Mel-Iza0's picture
Training in progress, epoch 1, checkpoint
3e8ca30
raw
history blame
85.2 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.1006397468528581,
"eval_steps": 500,
"global_step": 8000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.9934,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 3.3333333333333335e-05,
"loss": 1.0101,
"step": 20
},
{
"epoch": 0.0,
"learning_rate": 5e-05,
"loss": 0.98,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 6.666666666666667e-05,
"loss": 0.962,
"step": 40
},
{
"epoch": 0.01,
"learning_rate": 8.333333333333334e-05,
"loss": 0.9046,
"step": 50
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 0.8624,
"step": 60
},
{
"epoch": 0.01,
"learning_rate": 0.00011666666666666668,
"loss": 0.8147,
"step": 70
},
{
"epoch": 0.01,
"learning_rate": 0.00013333333333333334,
"loss": 0.807,
"step": 80
},
{
"epoch": 0.01,
"learning_rate": 0.00015000000000000001,
"loss": 0.7814,
"step": 90
},
{
"epoch": 0.01,
"learning_rate": 0.0001666666666666667,
"loss": 0.7618,
"step": 100
},
{
"epoch": 0.02,
"learning_rate": 0.00018333333333333334,
"loss": 0.7724,
"step": 110
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.7593,
"step": 120
},
{
"epoch": 0.02,
"learning_rate": 0.00021666666666666666,
"loss": 0.7546,
"step": 130
},
{
"epoch": 0.02,
"learning_rate": 0.00023333333333333336,
"loss": 0.7347,
"step": 140
},
{
"epoch": 0.02,
"learning_rate": 0.00025,
"loss": 0.7227,
"step": 150
},
{
"epoch": 0.02,
"learning_rate": 0.0002666666666666667,
"loss": 0.7359,
"step": 160
},
{
"epoch": 0.02,
"learning_rate": 0.00028333333333333335,
"loss": 0.7309,
"step": 170
},
{
"epoch": 0.02,
"learning_rate": 0.00030000000000000003,
"loss": 0.7237,
"step": 180
},
{
"epoch": 0.03,
"learning_rate": 0.00031666666666666665,
"loss": 0.7288,
"step": 190
},
{
"epoch": 0.03,
"learning_rate": 0.0003333333333333334,
"loss": 0.7329,
"step": 200
},
{
"epoch": 0.03,
"learning_rate": 0.00035,
"loss": 0.7229,
"step": 210
},
{
"epoch": 0.03,
"learning_rate": 0.00036666666666666667,
"loss": 0.7089,
"step": 220
},
{
"epoch": 0.03,
"learning_rate": 0.00038333333333333334,
"loss": 0.7214,
"step": 230
},
{
"epoch": 0.03,
"learning_rate": 0.0004,
"loss": 0.7022,
"step": 240
},
{
"epoch": 0.03,
"learning_rate": 0.0004,
"loss": 0.7097,
"step": 250
},
{
"epoch": 0.04,
"learning_rate": 0.0004,
"loss": 0.7128,
"step": 260
},
{
"epoch": 0.04,
"learning_rate": 0.0004,
"loss": 0.6895,
"step": 270
},
{
"epoch": 0.04,
"learning_rate": 0.0004,
"loss": 0.7036,
"step": 280
},
{
"epoch": 0.04,
"learning_rate": 0.0004,
"loss": 0.6802,
"step": 290
},
{
"epoch": 0.04,
"learning_rate": 0.0004,
"loss": 0.7051,
"step": 300
},
{
"epoch": 0.04,
"learning_rate": 0.0004,
"loss": 0.6901,
"step": 310
},
{
"epoch": 0.04,
"learning_rate": 0.0004,
"loss": 0.6852,
"step": 320
},
{
"epoch": 0.05,
"learning_rate": 0.0004,
"loss": 0.6823,
"step": 330
},
{
"epoch": 0.05,
"learning_rate": 0.0004,
"loss": 0.6889,
"step": 340
},
{
"epoch": 0.05,
"learning_rate": 0.0004,
"loss": 0.6698,
"step": 350
},
{
"epoch": 0.05,
"learning_rate": 0.0004,
"loss": 0.6695,
"step": 360
},
{
"epoch": 0.05,
"learning_rate": 0.0004,
"loss": 0.681,
"step": 370
},
{
"epoch": 0.05,
"learning_rate": 0.0004,
"loss": 0.6878,
"step": 380
},
{
"epoch": 0.05,
"learning_rate": 0.0004,
"loss": 0.6718,
"step": 390
},
{
"epoch": 0.06,
"learning_rate": 0.0004,
"loss": 0.6505,
"step": 400
},
{
"epoch": 0.06,
"learning_rate": 0.0004,
"loss": 0.686,
"step": 410
},
{
"epoch": 0.06,
"learning_rate": 0.0004,
"loss": 0.6634,
"step": 420
},
{
"epoch": 0.06,
"learning_rate": 0.0004,
"loss": 0.6701,
"step": 430
},
{
"epoch": 0.06,
"learning_rate": 0.0004,
"loss": 0.6733,
"step": 440
},
{
"epoch": 0.06,
"learning_rate": 0.0004,
"loss": 0.6889,
"step": 450
},
{
"epoch": 0.06,
"learning_rate": 0.0004,
"loss": 0.6591,
"step": 460
},
{
"epoch": 0.06,
"learning_rate": 0.0004,
"loss": 0.6769,
"step": 470
},
{
"epoch": 0.07,
"learning_rate": 0.0004,
