e-05,
"loss": 0.1104,
"step": 4590
},
{
"epoch": 7.03,
"learning_rate": 1.647978253482841e-05,
"loss": 0.1027,
"step": 4600
},
{
"epoch": 7.05,
"learning_rate": 1.6394835202174652e-05,
"loss": 0.0925,
"step": 4610
},
{
"epoch": 7.06,
"learning_rate": 1.63098878695209e-05,
"loss": 0.0849,
"step": 4620
},
{
"epoch": 7.08,
"learning_rate": 1.622494053686714e-05,
"loss": 0.1063,
"step": 4630
},
{
"epoch": 7.09,
"learning_rate": 1.6139993204213388e-05,
"loss": 0.1039,
"step": 4640
},
{
"epoch": 7.11,
"learning_rate": 1.6055045871559634e-05,
"loss": 0.0816,
"step": 4650
},
{
"epoch": 7.12,
"learning_rate": 1.5970098538905877e-05,
"loss": 0.1369,
"step": 4660
},
{
"epoch": 7.14,
"learning_rate": 1.5885151206252124e-05,
"loss": 0.072,
"step": 4670
},
{
"epoch": 7.16,
"learning_rate": 1.580020387359837e-05,
"loss": 0.1572,
"step": 4680
},
{
"epoch": 7.17,
"learning_rate": 1.5715256540944613e-05,
"loss": 0.1364,
"step": 4690
},
{
"epoch": 7.19,
"learning_rate": 1.563030920829086e-05,
"loss": 0.1231,
"step": 4700
},
{
"epoch": 7.2,
"learning_rate": 1.5545361875637103e-05,
"loss": 0.1029,
"step": 4710
},
{
"epoch": 7.22,
"learning_rate": 1.546041454298335e-05,
"loss": 0.1086,
"step": 4720
},
{
"epoch": 7.23,
"learning_rate": 1.5375467210329596e-05,
"loss": 0.1288,
"step": 4730
},
{
"epoch": 7.25,
"learning_rate": 1.5290519877675842e-05,
"loss": 0.0978,
"step": 4740
},
{
"epoch": 7.26,
"learning_rate": 1.5205572545022087e-05,
"loss": 0.132,
"step": 4750
},
{
"epoch": 7.28,
"learning_rate": 1.5120625212368333e-05,
"loss": 0.1073,
"step": 4760
},
{
"epoch": 7.29,
"learning_rate": 1.5035677879714576e-05,
"loss": 0.0635,
"step": 4770
},
{
"epoch": 7.31,
"learning_rate": 1.4950730547060823e-05,
"loss": 0.1048,
"step": 4780
},
{
"epoch": 7.32,
"learning_rate": 1.4865783214407069e-05,
"loss": 0.0925,
"step": 4790
},
{
"epoch": 7.34,
"learning_rate": 1.4780835881753314e-05,
"loss": 0.0982,
"step": 4800
},
{
"epoch": 7.35,
"learning_rate": 1.469588854909956e-05,
"loss": 0.1385,
"step": 4810
},
{
"epoch": 7.37,
"learning_rate": 1.4610941216445803e-05,
"loss": 0.112,
"step": 4820
},
{
"epoch": 7.38,
"learning_rate": 1.452599388379205e-05,
"loss": 0.1666,
"step": 4830
},
{
"epoch": 7.4,
"learning_rate": 1.4441046551138296e-05,
"loss": 0.1001,
"step": 4840
},
{
"epoch": 7.41,
"learning_rate": 1.435609921848454e-05,
"loss": 0.1285,
"step": 4850
},
{
"epoch": 7.43,
"learning_rate": 1.4271151885830786e-05,
"loss": 0.1185,
"step": 4860
},
{
"epoch": 7.45,
"learning_rate": 1.4186204553177032e-05,
"loss": 0.0936,
"step": 4870
},
{
"epoch": 7.46,
"learning_rate": 1.4101257220523275e-05,
"loss": 0.0754,
"step": 4880
