mmomm25's picture
Training in progress, epoch 6
13b7fdf verified
raw
history blame
132 kB
{
"best_metric": 1.9407862424850464,
"best_model_checkpoint": "pvt-small-224-ConcreteClassifier-PVT\\checkpoint-9635",
"epoch": 6.0,
"eval_steps": 500,
"global_step": 11562,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.001,
"loss": 2.7631,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 0.001,
"loss": 2.0945,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 0.001,
"loss": 1.9938,
"step": 30
},
{
"epoch": 0.02,
"learning_rate": 0.001,
"loss": 1.9829,
"step": 40
},
{
"epoch": 0.03,
"learning_rate": 0.001,
"loss": 2.0147,
"step": 50
},
{
"epoch": 0.03,
"learning_rate": 0.001,
"loss": 2.096,
"step": 60
},
{
"epoch": 0.04,
"learning_rate": 0.001,
"loss": 2.006,
"step": 70
},
{
"epoch": 0.04,
"learning_rate": 0.001,
"loss": 1.9784,
"step": 80
},
{
"epoch": 0.05,
"learning_rate": 0.001,
"loss": 1.9937,
"step": 90
},
{
"epoch": 0.05,
"learning_rate": 0.001,
"loss": 1.9689,
"step": 100
},
{
"epoch": 0.06,
"learning_rate": 0.001,
"loss": 2.0182,
"step": 110
},
{
"epoch": 0.06,
"learning_rate": 0.001,
"loss": 1.9828,
"step": 120
},
{
"epoch": 0.07,
"learning_rate": 0.001,
"loss": 1.9499,
"step": 130
},
{
"epoch": 0.07,
"learning_rate": 0.001,
"loss": 1.9696,
"step": 140
},
{
"epoch": 0.08,
"learning_rate": 0.001,
"loss": 1.9334,
"step": 150
},
{
"epoch": 0.08,
"learning_rate": 0.001,
"loss": 1.9834,
"step": 160
},
{
"epoch": 0.09,
"learning_rate": 0.001,
"loss": 1.9474,
"step": 170
},
{
"epoch": 0.09,
"learning_rate": 0.001,
"loss": 1.9558,
"step": 180
},
{
"epoch": 0.1,
"learning_rate": 0.001,
"loss": 1.9509,
"step": 190
},
{
"epoch": 0.1,
"learning_rate": 0.001,
"loss": 1.9384,
"step": 200
},
{
"epoch": 0.11,
"learning_rate": 0.001,
"loss": 1.9978,
"step": 210
},
{
"epoch": 0.11,
"learning_rate": 0.001,
"loss": 1.9604,
"step": 220
},
{
"epoch": 0.12,
"learning_rate": 0.001,
"loss": 1.971,
"step": 230
},
{
"epoch": 0.12,
"learning_rate": 0.001,
"loss": 1.9705,
"step": 240
},
{
"epoch": 0.13,
"learning_rate": 0.001,
"loss": 1.9544,
"step": 250
},
{
"epoch": 0.13,
"learning_rate": 0.001,
"loss": 1.9343,
"step": 260
},
{
"epoch": 0.14,
"learning_rate": 0.001,
"loss": 1.9263,
"step": 270
},
{
"epoch": 0.15,
"learning_rate": 0.001,
"loss": 1.9695,
"step": 280
},
{
"epoch": 0.15,
"learning_rate": 0.001,
"loss": 1.9348,
"step": 290
},
{
"epoch": 0.16,
"learning_rate": 0.001,
"loss": 1.9506,
"step": 300
},
{
"epoch": 0.16,
"learning_rate": 0.001,
"loss": 1.9976,
"step": 310
},
{
"epoch": 0.17,
"learning_rate": 0.001,
"loss": 1.9527,
"step": 320
},
{
"epoch": 0.17,
"learning_rate": 0.001,
"loss": 1.9526,
"step": 330
},
{
"epoch": 0.18,
"learning_rate": 0.001,
"loss": 1.9623,
"step": 340
},
{
"epoch": 0.18,
"learning_rate": 0.001,
"loss": 1.9455,
"step": 350
},
{
"epoch": 0.19,
"learning_rate": 0.001,
"loss": 1.9286,
"step": 360
},
{
"epoch": 0.19,
"learning_rate": 0.001,
"loss": 1.9476,
"step": 370
},
{
"epoch": 0.2,
"learning_rate": 0.001,
"loss": 1.9484,
"step": 380
},
{
"epoch": 0.2,
"learning_rate": 0.001,
"loss": 1.9564,
"step": 390
},
{
"epoch": 0.21,
"learning_rate": 0.001,
"loss": 1.9471,
"step": 400
},
{
"epoch": 0.21,
"learning_rate": 0.001,
"loss": 1.9434,
"step": 410
},
{
"epoch": 0.22,
"learning_rate": 0.001,
"loss": 1.928,
"step": 420
},
{
"epoch": 0.22,
"learning_rate": 0.001,
"loss": 1.9543,
"step": 430
},
{
"epoch": 0.23,
"learning_rate": 0.001,
"loss": 1.8994,
"step": 440
},
{
"epoch": 0.23,
"learning_rate": 0.001,
"loss": 2.029,
"step": 450
},
{
"epoch": 0.24,
"learning_rate": 0.001,
"loss": 1.9449,
"step": 460
},
{
"epoch": 0.24,
"learning_rate": 0.001,
"loss": 1.9539,
"step": 470
},
{
"epoch": 0.25,
"learning_rate": 0.001,
"loss": 1.9541,
"step": 480
},
{
"epoch": 0.25,
"learning_rate": 0.001,
"loss": 1.956,
"step": 490
},
{
"epoch": 0.26,
"learning_rate": 0.001,
"loss": 1.9707,
"step": 500
},
{
"epoch": 0.26,
"learning_rate": 0.001,
"loss": 1.9402,
"step": 510
},
{
"epoch": 0.27,
"learning_rate": 0.001,
"loss": 1.9656,
"step": 520
},
{
"epoch": 0.28,
"learning_rate": 0.001,
"loss": 1.9372,
"step": 530
},
{
"epoch": 0.28,
"learning_rate": 0.001,
"loss": 1.955,
"step": 540
},
{
"epoch": 0.29,
"learning_rate": 0.001,
"loss": 1.9288,
"step": 550
},
{
"epoch": 0.29,
"learning_rate": 0.001,
"loss": 1.9574,
"step": 560
},
{
"epoch": 0.3,
"learning_rate": 0.001,
"loss": 1.956,
"step": 570
},
{
"epoch": 0.3,
"learning_rate": 0.001,
"loss": 1.9587,
"step": 580
},
{
"epoch": 0.31,
"learning_rate": 0.001,
"loss": 1.9473,
"step": 590
},
{
"epoch": 0.31,
"learning_rate": 0.001,
"loss": 1.9452,
"step": 600
},
{
"epoch": 0.32,
"learning_rate": 0.001,
"loss": 1.9648,
"step": 610
},
{
"epoch": 0.32,
"learning_rate": 0.001,
"loss": 1.9314,
"step": 620
},
{
"epoch": 0.33,
"learning_rate": 0.001,
"loss": 1.961,
"step": 630
},
{
"epoch": 0.33,
"learning_rate": 0.001,
"loss": 1.9386,
"step": 640
},
{
"epoch": 0.34,
"learning_rate": 0.001,
"loss": 1.9546,
"step": 650
},
{
"epoch": 0.34,
"learning_rate": 0.001,
"loss": 1.967,
"step": 660
},
{
"epoch": 0.35,
"learning_rate": 0.001,
"loss": 1.9451,
"step": 670
},
{
"epoch": 0.35,
"learning_rate": 0.001,
"loss": 1.9475,
"step": 680
},
{
"epoch": 0.36,
"learning_rate": 0.001,
"loss": 1.9518,
"step": 690
},
{
"epoch": 0.36,
"learning_rate": 0.001,
"loss": 1.9518,
"step": 700
},
{
"epoch": 0.37,
"learning_rate": 0.001,
"loss": 1.9481,
"step": 710
},
{
"epoch": 0.37,
"learning_rate": 0.001,
"loss": 1.9456,
"step": 720
},
{
"epoch": 0.38,
"learning_rate": 0.001,
"loss": 1.9362,
"step": 730
},
{
"epoch": 0.38,
"learning_rate": 0.001,
"loss": 1.9188,
"step": 740
},
{
"epoch": 0.39,
"learning_rate": 0.001,
"loss": 2.0077,
"step": 750
},
{
"epoch": 0.39,
"learning_rate": 0.001,
"loss": 1.9442,
"step": 760
},
{
"epoch": 0.4,
"learning_rate": 0.001,
"loss": 1.9348,
"step": 770
},
{
"epoch": 0.4,
"learning_rate": 0.001,
"loss": 1.9512,
"step": 780
},
{
"epoch": 0.41,
"learning_rate": 0.001,
"loss": 1.9409,
"step": 790
},
{
"epoch": 0.42,
"learning_rate": 0.001,
"loss": 1.9404,
"step": 800
},
{
"epoch": 0.42,
"learning_rate": 0.001,
"loss": 1.9656,
"step": 810
},
{
"epoch": 0.43,
"learning_rate": 0.001,
"loss": 1.948,
"step": 820
},
{
"epoch": 0.43,
"learning_rate": 0.001,
"loss": 1.9471,
"step": 830
},
{
"epoch": 0.44,
"learning_rate": 0.001,
"loss": 1.9453,
"step": 840
},
{
"epoch": 0.44,
"learning_rate": 0.001,
"loss": 1.9386,
"step": 850
},
{
"epoch": 0.45,
"learning_rate": 0.001,
"loss": 1.9568,
"step": 860
},
{
"epoch": 0.45,
"learning_rate": 0.001,
"loss": 1.9498,
"step": 870
},
{
"epoch": 0.46,
"learning_rate": 0.001,
"loss": 1.9621,
"step": 880
},
{
"epoch": 0.46,
"learning_rate": 0.001,
"loss": 1.9444,
"step": 890
},
{
"epoch": 0.47,
"learning_rate": 0.001,
"loss": 1.9515,
"step": 900
},
{
"epoch": 0.47,
"learning_rate": 0.001,
"loss": 1.9419,
"step": 910
},
{
"epoch": 0.48,
"learning_rate": 0.001,
"loss": 1.948,
"step": 920
},
{
"epoch": 0.48,
"learning_rate": 0.001,
"loss": 1.9427,
"step": 930
},
{
"epoch": 0.49,
"learning_rate": 0.001,
"loss": 1.9586,
"step": 940
},
{
"epoch": 0.49,
"learning_rate": 0.001,
"loss": 1.9588,
"step": 950
},
{
"epoch": 0.5,
"learning_rate": 0.001,
"loss": 1.9511,
"step": 960
},
{
"epoch": 0.5,
"learning_rate": 0.001,
"loss": 1.9505,
"step": 970
},
{
"epoch": 0.51,
"learning_rate": 0.001,
"loss": 1.9424,
"step": 980
},
{
"epoch": 0.51,
"learning_rate": 0.001,
"loss": 1.9378,
"step": 990
},
{
"epoch": 0.52,
"learning_rate": 0.001,
"loss": 1.9501,
"step": 1000
},
{
"epoch": 0.52,
"learning_rate": 0.001,
"loss": 1.9352,
"step": 1010
},
{
"epoch": 0.53,
"learning_rate": 0.001,
"loss": 1.9338,
"step": 1020
},
{
"epoch": 0.53,
"learning_rate": 0.001,
"loss": 1.9546,
"step": 1030
},
{
"epoch": 0.54,
"learning_rate": 0.001,
"loss": 1.9436,
"step": 1040
},
{
"epoch": 0.54,
"learning_rate": 0.001,
"loss": 1.9347,
"step": 1050
},
{
"epoch": 0.55,
"learning_rate": 0.001,
"loss": 1.9458,
"step": 1060
},
{
"epoch": 0.56,
"learning_rate": 0.001,
"loss": 1.9389,
"step": 1070
},
{
"epoch": 0.56,
"learning_rate": 0.001,
"loss": 1.9445,
"step": 1080
},
{
"epoch": 0.57,
"learning_rate": 0.001,
"loss": 1.9594,
"step": 1090
},
{
"epoch": 0.57,
"learning_rate": 0.001,
"loss": 1.9666,
"step": 1100
},
{
"epoch": 0.58,
"learning_rate": 0.001,
"loss": 1.9567,
"step": 1110
},
{
"epoch": 0.58,
"learning_rate": 0.001,
"loss": 1.9527,
"step": 1120
},
{
"epoch": 0.59,
"learning_rate": 0.001,
"loss": 1.9434,
"step": 1130
},
{
"epoch": 0.59,
"learning_rate": 0.001,
"loss": 1.9252,
"step": 1140
},
{
"epoch": 0.6,
"learning_rate": 0.001,
"loss": 1.9541,
"step": 1150
},
{
"epoch": 0.6,
"learning_rate": 0.001,
"loss": 1.9619,
"step": 1160
},
{
"epoch": 0.61,
"learning_rate": 0.001,
"loss": 1.9531,
"step": 1170
},
{
"epoch": 0.61,
"learning_rate": 0.001,
"loss": 1.9419,
"step": 1180
},
{
"epoch": 0.62,
"learning_rate": 0.001,
"loss": 1.9521,
"step": 1190
},
{
"epoch": 0.62,
"learning_rate": 0.001,
"loss": 1.9358,
"step": 1200
},
{
"epoch": 0.63,
"learning_rate": 0.001,
"loss": 1.9166,
"step": 1210
},
{
"epoch": 0.63,
"learning_rate": 0.001,
"loss": 2.0,
"step": 1220
},
{
"epoch": 0.64,
"learning_rate": 0.001,
"loss": 1.9459,
"step": 1230
},
{
"epoch": 0.64,
"learning_rate": 0.001,
"loss": 1.9397,
"step": 1240
},
{
"epoch": 0.65,
"learning_rate": 0.001,
"loss": 1.9722,
"step": 1250
},
{
"epoch": 0.65,
"learning_rate": 0.001,
"loss": 1.9704,
"step": 1260
},
{
"epoch": 0.66,
"learning_rate": 0.001,
"loss": 1.957,
"step": 1270
},
{
"epoch": 0.66,
"learning_rate": 0.001,
"loss": 1.9551,
"step": 1280
},
{
"epoch": 0.67,
"learning_rate": 0.001,
"loss": 1.9534,
"step": 1290
},
{
"epoch": 0.67,
"learning_rate": 0.001,
"loss": 1.9718,
"step": 1300
},
{
"epoch": 0.68,
"learning_rate": 0.001,
"loss": 1.9597,
"step": 1310
},
{
"epoch": 0.69,
"learning_rate": 0.001,
"loss": 1.9527,
"step": 1320
},
{
"epoch": 0.69,
"learning_rate": 0.001,
"loss": 1.9362,
"step": 1330
},
{
"epoch": 0.7,
"learning_rate": 0.001,
"loss": 1.9636,
"step": 1340
},
{
"epoch": 0.7,
"learning_rate": 0.001,
"loss": 1.95,
"step": 1350
},
{
"epoch": 0.71,
"learning_rate": 0.001,
"loss": 1.9551,
"step": 1360
},
{
"epoch": 0.71,
"learning_rate": 0.001,
"loss": 2.0172,
"step": 1370
},
{
"epoch": 0.72,
"learning_rate": 0.001,
"loss": 1.943,
"step": 1380
},
{
"epoch": 0.72,
"learning_rate": 0.001,
"loss": 1.9486,
"step": 1390
},
{
"epoch": 0.73,
"learning_rate": 0.001,
"loss": 1.9877,
"step": 1400
},
{
"epoch": 0.73,
"learning_rate": 0.001,
"loss": 1.976,
"step": 1410
},
{
"epoch": 0.74,
"learning_rate": 0.001,
"loss": 1.9371,
"step": 1420
},
{
"epoch": 0.74,
"learning_rate": 0.001,
"loss": 1.9797,
"step": 1430
},
{
"epoch": 0.75,
"learning_rate": 0.001,
"loss": 1.9719,
"step": 1440
},
{
"epoch": 0.75,
"learning_rate": 0.001,
"loss": 1.925,
"step": 1450
},
{
"epoch": 0.76,
"learning_rate": 0.001,
"loss": 1.9756,
"step": 1460
},
{
"epoch": 0.76,
"learning_rate": 0.001,
"loss": 1.9553,