"loss": 0.6839,
"step": 480
},
{
"epoch": 0.07,
"learning_rate": 0.0004,
"loss": 0.6579,
"step": 490
},
{
"epoch": 0.07,
"learning_rate": 0.0004,
"loss": 0.6768,
"step": 500
},
{
"epoch": 0.07,
"learning_rate": 0.0004,
"loss": 0.6644,
"step": 510
},
{
"epoch": 0.07,
"learning_rate": 0.0004,
"loss": 0.6488,
"step": 520
},
{
"epoch": 0.07,
"learning_rate": 0.0004,
"loss": 0.6557,
"step": 530
},
{
"epoch": 0.07,
"learning_rate": 0.0004,
"loss": 0.6738,
"step": 540
},
{
"epoch": 0.08,
"learning_rate": 0.0004,
"loss": 0.6536,
"step": 550
},
{
"epoch": 0.08,
"learning_rate": 0.0004,
"loss": 0.6679,
"step": 560
},
{
"epoch": 0.08,
"learning_rate": 0.0004,
"loss": 0.6359,
"step": 570
},
{
"epoch": 0.08,
"learning_rate": 0.0004,
"loss": 0.6492,
"step": 580
},
{
"epoch": 0.08,
"learning_rate": 0.0004,
"loss": 0.6488,
"step": 590
},
{
"epoch": 0.08,
"learning_rate": 0.0004,
"loss": 0.6764,
"step": 600
},
{
"epoch": 0.08,
"learning_rate": 0.0004,
"loss": 0.6511,
"step": 610
},
{
"epoch": 0.09,
"learning_rate": 0.0004,
"loss": 0.6738,
"step": 620
},
{
"epoch": 0.09,
"learning_rate": 0.0004,
"loss": 0.6424,
"step": 630
},
{
"epoch": 0.09,
"learning_rate": 0.0004,
"loss": 0.6582,
"step": 640
},
{
"epoch": 0.09,
"learning_rate": 0.0004,
"loss": 0.6649,
"step": 650
},
{
"epoch": 0.09,
"learning_rate": 0.0004,
"loss": 0.6697,
"step": 660
},
{
"epoch": 0.09,
"learning_rate": 0.0004,
"loss": 0.6491,
"step": 670
},
{
"epoch": 0.09,
"learning_rate": 0.0004,
"loss": 0.665,
"step": 680
},
{
"epoch": 0.09,
"learning_rate": 0.0004,
"loss": 0.643,
"step": 690
},
{
"epoch": 0.1,
"learning_rate": 0.0004,
"loss": 0.656,
"step": 700
},
{
"epoch": 0.1,
"learning_rate": 0.0004,
"loss": 0.6469,
"step": 710
},
{
"epoch": 0.1,
"learning_rate": 0.0004,
"loss": 0.6543,
"step": 720
},
{
"epoch": 0.1,
"learning_rate": 0.0004,
"loss": 0.6673,
"step": 730
},
{
"epoch": 0.1,
"learning_rate": 0.0004,
"loss": 0.6515,
"step": 740
},
{
"epoch": 0.1,
"learning_rate": 0.0004,
"loss": 0.6462,
"step": 750
},
{
"epoch": 0.1,
"learning_rate": 0.0004,
"loss": 0.6559,
"step": 760
},
{
"epoch": 0.11,
"learning_rate": 0.0004,
"loss": 0.6439,
"step": 770
},
{
"epoch": 0.11,
"learning_rate": 0.0004,
"loss": 0.6417,
"step": 780
},
{
"epoch": 0.11,
"learning_rate": 0.0004,
"loss": 0.6525,
"step": 790
},
{
"epoch": 0.11,
"learning_rate": 0.0004,
"loss": 0.6406,
"step": 800
},
{
"epoch": 0.11,
"learning_rate": 0.0004,
"loss": 0.6524,
"step": 810
},
{
"epoch": 0.11,
"learning_rate": 0.0004,
"loss": 0.6399,
"step": 820
},
{
"epoch": 0.11,
"learning_rate": 0.0004,
"loss": 0.6609,
"step": 830
},
{
"epoch": 0.12,
"learning_rate": 0.0004,
"loss": 0.6179,
"step": 840
},
{
"epoch": 0.12,
"learning_rate": 0.0004,
"loss": 0.6528,
"step": 850
},
{
"epoch": 0.12,
"learning_rate": 0.0004,
"loss": 0.6528,
"step": 860
},
{
"epoch": 0.12,
"learning_rate": 0.0004,
"loss": 0.6432,
"step": 870
},
{
"epoch": 0.12,
"learning_rate": 0.0004,
"loss": 0.6584,
"step": 880
},
{
"epoch": 0.12,
"learning_rate": 0.0004,
"loss": 0.6601,
"step": 890
},
{
"epoch": 0.12,
"learning_rate": 0.0004,
"loss": 0.6547,
"step": 900
},
{
"epoch": 0.13,
"learning_rate": 0.0004,
"loss": 0.6497,
"step": 910
},
{
"epoch": 0.13,
"learning_rate": 0.0004,
"loss": 0.6312,
"step": 920
},
{
"epoch": 0.13,
"learning_rate": 0.0004,
"loss": 0.6408,
"step": 930
},
{
"epoch": 0.13,
"learning_rate": 0.0004,
"loss": 0.6441,
"step": 940
},
{
"epoch": 0.13,
"learning_rate": 0.0004,
"loss": 0.6168,
"step": 950
},
{
"epoch": 0.13,
"learning_rate": 0.0004,
"loss": 0.6247,
"step": 960
},
{
"epoch": 0.13,
"learning_rate": 0.0004,
"loss": 0.6398,
"step": 970
},
{
"epoch": 0.13,
"learning_rate": 0.0004,
"loss": 0.6227,
"step": 980
},
{
"epoch": 0.14,
"learning_rate": 0.0004,
"loss": 0.6254,
"step": 990
},
{
"epoch": 0.14,
"learning_rate": 0.0004,
"loss": 0.6468,
"step": 1000
},
{
"epoch": 0.14,
"learning_rate": 0.0004,
"loss": 0.6318,
"step": 1010
},
{
"epoch": 0.14,
"learning_rate": 0.0004,