},
{
"epoch": 7.48,
"learning_rate": 1.4016309887869522e-05,
"loss": 0.0842,
"step": 4890
},
{
"epoch": 7.49,
"learning_rate": 1.3931362555215766e-05,
"loss": 0.1387,
"step": 4900
},
{
"epoch": 7.51,
"learning_rate": 1.3846415222562013e-05,
"loss": 0.1285,
"step": 4910
},
{
"epoch": 7.52,
"learning_rate": 1.3761467889908258e-05,
"loss": 0.1909,
"step": 4920
},
{
"epoch": 7.54,
"learning_rate": 1.3676520557254502e-05,
"loss": 0.0862,
"step": 4930
},
{
"epoch": 7.55,
"learning_rate": 1.3591573224600749e-05,
"loss": 0.0951,
"step": 4940
},
{
"epoch": 7.57,
"learning_rate": 1.3506625891946995e-05,
"loss": 0.0812,
"step": 4950
},
{
"epoch": 7.58,
"learning_rate": 1.3421678559293238e-05,
"loss": 0.1107,
"step": 4960
},
{
"epoch": 7.6,
"learning_rate": 1.3336731226639485e-05,
"loss": 0.1025,
"step": 4970
},
{
"epoch": 7.61,
"learning_rate": 1.3251783893985731e-05,
"loss": 0.1235,
"step": 4980
},
{
"epoch": 7.63,
"learning_rate": 1.3166836561331974e-05,
"loss": 0.1164,
"step": 4990
},
{
"epoch": 7.64,
"learning_rate": 1.308188922867822e-05,
"loss": 0.1105,
"step": 5000
},
{
"epoch": 7.66,
"learning_rate": 1.2996941896024464e-05,
"loss": 0.0727,
"step": 5010
},
{
"epoch": 7.67,
"learning_rate": 1.291199456337071e-05,
"loss": 0.1,
"step": 5020
},
{
"epoch": 7.69,
"learning_rate": 1.2827047230716956e-05,
"loss": 0.0591,
"step": 5030
},
{
"epoch": 7.71,
"learning_rate": 1.2742099898063201e-05,
"loss": 0.1469,
"step": 5040
},
{
"epoch": 7.72,
"learning_rate": 1.2657152565409448e-05,
"loss": 0.094,
"step": 5050
},
{
"epoch": 7.74,
"learning_rate": 1.2572205232755694e-05,
"loss": 0.1413,
"step": 5060
},
{
"epoch": 7.75,
"learning_rate": 1.2487257900101937e-05,
"loss": 0.1544,
"step": 5070
},
{
"epoch": 7.77,
"learning_rate": 1.2402310567448183e-05,
"loss": 0.0947,
"step": 5080
},
{
"epoch": 7.78,
"learning_rate": 1.2317363234794428e-05,
"loss": 0.0794,
"step": 5090
},
{
"epoch": 7.8,
"learning_rate": 1.2232415902140673e-05,
"loss": 0.0734,
"step": 5100
},
{
"epoch": 7.81,
"learning_rate": 1.2147468569486918e-05,
"loss": 0.1328,
"step": 5110
},
{
"epoch": 7.83,
"learning_rate": 1.2062521236833164e-05,
"loss": 0.1425,
"step": 5120
},
{
"epoch": 7.84,
"learning_rate": 1.1977573904179409e-05,
"loss": 0.1404,
"step": 5130
},
{
"epoch": 7.86,
"learning_rate": 1.1892626571525654e-05,
"loss": 0.1005,
"step": 5140
},
{
"epoch": 7.87,
"learning_rate": 1.18076792388719e-05,
"loss": 0.1057,
"step": 5150
},
{
"epoch": 7.89,
"learning_rate": 1.1722731906218146e-05,
"loss": 0.089,
"step": 5160
},
{
"epoch": 7.9,
"learning_rate": 1.1637784573564391e-05,
"loss": 0.1242,
"step": 5170
},
{
"epoch": 7.92,