"step": 1470
},
{
"epoch": 0.77,
"learning_rate": 0.001,
"loss": 1.949,
"step": 1480
},
{
"epoch": 0.77,
"learning_rate": 0.001,
"loss": 1.9494,
"step": 1490
},
{
"epoch": 0.78,
"learning_rate": 0.001,
"loss": 1.9454,
"step": 1500
},
{
"epoch": 0.78,
"learning_rate": 0.001,
"loss": 1.9347,
"step": 1510
},
{
"epoch": 0.79,
"learning_rate": 0.001,
"loss": 1.9342,
"step": 1520
},
{
"epoch": 0.79,
"learning_rate": 0.001,
"loss": 1.9762,
"step": 1530
},
{
"epoch": 0.8,
"learning_rate": 0.001,
"loss": 1.9467,
"step": 1540
},
{
"epoch": 0.8,
"learning_rate": 0.001,
"loss": 1.9493,
"step": 1550
},
{
"epoch": 0.81,
"learning_rate": 0.001,
"loss": 1.9309,
"step": 1560
},
{
"epoch": 0.81,
"learning_rate": 0.001,
"loss": 1.9875,
"step": 1570
},
{
"epoch": 0.82,
"learning_rate": 0.001,
"loss": 1.9379,
"step": 1580
},
{
"epoch": 0.83,
"learning_rate": 0.001,
"loss": 1.9231,
"step": 1590
},
{
"epoch": 0.83,
"learning_rate": 0.001,
"loss": 1.9163,
"step": 1600
},
{
"epoch": 0.84,
"learning_rate": 0.001,
"loss": 1.9894,
"step": 1610
},
{
"epoch": 0.84,
"learning_rate": 0.001,
"loss": 1.9543,
"step": 1620
},
{
"epoch": 0.85,
"learning_rate": 0.001,
"loss": 1.9237,
"step": 1630
},
{
"epoch": 0.85,
"learning_rate": 0.001,
"loss": 2.1552,
"step": 1640
},
{
"epoch": 0.86,
"learning_rate": 0.001,
"loss": 2.0399,
"step": 1650
},
{
"epoch": 0.86,
"learning_rate": 0.001,
"loss": 1.971,
"step": 1660
},
{
"epoch": 0.87,
"learning_rate": 0.001,
"loss": 2.0006,
"step": 1670
},
{
"epoch": 0.87,
"learning_rate": 0.001,
"loss": 1.9451,
"step": 1680
},
{
"epoch": 0.88,
"learning_rate": 0.001,
"loss": 1.993,
"step": 1690
},
{
"epoch": 0.88,
"learning_rate": 0.001,
"loss": 1.9586,
"step": 1700
},
{
"epoch": 0.89,
"learning_rate": 0.001,
"loss": 1.963,
"step": 1710
},
{
"epoch": 0.89,
"learning_rate": 0.001,
"loss": 1.9641,
"step": 1720
},
{
"epoch": 0.9,
"learning_rate": 0.001,
"loss": 1.9555,
"step": 1730
},
{
"epoch": 0.9,
"learning_rate": 0.001,
"loss": 1.9381,
"step": 1740
},
{
"epoch": 0.91,
"learning_rate": 0.001,
"loss": 1.934,
"step": 1750
},
{
"epoch": 0.91,
"learning_rate": 0.001,
"loss": 2.0062,
"step": 1760
},
{
"epoch": 0.92,
"learning_rate": 0.001,
"loss": 1.9315,
"step": 1770
},
{
"epoch": 0.92,
"learning_rate": 0.001,
"loss": 1.9626,
"step": 1780
},
{
"epoch": 0.93,
"learning_rate": 0.001,
"loss": 1.9135,
"step": 1790
},
{
"epoch": 0.93,
"learning_rate": 0.001,
"loss": 1.9756,
"step": 1800
},
{
"epoch": 0.94,
"learning_rate": 0.001,
"loss": 1.9628,
"step": 1810
},
{
"epoch": 0.94,
"learning_rate": 0.001,
"loss": 1.952,
"step": 1820
},
{
"epoch": 0.95,
"learning_rate": 0.001,
"loss": 1.9326,
"step": 1830
},
{
"epoch": 0.95,
"learning_rate": 0.001,
"loss": 1.9552,
"step": 1840
},
{
"epoch": 0.96,
"learning_rate": 0.001,
"loss": 1.9527,
"step": 1850
},
{
"epoch": 0.97,
"learning_rate": 0.001,
"loss": 1.938,
"step": 1860
},
{
"epoch": 0.97,
"learning_rate": 0.001,
"loss": 1.9452,
"step": 1870
},
{
"epoch": 0.98,
"learning_rate": 0.001,
"loss": 1.9515,
"step": 1880
},
{
"epoch": 0.98,
"learning_rate": 0.001,
"loss": 1.9465,
"step": 1890
},
{
"epoch": 0.99,
"learning_rate": 0.001,
"loss": 1.9524,
"step": 1900
},
{
"epoch": 0.99,
"learning_rate": 0.001,
"loss": 1.9271,
"step": 1910
},
{
"epoch": 1.0,
"learning_rate": 0.001,
"loss": 1.981,
"step": 1920
},
{
"epoch": 1.0,
"eval_accuracy": {
"accuracy": 0.1556420233463035
},
"eval_f1": {
"f1": 0.03848003848003848
},
"eval_loss": 1.9584157466888428,
"eval_precision": {
"precision": 0.022234574763757644
},
"eval_recall": {
"recall": 0.14285714285714285
},
"eval_runtime": 201.5846,
"eval_samples_per_second": 19.123,
"eval_steps_per_second": 9.564,
"step": 1927
},
{
"epoch": 1.0,
"learning_rate": 0.001,
"loss": 1.9356,
"step": 1930
},
{
"epoch": 1.01,
"learning_rate": 0.001,
"loss": 1.9557,
"step": 1940
},
{
"epoch": 1.01,
"learning_rate": 0.001,
"loss": 1.9435,
"step": 1950
},
{
"epoch": 1.02,
"learning_rate": 0.001,
"loss": 1.9192,
"step": 1960
},
{
"epoch": 1.02,
"learning_rate": 0.001,
"loss": 1.9903,
"step": 1970
},
{
"epoch": 1.03,
"learning_rate": 0.001,
"loss": 1.9343,
"step": 1980
},
{
"epoch": 1.03,
"learning_rate": 0.001,
"loss": 1.9753,
"step": 1990
},
{
"epoch": 1.04,
"learning_rate": 0.001,
"loss": 1.9178,
"step": 2000
},
{
"epoch": 1.04,
"learning_rate": 0.001,
"loss": 1.925,
"step": 2010
},
{
"epoch": 1.05,
"learning_rate": 0.001,
"loss": 1.955,
"step": 2020
},
{
"epoch": 1.05,
"learning_rate": 0.001,
"loss": 1.9774,
"step": 2030
},
{
"epoch": 1.06,
"learning_rate": 0.001,
"loss": 1.9351,
"step": 2040
},
{
"epoch": 1.06,
"learning_rate": 0.001,
"loss": 1.9794,
"step": 2050
},
{
"epoch": 1.07,
"learning_rate": 0.001,
"loss": 1.9379,
"step": 2060
},
{
"epoch": 1.07,
"learning_rate": 0.001,
"loss": 1.9512,
"step": 2070
},
{
"epoch": 1.08,
"learning_rate": 0.001,
"loss": 1.9483,
"step": 2080
},
{
"epoch": 1.08,
"learning_rate": 0.001,
"loss": 1.9376,
"step": 2090
},
{
"epoch": 1.09,
"learning_rate": 0.001,
"loss": 1.9282,
"step": 2100
},
{
"epoch": 1.09,
"learning_rate": 0.001,
"loss": 1.936,
"step": 2110
},
{
"epoch": 1.1,
"learning_rate": 0.001,
"loss": 1.9811,
"step": 2120
},
{
"epoch": 1.11,
"learning_rate": 0.001,
"loss": 1.9467,
"step": 2130
},
{
"epoch": 1.11,
"learning_rate": 0.001,
"loss": 1.9484,
"step": 2140
},
{
"epoch": 1.12,
"learning_rate": 0.001,
"loss": 1.9356,
"step": 2150
},
{
"epoch": 1.12,
"learning_rate": 0.001,
"loss": 1.9418,
"step": 2160
},
{
"epoch": 1.13,
"learning_rate": 0.001,
"loss": 1.944,
"step": 2170
},
{
"epoch": 1.13,
"learning_rate": 0.001,
"loss": 1.9451,
"step": 2180
},
{
"epoch": 1.14,
"learning_rate": 0.001,
"loss": 1.9423,
"step": 2190
},
{
"epoch": 1.14,
"learning_rate": 0.001,
"loss": 1.9435,
"step": 2200
},
{
"epoch": 1.15,
"learning_rate": 0.001,
"loss": 1.9374,
"step": 2210
},
{
"epoch": 1.15,
"learning_rate": 0.001,
"loss": 1.9436,
"step": 2220
},
{
"epoch": 1.16,
"learning_rate": 0.001,
"loss": 1.9377,
"step": 2230
},
{
"epoch": 1.16,
"learning_rate": 0.001,
"loss": 1.9339,
"step": 2240
},
{
"epoch": 1.17,
"learning_rate": 0.001,
"loss": 1.9285,
"step": 2250
},
{
"epoch": 1.17,
"learning_rate": 0.001,
"loss": 1.9482,
"step": 2260
},
{
"epoch": 1.18,
"learning_rate": 0.001,
"loss": 1.9719,
"step": 2270
},
{
"epoch": 1.18,
"learning_rate": 0.001,
"loss": 1.9526,
"step": 2280
},
{
"epoch": 1.19,
"learning_rate": 0.001,
"loss": 1.9551,
"step": 2290
},
{
"epoch": 1.19,
"learning_rate": 0.001,
"loss": 1.9423,
"step": 2300
},
{
"epoch": 1.2,
"learning_rate": 0.001,
"loss": 1.9501,
"step": 2310
},
{
"epoch": 1.2,
"learning_rate": 0.001,
"loss": 1.9412,
"step": 2320
},
{
"epoch": 1.21,
"learning_rate": 0.001,
"loss": 1.9403,
"step": 2330
},
{
"epoch": 1.21,
"learning_rate": 0.001,
"loss": 1.9462,
"step": 2340
},
{
"epoch": 1.22,
"learning_rate": 0.001,
"loss": 1.9344,
"step": 2350
},
{
"epoch": 1.22,
"learning_rate": 0.001,
"loss": 1.9686,
"step": 2360
},
{
"epoch": 1.23,
"learning_rate": 0.001,
"loss": 1.9476,
"step": 2370
},
{
"epoch": 1.24,
"learning_rate": 0.001,
"loss": 1.955,
"step": 2380
},
{
"epoch": 1.24,
"learning_rate": 0.001,
"loss": 1.9482,
"step": 2390
},
{
"epoch": 1.25,
"learning_rate": 0.001,
"loss": 1.947,
"step": 2400
},
{
"epoch": 1.25,
"learning_rate": 0.001,
"loss": 1.9498,
"step": 2410
},
{
"epoch": 1.26,
"learning_rate": 0.001,
"loss": 1.9463,
"step": 2420
},
{
"epoch": 1.26,
"learning_rate": 0.001,
"loss": 1.9486,
"step": 2430
},
{
"epoch": 1.27,
"learning_rate": 0.001,
"loss": 1.9521,
"step": 2440
},
{
"epoch": 1.27,
"learning_rate": 0.001,
"loss": 1.9454,
"step": 2450
},
{
"epoch": 1.28,
"learning_rate": 0.001,
"loss": 1.939,
"step": 2460
},
{
"epoch": 1.28,
"learning_rate": 0.001,
"loss": 1.9401,
"step": 2470
},
{
"epoch": 1.29,
"learning_rate": 0.001,
"loss": 1.9452,
"step": 2480
},
{
"epoch": 1.29,
"learning_rate": 0.001,
"loss": 1.9474,
"step": 2490
},
{
"epoch": 1.3,
"learning_rate": 0.001,
"loss": 1.9452,
"step": 2500
},
{
"epoch": 1.3,
"learning_rate": 0.001,
"loss": 1.9416,
"step": 2510
},
{
"epoch": 1.31,
"learning_rate": 0.001,
"loss": 1.9523,
"step": 2520
},
{
"epoch": 1.31,
"learning_rate": 0.001,
"loss": 1.9497,
"step": 2530
},
{
"epoch": 1.32,
"learning_rate": 0.001,
"loss": 1.9332,
"step": 2540
},
{
"epoch": 1.32,
"learning_rate": 0.001,
"loss": 1.9372,
"step": 2550
},
{
"epoch": 1.33,
"learning_rate": 0.001,
"loss": 1.9374,
"step": 2560
},
{
"epoch": 1.33,
"learning_rate": 0.001,
"loss": 1.9349,
"step": 2570
},
{
"epoch": 1.34,
"learning_rate": 0.001,
"loss": 1.9223,
"step": 2580
},
{
"epoch": 1.34,
"learning_rate": 0.001,
"loss": 1.9679,
"step": 2590
},
{
"epoch": 1.35,
"learning_rate": 0.001,
"loss": 1.9427,
"step": 2600
},
{
"epoch": 1.35,
"learning_rate": 0.001,
"loss": 1.9377,
"step": 2610
},
{
"epoch": 1.36,
"learning_rate": 0.001,
"loss": 1.9311,
"step": 2620
},
{
"epoch": 1.36,
"learning_rate": 0.001,
"loss": 1.951,
"step": 2630
},
{
"epoch": 1.37,
"learning_rate": 0.001,
"loss": 1.9154,
"step": 2640
},
{
"epoch": 1.38,
"learning_rate": 0.001,
"loss": 1.965,
"step": 2650
},
{
"epoch": 1.38,
"learning_rate": 0.001,
"loss": 1.9611,
"step": 2660
},
{
"epoch": 1.39,
"learning_rate": 0.001,
"loss": 1.9356,
"step": 2670
},
{
"epoch": 1.39,
"learning_rate": 0.001,
"loss": 1.9417,
"step": 2680
},
{
"epoch": 1.4,
"learning_rate": 0.001,
"loss": 1.9597,
"step": 2690
},
{
"epoch": 1.4,
"learning_rate": 0.001,
"loss": 1.9337,
"step": 2700
},
{
"epoch": 1.41,
"learning_rate": 0.001,
"loss": 1.9329,
"step": 2710
},
{
"epoch": 1.41,
"learning_rate": 0.001,
"loss": 1.934,
"step": 2720
},
{
"epoch": 1.42,
"learning_rate": 0.001,
"loss": 1.921,
"step": 2730
},
{
"epoch": 1.42,
"learning_rate": 0.001,
"loss": 1.9422,
"step": 2740
},
{
"epoch": 1.43,
"learning_rate": 0.001,
"loss": 1.9407,
"step": 2750
},
{
"epoch": 1.43,
"learning_rate": 0.001,
"loss": 1.9546,
"step": 2760
},
{
"epoch": 1.44,
"learning_rate": 0.001,
"loss": 1.9527,
"step": 2770
},
{
"epoch": 1.44,
"learning_rate": 0.001,
"loss": 1.9362,
"step": 2780
},
{
"epoch": 1.45,
"learning_rate": 0.001,
"loss": 1.9506,
"step": 2790
},
{
"epoch": 1.45,
"learning_rate": 0.001,
"loss": 1.9293,
"step": 2800
},
{
"epoch": 1.46,
"learning_rate": 0.001,
"loss": 1.9577,
"step": 2810
},
{
"epoch": 1.46,
"learning_rate": 0.001,
"loss": 1.9549,
"step": 2820
},
{
"epoch": 1.47,
"learning_rate": 0.001,
"loss": 1.9555,
"step": 2830
},
{
"epoch": 1.47,
"learning_rate": 0.001,
"loss": 1.9427,
"step": 2840
},
{
"epoch": 1.48,
"learning_rate": 0.001,
"loss": 1.9417,
"step": 2850
},
{
"epoch": 1.48,
"learning_rate": 0.001,
"loss": 1.9328,
"step": 2860
},
{
"epoch": 1.49,
"learning_rate": 0.001,
"loss": 1.948,
"step": 2870
},
{
"epoch": 1.49,
"learning_rate": 0.001,
"loss": 1.9619,
"step": 2880
},
{
"epoch": 1.5,
"learning_rate": 0.001,
"loss": 1.9359,
"step": 2890
},
{
"epoch": 1.5,
"learning_rate": 0.001,
"loss": 1.9323,
"step": 2900
},
{
"epoch": 1.51,
"learning_rate": 0.001,
"loss": 1.9226,
"step": 2910