"loss": 0.611,
"step": 1020
},
{
"epoch": 0.14,
"learning_rate": 0.0004,
"loss": 0.6401,
"step": 1030
},
{
"epoch": 0.14,
"learning_rate": 0.0004,
"loss": 0.6165,
"step": 1040
},
{
"epoch": 0.14,
"learning_rate": 0.0004,
"loss": 0.6352,
"step": 1050
},
{
"epoch": 0.15,
"learning_rate": 0.0004,
"loss": 0.6532,
"step": 1060
},
{
"epoch": 0.15,
"learning_rate": 0.0004,
"loss": 0.6129,
"step": 1070
},
{
"epoch": 0.15,
"learning_rate": 0.0004,
"loss": 0.6254,
"step": 1080
},
{
"epoch": 0.15,
"learning_rate": 0.0004,
"loss": 0.6179,
"step": 1090
},
{
"epoch": 0.15,
"learning_rate": 0.0004,
"loss": 0.6141,
"step": 1100
},
{
"epoch": 0.15,
"learning_rate": 0.0004,
"loss": 0.6215,
"step": 1110
},
{
"epoch": 0.15,
"learning_rate": 0.0004,
"loss": 0.6333,
"step": 1120
},
{
"epoch": 0.16,
"learning_rate": 0.0004,
"loss": 0.6254,
"step": 1130
},
{
"epoch": 0.16,
"learning_rate": 0.0004,
"loss": 0.6284,
"step": 1140
},
{
"epoch": 0.16,
"learning_rate": 0.0004,
"loss": 0.6287,
"step": 1150
},
{
"epoch": 0.16,
"learning_rate": 0.0004,
"loss": 0.6085,
"step": 1160
},
{
"epoch": 0.16,
"learning_rate": 0.0004,
"loss": 0.6288,
"step": 1170
},
{
"epoch": 0.16,
"learning_rate": 0.0004,
"loss": 0.6339,
"step": 1180
},
{
"epoch": 0.16,
"learning_rate": 0.0004,
"loss": 0.6256,
"step": 1190
},
{
"epoch": 0.17,
"learning_rate": 0.0004,
"loss": 0.6382,
"step": 1200
},
{
"epoch": 0.17,
"learning_rate": 0.0004,
"loss": 0.6284,
"step": 1210
},
{
"epoch": 0.17,
"learning_rate": 0.0004,
"loss": 0.6147,
"step": 1220
},
{
"epoch": 0.17,
"learning_rate": 0.0004,
"loss": 0.6215,
"step": 1230
},
{
"epoch": 0.17,
"learning_rate": 0.0004,
"loss": 0.6045,
"step": 1240
},
{
"epoch": 0.17,
"learning_rate": 0.0004,
"loss": 0.6203,
"step": 1250
},
{
"epoch": 0.17,
"learning_rate": 0.0004,
"loss": 0.5984,
"step": 1260
},
{
"epoch": 0.17,
"learning_rate": 0.0004,
"loss": 0.5862,
"step": 1270
},
{
"epoch": 0.18,
"learning_rate": 0.0004,
"loss": 0.6168,
"step": 1280
},
{
"epoch": 0.18,
"learning_rate": 0.0004,
"loss": 0.6334,
"step": 1290
},
{
"epoch": 0.18,
"learning_rate": 0.0004,
"loss": 0.5835,
"step": 1300
},
{
"epoch": 0.18,
"learning_rate": 0.0004,
"loss": 0.6111,
"step": 1310
},
{
"epoch": 0.18,
"learning_rate": 0.0004,
"loss": 0.6041,
"step": 1320
},
{
"epoch": 0.18,
"learning_rate": 0.0004,
"loss": 0.6144,
"step": 1330
},
{
"epoch": 0.18,
"learning_rate": 0.0004,
"loss": 0.6292,
"step": 1340
},
{
"epoch": 0.19,
"learning_rate": 0.0004,
"loss": 0.5969,
"step": 1350
},
{
"epoch": 0.19,
"learning_rate": 0.0004,
"loss": 0.6309,
"step": 1360
},
{
"epoch": 0.19,
"learning_rate": 0.0004,
"loss": 0.6183,
"step": 1370
},
{
"epoch": 0.19,
"learning_rate": 0.0004,
"loss": 0.6182,
"step": 1380
},
{
"epoch": 0.19,
"learning_rate": 0.0004,
"loss": 0.6181,
"step": 1390
},
{
"epoch": 0.19,
"learning_rate": 0.0004,
"loss": 0.6138,
"step": 1400
},
{
"epoch": 0.19,
"learning_rate": 0.0004,
"loss": 0.617,
"step": 1410
},
{
"epoch": 0.2,
"learning_rate": 0.0004,
"loss": 0.6379,
"step": 1420
},
{
"epoch": 0.2,
"learning_rate": 0.0004,
"loss": 0.6138,
"step": 1430
},
{
"epoch": 0.2,
"learning_rate": 0.0004,
"loss": 0.6153,
"step": 1440
},
{
"epoch": 0.2,
"learning_rate": 0.0004,
"loss": 0.6062,
"step": 1450
},
{
"epoch": 0.2,
"learning_rate": 0.0004,
"loss": 0.5951,
"step": 1460
},
{
"epoch": 0.2,
"learning_rate": 0.0004,
"loss": 0.6155,
"step": 1470
},
{
"epoch": 0.2,
"learning_rate": 0.0004,
"loss": 0.5928,
"step": 1480
},
{
"epoch": 0.2,
"learning_rate": 0.0004,
"loss": 0.6116,
"step": 1490
},
{
"epoch": 0.21,
"learning_rate": 0.0004,
"loss": 0.5976,
"step": 1500
},
{
"epoch": 0.21,
"learning_rate": 0.0004,
"loss": 0.6131,
"step": 1510
},
{
"epoch": 0.21,
"learning_rate": 0.0004,
"loss": 0.606,
"step": 1520
},
{
"epoch": 0.21,
"learning_rate": 0.0004,
"loss": 0.6052,
"step": 1530
},
{
"epoch": 0.21,
"learning_rate": 0.0004,
"loss": 0.6266,
"step": 1540
},
{
"epoch": 0.21,
"learning_rate": 0.0004,
"loss": 0.6089,
"step": 1550