"learning_rate": 1.1552837240910636e-05,
"loss": 0.114,
"step": 5180
},
{
"epoch": 7.93,
"learning_rate": 1.1467889908256882e-05,
"loss": 0.0863,
"step": 5190
},
{
"epoch": 7.95,
"learning_rate": 1.1382942575603127e-05,
"loss": 0.1092,
"step": 5200
},
{
"epoch": 7.97,
"learning_rate": 1.1297995242949372e-05,
"loss": 0.1331,
"step": 5210
},
{
"epoch": 7.98,
"learning_rate": 1.1213047910295617e-05,
"loss": 0.0932,
"step": 5220
},
{
"epoch": 8.0,
"learning_rate": 1.1128100577641863e-05,
"loss": 0.0646,
"step": 5230
},
{
"epoch": 8.0,
"eval_accuracy": 0.7262655205348615,
"eval_loss": 1.0956766605377197,
"eval_runtime": 48.2758,
"eval_samples_per_second": 108.439,
"eval_steps_per_second": 13.568,
"step": 5232
},
{
"epoch": 8.01,
"learning_rate": 1.1043153244988108e-05,
"loss": 0.0684,
"step": 5240
},
{
"epoch": 8.03,
"learning_rate": 1.0958205912334353e-05,
"loss": 0.0661,
"step": 5250
},
{
"epoch": 8.04,
"learning_rate": 1.0873258579680597e-05,
"loss": 0.1048,
"step": 5260
},
{
"epoch": 8.06,
"learning_rate": 1.0788311247026844e-05,
"loss": 0.0763,
"step": 5270
},
{
"epoch": 8.07,
"learning_rate": 1.070336391437309e-05,
"loss": 0.0477,
"step": 5280
},
{
"epoch": 8.09,
"learning_rate": 1.0618416581719335e-05,
"loss": 0.0662,
"step": 5290
},
{
"epoch": 8.1,
"learning_rate": 1.053346924906558e-05,
"loss": 0.0479,
"step": 5300
},
{
"epoch": 8.12,
"learning_rate": 1.0448521916411826e-05,
"loss": 0.065,
"step": 5310
},
{
"epoch": 8.13,
"learning_rate": 1.036357458375807e-05,
"loss": 0.0685,
"step": 5320
},
{
"epoch": 8.15,
"learning_rate": 1.0278627251104316e-05,
"loss": 0.0763,
"step": 5330
},
{
"epoch": 8.16,
"learning_rate": 1.019367991845056e-05,
"loss": 0.061,
"step": 5340
},
{
"epoch": 8.18,
"learning_rate": 1.0108732585796807e-05,
"loss": 0.0848,
"step": 5350
},
{
"epoch": 8.19,
"learning_rate": 1.0023785253143051e-05,
"loss": 0.0621,
"step": 5360
},
{
"epoch": 8.21,
"learning_rate": 9.938837920489296e-06,
"loss": 0.0505,
"step": 5370
},
{
"epoch": 8.23,
"learning_rate": 9.853890587835543e-06,
"loss": 0.0823,
"step": 5380
},
{
"epoch": 8.24,
"learning_rate": 9.768943255181787e-06,
"loss": 0.0637,
"step": 5390
},
{
"epoch": 8.26,
"learning_rate": 9.683995922528034e-06,
"loss": 0.05,
"step": 5400
},
{
"epoch": 8.27,
"learning_rate": 9.599048589874278e-06,
"loss": 0.0393,
"step": 5410
},
{
"epoch": 8.29,
"learning_rate": 9.514101257220525e-06,
"loss": 0.0983,
"step": 5420
},
{
"epoch": 8.3,
"learning_rate": 9.42915392456677e-06,
"loss": 0.0467,
"step": 5430
},
{
"epoch": 8.32,
"learning_rate": 9.344206591913014e-06,
"loss": 0.0898,
"step": 5440
},
{
"epoch": 8.33,
"learning_rate": 9.259259259259259e-06,