},
{
"epoch": 1.52,
"learning_rate": 0.001,
"loss": 1.9836,
"step": 2920
},
{
"epoch": 1.52,
"learning_rate": 0.001,
"loss": 1.9518,
"step": 2930
},
{
"epoch": 1.53,
"learning_rate": 0.001,
"loss": 1.9512,
"step": 2940
},
{
"epoch": 1.53,
"learning_rate": 0.001,
"loss": 1.9445,
"step": 2950
},
{
"epoch": 1.54,
"learning_rate": 0.001,
"loss": 1.9528,
"step": 2960
},
{
"epoch": 1.54,
"learning_rate": 0.001,
"loss": 1.9518,
"step": 2970
},
{
"epoch": 1.55,
"learning_rate": 0.001,
"loss": 1.942,
"step": 2980
},
{
"epoch": 1.55,
"learning_rate": 0.001,
"loss": 1.9563,
"step": 2990
},
{
"epoch": 1.56,
"learning_rate": 0.001,
"loss": 1.9378,
"step": 3000
},
{
"epoch": 1.56,
"learning_rate": 0.001,
"loss": 1.9591,
"step": 3010
},
{
"epoch": 1.57,
"learning_rate": 0.001,
"loss": 1.9421,
"step": 3020
},
{
"epoch": 1.57,
"learning_rate": 0.001,
"loss": 1.9447,
"step": 3030
},
{
"epoch": 1.58,
"learning_rate": 0.001,
"loss": 1.9345,
"step": 3040
},
{
"epoch": 1.58,
"learning_rate": 0.001,
"loss": 1.9399,
"step": 3050
},
{
"epoch": 1.59,
"learning_rate": 0.001,
"loss": 1.9321,
"step": 3060
},
{
"epoch": 1.59,
"learning_rate": 0.001,
"loss": 1.9367,
"step": 3070
},
{
"epoch": 1.6,
"learning_rate": 0.001,
"loss": 1.9368,
"step": 3080
},
{
"epoch": 1.6,
"learning_rate": 0.001,
"loss": 1.9531,
"step": 3090
},
{
"epoch": 1.61,
"learning_rate": 0.001,
"loss": 1.9573,
"step": 3100
},
{
"epoch": 1.61,
"learning_rate": 0.001,
"loss": 1.9359,
"step": 3110
},
{
"epoch": 1.62,
"learning_rate": 0.001,
"loss": 1.9541,
"step": 3120
},
{
"epoch": 1.62,
"learning_rate": 0.001,
"loss": 1.9457,
"step": 3130
},
{
"epoch": 1.63,
"learning_rate": 0.001,
"loss": 1.9443,
"step": 3140
},
{
"epoch": 1.63,
"learning_rate": 0.001,
"loss": 1.9431,
"step": 3150
},
{
"epoch": 1.64,
"learning_rate": 0.001,
"loss": 1.9507,
"step": 3160
},
{
"epoch": 1.65,
"learning_rate": 0.001,
"loss": 1.9282,
"step": 3170
},
{
"epoch": 1.65,
"learning_rate": 0.001,
"loss": 1.9731,
"step": 3180
},
{
"epoch": 1.66,
"learning_rate": 0.001,
"loss": 1.9422,
"step": 3190
},
{
"epoch": 1.66,
"learning_rate": 0.001,
"loss": 1.9436,
"step": 3200
},
{
"epoch": 1.67,
"learning_rate": 0.001,
"loss": 1.9439,
"step": 3210
},
{
"epoch": 1.67,
"learning_rate": 0.001,
"loss": 1.9339,
"step": 3220
},
{
"epoch": 1.68,
"learning_rate": 0.001,
"loss": 1.9413,
"step": 3230
},
{
"epoch": 1.68,
"learning_rate": 0.001,
"loss": 1.9429,
"step": 3240
},
{
"epoch": 1.69,
"learning_rate": 0.001,
"loss": 1.9539,
"step": 3250
},
{
"epoch": 1.69,
"learning_rate": 0.001,
"loss": 1.9412,
"step": 3260
},
{
"epoch": 1.7,
"learning_rate": 0.001,
"loss": 1.9442,
"step": 3270
},
{
"epoch": 1.7,
"learning_rate": 0.001,
"loss": 1.953,
"step": 3280
},
{
"epoch": 1.71,
"learning_rate": 0.001,
"loss": 1.9504,
"step": 3290
},
{
"epoch": 1.71,
"learning_rate": 0.001,
"loss": 1.9493,
"step": 3300
},
{
"epoch": 1.72,
"learning_rate": 0.001,
"loss": 1.9371,
"step": 3310
},
{
"epoch": 1.72,
"learning_rate": 0.001,
"loss": 1.9394,
"step": 3320
},
{
"epoch": 1.73,
"learning_rate": 0.001,
"loss": 1.9654,
"step": 3330
},
{
"epoch": 1.73,
"learning_rate": 0.001,
"loss": 1.9607,
"step": 3340
},
{
"epoch": 1.74,
"learning_rate": 0.001,
"loss": 1.956,
"step": 3350
},
{
"epoch": 1.74,
"learning_rate": 0.001,
"loss": 1.9358,
"step": 3360
},
{
"epoch": 1.75,
"learning_rate": 0.001,
"loss": 1.9138,
"step": 3370
},
{
"epoch": 1.75,
"learning_rate": 0.001,
"loss": 1.928,
"step": 3380
},
{
"epoch": 1.76,
"learning_rate": 0.001,
"loss": 1.9845,
"step": 3390
},
{
"epoch": 1.76,
"learning_rate": 0.001,
"loss": 1.9536,
"step": 3400
},
{
"epoch": 1.77,
"learning_rate": 0.001,
"loss": 1.9458,
"step": 3410
},
{
"epoch": 1.77,
"learning_rate": 0.001,
"loss": 1.9565,
"step": 3420
},
{
"epoch": 1.78,
"learning_rate": 0.001,
"loss": 1.935,
"step": 3430
},
{
"epoch": 1.79,
"learning_rate": 0.001,
"loss": 1.9366,
"step": 3440
},
{
"epoch": 1.79,
"learning_rate": 0.001,
"loss": 1.931,
"step": 3450
},
{
"epoch": 1.8,
"learning_rate": 0.001,
"loss": 1.9534,
"step": 3460
},
{
"epoch": 1.8,
"learning_rate": 0.001,
"loss": 1.949,
"step": 3470
},
{
"epoch": 1.81,
"learning_rate": 0.001,
"loss": 1.9455,
"step": 3480
},
{
"epoch": 1.81,
"learning_rate": 0.001,
"loss": 1.9437,
"step": 3490
},
{
"epoch": 1.82,
"learning_rate": 0.001,
"loss": 1.9459,
"step": 3500
},
{
"epoch": 1.82,
"learning_rate": 0.001,
"loss": 1.9354,
"step": 3510
},
{
"epoch": 1.83,
"learning_rate": 0.001,
"loss": 1.9056,
"step": 3520
},
{
"epoch": 1.83,
"learning_rate": 0.001,
"loss": 1.9871,
"step": 3530
},
{
"epoch": 1.84,
"learning_rate": 0.001,
"loss": 1.9884,
"step": 3540
},
{
"epoch": 1.84,
"learning_rate": 0.001,
"loss": 1.944,
"step": 3550
},
{
"epoch": 1.85,
"learning_rate": 0.001,
"loss": 1.9365,
"step": 3560
},
{
"epoch": 1.85,
"learning_rate": 0.001,
"loss": 1.9536,
"step": 3570
},
{
"epoch": 1.86,
"learning_rate": 0.001,
"loss": 1.9269,
"step": 3580
},
{
"epoch": 1.86,
"learning_rate": 0.001,
"loss": 1.9259,
"step": 3590
},
{
"epoch": 1.87,
"learning_rate": 0.001,
"loss": 1.9648,
"step": 3600
},
{
"epoch": 1.87,
"learning_rate": 0.001,
"loss": 1.9642,
"step": 3610
},
{
"epoch": 1.88,
"learning_rate": 0.001,
"loss": 1.9677,
"step": 3620
},
{
"epoch": 1.88,
"learning_rate": 0.001,
"loss": 1.9543,
"step": 3630
},
{
"epoch": 1.89,
"learning_rate": 0.001,
"loss": 1.9517,
"step": 3640
},
{
"epoch": 1.89,
"learning_rate": 0.001,
"loss": 1.9523,
"step": 3650
},
{
"epoch": 1.9,
"learning_rate": 0.001,
"loss": 1.9372,
"step": 3660
},
{
"epoch": 1.9,
"learning_rate": 0.001,
"loss": 1.9453,
"step": 3670
},
{
"epoch": 1.91,
"learning_rate": 0.001,
"loss": 1.9463,
"step": 3680
},
{
"epoch": 1.91,
"learning_rate": 0.001,
"loss": 1.9392,
"step": 3690
},
{
"epoch": 1.92,
"learning_rate": 0.001,
"loss": 1.9467,
"step": 3700
},
{
"epoch": 1.93,
"learning_rate": 0.001,
"loss": 1.9575,
"step": 3710
},
{
"epoch": 1.93,
"learning_rate": 0.001,
"loss": 1.9441,
"step": 3720
},
{
"epoch": 1.94,
"learning_rate": 0.001,
"loss": 1.9534,
"step": 3730
},
{
"epoch": 1.94,
"learning_rate": 0.001,
"loss": 1.9484,
"step": 3740
},
{
"epoch": 1.95,
"learning_rate": 0.001,
"loss": 1.9277,
"step": 3750
},
{
"epoch": 1.95,
"learning_rate": 0.001,
"loss": 1.9326,
"step": 3760
},
{
"epoch": 1.96,
"learning_rate": 0.001,
"loss": 1.9501,
"step": 3770
},
{
"epoch": 1.96,
"learning_rate": 0.001,
"loss": 1.9568,
"step": 3780
},
{
"epoch": 1.97,
"learning_rate": 0.001,
"loss": 1.9535,
"step": 3790
},
{
"epoch": 1.97,
"learning_rate": 0.001,
"loss": 1.9523,
"step": 3800
},
{
"epoch": 1.98,
"learning_rate": 0.001,
"loss": 1.943,
"step": 3810
},
{
"epoch": 1.98,
"learning_rate": 0.001,
"loss": 1.9607,
"step": 3820
},
{
"epoch": 1.99,
"learning_rate": 0.001,
"loss": 1.9499,
"step": 3830
},
{
"epoch": 1.99,
"learning_rate": 0.001,
"loss": 1.9524,
"step": 3840
},
{
"epoch": 2.0,
"learning_rate": 0.001,
"loss": 1.951,
"step": 3850
},
{
"epoch": 2.0,
"eval_accuracy": {
"accuracy": 0.1556420233463035
},
"eval_f1": {
"f1": 0.03848003848003848
},
"eval_loss": 1.9446961879730225,
"eval_precision": {
"precision": 0.022234574763757644
},
"eval_recall": {
"recall": 0.14285714285714285
},
"eval_runtime": 78.0133,
"eval_samples_per_second": 49.415,
"eval_steps_per_second": 24.714,
"step": 3854
},
{
"epoch": 2.0,
"learning_rate": 0.001,
"loss": 1.9442,
"step": 3860
},
{
"epoch": 2.01,
"learning_rate": 0.001,
"loss": 1.9355,
"step": 3870
},
{
"epoch": 2.01,
"learning_rate": 0.001,
"loss": 1.9457,
"step": 3880
},
{
"epoch": 2.02,
"learning_rate": 0.001,
"loss": 1.9509,
"step": 3890
},
{
"epoch": 2.02,
"learning_rate": 0.001,
"loss": 1.9332,
"step": 3900
},
{
"epoch": 2.03,
"learning_rate": 0.001,
"loss": 1.9269,
"step": 3910
},
{
"epoch": 2.03,
"learning_rate": 0.001,
"loss": 1.9283,
"step": 3920
},
{
"epoch": 2.04,
"learning_rate": 0.001,
"loss": 1.9559,
"step": 3930
},
{
"epoch": 2.04,
"learning_rate": 0.001,
"loss": 1.9414,
"step": 3940
},
{
"epoch": 2.05,
"learning_rate": 0.001,
"loss": 1.9505,
"step": 3950
},
{
"epoch": 2.06,
"learning_rate": 0.001,
"loss": 1.9506,
"step": 3960
},
{
"epoch": 2.06,
"learning_rate": 0.001,
"loss": 1.9453,
"step": 3970
},
{
"epoch": 2.07,
"learning_rate": 0.001,
"loss": 1.9479,
"step": 3980
},
{
"epoch": 2.07,
"learning_rate": 0.001,
"loss": 1.9362,
"step": 3990
},
{
"epoch": 2.08,
"learning_rate": 0.001,
"loss": 1.949,
"step": 4000
},
{
"epoch": 2.08,
"learning_rate": 0.001,
"loss": 1.9581,
"step": 4010
},
{
"epoch": 2.09,
"learning_rate": 0.001,
"loss": 1.9388,
"step": 4020
},
{
"epoch": 2.09,
"learning_rate": 0.001,
"loss": 1.935,
"step": 4030
},
{
"epoch": 2.1,
"learning_rate": 0.001,
"loss": 1.9466,
"step": 4040
},
{
"epoch": 2.1,
"learning_rate": 0.001,
"loss": 1.9417,
"step": 4050
},
{
"epoch": 2.11,
"learning_rate": 0.001,
"loss": 1.9401,
"step": 4060
},
{
"epoch": 2.11,
"learning_rate": 0.001,
"loss": 1.9596,
"step": 4070
},
{
"epoch": 2.12,
"learning_rate": 0.001,
"loss": 1.9571,
"step": 4080
},
{
"epoch": 2.12,
"learning_rate": 0.001,
"loss": 1.9452,
"step": 4090
},
{
"epoch": 2.13,
"learning_rate": 0.001,
"loss": 1.9431,
"step": 4100
},
{
"epoch": 2.13,
"learning_rate": 0.001,
"loss": 1.942,
"step": 4110
},
{
"epoch": 2.14,
"learning_rate": 0.001,
"loss": 1.9499,
"step": 4120
},
{
"epoch": 2.14,
"learning_rate": 0.001,
"loss": 1.94,
"step": 4130
},
{
"epoch": 2.15,
"learning_rate": 0.001,
"loss": 1.9363,
"step": 4140
},
{
"epoch": 2.15,
"learning_rate": 0.001,
"loss": 1.9478,
"step": 4150
},
{
"epoch": 2.16,
"learning_rate": 0.001,
"loss": 1.9543,
"step": 4160
},
{
"epoch": 2.16,
"learning_rate": 0.001,
"loss": 1.9266,
"step": 4170
},
{
"epoch": 2.17,
"learning_rate": 0.001,
"loss": 1.9416,
"step": 4180
},
{
"epoch": 2.17,
"learning_rate": 0.001,
"loss": 1.9441,
"step": 4190
},
{
"epoch": 2.18,
"learning_rate": 0.001,
"loss": 1.9429,
"step": 4200
},
{
"epoch": 2.18,
"learning_rate": 0.001,
"loss": 1.9465,
"step": 4210
},
{
"epoch": 2.19,
"learning_rate": 0.001,
"loss": 1.952,
"step": 4220
},
{
"epoch": 2.2,
"learning_rate": 0.001,
"loss": 1.9493,
"step": 4230
},
{
"epoch": 2.2,
"learning_rate": 0.001,
"loss": 1.9393,
"step": 4240
},
{
"epoch": 2.21,
"learning_rate": 0.001,
"loss": 1.9531,
"step": 4250
},
{
"epoch": 2.21,
"learning_rate": 0.001,
"loss": 1.9412,
"step": 4260
},
{
"epoch": 2.22,
"learning_rate": 0.001,
"loss": 1.9493,
"step": 4270
},
{
"epoch": 2.22,
"learning_rate": 0.001,
"loss": 1.944,
"step": 4280
},
{
"epoch": 2.23,
"learning_rate": 0.001,
"loss": 1.9572,
"step": 4290
},
{
"epoch": 2.23,
"learning_rate": 0.001,
"loss": 1.9311,
"step": 4300
},
{
"epoch": 2.24,
"learning_rate": 0.001,
"loss": 1.9446,
"step": 4310
},
{
"epoch": 2.24,
"learning_rate": 0.001,
"loss": 1.9557,
"step": 4320
},
{
"epoch": 2.25,
"learning_rate": 0.001,
"loss": 1.9396,
"step": 4330
},
{
"epoch": 2.25,
"learning_rate": 0.001,
"loss": 1.9253,
"step": 4340
},
{
"epoch": 2.26,
"learning_rate": 0.001,
"loss": 1.9697,
"step": 4350
},
{
"epoch": 2.26,