},
{
"epoch": 0.21,
"learning_rate": 0.0004,
"loss": 0.6095,
"step": 1560
},
{
"epoch": 0.22,
"learning_rate": 0.0004,
"loss": 0.6151,
"step": 1570
},
{
"epoch": 0.22,
"learning_rate": 0.0004,
"loss": 0.6155,
"step": 1580
},
{
"epoch": 0.22,
"learning_rate": 0.0004,
"loss": 0.6056,
"step": 1590
},
{
"epoch": 0.22,
"learning_rate": 0.0004,
"loss": 0.599,
"step": 1600
},
{
"epoch": 0.22,
"learning_rate": 0.0004,
"loss": 0.6191,
"step": 1610
},
{
"epoch": 0.22,
"learning_rate": 0.0004,
"loss": 0.61,
"step": 1620
},
{
"epoch": 0.22,
"learning_rate": 0.0004,
"loss": 0.5986,
"step": 1630
},
{
"epoch": 0.23,
"learning_rate": 0.0004,
"loss": 0.6285,
"step": 1640
},
{
"epoch": 0.23,
"learning_rate": 0.0004,
"loss": 0.6076,
"step": 1650
},
{
"epoch": 0.23,
"learning_rate": 0.0004,
"loss": 0.5945,
"step": 1660
},
{
"epoch": 0.23,
"learning_rate": 0.0004,
"loss": 0.6044,
"step": 1670
},
{
"epoch": 0.23,
"learning_rate": 0.0004,
"loss": 0.6068,
"step": 1680
},
{
"epoch": 0.23,
"learning_rate": 0.0004,
"loss": 0.6028,
"step": 1690
},
{
"epoch": 0.23,
"learning_rate": 0.0004,
"loss": 0.6155,
"step": 1700
},
{
"epoch": 0.24,
"learning_rate": 0.0004,
"loss": 0.5815,
"step": 1710
},
{
"epoch": 0.24,
"learning_rate": 0.0004,
"loss": 0.6384,
"step": 1720
},
{
"epoch": 0.24,
"learning_rate": 0.0004,
"loss": 0.6108,
"step": 1730
},
{
"epoch": 0.24,
"learning_rate": 0.0004,
"loss": 0.5913,
"step": 1740
},
{
"epoch": 0.24,
"learning_rate": 0.0004,
"loss": 0.6011,
"step": 1750
},
{
"epoch": 0.24,
"learning_rate": 0.0004,
"loss": 0.6169,
"step": 1760
},
{
"epoch": 0.24,
"learning_rate": 0.0004,
"loss": 0.5958,
"step": 1770
},
{
"epoch": 0.24,
"learning_rate": 0.0004,
"loss": 0.6034,
"step": 1780
},
{
"epoch": 0.25,
"learning_rate": 0.0004,
"loss": 0.6142,
"step": 1790
},
{
"epoch": 0.25,
"learning_rate": 0.0004,
"loss": 0.587,
"step": 1800
},
{
"epoch": 0.25,
"learning_rate": 0.0004,
"loss": 0.5915,
"step": 1810
},
{
"epoch": 0.25,
"learning_rate": 0.0004,
"loss": 0.5921,
"step": 1820
},
{
"epoch": 0.25,
"learning_rate": 0.0004,
"loss": 0.6091,
"step": 1830
},
{
"epoch": 0.25,
"learning_rate": 0.0004,
"loss": 0.6042,
"step": 1840
},
{
"epoch": 0.25,
"learning_rate": 0.0004,
"loss": 0.5896,
"step": 1850
},
{
"epoch": 0.26,
"learning_rate": 0.0004,
"loss": 0.6045,
"step": 1860
},
{
"epoch": 0.26,
"learning_rate": 0.0004,
"loss": 0.5877,
"step": 1870
},
{
"epoch": 0.26,
"learning_rate": 0.0004,
"loss": 0.5885,
"step": 1880
},
{
"epoch": 0.26,
"learning_rate": 0.0004,
"loss": 0.6048,
"step": 1890
},
{
"epoch": 0.26,
"learning_rate": 0.0004,
"loss": 0.6154,
"step": 1900
},
{
"epoch": 0.26,
"learning_rate": 0.0004,
"loss": 0.6036,
"step": 1910
},
{
"epoch": 0.26,
"learning_rate": 0.0004,
"loss": 0.6164,
"step": 1920
},
{
"epoch": 0.27,
"learning_rate": 0.0004,
"loss": 0.5781,
"step": 1930
},
{
"epoch": 0.27,
"learning_rate": 0.0004,
"loss": 0.5881,
"step": 1940
},
{
"epoch": 0.27,
"learning_rate": 0.0004,
"loss": 0.583,
"step": 1950
},
{
"epoch": 0.27,
"learning_rate": 0.0004,
"loss": 0.5912,
"step": 1960
},
{
"epoch": 0.27,
"learning_rate": 0.0004,
"loss": 0.5967,
"step": 1970
},
{
"epoch": 0.27,
"learning_rate": 0.0004,
"loss": 0.5733,
"step": 1980
},
{
"epoch": 0.27,
"learning_rate": 0.0004,
"loss": 0.6067,
"step": 1990
},
{
"epoch": 0.28,
"learning_rate": 0.0004,
"loss": 0.5786,
"step": 2000
},
{
"epoch": 0.28,
"learning_rate": 0.0004,
"loss": 0.5948,
"step": 2010
},
{
"epoch": 0.28,
"learning_rate": 0.0004,
"loss": 0.5933,
"step": 2020
},
{
"epoch": 0.28,
"learning_rate": 0.0004,
"loss": 0.5901,
"step": 2030
},
{
"epoch": 0.28,
"learning_rate": 0.0004,
"loss": 0.5929,
"step": 2040
},
{
"epoch": 0.28,
"learning_rate": 0.0004,
"loss": 0.5845,
"step": 2050
},
{
"epoch": 0.28,
"learning_rate": 0.0004,
"loss": 0.5843,
"step": 2060
},
{
"epoch": 0.28,
"learning_rate": 0.0004,
"loss": 0.5986,
"step": 2070
},
{
"epoch": 0.29,
"learning_rate": 0.0004,
"loss": 0.6027,
"step": 2080
},
{
"epoch": 0.29,