"loss": 0.0757,
"step": 5450
},
{
"epoch": 8.35,
"learning_rate": 9.174311926605506e-06,
"loss": 0.0849,
"step": 5460
},
{
"epoch": 8.36,
"learning_rate": 9.08936459395175e-06,
"loss": 0.0653,
"step": 5470
},
{
"epoch": 8.38,
"learning_rate": 9.004417261297995e-06,
"loss": 0.0816,
"step": 5480
},
{
"epoch": 8.39,
"learning_rate": 8.91946992864424e-06,
"loss": 0.0846,
"step": 5490
},
{
"epoch": 8.41,
"learning_rate": 8.834522595990486e-06,
"loss": 0.0766,
"step": 5500
},
{
"epoch": 8.42,
"learning_rate": 8.749575263336731e-06,
"loss": 0.0697,
"step": 5510
},
{
"epoch": 8.44,
"learning_rate": 8.664627930682977e-06,
"loss": 0.0611,
"step": 5520
},
{
"epoch": 8.45,
"learning_rate": 8.579680598029222e-06,
"loss": 0.0808,
"step": 5530
},
{
"epoch": 8.47,
"learning_rate": 8.494733265375469e-06,
"loss": 0.0697,
"step": 5540
},
{
"epoch": 8.48,
"learning_rate": 8.409785932721713e-06,
"loss": 0.1034,
"step": 5550
},
{
"epoch": 8.5,
"learning_rate": 8.324838600067958e-06,
"loss": 0.0583,
"step": 5560
},
{
"epoch": 8.52,
"learning_rate": 8.239891267414204e-06,
"loss": 0.0638,
"step": 5570
},
{
"epoch": 8.53,
"learning_rate": 8.15494393476045e-06,
"loss": 0.0319,
"step": 5580
},
{
"epoch": 8.55,
"learning_rate": 8.069996602106694e-06,
"loss": 0.071,
"step": 5590
},
{
"epoch": 8.56,
"learning_rate": 7.985049269452939e-06,
"loss": 0.0929,
"step": 5600
},
{
"epoch": 8.58,
"learning_rate": 7.900101936799185e-06,
"loss": 0.0728,
"step": 5610
},
{
"epoch": 8.59,
"learning_rate": 7.81515460414543e-06,
"loss": 0.0868,
"step": 5620
},
{
"epoch": 8.61,
"learning_rate": 7.730207271491675e-06,
"loss": 0.0725,
"step": 5630
},
{
"epoch": 8.62,
"learning_rate": 7.645259938837921e-06,
"loss": 0.1055,
"step": 5640
},
{
"epoch": 8.64,
"learning_rate": 7.560312606184167e-06,
"loss": 0.0678,
"step": 5650
},
{
"epoch": 8.65,
"learning_rate": 7.475365273530411e-06,
"loss": 0.0914,
"step": 5660
},
{
"epoch": 8.67,
"learning_rate": 7.390417940876657e-06,
"loss": 0.0646,
"step": 5670
},
{
"epoch": 8.68,
"learning_rate": 7.305470608222902e-06,
"loss": 0.0699,
"step": 5680
},
{
"epoch": 8.7,
"learning_rate": 7.220523275569148e-06,
"loss": 0.071,
"step": 5690
},
{
"epoch": 8.71,
"learning_rate": 7.135575942915393e-06,
"loss": 0.1006,
"step": 5700
},
{
"epoch": 8.73,
"learning_rate": 7.050628610261638e-06,
"loss": 0.0402,
"step": 5710
},
{
"epoch": 8.74,
"learning_rate": 6.965681277607883e-06,
"loss": 0.1133,
"step": 5720
},
{
"epoch": 8.76,
"learning_rate": 6.880733944954129e-06,
"loss": 0.0616,
"step": 5730
},
{
"epoch": 8.78,
"learning_rate": 6.795786612300374e-06,
"loss": 0.0836,
"step": 5740
},
{