"learning_rate": 0.001,
"loss": 1.9489,
"step": 4360
},
{
"epoch": 2.27,
"learning_rate": 0.001,
"loss": 1.9489,
"step": 4370
},
{
"epoch": 2.27,
"learning_rate": 0.001,
"loss": 1.9589,
"step": 4380
},
{
"epoch": 2.28,
"learning_rate": 0.001,
"loss": 1.95,
"step": 4390
},
{
"epoch": 2.28,
"learning_rate": 0.001,
"loss": 1.9422,
"step": 4400
},
{
"epoch": 2.29,
"learning_rate": 0.001,
"loss": 1.958,
"step": 4410
},
{
"epoch": 2.29,
"learning_rate": 0.001,
"loss": 1.9288,
"step": 4420
},
{
"epoch": 2.3,
"learning_rate": 0.001,
"loss": 1.9225,
"step": 4430
},
{
"epoch": 2.3,
"learning_rate": 0.001,
"loss": 1.9194,
"step": 4440
},
{
"epoch": 2.31,
"learning_rate": 0.001,
"loss": 1.9816,
"step": 4450
},
{
"epoch": 2.31,
"learning_rate": 0.001,
"loss": 1.9352,
"step": 4460
},
{
"epoch": 2.32,
"learning_rate": 0.001,
"loss": 1.939,
"step": 4470
},
{
"epoch": 2.32,
"learning_rate": 0.001,
"loss": 1.9567,
"step": 4480
},
{
"epoch": 2.33,
"learning_rate": 0.001,
"loss": 1.955,
"step": 4490
},
{
"epoch": 2.34,
"learning_rate": 0.001,
"loss": 1.9545,
"step": 4500
},
{
"epoch": 2.34,
"learning_rate": 0.001,
"loss": 1.9386,
"step": 4510
},
{
"epoch": 2.35,
"learning_rate": 0.001,
"loss": 1.9513,
"step": 4520
},
{
"epoch": 2.35,
"learning_rate": 0.001,
"loss": 1.9269,
"step": 4530
},
{
"epoch": 2.36,
"learning_rate": 0.001,
"loss": 1.9262,
"step": 4540
},
{
"epoch": 2.36,
"learning_rate": 0.001,
"loss": 1.9299,
"step": 4550
},
{
"epoch": 2.37,
"learning_rate": 0.001,
"loss": 1.9358,
"step": 4560
},
{
"epoch": 2.37,
"learning_rate": 0.001,
"loss": 1.9701,
"step": 4570
},
{
"epoch": 2.38,
"learning_rate": 0.001,
"loss": 1.9508,
"step": 4580
},
{
"epoch": 2.38,
"learning_rate": 0.001,
"loss": 1.9402,
"step": 4590
},
{
"epoch": 2.39,
"learning_rate": 0.001,
"loss": 1.9614,
"step": 4600
},
{
"epoch": 2.39,
"learning_rate": 0.001,
"loss": 1.9515,
"step": 4610
},
{
"epoch": 2.4,
"learning_rate": 0.001,
"loss": 1.9401,
"step": 4620
},
{
"epoch": 2.4,
"learning_rate": 0.001,
"loss": 1.9388,
"step": 4630
},
{
"epoch": 2.41,
"learning_rate": 0.001,
"loss": 1.9659,
"step": 4640
},
{
"epoch": 2.41,
"learning_rate": 0.001,
"loss": 1.9382,
"step": 4650
},
{
"epoch": 2.42,
"learning_rate": 0.001,
"loss": 1.9402,
"step": 4660
},
{
"epoch": 2.42,
"learning_rate": 0.001,
"loss": 1.9567,
"step": 4670
},
{
"epoch": 2.43,
"learning_rate": 0.001,
"loss": 1.9468,
"step": 4680
},
{
"epoch": 2.43,
"learning_rate": 0.001,
"loss": 1.9426,
"step": 4690
},
{
"epoch": 2.44,
"learning_rate": 0.001,
"loss": 1.9659,
"step": 4700
},
{
"epoch": 2.44,
"learning_rate": 0.001,
"loss": 1.9491,
"step": 4710
},
{
"epoch": 2.45,
"learning_rate": 0.001,
"loss": 1.9372,
"step": 4720
},
{
"epoch": 2.45,
"learning_rate": 0.001,
"loss": 1.9482,
"step": 4730
},
{
"epoch": 2.46,
"learning_rate": 0.001,
"loss": 1.9546,
"step": 4740
},
{
"epoch": 2.46,
"learning_rate": 0.001,
"loss": 1.9404,
"step": 4750
},
{
"epoch": 2.47,
"learning_rate": 0.001,
"loss": 1.94,
"step": 4760
},
{
"epoch": 2.48,
"learning_rate": 0.001,
"loss": 1.9248,
"step": 4770
},
{
"epoch": 2.48,
"learning_rate": 0.001,
"loss": 1.9324,
"step": 4780
},
{
"epoch": 2.49,
"learning_rate": 0.001,
"loss": 1.9833,
"step": 4790
},
{
"epoch": 2.49,
"learning_rate": 0.001,
"loss": 1.9301,
"step": 4800
},
{
"epoch": 2.5,
"learning_rate": 0.001,
"loss": 1.939,
"step": 4810
},
{
"epoch": 2.5,
"learning_rate": 0.001,
"loss": 1.9267,
"step": 4820
},
{
"epoch": 2.51,
"learning_rate": 0.001,
"loss": 1.9304,
"step": 4830
},
{
"epoch": 2.51,
"learning_rate": 0.001,
"loss": 1.9502,
"step": 4840
},
{
"epoch": 2.52,
"learning_rate": 0.001,
"loss": 1.9482,
"step": 4850
},
{
"epoch": 2.52,
"learning_rate": 0.001,
"loss": 1.9399,
"step": 4860
},
{
"epoch": 2.53,
"learning_rate": 0.001,
"loss": 1.9452,
"step": 4870
},
{
"epoch": 2.53,
"learning_rate": 0.001,
"loss": 1.92,
"step": 4880
},
{
"epoch": 2.54,
"learning_rate": 0.001,
"loss": 1.9378,
"step": 4890
},
{
"epoch": 2.54,
"learning_rate": 0.001,
"loss": 1.9481,
"step": 4900
},
{
"epoch": 2.55,
"learning_rate": 0.001,
"loss": 1.9496,
"step": 4910
},
{
"epoch": 2.55,
"learning_rate": 0.001,
"loss": 1.9494,
"step": 4920
},
{
"epoch": 2.56,
"learning_rate": 0.001,
"loss": 1.9501,
"step": 4930
},
{
"epoch": 2.56,
"learning_rate": 0.001,
"loss": 1.9553,
"step": 4940
},
{
"epoch": 2.57,
"learning_rate": 0.001,
"loss": 1.9423,
"step": 4950
},
{
"epoch": 2.57,
"learning_rate": 0.001,
"loss": 1.951,
"step": 4960
},
{
"epoch": 2.58,
"learning_rate": 0.001,
"loss": 1.8918,
"step": 4970
},
{
"epoch": 2.58,
"learning_rate": 0.001,
"loss": 1.94,
"step": 4980
},
{
"epoch": 2.59,
"learning_rate": 0.001,
"loss": 1.9264,
"step": 4990
},
{
"epoch": 2.59,
"learning_rate": 0.001,
"loss": 1.9679,
"step": 5000
},
{
"epoch": 2.6,
"learning_rate": 0.001,
"loss": 1.9513,
"step": 5010
},
{
"epoch": 2.61,
"learning_rate": 0.001,
"loss": 1.9212,
"step": 5020
},
{
"epoch": 2.61,
"learning_rate": 0.001,
"loss": 1.929,
"step": 5030
},
{
"epoch": 2.62,
"learning_rate": 0.001,
"loss": 1.9478,
"step": 5040
},
{
"epoch": 2.62,
"learning_rate": 0.001,
"loss": 1.9475,
"step": 5050
},
{
"epoch": 2.63,
"learning_rate": 0.001,
"loss": 1.9432,
"step": 5060
},
{
"epoch": 2.63,
"learning_rate": 0.001,
"loss": 1.9235,
"step": 5070
},
{
"epoch": 2.64,
"learning_rate": 0.001,
"loss": 1.9589,
"step": 5080
},
{
"epoch": 2.64,
"learning_rate": 0.001,
"loss": 1.9806,
"step": 5090
},
{
"epoch": 2.65,
"learning_rate": 0.001,
"loss": 1.9347,
"step": 5100
},
{
"epoch": 2.65,
"learning_rate": 0.001,
"loss": 1.9781,
"step": 5110
},
{
"epoch": 2.66,
"learning_rate": 0.001,
"loss": 1.9489,
"step": 5120
},
{
"epoch": 2.66,
"learning_rate": 0.001,
"loss": 1.9359,
"step": 5130
},
{
"epoch": 2.67,
"learning_rate": 0.001,
"loss": 1.9579,
"step": 5140
},
{
"epoch": 2.67,
"learning_rate": 0.001,
"loss": 1.967,
"step": 5150
},
{
"epoch": 2.68,
"learning_rate": 0.001,
"loss": 1.9475,
"step": 5160
},
{
"epoch": 2.68,
"learning_rate": 0.001,
"loss": 1.9492,
"step": 5170
},
{
"epoch": 2.69,
"learning_rate": 0.001,
"loss": 1.9345,
"step": 5180
},
{
"epoch": 2.69,
"learning_rate": 0.001,
"loss": 1.9456,
"step": 5190
},
{
"epoch": 2.7,
"learning_rate": 0.001,
"loss": 1.9515,
"step": 5200
},
{
"epoch": 2.7,
"learning_rate": 0.001,
"loss": 1.96,
"step": 5210
},
{
"epoch": 2.71,
"learning_rate": 0.001,
"loss": 1.9477,
"step": 5220
},
{
"epoch": 2.71,
"learning_rate": 0.001,
"loss": 1.9319,
"step": 5230
},
{
"epoch": 2.72,
"learning_rate": 0.001,
"loss": 1.9564,
"step": 5240
},
{
"epoch": 2.72,
"learning_rate": 0.001,
"loss": 1.9389,
"step": 5250
},
{
"epoch": 2.73,
"learning_rate": 0.001,
"loss": 1.9474,
"step": 5260
},
{
"epoch": 2.73,
"learning_rate": 0.001,
"loss": 1.9454,
"step": 5270
},
{
"epoch": 2.74,
"learning_rate": 0.001,
"loss": 1.9403,
"step": 5280
},
{
"epoch": 2.75,
"learning_rate": 0.001,
"loss": 1.9624,
"step": 5290
},
{
"epoch": 2.75,
"learning_rate": 0.001,
"loss": 1.9514,
"step": 5300
},
{
"epoch": 2.76,
"learning_rate": 0.001,
"loss": 1.9217,
"step": 5310
},
{
"epoch": 2.76,
"learning_rate": 0.001,
"loss": 1.9347,
"step": 5320
},
{
"epoch": 2.77,
"learning_rate": 0.001,
"loss": 1.9502,
"step": 5330
},
{
"epoch": 2.77,
"learning_rate": 0.001,
"loss": 1.99,
"step": 5340
},
{
"epoch": 2.78,
"learning_rate": 0.001,
"loss": 1.9212,
"step": 5350
},
{
"epoch": 2.78,
"learning_rate": 0.001,
"loss": 1.9377,
"step": 5360
},
{
"epoch": 2.79,
"learning_rate": 0.001,
"loss": 1.9435,
"step": 5370
},
{
"epoch": 2.79,
"learning_rate": 0.001,
"loss": 1.9398,
"step": 5380
},
{
"epoch": 2.8,
"learning_rate": 0.001,
"loss": 1.9381,
"step": 5390
},
{
"epoch": 2.8,
"learning_rate": 0.001,
"loss": 1.9239,
"step": 5400
},
{
"epoch": 2.81,
"learning_rate": 0.001,
"loss": 1.9821,
"step": 5410
},
{
"epoch": 2.81,
"learning_rate": 0.001,
"loss": 1.934,
"step": 5420
},
{
"epoch": 2.82,
"learning_rate": 0.001,
"loss": 1.9505,
"step": 5430
},
{
"epoch": 2.82,
"learning_rate": 0.001,
"loss": 1.9296,
"step": 5440
},
{
"epoch": 2.83,
"learning_rate": 0.001,
"loss": 1.9525,
"step": 5450
},
{
"epoch": 2.83,
"learning_rate": 0.001,
"loss": 1.9197,
"step": 5460
},
{
"epoch": 2.84,
"learning_rate": 0.001,
"loss": 1.9298,
"step": 5470
},
{
"epoch": 2.84,
"learning_rate": 0.001,
"loss": 1.9653,
"step": 5480
},
{
"epoch": 2.85,
"learning_rate": 0.001,
"loss": 1.947,
"step": 5490
},
{
"epoch": 2.85,
"learning_rate": 0.001,
"loss": 1.9438,
"step": 5500
},
{
"epoch": 2.86,
"learning_rate": 0.001,
"loss": 1.9581,
"step": 5510
},
{
"epoch": 2.86,
"learning_rate": 0.001,
"loss": 1.9582,
"step": 5520
},
{
"epoch": 2.87,
"learning_rate": 0.001,
"loss": 1.9202,
"step": 5530
},
{
"epoch": 2.87,
"learning_rate": 0.001,
"loss": 1.9561,
"step": 5540
},
{
"epoch": 2.88,
"learning_rate": 0.001,
"loss": 1.939,
"step": 5550
},
{
"epoch": 2.89,
"learning_rate": 0.001,
"loss": 1.9475,
"step": 5560
},
{
"epoch": 2.89,
"learning_rate": 0.001,
"loss": 1.9328,
"step": 5570
},
{
"epoch": 2.9,
"learning_rate": 0.001,
"loss": 1.9546,
"step": 5580
},
{
"epoch": 2.9,
"learning_rate": 0.001,
"loss": 1.9488,
"step": 5590
},
{
"epoch": 2.91,
"learning_rate": 0.001,
"loss": 1.9404,
"step": 5600
},
{
"epoch": 2.91,
"learning_rate": 0.001,
"loss": 1.959,
"step": 5610
},
{
"epoch": 2.92,
"learning_rate": 0.001,
"loss": 1.9649,
"step": 5620
},
{
"epoch": 2.92,
"learning_rate": 0.001,
"loss": 1.9498,
"step": 5630
},
{
"epoch": 2.93,
"learning_rate": 0.001,
"loss": 1.9353,
"step": 5640
},
{
"epoch": 2.93,
"learning_rate": 0.001,
"loss": 1.9521,
"step": 5650
},
{
"epoch": 2.94,
"learning_rate": 0.001,
"loss": 1.9564,
"step": 5660
},
{
"epoch": 2.94,
"learning_rate": 0.001,
"loss": 1.949,
"step": 5670
},
{
"epoch": 2.95,
"learning_rate": 0.001,
"loss": 1.9463,
"step": 5680
},
{
"epoch": 2.95,
"learning_rate": 0.001,
"loss": 1.95,
"step": 5690
},
{
"epoch": 2.96,
"learning_rate": 0.001,
"loss": 1.9389,
"step": 5700
},
{
"epoch": 2.96,
"learning_rate": 0.001,
"loss": 1.9575,
"step": 5710
},
{
"epoch": 2.97,
"learning_rate": 0.001,
"loss": 1.9573,
"step": 5720
},
{
"epoch": 2.97,
"learning_rate": 0.001,
"loss": 1.9435,
"step": 5730
},
{
"epoch": 2.98,
"learning_rate": 0.001,
"loss": 1.9379,
"step": 5740
},
{
"epoch": 2.98,
"learning_rate": 0.001,
"loss": 1.9365,
"step": 5750
},
{
"epoch": 2.99,
"learning_rate": 0.001,
"loss": 1.9192,
"step": 5760
},
{
"epoch": 2.99,
"learning_rate": 0.001,
"loss": 1.9526,
"step": 5770
},
{
"epoch": 3.0,
"learning_rate": 0.001,
"loss": 1.9799,
"step": 5780
},
{
"epoch": 3.0,
"eval_accuracy": {
"accuracy": 0.13618677042801555
},
"eval_f1": {
"f1": 0.03424657534246575
},
"eval_loss": 1.9497852325439453,
"eval_precision": {
"precision": 0.019455252918287935
},
"eval_recall": {
"recall": 0.14285714285714285
},
"eval_runtime": 77.5559,
"eval_samples_per_second": 49.706,
"eval_steps_per_second": 24.859,
"step": 5781
},
{
"epoch": 3.0,
"learning_rate": 0.001,
"loss": 1.9658,
"step": 5790
},
{
"epoch": 3.01,
"learning_rate": 0.001,