"learning_rate": 0.0004,
"loss": 0.5922,
"step": 2090
},
{
"epoch": 0.29,
"learning_rate": 0.0004,
"loss": 0.5832,
"step": 2100
},
{
"epoch": 0.29,
"learning_rate": 0.0004,
"loss": 0.5973,
"step": 2110
},
{
"epoch": 0.29,
"learning_rate": 0.0004,
"loss": 0.6133,
"step": 2120
},
{
"epoch": 0.29,
"learning_rate": 0.0004,
"loss": 0.591,
"step": 2130
},
{
"epoch": 0.29,
"learning_rate": 0.0004,
"loss": 0.5949,
"step": 2140
},
{
"epoch": 0.3,
"learning_rate": 0.0004,
"loss": 0.5804,
"step": 2150
},
{
"epoch": 0.3,
"learning_rate": 0.0004,
"loss": 0.5818,
"step": 2160
},
{
"epoch": 0.3,
"learning_rate": 0.0004,
"loss": 0.5997,
"step": 2170
},
{
"epoch": 0.3,
"learning_rate": 0.0004,
"loss": 0.5953,
"step": 2180
},
{
"epoch": 0.3,
"learning_rate": 0.0004,
"loss": 0.5913,
"step": 2190
},
{
"epoch": 0.3,
"learning_rate": 0.0004,
"loss": 0.5865,
"step": 2200
},
{
"epoch": 0.3,
"learning_rate": 0.0004,
"loss": 0.5891,
"step": 2210
},
{
"epoch": 0.31,
"learning_rate": 0.0004,
"loss": 0.584,
"step": 2220
},
{
"epoch": 0.31,
"learning_rate": 0.0004,
"loss": 0.5916,
"step": 2230
},
{
"epoch": 0.31,
"learning_rate": 0.0004,
"loss": 0.5828,
"step": 2240
},
{
"epoch": 0.31,
"learning_rate": 0.0004,
"loss": 0.581,
"step": 2250
},
{
"epoch": 0.31,
"learning_rate": 0.0004,
"loss": 0.5856,
"step": 2260
},
{
"epoch": 0.31,
"learning_rate": 0.0004,
"loss": 0.5822,
"step": 2270
},
{
"epoch": 0.31,
"learning_rate": 0.0004,
"loss": 0.5786,
"step": 2280
},
{
"epoch": 0.32,
"learning_rate": 0.0004,
"loss": 0.5882,
"step": 2290
},
{
"epoch": 0.32,
"learning_rate": 0.0004,
"loss": 0.5876,
"step": 2300
},
{
"epoch": 0.32,
"learning_rate": 0.0004,
"loss": 0.5954,
"step": 2310
},
{
"epoch": 0.32,
"learning_rate": 0.0004,
"loss": 0.5752,
"step": 2320
},
{
"epoch": 0.32,
"learning_rate": 0.0004,
"loss": 0.5977,
"step": 2330
},
{
"epoch": 0.32,
"learning_rate": 0.0004,
"loss": 0.5705,
"step": 2340
},
{
"epoch": 0.32,
"learning_rate": 0.0004,
"loss": 0.5805,
"step": 2350
},
{
"epoch": 0.32,
"learning_rate": 0.0004,
"loss": 0.5896,
"step": 2360
},
{
"epoch": 0.33,
"learning_rate": 0.0004,
"loss": 0.5804,
"step": 2370
},
{
"epoch": 0.33,
"learning_rate": 0.0004,
"loss": 0.5922,
"step": 2380
},
{
"epoch": 0.33,
"learning_rate": 0.0004,
"loss": 0.59,
"step": 2390
},
{
"epoch": 0.33,
"learning_rate": 0.0004,
"loss": 0.5868,
"step": 2400
},
{
"epoch": 0.33,
"learning_rate": 0.0004,
"loss": 0.5954,
"step": 2410
},
{
"epoch": 0.33,
"learning_rate": 0.0004,
"loss": 0.5729,
"step": 2420
},
{
"epoch": 0.33,
"learning_rate": 0.0004,
"loss": 0.5768,
"step": 2430
},
{
"epoch": 0.34,
"learning_rate": 0.0004,
"loss": 0.5826,
"step": 2440
},
{
"epoch": 0.34,
"learning_rate": 0.0004,
"loss": 0.5836,
"step": 2450
},
{
"epoch": 0.34,
"learning_rate": 0.0004,
"loss": 0.575,
"step": 2460
},
{
"epoch": 0.34,
"learning_rate": 0.0004,
"loss": 0.5957,
"step": 2470
},
{
"epoch": 0.34,
"learning_rate": 0.0004,
"loss": 0.5653,
"step": 2480
},
{
"epoch": 0.34,
"learning_rate": 0.0004,
"loss": 0.5697,
"step": 2490
},
{
"epoch": 0.34,
"learning_rate": 0.0004,
"loss": 0.5876,
"step": 2500
},
{
"epoch": 0.35,
"learning_rate": 0.0004,
"loss": 0.5703,
"step": 2510
},
{
"epoch": 0.35,
"learning_rate": 0.0004,
"loss": 0.5711,
"step": 2520
},
{
"epoch": 0.35,
"learning_rate": 0.0004,
"loss": 0.5714,
"step": 2530
},
{
"epoch": 0.35,
"learning_rate": 0.0004,
"loss": 0.5933,
"step": 2540
},
{
"epoch": 0.35,
"learning_rate": 0.0004,
"loss": 0.5651,
"step": 2550
},
{
"epoch": 0.35,
"learning_rate": 0.0004,
"loss": 0.5806,
"step": 2560
},
{
"epoch": 0.35,
"learning_rate": 0.0004,
"loss": 0.5819,
"step": 2570
},
{
"epoch": 0.35,
"learning_rate": 0.0004,
"loss": 0.5818,
"step": 2580
},
{
"epoch": 0.36,
"learning_rate": 0.0004,
"loss": 0.5686,
"step": 2590
},
{
"epoch": 0.36,
"learning_rate": 0.0004,
"loss": 0.5809,
"step": 2600
},
{
"epoch": 0.36,
"learning_rate": 0.0004,
"loss": 0.5801,
"step": 2610
},
{
"epoch": 0.36,
"learning_rate": 0.0004,