"epoch": 8.79,
"learning_rate": 6.710839279646619e-06,
"loss": 0.0516,
"step": 5750
},
{
"epoch": 8.81,
"learning_rate": 6.6258919469928655e-06,
"loss": 0.0467,
"step": 5760
},
{
"epoch": 8.82,
"learning_rate": 6.54094461433911e-06,
"loss": 0.1025,
"step": 5770
},
{
"epoch": 8.84,
"learning_rate": 6.455997281685355e-06,
"loss": 0.071,
"step": 5780
},
{
"epoch": 8.85,
"learning_rate": 6.3710499490316006e-06,
"loss": 0.154,
"step": 5790
},
{
"epoch": 8.87,
"learning_rate": 6.286102616377847e-06,
"loss": 0.0633,
"step": 5800
},
{
"epoch": 8.88,
"learning_rate": 6.201155283724092e-06,
"loss": 0.0912,
"step": 5810
},
{
"epoch": 8.9,
"learning_rate": 6.1162079510703365e-06,
"loss": 0.051,
"step": 5820
},
{
"epoch": 8.91,
"learning_rate": 6.031260618416582e-06,
"loss": 0.0584,
"step": 5830
},
{
"epoch": 8.93,
"learning_rate": 5.946313285762827e-06,
"loss": 0.0714,
"step": 5840
},
{
"epoch": 8.94,
"learning_rate": 5.861365953109073e-06,
"loss": 0.0534,
"step": 5850
},
{
"epoch": 8.96,
"learning_rate": 5.776418620455318e-06,
"loss": 0.0411,
"step": 5860
},
{
"epoch": 8.97,
"learning_rate": 5.6914712878015636e-06,
"loss": 0.0461,
"step": 5870
},
{
"epoch": 8.99,
"learning_rate": 5.606523955147808e-06,
"loss": 0.063,
"step": 5880
},
{
"epoch": 9.0,
"eval_accuracy": 0.7262655205348615,
"eval_loss": 1.1334831714630127,
"eval_runtime": 48.13,
"eval_samples_per_second": 108.768,
"eval_steps_per_second": 13.609,
"step": 5887
},
{
"epoch": 9.0,
"learning_rate": 5.521576622494054e-06,
"loss": 0.0773,
"step": 5890
},
{
"epoch": 9.02,
"learning_rate": 5.436629289840299e-06,
"loss": 0.0471,
"step": 5900
},
{
"epoch": 9.04,
"learning_rate": 5.351681957186545e-06,
"loss": 0.0497,
"step": 5910
},
{
"epoch": 9.05,
"learning_rate": 5.26673462453279e-06,
"loss": 0.1033,
"step": 5920
},
{
"epoch": 9.07,
"learning_rate": 5.181787291879035e-06,
"loss": 0.0409,
"step": 5930
},
{
"epoch": 9.08,
"learning_rate": 5.09683995922528e-06,
"loss": 0.0626,
"step": 5940
},
{
"epoch": 9.1,
"learning_rate": 5.011892626571526e-06,
"loss": 0.05,
"step": 5950
},
{
"epoch": 9.11,
"learning_rate": 4.926945293917771e-06,
"loss": 0.0466,
"step": 5960
},
{
"epoch": 9.13,
"learning_rate": 4.841997961264017e-06,
"loss": 0.0698,
"step": 5970
},
{
"epoch": 9.14,
"learning_rate": 4.7570506286102625e-06,
"loss": 0.0583,
"step": 5980
},
{
"epoch": 9.16,
"learning_rate": 4.672103295956507e-06,
"loss": 0.0232,
"step": 5990
},
{
"epoch": 9.17,
"learning_rate": 4.587155963302753e-06,
"loss": 0.0466,
"step": 6000
},
{
"epoch": 9.19,
"learning_rate": 4.5022086306489975e-06,
"loss": 0.0613,
"step": 6010
},
{
"epoch": 9.2,
"learning_rate": 4.417261297995243e-06,