"loss": 1.9546,
"step": 5800
},
{
"epoch": 3.02,
"learning_rate": 0.001,
"loss": 1.9521,
"step": 5810
},
{
"epoch": 3.02,
"learning_rate": 0.001,
"loss": 1.957,
"step": 5820
},
{
"epoch": 3.03,
"learning_rate": 0.001,
"loss": 1.9467,
"step": 5830
},
{
"epoch": 3.03,
"learning_rate": 0.001,
"loss": 1.9454,
"step": 5840
},
{
"epoch": 3.04,
"learning_rate": 0.001,
"loss": 1.9407,
"step": 5850
},
{
"epoch": 3.04,
"learning_rate": 0.001,
"loss": 1.9418,
"step": 5860
},
{
"epoch": 3.05,
"learning_rate": 0.001,
"loss": 1.9464,
"step": 5870
},
{
"epoch": 3.05,
"learning_rate": 0.001,
"loss": 1.9605,
"step": 5880
},
{
"epoch": 3.06,
"learning_rate": 0.001,
"loss": 1.9525,
"step": 5890
},
{
"epoch": 3.06,
"learning_rate": 0.001,
"loss": 1.9427,
"step": 5900
},
{
"epoch": 3.07,
"learning_rate": 0.001,
"loss": 1.9498,
"step": 5910
},
{
"epoch": 3.07,
"learning_rate": 0.001,
"loss": 1.944,
"step": 5920
},
{
"epoch": 3.08,
"learning_rate": 0.001,
"loss": 1.9379,
"step": 5930
},
{
"epoch": 3.08,
"learning_rate": 0.001,
"loss": 1.9408,
"step": 5940
},
{
"epoch": 3.09,
"learning_rate": 0.001,
"loss": 1.9169,
"step": 5950
},
{
"epoch": 3.09,
"learning_rate": 0.001,
"loss": 1.9782,
"step": 5960
},
{
"epoch": 3.1,
"learning_rate": 0.001,
"loss": 1.9376,
"step": 5970
},
{
"epoch": 3.1,
"learning_rate": 0.001,
"loss": 1.9358,
"step": 5980
},
{
"epoch": 3.11,
"learning_rate": 0.001,
"loss": 1.9446,
"step": 5990
},
{
"epoch": 3.11,
"learning_rate": 0.001,
"loss": 1.9434,
"step": 6000
},
{
"epoch": 3.12,
"learning_rate": 0.001,
"loss": 1.9421,
"step": 6010
},
{
"epoch": 3.12,
"learning_rate": 0.001,
"loss": 1.9364,
"step": 6020
},
{
"epoch": 3.13,
"learning_rate": 0.001,
"loss": 1.9587,
"step": 6030
},
{
"epoch": 3.13,
"learning_rate": 0.001,
"loss": 1.9465,
"step": 6040
},
{
"epoch": 3.14,
"learning_rate": 0.001,
"loss": 1.9405,
"step": 6050
},
{
"epoch": 3.14,
"learning_rate": 0.001,
"loss": 1.9475,
"step": 6060
},
{
"epoch": 3.15,
"learning_rate": 0.001,
"loss": 1.9451,
"step": 6070
},
{
"epoch": 3.16,
"learning_rate": 0.001,
"loss": 1.9602,
"step": 6080
},
{
"epoch": 3.16,
"learning_rate": 0.001,
"loss": 1.9448,
"step": 6090
},
{
"epoch": 3.17,
"learning_rate": 0.001,
"loss": 1.9438,
"step": 6100
},
{
"epoch": 3.17,
"learning_rate": 0.001,
"loss": 1.935,
"step": 6110
},
{
"epoch": 3.18,
"learning_rate": 0.001,
"loss": 1.9541,
"step": 6120
},
{
"epoch": 3.18,
"learning_rate": 0.001,
"loss": 1.9377,
"step": 6130
},
{
"epoch": 3.19,
"learning_rate": 0.001,
"loss": 1.9538,
"step": 6140
},
{
"epoch": 3.19,
"learning_rate": 0.001,
"loss": 1.943,
"step": 6150
},
{
"epoch": 3.2,
"learning_rate": 0.001,
"loss": 1.9523,
"step": 6160
},
{
"epoch": 3.2,
"learning_rate": 0.001,
"loss": 1.9423,
"step": 6170
},
{
"epoch": 3.21,
"learning_rate": 0.001,
"loss": 1.9503,
"step": 6180
},
{
"epoch": 3.21,
"learning_rate": 0.001,
"loss": 1.946,
"step": 6190
},
{
"epoch": 3.22,
"learning_rate": 0.001,
"loss": 1.9468,
"step": 6200
},
{
"epoch": 3.22,
"learning_rate": 0.001,
"loss": 1.9536,
"step": 6210
},
{
"epoch": 3.23,
"learning_rate": 0.001,
"loss": 1.943,
"step": 6220
},
{
"epoch": 3.23,
"learning_rate": 0.001,
"loss": 1.9413,
"step": 6230
},
{
"epoch": 3.24,
"learning_rate": 0.001,
"loss": 1.9454,
"step": 6240
},
{
"epoch": 3.24,
"learning_rate": 0.001,
"loss": 1.9423,
"step": 6250
},
{
"epoch": 3.25,
"learning_rate": 0.001,
"loss": 1.9534,
"step": 6260
},
{
"epoch": 3.25,
"learning_rate": 0.001,
"loss": 1.9348,
"step": 6270
},
{
"epoch": 3.26,
"learning_rate": 0.001,
"loss": 1.9276,
"step": 6280
},
{
"epoch": 3.26,
"learning_rate": 0.001,
"loss": 1.9378,
"step": 6290
},
{
"epoch": 3.27,
"learning_rate": 0.001,
"loss": 1.9499,
"step": 6300
},
{
"epoch": 3.27,
"learning_rate": 0.001,
"loss": 1.9618,
"step": 6310
},
{
"epoch": 3.28,
"learning_rate": 0.001,
"loss": 1.9505,
"step": 6320
},
{
"epoch": 3.28,
"learning_rate": 0.001,
"loss": 1.9423,
"step": 6330
},
{
"epoch": 3.29,
"learning_rate": 0.001,
"loss": 1.9453,
"step": 6340
},
{
"epoch": 3.3,
"learning_rate": 0.001,
"loss": 1.9393,
"step": 6350
},
{
"epoch": 3.3,
"learning_rate": 0.001,
"loss": 1.9482,
"step": 6360
},
{
"epoch": 3.31,
"learning_rate": 0.001,
"loss": 1.9318,
"step": 6370
},
{
"epoch": 3.31,
"learning_rate": 0.001,
"loss": 1.9617,
"step": 6380
},
{
"epoch": 3.32,
"learning_rate": 0.001,
"loss": 1.9354,
"step": 6390
},
{
"epoch": 3.32,
"learning_rate": 0.001,
"loss": 1.9444,
"step": 6400
},
{
"epoch": 3.33,
"learning_rate": 0.001,
"loss": 1.9657,
"step": 6410
},
{
"epoch": 3.33,
"learning_rate": 0.001,
"loss": 1.9473,
"step": 6420
},
{
"epoch": 3.34,
"learning_rate": 0.001,
"loss": 1.9572,
"step": 6430
},
{
"epoch": 3.34,
"learning_rate": 0.001,
"loss": 1.941,
"step": 6440
},
{
"epoch": 3.35,
"learning_rate": 0.001,
"loss": 1.9316,
"step": 6450
},
{
"epoch": 3.35,
"learning_rate": 0.001,
"loss": 1.9525,
"step": 6460
},
{
"epoch": 3.36,
"learning_rate": 0.001,
"loss": 1.9372,
"step": 6470
},
{
"epoch": 3.36,
"learning_rate": 0.001,
"loss": 1.9664,
"step": 6480
},
{
"epoch": 3.37,
"learning_rate": 0.001,
"loss": 1.9279,
"step": 6490
},
{
"epoch": 3.37,
"learning_rate": 0.001,
"loss": 1.9534,
"step": 6500
},
{
"epoch": 3.38,
"learning_rate": 0.001,
"loss": 1.9162,
"step": 6510
},
{
"epoch": 3.38,
"learning_rate": 0.001,
"loss": 1.9218,
"step": 6520
},
{
"epoch": 3.39,
"learning_rate": 0.001,
"loss": 1.9517,
"step": 6530
},
{
"epoch": 3.39,
"learning_rate": 0.001,
"loss": 1.9523,
"step": 6540
},
{
"epoch": 3.4,
"learning_rate": 0.001,
"loss": 1.9532,
"step": 6550
},
{
"epoch": 3.4,
"learning_rate": 0.001,
"loss": 1.9327,
"step": 6560
},
{
"epoch": 3.41,
"learning_rate": 0.001,
"loss": 1.9576,
"step": 6570
},
{
"epoch": 3.41,
"learning_rate": 0.001,
"loss": 1.9478,
"step": 6580
},
{
"epoch": 3.42,
"learning_rate": 0.001,
"loss": 1.944,
"step": 6590
},
{
"epoch": 3.43,
"learning_rate": 0.001,
"loss": 1.9472,
"step": 6600
},
{
"epoch": 3.43,
"learning_rate": 0.001,
"loss": 1.9501,
"step": 6610
},
{
"epoch": 3.44,
"learning_rate": 0.001,
"loss": 1.9513,
"step": 6620
},
{
"epoch": 3.44,
"learning_rate": 0.001,
"loss": 1.9519,
"step": 6630
},
{
"epoch": 3.45,
"learning_rate": 0.001,
"loss": 1.9256,
"step": 6640
},
{
"epoch": 3.45,
"learning_rate": 0.001,
"loss": 1.9366,
"step": 6650
},
{
"epoch": 3.46,
"learning_rate": 0.001,
"loss": 1.9464,
"step": 6660
},
{
"epoch": 3.46,
"learning_rate": 0.001,
"loss": 1.9364,
"step": 6670
},
{
"epoch": 3.47,
"learning_rate": 0.001,
"loss": 1.9324,
"step": 6680
},
{
"epoch": 3.47,
"learning_rate": 0.001,
"loss": 1.9474,
"step": 6690
},
{
"epoch": 3.48,
"learning_rate": 0.001,
"loss": 1.9316,
"step": 6700
},
{
"epoch": 3.48,
"learning_rate": 0.001,
"loss": 1.9327,
"step": 6710
},
{
"epoch": 3.49,
"learning_rate": 0.001,
"loss": 1.9277,
"step": 6720
},
{
"epoch": 3.49,
"learning_rate": 0.001,
"loss": 1.9321,
"step": 6730
},
{
"epoch": 3.5,
"learning_rate": 0.001,
"loss": 1.9355,
"step": 6740
},
{
"epoch": 3.5,
"learning_rate": 0.001,
"loss": 1.9642,
"step": 6750
},
{
"epoch": 3.51,
"learning_rate": 0.001,
"loss": 1.9501,
"step": 6760
},
{
"epoch": 3.51,
"learning_rate": 0.001,
"loss": 1.9515,
"step": 6770
},
{
"epoch": 3.52,
"learning_rate": 0.001,
"loss": 1.9563,
"step": 6780
},
{
"epoch": 3.52,
"learning_rate": 0.001,
"loss": 1.9461,
"step": 6790
},
{
"epoch": 3.53,
"learning_rate": 0.001,
"loss": 1.9509,
"step": 6800
},
{
"epoch": 3.53,
"learning_rate": 0.001,
"loss": 1.9438,
"step": 6810
},
{
"epoch": 3.54,
"learning_rate": 0.001,
"loss": 1.9475,
"step": 6820
},
{
"epoch": 3.54,
"learning_rate": 0.001,
"loss": 1.9368,
"step": 6830
},
{
"epoch": 3.55,
"learning_rate": 0.001,
"loss": 1.9375,
"step": 6840
},
{
"epoch": 3.55,
"learning_rate": 0.001,
"loss": 1.9433,
"step": 6850
},
{
"epoch": 3.56,
"learning_rate": 0.001,
"loss": 1.9526,
"step": 6860
},
{
"epoch": 3.57,
"learning_rate": 0.001,
"loss": 1.9679,
"step": 6870
},
{
"epoch": 3.57,
"learning_rate": 0.001,
"loss": 1.9444,
"step": 6880
},
{
"epoch": 3.58,
"learning_rate": 0.001,
"loss": 1.9332,
"step": 6890
},
{
"epoch": 3.58,
"learning_rate": 0.001,
"loss": 1.9424,
"step": 6900
},
{
"epoch": 3.59,
"learning_rate": 0.001,
"loss": 1.9502,
"step": 6910
},
{
"epoch": 3.59,
"learning_rate": 0.001,
"loss": 1.9504,
"step": 6920
},
{
"epoch": 3.6,
"learning_rate": 0.001,
"loss": 1.9308,
"step": 6930
},
{
"epoch": 3.6,
"learning_rate": 0.001,
"loss": 1.9461,
"step": 6940
},
{
"epoch": 3.61,
"learning_rate": 0.001,
"loss": 1.9349,
"step": 6950
},
{
"epoch": 3.61,
"learning_rate": 0.001,
"loss": 1.9407,
"step": 6960
},
{
"epoch": 3.62,
"learning_rate": 0.001,
"loss": 1.9487,
"step": 6970
},
{
"epoch": 3.62,
"learning_rate": 0.001,
"loss": 1.9396,
"step": 6980
},
{
"epoch": 3.63,
"learning_rate": 0.001,
"loss": 1.9337,
"step": 6990
},
{
"epoch": 3.63,
"learning_rate": 0.001,
"loss": 1.9433,
"step": 7000
},
{
"epoch": 3.64,
"learning_rate": 0.001,
"loss": 1.933,
"step": 7010
},
{
"epoch": 3.64,
"learning_rate": 0.001,
"loss": 1.9064,
"step": 7020
},
{
"epoch": 3.65,
"learning_rate": 0.001,
"loss": 1.9386,
"step": 7030
},
{
"epoch": 3.65,
"learning_rate": 0.001,
"loss": 1.9323,
"step": 7040
},
{
"epoch": 3.66,
"learning_rate": 0.001,
"loss": 1.946,
"step": 7050
},
{
"epoch": 3.66,
"learning_rate": 0.001,
"loss": 1.9297,
"step": 7060
},
{
"epoch": 3.67,
"learning_rate": 0.001,
"loss": 1.8934,
"step": 7070
},
{
"epoch": 3.67,
"learning_rate": 0.001,
"loss": 1.9523,
"step": 7080
},
{
"epoch": 3.68,
"learning_rate": 0.001,
"loss": 1.9222,
"step": 7090
},
{
"epoch": 3.68,
"learning_rate": 0.001,
"loss": 1.9464,
"step": 7100
},
{
"epoch": 3.69,
"learning_rate": 0.001,
"loss": 1.9453,
"step": 7110
},
{
"epoch": 3.69,
"learning_rate": 0.001,
"loss": 1.9425,
"step": 7120
},
{
"epoch": 3.7,
"learning_rate": 0.001,
"loss": 1.9329,
"step": 7130
},
{
"epoch": 3.71,
"learning_rate": 0.001,
"loss": 1.9393,
"step": 7140
},
{
"epoch": 3.71,
"learning_rate": 0.001,
"loss": 1.9481,
"step": 7150
},
{
"epoch": 3.72,
"learning_rate": 0.001,
"loss": 1.9641,
"step": 7160
},
{
"epoch": 3.72,
"learning_rate": 0.001,
"loss": 1.9414,
"step": 7170
},
{
"epoch": 3.73,
"learning_rate": 0.001,
"loss": 1.9574,
"step": 7180
},
{
"epoch": 3.73,
"learning_rate": 0.001,
"loss": 1.9491,
"step": 7190
},
{
"epoch": 3.74,
"learning_rate": 0.001,
"loss": 1.9342,
"step": 7200
},
{
"epoch": 3.74,
"learning_rate": 0.001,
"loss": 1.9548,
"step": 7210
},
{
"epoch": 3.75,
"learning_rate": 0.001,
"loss": 1.9333,
"step": 7220
},
{
"epoch": 3.75,
"learning_rate": 0.001,
"loss": 1.9731,
"step": 7230
},
{
"epoch": 3.76,
"learning_rate": 0.001,
"loss": 1.9384,
"step": 7240
},
{
"epoch": 3.76,
"learning_rate": 0.001,
"loss": 1.949,
"step": 7250
},
{
"epoch": 3.77,
"learning_rate": 0.001,
"loss": 1.9463,
"step": 7260
},
{
"epoch": 3.77,
"learning_rate": 0.001,
"loss": 1.9327,
"step": 7270
},
{
"epoch": 3.78,
"learning_rate": 0.001,
"loss": 1.9445,
"step": 7280
},
{
"epoch": 3.78,
"learning_rate": 0.001,