"loss": 0.5729,
"step": 2620
},
{
"epoch": 0.36,
"learning_rate": 0.0004,
"loss": 0.5673,
"step": 2630
},
{
"epoch": 0.36,
"learning_rate": 0.0004,
"loss": 0.5733,
"step": 2640
},
{
"epoch": 0.36,
"learning_rate": 0.0004,
"loss": 0.5652,
"step": 2650
},
{
"epoch": 0.37,
"learning_rate": 0.0004,
"loss": 0.5834,
"step": 2660
},
{
"epoch": 0.37,
"learning_rate": 0.0004,
"loss": 0.5689,
"step": 2670
},
{
"epoch": 0.37,
"learning_rate": 0.0004,
"loss": 0.5708,
"step": 2680
},
{
"epoch": 0.37,
"learning_rate": 0.0004,
"loss": 0.5689,
"step": 2690
},
{
"epoch": 0.37,
"learning_rate": 0.0004,
"loss": 0.5807,
"step": 2700
},
{
"epoch": 0.37,
"learning_rate": 0.0004,
"loss": 0.5909,
"step": 2710
},
{
"epoch": 0.37,
"learning_rate": 0.0004,
"loss": 0.5859,
"step": 2720
},
{
"epoch": 0.38,
"learning_rate": 0.0004,
"loss": 0.5694,
"step": 2730
},
{
"epoch": 0.38,
"learning_rate": 0.0004,
"loss": 0.5855,
"step": 2740
},
{
"epoch": 0.38,
"learning_rate": 0.0004,
"loss": 0.5655,
"step": 2750
},
{
"epoch": 0.38,
"learning_rate": 0.0004,
"loss": 0.5816,
"step": 2760
},
{
"epoch": 0.38,
"learning_rate": 0.0004,
"loss": 0.5745,
"step": 2770
},
{
"epoch": 0.38,
"learning_rate": 0.0004,
"loss": 0.5803,
"step": 2780
},
{
"epoch": 0.38,
"learning_rate": 0.0004,
"loss": 0.5718,
"step": 2790
},
{
"epoch": 0.39,
"learning_rate": 0.0004,
"loss": 0.5839,
"step": 2800
},
{
"epoch": 0.39,
"learning_rate": 0.0004,
"loss": 0.564,
"step": 2810
},
{
"epoch": 0.39,
"learning_rate": 0.0004,
"loss": 0.5592,
"step": 2820
},
{
"epoch": 0.39,
"learning_rate": 0.0004,
"loss": 0.5561,
"step": 2830
},
{
"epoch": 0.39,
"learning_rate": 0.0004,
"loss": 0.5673,
"step": 2840
},
{
"epoch": 0.39,
"learning_rate": 0.0004,
"loss": 0.5781,
"step": 2850
},
{
"epoch": 0.39,
"learning_rate": 0.0004,
"loss": 0.5787,
"step": 2860
},
{
"epoch": 0.39,
"learning_rate": 0.0004,
"loss": 0.5649,
"step": 2870
},
{
"epoch": 0.4,
"learning_rate": 0.0004,
"loss": 0.5706,
"step": 2880
},
{
"epoch": 0.4,
"learning_rate": 0.0004,
"loss": 0.5649,
"step": 2890
},
{
"epoch": 0.4,
"learning_rate": 0.0004,
"loss": 0.5743,
"step": 2900
},
{
"epoch": 0.4,
"learning_rate": 0.0004,
"loss": 0.5665,
"step": 2910
},
{
"epoch": 0.4,
"learning_rate": 0.0004,
"loss": 0.5653,
"step": 2920
},
{
"epoch": 0.4,
"learning_rate": 0.0004,
"loss": 0.5723,
"step": 2930
},
{
"epoch": 0.4,
"learning_rate": 0.0004,
"loss": 0.5728,
"step": 2940
},
{
"epoch": 0.41,
"learning_rate": 0.0004,
"loss": 0.5627,
"step": 2950
},
{
"epoch": 0.41,
"learning_rate": 0.0004,
"loss": 0.5582,
"step": 2960
},
{
"epoch": 0.41,
"learning_rate": 0.0004,
"loss": 0.5783,
"step": 2970
},
{
"epoch": 0.41,
"learning_rate": 0.0004,
"loss": 0.5683,
"step": 2980
},
{
"epoch": 0.41,
"learning_rate": 0.0004,
"loss": 0.571,
"step": 2990
},
{
"epoch": 0.41,
"learning_rate": 0.0004,
"loss": 0.5644,
"step": 3000
},
{
"epoch": 0.41,
"learning_rate": 0.0004,
"loss": 0.5693,
"step": 3010
},
{
"epoch": 0.42,
"learning_rate": 0.0004,
"loss": 0.5663,
"step": 3020
},
{
"epoch": 0.42,
"learning_rate": 0.0004,
"loss": 0.5728,
"step": 3030
},
{
"epoch": 0.42,
"learning_rate": 0.0004,
"loss": 0.5683,
"step": 3040
},
{
"epoch": 0.42,
"learning_rate": 0.0004,
"loss": 0.5829,
"step": 3050
},
{
"epoch": 0.42,
"learning_rate": 0.0004,
"loss": 0.5659,
"step": 3060
},
{
"epoch": 0.42,
"learning_rate": 0.0004,
"loss": 0.5676,
"step": 3070
},
{
"epoch": 0.42,
"learning_rate": 0.0004,
"loss": 0.5776,
"step": 3080
},
{
"epoch": 0.43,
"learning_rate": 0.0004,
"loss": 0.5473,
"step": 3090
},
{
"epoch": 0.43,
"learning_rate": 0.0004,
"loss": 0.5703,
"step": 3100
},
{
"epoch": 0.43,
"learning_rate": 0.0004,
"loss": 0.5412,
"step": 3110
},
{
"epoch": 0.43,
"learning_rate": 0.0004,
"loss": 0.5584,
"step": 3120
},
{
"epoch": 0.43,
"learning_rate": 0.0004,
"loss": 0.5571,
"step": 3130
},
{
"epoch": 0.43,
"learning_rate": 0.0004,
"loss": 0.556,
"step": 3140
},
{
"epoch": 0.43,
"learning_rate": 0.0004,
"loss": 0.5774,
"step": 3150
},