"loss": 0.0691,
"step": 6020
},
{
"epoch": 9.22,
"learning_rate": 4.332313965341489e-06,
"loss": 0.0281,
"step": 6030
},
{
"epoch": 9.23,
"learning_rate": 4.247366632687734e-06,
"loss": 0.0601,
"step": 6040
},
{
"epoch": 9.25,
"learning_rate": 4.162419300033979e-06,
"loss": 0.059,
"step": 6050
},
{
"epoch": 9.26,
"learning_rate": 4.077471967380225e-06,
"loss": 0.0577,
"step": 6060
},
{
"epoch": 9.28,
"learning_rate": 3.992524634726469e-06,
"loss": 0.085,
"step": 6070
},
{
"epoch": 9.29,
"learning_rate": 3.907577302072715e-06,
"loss": 0.0246,
"step": 6080
},
{
"epoch": 9.31,
"learning_rate": 3.8226299694189605e-06,
"loss": 0.0697,
"step": 6090
},
{
"epoch": 9.33,
"learning_rate": 3.7376826367652057e-06,
"loss": 0.0333,
"step": 6100
},
{
"epoch": 9.34,
"learning_rate": 3.652735304111451e-06,
"loss": 0.0165,
"step": 6110
},
{
"epoch": 9.36,
"learning_rate": 3.5677879714576964e-06,
"loss": 0.0401,
"step": 6120
},
{
"epoch": 9.37,
"learning_rate": 3.4828406388039416e-06,
"loss": 0.0526,
"step": 6130
},
{
"epoch": 9.39,
"learning_rate": 3.397893306150187e-06,
"loss": 0.0617,
"step": 6140
},
{
"epoch": 9.4,
"learning_rate": 3.3129459734964328e-06,
"loss": 0.0576,
"step": 6150
},
{
"epoch": 9.42,
"learning_rate": 3.2279986408426775e-06,
"loss": 0.0541,
"step": 6160
},
{
"epoch": 9.43,
"learning_rate": 3.1430513081889235e-06,
"loss": 0.0522,
"step": 6170
},
{
"epoch": 9.45,
"learning_rate": 3.0581039755351682e-06,
"loss": 0.031,
"step": 6180
},
{
"epoch": 9.46,
"learning_rate": 2.9731566428814134e-06,
"loss": 0.0298,
"step": 6190
},
{
"epoch": 9.48,
"learning_rate": 2.888209310227659e-06,
"loss": 0.022,
"step": 6200
},
{
"epoch": 9.49,
"learning_rate": 2.803261977573904e-06,
"loss": 0.0553,
"step": 6210
},
{
"epoch": 9.51,
"learning_rate": 2.7183146449201493e-06,
"loss": 0.0275,
"step": 6220
},
{
"epoch": 9.52,
"learning_rate": 2.633367312266395e-06,
"loss": 0.0227,
"step": 6230
},
{
"epoch": 9.54,
"learning_rate": 2.54841997961264e-06,
"loss": 0.0528,
"step": 6240
},
{
"epoch": 9.55,
"learning_rate": 2.4634726469588856e-06,
"loss": 0.0635,
"step": 6250
},
{
"epoch": 9.57,
"learning_rate": 2.3785253143051312e-06,
"loss": 0.0572,
"step": 6260
},
{
"epoch": 9.59,
"learning_rate": 2.2935779816513764e-06,
"loss": 0.042,
"step": 6270
},
{
"epoch": 9.6,
"learning_rate": 2.2086306489976216e-06,
"loss": 0.0422,
"step": 6280
},
{
"epoch": 9.62,
"learning_rate": 2.123683316343867e-06,
"loss": 0.0311,
"step": 6290
},
{
"epoch": 9.63,
"learning_rate": 2.0387359836901123e-06,
"loss": 0.0375,
"step": 6300
},
{
"epoch": 9.65,
"learning_rate": 1.9537886510363575e-06,
"loss": 0.0491,