"loss": 1.9498,
"step": 7290
},
{
"epoch": 3.79,
"learning_rate": 0.001,
"loss": 1.9376,
"step": 7300
},
{
"epoch": 3.79,
"learning_rate": 0.001,
"loss": 1.9477,
"step": 7310
},
{
"epoch": 3.8,
"learning_rate": 0.001,
"loss": 1.931,
"step": 7320
},
{
"epoch": 3.8,
"learning_rate": 0.001,
"loss": 1.9003,
"step": 7330
},
{
"epoch": 3.81,
"learning_rate": 0.001,
"loss": 1.9372,
"step": 7340
},
{
"epoch": 3.81,
"learning_rate": 0.001,
"loss": 1.9369,
"step": 7350
},
{
"epoch": 3.82,
"learning_rate": 0.001,
"loss": 1.9529,
"step": 7360
},
{
"epoch": 3.82,
"learning_rate": 0.001,
"loss": 1.946,
"step": 7370
},
{
"epoch": 3.83,
"learning_rate": 0.001,
"loss": 1.9339,
"step": 7380
},
{
"epoch": 3.83,
"learning_rate": 0.001,
"loss": 1.9422,
"step": 7390
},
{
"epoch": 3.84,
"learning_rate": 0.001,
"loss": 1.9303,
"step": 7400
},
{
"epoch": 3.85,
"learning_rate": 0.001,
"loss": 1.967,
"step": 7410
},
{
"epoch": 3.85,
"learning_rate": 0.001,
"loss": 1.9406,
"step": 7420
},
{
"epoch": 3.86,
"learning_rate": 0.001,
"loss": 1.9433,
"step": 7430
},
{
"epoch": 3.86,
"learning_rate": 0.001,
"loss": 1.9486,
"step": 7440
},
{
"epoch": 3.87,
"learning_rate": 0.001,
"loss": 1.9309,
"step": 7450
},
{
"epoch": 3.87,
"learning_rate": 0.001,
"loss": 1.9528,
"step": 7460
},
{
"epoch": 3.88,
"learning_rate": 0.001,
"loss": 1.9419,
"step": 7470
},
{
"epoch": 3.88,
"learning_rate": 0.001,
"loss": 1.9494,
"step": 7480
},
{
"epoch": 3.89,
"learning_rate": 0.001,
"loss": 1.9622,
"step": 7490
},
{
"epoch": 3.89,
"learning_rate": 0.001,
"loss": 1.9342,
"step": 7500
},
{
"epoch": 3.9,
"learning_rate": 0.001,
"loss": 1.9044,
"step": 7510
},
{
"epoch": 3.9,
"learning_rate": 0.001,
"loss": 1.9564,
"step": 7520
},
{
"epoch": 3.91,
"learning_rate": 0.001,
"loss": 1.9608,
"step": 7530
},
{
"epoch": 3.91,
"learning_rate": 0.001,
"loss": 1.9298,
"step": 7540
},
{
"epoch": 3.92,
"learning_rate": 0.001,
"loss": 1.9511,
"step": 7550
},
{
"epoch": 3.92,
"learning_rate": 0.001,
"loss": 1.9408,
"step": 7560
},
{
"epoch": 3.93,
"learning_rate": 0.001,
"loss": 1.9408,
"step": 7570
},
{
"epoch": 3.93,
"learning_rate": 0.001,
"loss": 1.9561,
"step": 7580
},
{
"epoch": 3.94,
"learning_rate": 0.001,
"loss": 1.9461,
"step": 7590
},
{
"epoch": 3.94,
"learning_rate": 0.001,
"loss": 1.9429,
"step": 7600
},
{
"epoch": 3.95,
"learning_rate": 0.001,
"loss": 1.9495,
"step": 7610
},
{
"epoch": 3.95,
"learning_rate": 0.001,
"loss": 1.9481,
"step": 7620
},
{
"epoch": 3.96,
"learning_rate": 0.001,
"loss": 1.9475,
"step": 7630
},
{
"epoch": 3.96,
"learning_rate": 0.001,
"loss": 1.9467,
"step": 7640
},
{
"epoch": 3.97,
"learning_rate": 0.001,
"loss": 1.9564,
"step": 7650
},
{
"epoch": 3.98,
"learning_rate": 0.001,
"loss": 1.9408,
"step": 7660
},
{
"epoch": 3.98,
"learning_rate": 0.001,
"loss": 1.9428,
"step": 7670
},
{
"epoch": 3.99,
"learning_rate": 0.001,
"loss": 1.9222,
"step": 7680
},
{
"epoch": 3.99,
"learning_rate": 0.001,
"loss": 1.9615,
"step": 7690
},
{
"epoch": 4.0,
"learning_rate": 0.001,
"loss": 1.9458,
"step": 7700
},
{
"epoch": 4.0,
"eval_accuracy": {
"accuracy": 0.17665369649805449
},
"eval_f1": {
"f1": 0.04289493575207861
},
"eval_loss": 1.9412175416946411,
"eval_precision": {
"precision": 0.025236242356864926
},
"eval_recall": {
"recall": 0.14285714285714285
},
"eval_runtime": 77.9759,
"eval_samples_per_second": 49.438,
"eval_steps_per_second": 24.726,
"step": 7708
},
{
"epoch": 4.0,
"learning_rate": 0.001,
"loss": 1.9413,
"step": 7710
},
{
"epoch": 4.01,
"learning_rate": 0.001,
"loss": 1.9409,
"step": 7720
},
{
"epoch": 4.01,
"learning_rate": 0.001,
"loss": 1.9472,
"step": 7730
},
{
"epoch": 4.02,
"learning_rate": 0.001,
"loss": 1.9453,
"step": 7740
},
{
"epoch": 4.02,
"learning_rate": 0.001,
"loss": 1.9466,
"step": 7750
},
{
"epoch": 4.03,
"learning_rate": 0.001,
"loss": 1.9387,
"step": 7760
},
{
"epoch": 4.03,
"learning_rate": 0.001,
"loss": 1.939,
"step": 7770
},
{
"epoch": 4.04,
"learning_rate": 0.001,
"loss": 1.9473,
"step": 7780
},
{
"epoch": 4.04,
"learning_rate": 0.001,
"loss": 1.9302,
"step": 7790
},
{
"epoch": 4.05,
"learning_rate": 0.001,
"loss": 1.9263,
"step": 7800
},
{
"epoch": 4.05,
"learning_rate": 0.001,
"loss": 1.9636,
"step": 7810
},
{
"epoch": 4.06,
"learning_rate": 0.001,
"loss": 1.9634,
"step": 7820
},
{
"epoch": 4.06,
"learning_rate": 0.001,
"loss": 1.9548,
"step": 7830
},
{
"epoch": 4.07,
"learning_rate": 0.001,
"loss": 1.9345,
"step": 7840
},
{
"epoch": 4.07,
"learning_rate": 0.001,
"loss": 1.9362,
"step": 7850
},
{
"epoch": 4.08,
"learning_rate": 0.001,
"loss": 1.9491,
"step": 7860
},
{
"epoch": 4.08,
"learning_rate": 0.001,
"loss": 1.9305,
"step": 7870
},
{
"epoch": 4.09,
"learning_rate": 0.001,
"loss": 1.9365,
"step": 7880
},
{
"epoch": 4.09,
"learning_rate": 0.001,
"loss": 1.9428,
"step": 7890
},
{
"epoch": 4.1,
"learning_rate": 0.001,
"loss": 1.929,
"step": 7900
},
{
"epoch": 4.1,
"learning_rate": 0.001,
"loss": 1.9336,
"step": 7910
},
{
"epoch": 4.11,
"learning_rate": 0.001,
"loss": 1.9416,
"step": 7920
},
{
"epoch": 4.12,
"learning_rate": 0.001,
"loss": 1.9622,
"step": 7930
},
{
"epoch": 4.12,
"learning_rate": 0.001,
"loss": 1.9435,
"step": 7940
},
{
"epoch": 4.13,
"learning_rate": 0.001,
"loss": 1.9243,
"step": 7950
},
{
"epoch": 4.13,
"learning_rate": 0.001,
"loss": 1.9435,
"step": 7960
},
{
"epoch": 4.14,
"learning_rate": 0.001,
"loss": 1.9542,
"step": 7970
},
{
"epoch": 4.14,
"learning_rate": 0.001,
"loss": 1.9191,
"step": 7980
},
{
"epoch": 4.15,
"learning_rate": 0.001,
"loss": 1.9585,
"step": 7990
},
{
"epoch": 4.15,
"learning_rate": 0.001,
"loss": 1.9433,
"step": 8000
},
{
"epoch": 4.16,
"learning_rate": 0.001,
"loss": 1.9774,
"step": 8010
},
{
"epoch": 4.16,
"learning_rate": 0.001,
"loss": 1.9324,
"step": 8020
},
{
"epoch": 4.17,
"learning_rate": 0.001,
"loss": 1.9455,
"step": 8030
},
{
"epoch": 4.17,
"learning_rate": 0.001,
"loss": 1.9479,
"step": 8040
},
{
"epoch": 4.18,
"learning_rate": 0.001,
"loss": 1.9473,
"step": 8050
},
{
"epoch": 4.18,
"learning_rate": 0.001,
"loss": 1.9287,
"step": 8060
},
{
"epoch": 4.19,
"learning_rate": 0.001,
"loss": 1.9451,
"step": 8070
},
{
"epoch": 4.19,
"learning_rate": 0.001,
"loss": 1.9786,
"step": 8080
},
{
"epoch": 4.2,
"learning_rate": 0.001,
"loss": 1.9257,
"step": 8090
},
{
"epoch": 4.2,
"learning_rate": 0.001,
"loss": 1.9269,
"step": 8100
},
{
"epoch": 4.21,
"learning_rate": 0.001,
"loss": 1.9279,
"step": 8110
},
{
"epoch": 4.21,
"learning_rate": 0.001,
"loss": 1.9575,
"step": 8120
},
{
"epoch": 4.22,
"learning_rate": 0.001,
"loss": 1.9488,
"step": 8130
},
{
"epoch": 4.22,
"learning_rate": 0.001,
"loss": 1.9546,
"step": 8140
},
{
"epoch": 4.23,
"learning_rate": 0.001,
"loss": 1.9358,
"step": 8150
},
{
"epoch": 4.23,
"learning_rate": 0.001,
"loss": 1.9317,
"step": 8160
},
{
"epoch": 4.24,
"learning_rate": 0.001,
"loss": 1.9328,
"step": 8170
},
{
"epoch": 4.24,
"learning_rate": 0.001,
"loss": 1.9304,
"step": 8180
},
{
"epoch": 4.25,
"learning_rate": 0.001,
"loss": 1.9382,
"step": 8190
},
{
"epoch": 4.26,
"learning_rate": 0.001,
"loss": 1.9339,
"step": 8200
},
{
"epoch": 4.26,
"learning_rate": 0.001,
"loss": 1.9357,
"step": 8210
},
{
"epoch": 4.27,
"learning_rate": 0.001,
"loss": 1.9401,
"step": 8220
},
{
"epoch": 4.27,
"learning_rate": 0.001,
"loss": 1.9633,
"step": 8230
},
{
"epoch": 4.28,
"learning_rate": 0.001,
"loss": 1.9443,
"step": 8240
},
{
"epoch": 4.28,
"learning_rate": 0.001,
"loss": 1.9585,
"step": 8250
},
{
"epoch": 4.29,
"learning_rate": 0.001,
"loss": 1.954,
"step": 8260
},
{
"epoch": 4.29,
"learning_rate": 0.001,
"loss": 1.9456,
"step": 8270
},
{
"epoch": 4.3,
"learning_rate": 0.001,
"loss": 1.9436,
"step": 8280
},
{
"epoch": 4.3,
"learning_rate": 0.001,
"loss": 1.9522,
"step": 8290
},
{
"epoch": 4.31,
"learning_rate": 0.001,
"loss": 1.9369,
"step": 8300
},
{
"epoch": 4.31,
"learning_rate": 0.001,
"loss": 1.9428,
"step": 8310
},
{
"epoch": 4.32,
"learning_rate": 0.001,
"loss": 1.9492,
"step": 8320
},
{
"epoch": 4.32,
"learning_rate": 0.001,
"loss": 1.9515,
"step": 8330
},
{
"epoch": 4.33,
"learning_rate": 0.001,
"loss": 1.9559,
"step": 8340
},
{
"epoch": 4.33,
"learning_rate": 0.001,
"loss": 1.9503,
"step": 8350
},
{
"epoch": 4.34,
"learning_rate": 0.001,
"loss": 1.9615,
"step": 8360
},
{
"epoch": 4.34,
"learning_rate": 0.001,
"loss": 1.9387,
"step": 8370
},
{
"epoch": 4.35,
"learning_rate": 0.001,
"loss": 1.9528,
"step": 8380
},
{
"epoch": 4.35,
"learning_rate": 0.001,
"loss": 1.947,
"step": 8390
},
{
"epoch": 4.36,
"learning_rate": 0.001,
"loss": 1.9563,
"step": 8400
},
{
"epoch": 4.36,
"learning_rate": 0.001,
"loss": 1.9457,
"step": 8410
},
{
"epoch": 4.37,
"learning_rate": 0.001,
"loss": 1.9399,
"step": 8420
},
{
"epoch": 4.37,
"learning_rate": 0.001,
"loss": 1.9534,
"step": 8430
},
{
"epoch": 4.38,
"learning_rate": 0.001,
"loss": 1.93,
"step": 8440
},
{
"epoch": 4.39,
"learning_rate": 0.001,
"loss": 1.9513,
"step": 8450
},
{
"epoch": 4.39,
"learning_rate": 0.001,
"loss": 1.9528,
"step": 8460
},
{
"epoch": 4.4,
"learning_rate": 0.001,
"loss": 1.9232,
"step": 8470
},
{
"epoch": 4.4,
"learning_rate": 0.001,
"loss": 1.9481,
"step": 8480
},
{
"epoch": 4.41,
"learning_rate": 0.001,
"loss": 1.9544,
"step": 8490
},
{
"epoch": 4.41,
"learning_rate": 0.001,
"loss": 1.9436,
"step": 8500
},
{
"epoch": 4.42,
"learning_rate": 0.001,
"loss": 1.9418,
"step": 8510
},
{
"epoch": 4.42,
"learning_rate": 0.001,
"loss": 1.9432,
"step": 8520
},
{
"epoch": 4.43,
"learning_rate": 0.001,
"loss": 1.9374,
"step": 8530
},
{
"epoch": 4.43,
"learning_rate": 0.001,
"loss": 1.9412,
"step": 8540
},
{
"epoch": 4.44,
"learning_rate": 0.001,
"loss": 1.9362,
"step": 8550
},
{
"epoch": 4.44,
"learning_rate": 0.001,
"loss": 1.9077,
"step": 8560
},
{
"epoch": 4.45,
"learning_rate": 0.001,
"loss": 1.9779,
"step": 8570
},
{
"epoch": 4.45,
"learning_rate": 0.001,
"loss": 1.9489,
"step": 8580
},
{
"epoch": 4.46,
"learning_rate": 0.001,
"loss": 1.9406,
"step": 8590
},
{
"epoch": 4.46,
"learning_rate": 0.001,
"loss": 1.9254,
"step": 8600
},
{
"epoch": 4.47,
"learning_rate": 0.001,
"loss": 1.9372,
"step": 8610
},
{
"epoch": 4.47,
"learning_rate": 0.001,
"loss": 1.946,
"step": 8620
},
{
"epoch": 4.48,
"learning_rate": 0.001,
"loss": 1.9543,
"step": 8630
},
{
"epoch": 4.48,
"learning_rate": 0.001,
"loss": 1.9333,
"step": 8640
},
{
"epoch": 4.49,
"learning_rate": 0.001,
"loss": 1.9384,
"step": 8650
},
{
"epoch": 4.49,
"learning_rate": 0.001,
"loss": 1.9443,
"step": 8660
},
{
"epoch": 4.5,
"learning_rate": 0.001,
"loss": 1.962,
"step": 8670
},
{
"epoch": 4.5,
"learning_rate": 0.001,
"loss": 1.958,
"step": 8680
},
{
"epoch": 4.51,
"learning_rate": 0.001,
"loss": 1.9449,
"step": 8690
},
{
"epoch": 4.51,
"learning_rate": 0.001,
"loss": 1.9509,
"step": 8700
},
{
"epoch": 4.52,
"learning_rate": 0.001,
"loss": 1.9468,
"step": 8710
},
{
"epoch": 4.53,
"learning_rate": 0.001,
"loss": 1.9566,
"step": 8720
},
{
"epoch": 4.53,
"learning_rate": 0.001,
"loss": 1.9368,