{
"epoch": 0.43,
"learning_rate": 0.0004,
"loss": 0.5523,
"step": 3160
},
{
"epoch": 0.44,
"learning_rate": 0.0004,
"loss": 0.5712,
"step": 3170
},
{
"epoch": 0.44,
"learning_rate": 0.0004,
"loss": 0.5693,
"step": 3180
},
{
"epoch": 0.44,
"learning_rate": 0.0004,
"loss": 0.5712,
"step": 3190
},
{
"epoch": 0.44,
"learning_rate": 0.0004,
"loss": 0.566,
"step": 3200
},
{
"epoch": 0.44,
"learning_rate": 0.0004,
"loss": 0.5677,
"step": 3210
},
{
"epoch": 0.44,
"learning_rate": 0.0004,
"loss": 0.5625,
"step": 3220
},
{
"epoch": 0.44,
"learning_rate": 0.0004,
"loss": 0.5561,
"step": 3230
},
{
"epoch": 0.45,
"learning_rate": 0.0004,
"loss": 0.5867,
"step": 3240
},
{
"epoch": 0.45,
"learning_rate": 0.0004,
"loss": 0.5406,
"step": 3250
},
{
"epoch": 0.45,
"learning_rate": 0.0004,
"loss": 0.5673,
"step": 3260
},
{
"epoch": 0.45,
"learning_rate": 0.0004,
"loss": 0.5676,
"step": 3270
},
{
"epoch": 0.45,
"learning_rate": 0.0004,
"loss": 0.555,
"step": 3280
},
{
"epoch": 0.45,
"learning_rate": 0.0004,
"loss": 0.5585,
"step": 3290
},
{
"epoch": 0.45,
"learning_rate": 0.0004,
"loss": 0.5795,
"step": 3300
},
{
"epoch": 0.46,
"learning_rate": 0.0004,
"loss": 0.5663,
"step": 3310
},
{
"epoch": 0.46,
"learning_rate": 0.0004,
"loss": 0.5717,
"step": 3320
},
{
"epoch": 0.46,
"learning_rate": 0.0004,
"loss": 0.5676,
"step": 3330
},
{
"epoch": 0.46,
"learning_rate": 0.0004,
"loss": 0.5592,
"step": 3340
},
{
"epoch": 0.46,
"learning_rate": 0.0004,
"loss": 0.5566,
"step": 3350
},
{
"epoch": 0.46,
"learning_rate": 0.0004,
"loss": 0.5694,
"step": 3360
},
{
"epoch": 0.46,
"learning_rate": 0.0004,
"loss": 0.5656,
"step": 3370
},
{
"epoch": 0.47,
"learning_rate": 0.0004,
"loss": 0.5751,
"step": 3380
},
{
"epoch": 0.47,
"learning_rate": 0.0004,
"loss": 0.5439,
"step": 3390
},
{
"epoch": 0.47,
"learning_rate": 0.0004,
"loss": 0.5595,
"step": 3400
},
{
"epoch": 0.47,
"learning_rate": 0.0004,
"loss": 0.5614,
"step": 3410
},
{
"epoch": 0.47,
"learning_rate": 0.0004,
"loss": 0.5281,
"step": 3420
},
{
"epoch": 0.47,
"learning_rate": 0.0004,
"loss": 0.5468,
"step": 3430
},
{
"epoch": 0.47,
"learning_rate": 0.0004,
"loss": 0.529,
"step": 3440
},
{
"epoch": 0.47,
"learning_rate": 0.0004,
"loss": 0.5733,
"step": 3450
},
{
"epoch": 0.48,
"learning_rate": 0.0004,
"loss": 0.5489,
"step": 3460
},
{
"epoch": 0.48,
"learning_rate": 0.0004,
"loss": 0.5494,
"step": 3470
},
{
"epoch": 0.48,
"learning_rate": 0.0004,
"loss": 0.5452,
"step": 3480
},
{
"epoch": 0.48,
"learning_rate": 0.0004,
"loss": 0.5643,
"step": 3490
},
{
"epoch": 0.48,
"learning_rate": 0.0004,
"loss": 0.5633,
"step": 3500
},
{
"epoch": 0.48,
"learning_rate": 0.0004,
"loss": 0.5599,
"step": 3510
},
{
"epoch": 0.48,
"learning_rate": 0.0004,
"loss": 0.5598,
"step": 3520
},
{
"epoch": 0.49,
"learning_rate": 0.0004,
"loss": 0.5383,
"step": 3530
},
{
"epoch": 0.49,
"learning_rate": 0.0004,
"loss": 0.5421,
"step": 3540
},
{
"epoch": 0.49,
"learning_rate": 0.0004,
"loss": 0.5691,
"step": 3550
},
{
"epoch": 0.49,
"learning_rate": 0.0004,
"loss": 0.5675,
"step": 3560
},
{
"epoch": 0.49,
"learning_rate": 0.0004,
"loss": 0.5517,
"step": 3570
},
{
"epoch": 0.49,
"learning_rate": 0.0004,
"loss": 0.5462,
"step": 3580
},
{
"epoch": 0.49,
"learning_rate": 0.0004,
"loss": 0.558,
"step": 3590
},
{
"epoch": 0.5,
"learning_rate": 0.0004,
"loss": 0.563,
"step": 3600
},
{
"epoch": 0.5,
"learning_rate": 0.0004,
"loss": 0.5406,
"step": 3610
},
{
"epoch": 0.5,
"learning_rate": 0.0004,
"loss": 0.5541,
"step": 3620
},
{
"epoch": 0.5,
"learning_rate": 0.0004,
"loss": 0.5613,
"step": 3630
},
{
"epoch": 0.5,
"learning_rate": 0.0004,
"loss": 0.5341,
"step": 3640
},
{
"epoch": 0.5,
"learning_rate": 0.0004,
"loss": 0.5778,
"step": 3650
},
{
"epoch": 0.5,
"learning_rate": 0.0004,
"loss": 0.5505,
"step": 3660
},
{
"epoch": 0.5,
"learning_rate": 0.0004,
"loss": 0.5547,
"step": 3670
},
{
"epoch": 0.51,
"learning_rate": 0.0004,
"loss": 0.5444,
"step": 3680
},
{
"epoch": 0.51,