"step": 6310
},
{
"epoch": 9.66,
"learning_rate": 1.8688413183826028e-06,
"loss": 0.0537,
"step": 6320
},
{
"epoch": 9.68,
"learning_rate": 1.7838939857288482e-06,
"loss": 0.0496,
"step": 6330
},
{
"epoch": 9.69,
"learning_rate": 1.6989466530750936e-06,
"loss": 0.0478,
"step": 6340
},
{
"epoch": 9.71,
"learning_rate": 1.6139993204213387e-06,
"loss": 0.0283,
"step": 6350
},
{
"epoch": 9.72,
"learning_rate": 1.5290519877675841e-06,
"loss": 0.0373,
"step": 6360
},
{
"epoch": 9.74,
"learning_rate": 1.4441046551138295e-06,
"loss": 0.0491,
"step": 6370
},
{
"epoch": 9.75,
"learning_rate": 1.3591573224600747e-06,
"loss": 0.0213,
"step": 6380
},
{
"epoch": 9.77,
"learning_rate": 1.27420998980632e-06,
"loss": 0.0414,
"step": 6390
},
{
"epoch": 9.78,
"learning_rate": 1.1892626571525656e-06,
"loss": 0.0573,
"step": 6400
},
{
"epoch": 9.8,
"learning_rate": 1.1043153244988108e-06,
"loss": 0.0467,
"step": 6410
},
{
"epoch": 9.81,
"learning_rate": 1.0193679918450562e-06,
"loss": 0.0545,
"step": 6420
},
{
"epoch": 9.83,
"learning_rate": 9.344206591913014e-07,
"loss": 0.042,
"step": 6430
},
{
"epoch": 9.85,
"learning_rate": 8.494733265375468e-07,
"loss": 0.0404,
"step": 6440
},
{
"epoch": 9.86,
"learning_rate": 7.645259938837921e-07,
"loss": 0.0524,
"step": 6450
},
{
"epoch": 9.88,
"learning_rate": 6.795786612300373e-07,
"loss": 0.0228,
"step": 6460
},
{
"epoch": 9.89,
"learning_rate": 5.946313285762828e-07,
"loss": 0.0444,
"step": 6470
},
{
"epoch": 9.91,
"learning_rate": 5.096839959225281e-07,
"loss": 0.0197,
"step": 6480
},
{
"epoch": 9.92,
"learning_rate": 4.247366632687734e-07,
"loss": 0.0297,
"step": 6490
},
{
"epoch": 9.94,
"learning_rate": 3.3978933061501866e-07,
"loss": 0.0422,
"step": 6500
},
{
"epoch": 9.95,
"learning_rate": 2.5484199796126404e-07,
"loss": 0.041,
"step": 6510
},
{
"epoch": 9.97,
"learning_rate": 1.6989466530750933e-07,
"loss": 0.0314,
"step": 6520
},
{
"epoch": 9.98,
"learning_rate": 8.494733265375467e-08,
"loss": 0.0388,
"step": 6530
},
{
"epoch": 10.0,
"learning_rate": 0.0,
"loss": 0.0562,
"step": 6540
},
{
"epoch": 10.0,
"eval_accuracy": 0.7306590257879656,
"eval_loss": 1.1663085222244263,
"eval_runtime": 50.0529,
"eval_samples_per_second": 104.589,
"eval_steps_per_second": 13.086,
"step": 6540
},
{
"epoch": 10.0,
"step": 6540,
"total_flos": 1.6218250349213123e+19,
"train_loss": 0.06548295821026195,
"train_runtime": 2722.3253,
"train_samples_per_second": 76.905,
"train_steps_per_second": 2.402
}
],
"logging_steps": 10,
"max_steps": 6540,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 1.6218250349213123e+19,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}