"step": 8730
},
{
"epoch": 4.54,
"learning_rate": 0.001,
"loss": 1.9394,
"step": 8740
},
{
"epoch": 4.54,
"learning_rate": 0.001,
"loss": 1.9565,
"step": 8750
},
{
"epoch": 4.55,
"learning_rate": 0.001,
"loss": 1.9292,
"step": 8760
},
{
"epoch": 4.55,
"learning_rate": 0.001,
"loss": 1.9345,
"step": 8770
},
{
"epoch": 4.56,
"learning_rate": 0.001,
"loss": 1.9686,
"step": 8780
},
{
"epoch": 4.56,
"learning_rate": 0.001,
"loss": 1.9181,
"step": 8790
},
{
"epoch": 4.57,
"learning_rate": 0.001,
"loss": 1.9606,
"step": 8800
},
{
"epoch": 4.57,
"learning_rate": 0.001,
"loss": 1.937,
"step": 8810
},
{
"epoch": 4.58,
"learning_rate": 0.001,
"loss": 1.9302,
"step": 8820
},
{
"epoch": 4.58,
"learning_rate": 0.001,
"loss": 1.9756,
"step": 8830
},
{
"epoch": 4.59,
"learning_rate": 0.001,
"loss": 1.9396,
"step": 8840
},
{
"epoch": 4.59,
"learning_rate": 0.001,
"loss": 1.9381,
"step": 8850
},
{
"epoch": 4.6,
"learning_rate": 0.001,
"loss": 1.962,
"step": 8860
},
{
"epoch": 4.6,
"learning_rate": 0.001,
"loss": 1.9464,
"step": 8870
},
{
"epoch": 4.61,
"learning_rate": 0.001,
"loss": 1.9375,
"step": 8880
},
{
"epoch": 4.61,
"learning_rate": 0.001,
"loss": 1.9495,
"step": 8890
},
{
"epoch": 4.62,
"learning_rate": 0.001,
"loss": 1.9378,
"step": 8900
},
{
"epoch": 4.62,
"learning_rate": 0.001,
"loss": 1.9363,
"step": 8910
},
{
"epoch": 4.63,
"learning_rate": 0.001,
"loss": 1.9567,
"step": 8920
},
{
"epoch": 4.63,
"learning_rate": 0.001,
"loss": 1.9389,
"step": 8930
},
{
"epoch": 4.64,
"learning_rate": 0.001,
"loss": 1.9319,
"step": 8940
},
{
"epoch": 4.64,
"learning_rate": 0.001,
"loss": 1.9479,
"step": 8950
},
{
"epoch": 4.65,
"learning_rate": 0.001,
"loss": 1.908,
"step": 8960
},
{
"epoch": 4.65,
"learning_rate": 0.001,
"loss": 1.9273,
"step": 8970
},
{
"epoch": 4.66,
"learning_rate": 0.001,
"loss": 1.9423,
"step": 8980
},
{
"epoch": 4.67,
"learning_rate": 0.001,
"loss": 1.9577,
"step": 8990
},
{
"epoch": 4.67,
"learning_rate": 0.001,
"loss": 1.9407,
"step": 9000
},
{
"epoch": 4.68,
"learning_rate": 0.001,
"loss": 1.9585,
"step": 9010
},
{
"epoch": 4.68,
"learning_rate": 0.001,
"loss": 1.9553,
"step": 9020
},
{
"epoch": 4.69,
"learning_rate": 0.001,
"loss": 1.9484,
"step": 9030
},
{
"epoch": 4.69,
"learning_rate": 0.001,
"loss": 1.9468,
"step": 9040
},
{
"epoch": 4.7,
"learning_rate": 0.001,
"loss": 1.9492,
"step": 9050
},
{
"epoch": 4.7,
"learning_rate": 0.001,
"loss": 1.9426,
"step": 9060
},
{
"epoch": 4.71,
"learning_rate": 0.001,
"loss": 1.9381,
"step": 9070
},
{
"epoch": 4.71,
"learning_rate": 0.001,
"loss": 1.9491,
"step": 9080
},
{
"epoch": 4.72,
"learning_rate": 0.001,
"loss": 1.9539,
"step": 9090
},
{
"epoch": 4.72,
"learning_rate": 0.001,
"loss": 1.9422,
"step": 9100
},
{
"epoch": 4.73,
"learning_rate": 0.001,
"loss": 1.9509,
"step": 9110
},
{
"epoch": 4.73,
"learning_rate": 0.001,
"loss": 1.9398,
"step": 9120
},
{
"epoch": 4.74,
"learning_rate": 0.001,
"loss": 1.9438,
"step": 9130
},
{
"epoch": 4.74,
"learning_rate": 0.001,
"loss": 1.9456,
"step": 9140
},
{
"epoch": 4.75,
"learning_rate": 0.001,
"loss": 1.9528,
"step": 9150
},
{
"epoch": 4.75,
"learning_rate": 0.001,
"loss": 1.9393,
"step": 9160
},
{
"epoch": 4.76,
"learning_rate": 0.001,
"loss": 1.9404,
"step": 9170
},
{
"epoch": 4.76,
"learning_rate": 0.001,
"loss": 1.9372,
"step": 9180
},
{
"epoch": 4.77,
"learning_rate": 0.001,
"loss": 1.9358,
"step": 9190
},
{
"epoch": 4.77,
"learning_rate": 0.001,
"loss": 1.9312,
"step": 9200
},
{
"epoch": 4.78,
"learning_rate": 0.001,
"loss": 1.9432,
"step": 9210
},
{
"epoch": 4.78,
"learning_rate": 0.001,
"loss": 1.9419,
"step": 9220
},
{
"epoch": 4.79,
"learning_rate": 0.001,
"loss": 1.9423,
"step": 9230
},
{
"epoch": 4.8,
"learning_rate": 0.001,
"loss": 1.9454,
"step": 9240
},
{
"epoch": 4.8,
"learning_rate": 0.001,
"loss": 1.9497,
"step": 9250
},
{
"epoch": 4.81,
"learning_rate": 0.001,
"loss": 1.9563,
"step": 9260
},
{
"epoch": 4.81,
"learning_rate": 0.001,
"loss": 1.9416,
"step": 9270
},
{
"epoch": 4.82,
"learning_rate": 0.001,
"loss": 1.9485,
"step": 9280
},
{
"epoch": 4.82,
"learning_rate": 0.001,
"loss": 1.9423,
"step": 9290
},
{
"epoch": 4.83,
"learning_rate": 0.001,
"loss": 1.9426,
"step": 9300
},
{
"epoch": 4.83,
"learning_rate": 0.001,
"loss": 1.9375,
"step": 9310
},
{
"epoch": 4.84,
"learning_rate": 0.001,
"loss": 1.9337,
"step": 9320
},
{
"epoch": 4.84,
"learning_rate": 0.001,
"loss": 1.9413,
"step": 9330
},
{
"epoch": 4.85,
"learning_rate": 0.001,
"loss": 1.9385,
"step": 9340
},
{
"epoch": 4.85,
"learning_rate": 0.001,
"loss": 1.9565,
"step": 9350
},
{
"epoch": 4.86,
"learning_rate": 0.001,
"loss": 1.9384,
"step": 9360
},
{
"epoch": 4.86,
"learning_rate": 0.001,
"loss": 1.9452,
"step": 9370
},
{
"epoch": 4.87,
"learning_rate": 0.001,
"loss": 1.9422,
"step": 9380
},
{
"epoch": 4.87,
"learning_rate": 0.001,
"loss": 1.9125,
"step": 9390
},
{
"epoch": 4.88,
"learning_rate": 0.001,
"loss": 1.9585,
"step": 9400
},
{
"epoch": 4.88,
"learning_rate": 0.001,
"loss": 1.9505,
"step": 9410
},
{
"epoch": 4.89,
"learning_rate": 0.001,
"loss": 1.9282,
"step": 9420
},
{
"epoch": 4.89,
"learning_rate": 0.001,
"loss": 1.9482,
"step": 9430
},
{
"epoch": 4.9,
"learning_rate": 0.001,
"loss": 1.9634,
"step": 9440
},
{
"epoch": 4.9,
"learning_rate": 0.001,
"loss": 1.9432,
"step": 9450
},
{
"epoch": 4.91,
"learning_rate": 0.001,
"loss": 1.9419,
"step": 9460
},
{
"epoch": 4.91,
"learning_rate": 0.001,
"loss": 1.9443,
"step": 9470
},
{
"epoch": 4.92,
"learning_rate": 0.001,
"loss": 1.9478,
"step": 9480
},
{
"epoch": 4.92,
"learning_rate": 0.001,
"loss": 1.9461,
"step": 9490
},
{
"epoch": 4.93,
"learning_rate": 0.001,
"loss": 1.9465,
"step": 9500
},
{
"epoch": 4.94,
"learning_rate": 0.001,
"loss": 1.9419,
"step": 9510
},
{
"epoch": 4.94,
"learning_rate": 0.001,
"loss": 1.9322,
"step": 9520
},
{
"epoch": 4.95,
"learning_rate": 0.001,
"loss": 1.9429,
"step": 9530
},
{
"epoch": 4.95,
"learning_rate": 0.001,
"loss": 1.9294,
"step": 9540
},
{
"epoch": 4.96,
"learning_rate": 0.001,
"loss": 1.966,
"step": 9550
},
{
"epoch": 4.96,
"learning_rate": 0.001,
"loss": 1.9419,
"step": 9560
},
{
"epoch": 4.97,
"learning_rate": 0.001,
"loss": 1.9477,
"step": 9570
},
{
"epoch": 4.97,
"learning_rate": 0.001,
"loss": 1.9377,
"step": 9580
},
{
"epoch": 4.98,
"learning_rate": 0.001,
"loss": 1.9563,
"step": 9590
},
{
"epoch": 4.98,
"learning_rate": 0.001,
"loss": 1.9393,
"step": 9600
},
{
"epoch": 4.99,
"learning_rate": 0.001,
"loss": 1.9378,
"step": 9610
},
{
"epoch": 4.99,
"learning_rate": 0.001,
"loss": 1.9558,
"step": 9620
},
{
"epoch": 5.0,
"learning_rate": 0.001,
"loss": 1.9444,
"step": 9630
},
{
"epoch": 5.0,
"eval_accuracy": {
"accuracy": 0.17665369649805449
},
"eval_f1": {
"f1": 0.04289493575207861
},
"eval_loss": 1.9407862424850464,
"eval_precision": {
"precision": 0.025236242356864926
},
"eval_recall": {
"recall": 0.14285714285714285
},
"eval_runtime": 76.9258,
"eval_samples_per_second": 50.113,
"eval_steps_per_second": 25.063,
"step": 9635
},
{
"epoch": 5.0,
"learning_rate": 0.001,
"loss": 1.9518,
"step": 9640
},
{
"epoch": 5.01,
"learning_rate": 0.001,
"loss": 1.9466,
"step": 9650
},
{
"epoch": 5.01,
"learning_rate": 0.001,
"loss": 1.9411,
"step": 9660
},
{
"epoch": 5.02,
"learning_rate": 0.001,
"loss": 1.9391,
"step": 9670
},
{
"epoch": 5.02,
"learning_rate": 0.001,
"loss": 1.9364,
"step": 9680
},
{
"epoch": 5.03,
"learning_rate": 0.001,
"loss": 1.9595,
"step": 9690
},
{
"epoch": 5.03,
"learning_rate": 0.001,
"loss": 1.9501,
"step": 9700
},
{
"epoch": 5.04,
"learning_rate": 0.001,
"loss": 1.9352,
"step": 9710
},
{
"epoch": 5.04,
"learning_rate": 0.001,
"loss": 1.9405,
"step": 9720
},
{
"epoch": 5.05,
"learning_rate": 0.001,
"loss": 1.9598,
"step": 9730
},
{
"epoch": 5.05,
"learning_rate": 0.001,
"loss": 1.9447,
"step": 9740
},
{
"epoch": 5.06,
"learning_rate": 0.001,
"loss": 1.9469,
"step": 9750
},
{
"epoch": 5.06,
"learning_rate": 0.001,
"loss": 1.936,
"step": 9760
},
{
"epoch": 5.07,
"learning_rate": 0.001,
"loss": 1.9361,
"step": 9770
},
{
"epoch": 5.08,
"learning_rate": 0.001,
"loss": 1.9465,
"step": 9780
},
{
"epoch": 5.08,
"learning_rate": 0.001,
"loss": 1.9325,
"step": 9790
},
{
"epoch": 5.09,
"learning_rate": 0.001,
"loss": 1.9453,
"step": 9800
},
{
"epoch": 5.09,
"learning_rate": 0.001,
"loss": 1.9412,
"step": 9810
},
{
"epoch": 5.1,
"learning_rate": 0.001,
"loss": 1.9248,
"step": 9820
},
{
"epoch": 5.1,
"learning_rate": 0.001,
"loss": 1.9434,
"step": 9830
},
{
"epoch": 5.11,
"learning_rate": 0.001,
"loss": 1.9291,
"step": 9840
},
{
"epoch": 5.11,
"learning_rate": 0.001,
"loss": 1.9407,
"step": 9850
},
{
"epoch": 5.12,
"learning_rate": 0.001,
"loss": 1.9049,
"step": 9860
},
{
"epoch": 5.12,
"learning_rate": 0.001,
"loss": 1.9437,
"step": 9870
},
{
"epoch": 5.13,
"learning_rate": 0.001,
"loss": 1.9416,
"step": 9880
},
{
"epoch": 5.13,
"learning_rate": 0.001,
"loss": 1.9415,
"step": 9890
},
{
"epoch": 5.14,
"learning_rate": 0.001,
"loss": 1.9756,
"step": 9900
},
{
"epoch": 5.14,
"learning_rate": 0.001,
"loss": 1.9386,
"step": 9910
},
{
"epoch": 5.15,
"learning_rate": 0.001,
"loss": 1.9301,
"step": 9920
},
{
"epoch": 5.15,
"learning_rate": 0.001,
"loss": 1.9419,
"step": 9930
},
{
"epoch": 5.16,
"learning_rate": 0.001,
"loss": 1.9548,
"step": 9940
},
{
"epoch": 5.16,
"learning_rate": 0.001,
"loss": 1.9657,
"step": 9950
},
{
"epoch": 5.17,
"learning_rate": 0.001,
"loss": 1.945,
"step": 9960
},
{
"epoch": 5.17,
"learning_rate": 0.001,
"loss": 1.9526,
"step": 9970
},
{
"epoch": 5.18,
"learning_rate": 0.001,
"loss": 1.9477,
"step": 9980
},
{
"epoch": 5.18,
"learning_rate": 0.001,
"loss": 1.952,
"step": 9990
},
{
"epoch": 5.19,
"learning_rate": 0.001,
"loss": 1.9479,
"step": 10000
},
{
"epoch": 5.19,
"learning_rate": 0.001,
"loss": 1.9528,
"step": 10010
},
{
"epoch": 5.2,
"learning_rate": 0.001,
"loss": 1.9458,
"step": 10020
},
{
"epoch": 5.2,
"learning_rate": 0.001,
"loss": 1.9475,
"step": 10030
},
{
"epoch": 5.21,
"learning_rate": 0.001,
"loss": 1.9444,
"step": 10040
},
{
"epoch": 5.22,
"learning_rate": 0.001,
"loss": 1.9454,
"step": 10050
},
{
"epoch": 5.22,
"learning_rate": 0.001,
"loss": 1.9372,
"step": 10060
},
{
"epoch": 5.23,
"learning_rate": 0.001,
"loss": 1.9441,
"step": 10070
},
{
"epoch": 5.23,
"learning_rate": 0.001,
"loss": 1.9381,
"step": 10080
},
{
"epoch": 5.24,
"learning_rate": 0.001,
"loss": 1.9352,
"step": 10090
},
{
"epoch": 5.24,
"learning_rate": 0.001,
"loss": 1.9483,
"step": 10100
},
{
"epoch": 5.25,
"learning_rate": 0.001,
"loss": 1.9278,
"step": 10110
},
{
"epoch": 5.25,
"learning_rate": 0.001,
"loss": 1.9271,
"step": 10120
},
{
"epoch": 5.26,
"learning_rate": 0.001,
"loss": 1.94,
"step": 10130
},
{
"epoch": 5.26,
"learning_rate": 0.001,
"loss": 1.9341,
"step": 10140
},
{
"epoch": 5.27,
"learning_rate": 0.001,
"loss": 1.9475,
"step": 10150
},
{
"epoch": 5.27,
"learning_rate": 0.001,
"loss": 1.918,
"step": 10160
},
{
"epoch": 5.28,
"learning_rate": 0.001,
"loss": 1.9338,
"step": 10170
},
{
"epoch": 5.28,
"learning_rate": 0.001,
"loss": 1.9352,
"step": 10180
},
{
"epoch": 5.29,
"learning_rate": 0.001,
"loss": 1.9636,
"step": 10190
},
{
"epoch": 5.29,
"learning_rate": 0.001,
"loss": 1.9425,
"step": 10200
},
{
"epoch": 5.3,
"learning_rate": 0.001,
"loss": 1.9239,
"step": 10210
},
{
"epoch": 5.3,
"learning_rate": 0.001,
"loss": 1.9486,
"step": 10220
},
{
"epoch": 5.31,
"learning_rate": 0.001,
"loss": 1.9801,
"step": 10230
},
{
"epoch": 5.31,
"learning_rate": 0.001,
"loss": 1.9297,
"step": 10240
},
{
"epoch": 5.32,
"learning_rate": 0.001,
"loss": 1.9544,
"step": 10250
},
{
"epoch": 5.32,
"learning_rate": 0.001,
"loss": 1.9478,
"step": 10260
},
{
"epoch": 5.33,
"learning_rate": 0.001,
"loss": 1.9295,
"step": 10270
},
{
"epoch": 5.33,
"learning_rate": 0.001,
"loss": 1.9481,
"step": 10280
},
{
"epoch": 5.34,
"learning_rate": 0.001,
"loss": 1.9489,
"step": 10290
},
{
"epoch": 5.35,
"learning_rate": 0.001,
"loss": 1.9641,
"step": 10300
},
{
"epoch": 5.35,
"learning_rate": 0.001,
"loss": 1.9478,
"step": 10310
},
{
"epoch": 5.36,
"learning_rate": 0.001,
"loss": 1.925,
"step": 10320
},
{
"epoch": 5.36,
"learning_rate": 0.001,
"loss": 1.9391,
"step": 10330
},
{
"epoch": 5.37,
"learning_rate": 0.001,
"loss": 1.9426,
"step": 10340
},
{
"epoch": 5.37,
"learning_rate": 0.001,
"loss": 1.951,
"step": 10350
},
{
"epoch": 5.38,
"learning_rate": 0.001,
"loss": 1.955,
"step": 10360
},
{
"epoch": 5.38,
"learning_rate": 0.001,
"loss": 1.9401,
"step": 10370
},
{
"epoch": 5.39,
"learning_rate": 0.001,
"loss": 1.9553,
"step": 10380
},
{
"epoch": 5.39,
"learning_rate": 0.001,
"loss": 1.9264,
"step": 10390
},
{
"epoch": 5.4,
"learning_rate": 0.001,
"loss": 1.9397,
"step": 10400
},
{
"epoch": 5.4,
"learning_rate": 0.001,
"loss": 1.9305,
"step": 10410
},
{
"epoch": 5.41,
"learning_rate": 0.001,
"loss": 1.9285,
"step": 10420
},
{
"epoch": 5.41,
"learning_rate": 0.001,
"loss": 1.9221,
"step": 10430
},
{
"epoch": 5.42,
"learning_rate": 0.001,
"loss": 1.95,
"step": 10440
},
{
"epoch": 5.42,
"learning_rate": 0.001,
"loss": 1.9425,
"step": 10450
},
{
"epoch": 5.43,
"learning_rate": 0.001,
"loss": 1.9596,
"step": 10460
},
{
"epoch": 5.43,
"learning_rate": 0.001,
"loss": 1.9522,
"step": 10470
},
{
"epoch": 5.44,
"learning_rate": 0.001,
"loss": 1.9427,
"step": 10480
},
{
"epoch": 5.44,
"learning_rate": 0.001,
"loss": 1.948,
"step": 10490
},
{
"epoch": 5.45,
"learning_rate": 0.001,
"loss": 1.9427,
"step": 10500
},
{
"epoch": 5.45,
"learning_rate": 0.001,
"loss": 1.9405,
"step": 10510
},
{
"epoch": 5.46,
"learning_rate": 0.001,
"loss": 1.9321,
"step": 10520
},
{
"epoch": 5.46,
"learning_rate": 0.001,
"loss": 1.9522,
"step": 10530
},
{
"epoch": 5.47,
"learning_rate": 0.001,
"loss": 1.9327,
"step": 10540
},
{
"epoch": 5.47,
"learning_rate": 0.001,
"loss": 1.9516,
"step": 10550
},
{
"epoch": 5.48,
"learning_rate": 0.001,
"loss": 1.9371,
"step": 10560
},
{
"epoch": 5.49,
"learning_rate": 0.001,
"loss": 1.9446,
"step": 10570
},
{
"epoch": 5.49,
"learning_rate": 0.001,
"loss": 1.9374,
"step": 10580
},
{
"epoch": 5.5,
"learning_rate": 0.001,
"loss": 1.9682,
"step": 10590
},
{
"epoch": 5.5,
"learning_rate": 0.001,
"loss": 1.9543,
"step": 10600
},
{
"epoch": 5.51,
"learning_rate": 0.001,
"loss": 1.9424,
"step": 10610
},
{
"epoch": 5.51,
"learning_rate": 0.001,
"loss": 1.9497,
"step": 10620
},
{
"epoch": 5.52,
"learning_rate": 0.001,
"loss": 1.9522,
"step": 10630
},
{
"epoch": 5.52,
"learning_rate": 0.001,
"loss": 1.9715,
"step": 10640
},
{
"epoch": 5.53,
"learning_rate": 0.001,
"loss": 1.9503,
"step": 10650
},
{
"epoch": 5.53,
"learning_rate": 0.001,
"loss": 1.9623,
"step": 10660
},
{
"epoch": 5.54,
"learning_rate": 0.001,
"loss": 1.9432,
"step": 10670
},
{
"epoch": 5.54,
"learning_rate": 0.001,
"loss": 1.9368,
"step": 10680
},
{
"epoch": 5.55,
"learning_rate": 0.001,
"loss": 1.9645,
"step": 10690
},
{
"epoch": 5.55,
"learning_rate": 0.001,
"loss": 1.9501,
"step": 10700
},
{
"epoch": 5.56,
"learning_rate": 0.001,
"loss": 1.9521,
"step": 10710
},
{
"epoch": 5.56,
"learning_rate": 0.001,
"loss": 1.9347,
"step": 10720
},
{
"epoch": 5.57,
"learning_rate": 0.001,
"loss": 1.9674,
"step": 10730
},
{
"epoch": 5.57,
"learning_rate": 0.001,
"loss": 1.9482,
"step": 10740
},
{
"epoch": 5.58,
"learning_rate": 0.001,
"loss": 1.9487,
"step": 10750
},
{
"epoch": 5.58,
"learning_rate": 0.001,
"loss": 1.9223,
"step": 10760
},
{
"epoch": 5.59,
"learning_rate": 0.001,
"loss": 1.9382,
"step": 10770
},
{
"epoch": 5.59,
"learning_rate": 0.001,
"loss": 1.9707,
"step": 10780
},
{
"epoch": 5.6,
"learning_rate": 0.001,
"loss": 1.9595,
"step": 10790
},
{
"epoch": 5.6,
"learning_rate": 0.001,
"loss": 1.9353,
"step": 10800
},
{
"epoch": 5.61,
"learning_rate": 0.001,
"loss": 1.9548,
"step": 10810
},
{
"epoch": 5.61,
"learning_rate": 0.001,
"loss": 1.9412,
"step": 10820
},
{
"epoch": 5.62,
"learning_rate": 0.001,
"loss": 1.9371,
"step": 10830
},
{
"epoch": 5.63,
"learning_rate": 0.001,
"loss": 1.9316,
"step": 10840
},
{
"epoch": 5.63,
"learning_rate": 0.001,
"loss": 1.9244,
"step": 10850
},
{
"epoch": 5.64,
"learning_rate": 0.001,
"loss": 1.9322,
"step": 10860
},
{
"epoch": 5.64,
"learning_rate": 0.001,
"loss": 1.9484,
"step": 10870
},
{
"epoch": 5.65,
"learning_rate": 0.001,
"loss": 1.9485,
"step": 10880
},
{
"epoch": 5.65,
"learning_rate": 0.001,
"loss": 1.9679,
"step": 10890
},
{
"epoch": 5.66,
"learning_rate": 0.001,
"loss": 1.9401,
"step": 10900
},
{
"epoch": 5.66,
"learning_rate": 0.001,
"loss": 1.9439,
"step": 10910
},
{
"epoch": 5.67,
"learning_rate": 0.001,
"loss": 1.9481,
"step": 10920
},
{
"epoch": 5.67,
"learning_rate": 0.001,
"loss": 1.9482,
"step": 10930
},
{
"epoch": 5.68,
"learning_rate": 0.001,
"loss": 1.9587,
"step": 10940
},
{
"epoch": 5.68,
"learning_rate": 0.001,
"loss": 1.9387,
"step": 10950
},
{
"epoch": 5.69,
"learning_rate": 0.001,
"loss": 1.959,
"step": 10960
},
{
"epoch": 5.69,
"learning_rate": 0.001,
"loss": 1.9449,
"step": 10970
},
{
"epoch": 5.7,
"learning_rate": 0.001,
"loss": 1.9478,
"step": 10980
},
{
"epoch": 5.7,
"learning_rate": 0.001,
"loss": 1.9518,
"step": 10990
},
{
"epoch": 5.71,
"learning_rate": 0.001,
"loss": 1.94,
"step": 11000
},
{
"epoch": 5.71,
"learning_rate": 0.001,
"loss": 1.9562,
"step": 11010
},
{
"epoch": 5.72,
"learning_rate": 0.001,
"loss": 1.9549,
"step": 11020
},
{
"epoch": 5.72,
"learning_rate": 0.001,
"loss": 1.9322,
"step": 11030
},
{
"epoch": 5.73,
"learning_rate": 0.001,
"loss": 1.9551,
"step": 11040
},
{
"epoch": 5.73,
"learning_rate": 0.001,
"loss": 1.9407,
"step": 11050
},
{
"epoch": 5.74,
"learning_rate": 0.001,
"loss": 1.951,
"step": 11060
},
{
"epoch": 5.74,
"learning_rate": 0.001,
"loss": 1.9303,
"step": 11070
},
{
"epoch": 5.75,
"learning_rate": 0.001,
"loss": 1.9343,
"step": 11080
},
{
"epoch": 5.76,
"learning_rate": 0.001,
"loss": 1.9496,
"step": 11090
},
{
"epoch": 5.76,
"learning_rate": 0.001,
"loss": 1.9437,
"step": 11100
},
{
"epoch": 5.77,
"learning_rate": 0.001,
"loss": 1.9563,
"step": 11110
},
{
"epoch": 5.77,
"learning_rate": 0.001,
"loss": 1.9291,
"step": 11120
},
{
"epoch": 5.78,
"learning_rate": 0.001,
"loss": 1.9516,
"step": 11130
},
{
"epoch": 5.78,
"learning_rate": 0.001,
"loss": 1.9541,
"step": 11140
},
{
"epoch": 5.79,
"learning_rate": 0.001,
"loss": 1.9448,
"step": 11150
},
{
"epoch": 5.79,
"learning_rate": 0.001,
"loss": 1.948,
"step": 11160
},
{
"epoch": 5.8,
"learning_rate": 0.001,
"loss": 1.9448,
"step": 11170
},
{
"epoch": 5.8,
"learning_rate": 0.001,
"loss": 1.9379,
"step": 11180
},
{
"epoch": 5.81,
"learning_rate": 0.001,
"loss": 1.9418,
"step": 11190
},
{
"epoch": 5.81,
"learning_rate": 0.001,
"loss": 1.9425,
"step": 11200
},
{
"epoch": 5.82,
"learning_rate": 0.001,
"loss": 1.9495,
"step": 11210
},
{
"epoch": 5.82,
"learning_rate": 0.001,
"loss": 1.9299,
"step": 11220
},
{
"epoch": 5.83,
"learning_rate": 0.001,
"loss": 1.9392,
"step": 11230
},
{
"epoch": 5.83,
"learning_rate": 0.001,
"loss": 1.9585,
"step": 11240
},
{
"epoch": 5.84,
"learning_rate": 0.001,
"loss": 1.9438,
"step": 11250
},
{
"epoch": 5.84,
"learning_rate": 0.001,
"loss": 1.9355,
"step": 11260
},
{
"epoch": 5.85,
"learning_rate": 0.001,
"loss": 1.9471,
"step": 11270
},
{
"epoch": 5.85,
"learning_rate": 0.001,
"loss": 1.9193,
"step": 11280
},
{
"epoch": 5.86,
"learning_rate": 0.001,
"loss": 1.9572,
"step": 11290
},
{
"epoch": 5.86,
"learning_rate": 0.001,
"loss": 1.9644,
"step": 11300
},
{
"epoch": 5.87,
"learning_rate": 0.001,
"loss": 1.9381,
"step": 11310
},
{
"epoch": 5.87,
"learning_rate": 0.001,
"loss": 1.9584,
"step": 11320
},
{
"epoch": 5.88,
"learning_rate": 0.001,
"loss": 1.9362,
"step": 11330
},
{
"epoch": 5.88,
"learning_rate": 0.001,
"loss": 1.9213,
"step": 11340
},
{
"epoch": 5.89,
"learning_rate": 0.001,
"loss": 1.9494,
"step": 11350
},
{
"epoch": 5.9,
"learning_rate": 0.001,
"loss": 1.9472,
"step": 11360
},
{
"epoch": 5.9,
"learning_rate": 0.001,
"loss": 1.9359,
"step": 11370
},
{
"epoch": 5.91,
"learning_rate": 0.001,
"loss": 1.9538,
"step": 11380
},
{
"epoch": 5.91,
"learning_rate": 0.001,
"loss": 1.9502,
"step": 11390
},
{
"epoch": 5.92,
"learning_rate": 0.001,
"loss": 1.9348,
"step": 11400
},
{
"epoch": 5.92,
"learning_rate": 0.001,
"loss": 1.9488,
"step": 11410
},
{
"epoch": 5.93,
"learning_rate": 0.001,
"loss": 1.9585,
"step": 11420
},
{
"epoch": 5.93,
"learning_rate": 0.001,
"loss": 1.945,
"step": 11430
},
{
"epoch": 5.94,
"learning_rate": 0.001,
"loss": 1.9359,
"step": 11440
},
{
"epoch": 5.94,
"learning_rate": 0.001,
"loss": 1.9599,
"step": 11450
},
{
"epoch": 5.95,
"learning_rate": 0.001,
"loss": 1.9445,
"step": 11460
},
{
"epoch": 5.95,
"learning_rate": 0.001,
"loss": 1.94,
"step": 11470
},
{
"epoch": 5.96,
"learning_rate": 0.001,
"loss": 1.943,
"step": 11480
},
{
"epoch": 5.96,
"learning_rate": 0.001,
"loss": 1.9242,
"step": 11490
},
{
"epoch": 5.97,
"learning_rate": 0.001,
"loss": 1.9447,
"step": 11500
},
{
"epoch": 5.97,
"learning_rate": 0.001,
"loss": 1.9472,
"step": 11510
},
{
"epoch": 5.98,
"learning_rate": 0.001,
"loss": 1.9703,
"step": 11520
},
{
"epoch": 5.98,
"learning_rate": 0.001,
"loss": 1.9566,
"step": 11530
},
{
"epoch": 5.99,
"learning_rate": 0.001,
"loss": 1.9436,
"step": 11540
},
{
"epoch": 5.99,
"learning_rate": 0.001,
"loss": 1.9345,
"step": 11550
},
{
"epoch": 6.0,
"learning_rate": 0.001,
"loss": 1.9441,
"step": 11560
},
{
"epoch": 6.0,
"eval_accuracy": {
"accuracy": 0.17665369649805449
},
"eval_f1": {
"f1": 0.04289493575207861
},
"eval_loss": 1.9427300691604614,
"eval_precision": {
"precision": 0.025236242356864926
},
"eval_recall": {
"recall": 0.14285714285714285
},
"eval_runtime": 77.3874,
"eval_samples_per_second": 49.814,
"eval_steps_per_second": 24.914,
"step": 11562
}
],
"logging_steps": 10,
"max_steps": 57810,
"num_input_tokens_seen": 0,
"num_train_epochs": 30,
"save_steps": 500,
"total_flos": 2.0029793200555622e+18,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}