"learning_rate": 0.0004,
"loss": 0.5398,
"step": 3690
},
{
"epoch": 0.51,
"learning_rate": 0.0004,
"loss": 0.5362,
"step": 3700
},
{
"epoch": 0.51,
"learning_rate": 0.0004,
"loss": 0.5711,
"step": 3710
},
{
"epoch": 0.51,
"learning_rate": 0.0004,
"loss": 0.5807,
"step": 3720
},
{
"epoch": 0.51,
"learning_rate": 0.0004,
"loss": 0.5608,
"step": 3730
},
{
"epoch": 0.51,
"learning_rate": 0.0004,
"loss": 0.5509,
"step": 3740
},
{
"epoch": 0.52,
"learning_rate": 0.0004,
"loss": 0.5554,
"step": 3750
},
{
"epoch": 0.52,
"learning_rate": 0.0004,
"loss": 0.5524,
"step": 3760
},
{
"epoch": 0.52,
"learning_rate": 0.0004,
"loss": 0.5323,
"step": 3770
},
{
"epoch": 0.52,
"learning_rate": 0.0004,
"loss": 0.552,
"step": 3780
},
{
"epoch": 0.52,
"learning_rate": 0.0004,
"loss": 0.5616,
"step": 3790
},
{
"epoch": 0.52,
"learning_rate": 0.0004,
"loss": 0.5462,
"step": 3800
},
{
"epoch": 0.52,
"learning_rate": 0.0004,
"loss": 0.5636,
"step": 3810
},
{
"epoch": 0.53,
"learning_rate": 0.0004,
"loss": 0.5556,
"step": 3820
},
{
"epoch": 0.53,
"learning_rate": 0.0004,
"loss": 0.5631,
"step": 3830
},
{
"epoch": 0.53,
"learning_rate": 0.0004,
"loss": 0.5554,
"step": 3840
},
{
"epoch": 0.53,
"learning_rate": 0.0004,
"loss": 0.5614,
"step": 3850
},
{
"epoch": 0.53,
"learning_rate": 0.0004,
"loss": 0.5507,
"step": 3860
},
{
"epoch": 0.53,
"learning_rate": 0.0004,
"loss": 0.576,
"step": 3870
},
{
"epoch": 0.53,
"learning_rate": 0.0004,
"loss": 0.5495,
"step": 3880
},
{
"epoch": 0.54,
"learning_rate": 0.0004,
"loss": 0.5673,
"step": 3890
},
{
"epoch": 0.54,
"learning_rate": 0.0004,
"loss": 0.5611,
"step": 3900
},
{
"epoch": 0.54,
"learning_rate": 0.0004,
"loss": 0.5412,
"step": 3910
},
{
"epoch": 0.54,
"learning_rate": 0.0004,
"loss": 0.5356,
"step": 3920
},
{
"epoch": 0.54,
"learning_rate": 0.0004,
"loss": 0.568,
"step": 3930
},
{
"epoch": 0.54,
"learning_rate": 0.0004,
"loss": 0.5221,
"step": 3940
},
{
"epoch": 0.54,
"learning_rate": 0.0004,
"loss": 0.5448,
"step": 3950
},
{
"epoch": 0.54,
"learning_rate": 0.0004,
"loss": 0.5453,
"step": 3960
},
{
"epoch": 0.55,
"learning_rate": 0.0004,
"loss": 0.5405,
"step": 3970
},
{
"epoch": 0.55,
"learning_rate": 0.0004,
"loss": 0.5473,
"step": 3980
},
{
"epoch": 0.55,
"learning_rate": 0.0004,
"loss": 0.5419,
"step": 3990
},
{
"epoch": 0.55,
"learning_rate": 0.0004,
"loss": 0.5503,
"step": 4000
},
{
"epoch": 0.55,
"learning_rate": 0.0004,
"loss": 0.5486,
"step": 4010
},
{
"epoch": 0.55,
"learning_rate": 0.0004,
"loss": 0.5464,
"step": 4020
},
{
"epoch": 0.55,
"learning_rate": 0.0004,
"loss": 0.5374,
"step": 4030
},
{
"epoch": 0.56,
"learning_rate": 0.0004,
"loss": 0.531,
"step": 4040
},
{
"epoch": 0.56,
"learning_rate": 0.0004,
"loss": 0.5624,
"step": 4050
},
{
"epoch": 0.56,
"learning_rate": 0.0004,
"loss": 0.5268,
"step": 4060
},
{
"epoch": 0.56,
"learning_rate": 0.0004,
"loss": 0.5612,
"step": 4070
},
{
"epoch": 0.56,
"learning_rate": 0.0004,
"loss": 0.5606,
"step": 4080
},
{
"epoch": 0.56,
"learning_rate": 0.0004,
"loss": 0.548,
"step": 4090
},
{
"epoch": 0.56,
"learning_rate": 0.0004,
"loss": 0.5552,
"step": 4100
},
{
"epoch": 0.57,
"learning_rate": 0.0004,
"loss": 0.5403,
"step": 4110
},
{
"epoch": 0.57,
"learning_rate": 0.0004,
"loss": 0.5516,
"step": 4120
},
{
"epoch": 0.57,
"learning_rate": 0.0004,
"loss": 0.542,
"step": 4130
},
{
"epoch": 0.57,
"learning_rate": 0.0004,
"loss": 0.5519,
"step": 4140
},
{
"epoch": 0.57,
"learning_rate": 0.0004,
"loss": 0.5438,
"step": 4150
},
{
"epoch": 0.57,
"learning_rate": 0.0004,
"loss": 0.5379,
"step": 4160
},
{
"epoch": 0.57,
"learning_rate": 0.0004,
"loss": 0.5441,
"step": 4170
},
{
"epoch": 0.58,
"learning_rate": 0.0004,
"loss": 0.5496,
"step": 4180
},
{
"epoch": 0.58,
"learning_rate": 0.0004,
"loss": 0.5462,
"step": 4190
},
{
"epoch": 0.58,
"learning_rate": 0.0004,
"loss": 0.5498,
"step": 4200
},
{
"epoch": 0.58,
"learning_rate": 0.0004,
"loss": 0.5462,
"step": 4210
},
{
"epoch": 0.58,
"learning_rate": 0.0004,
"loss": 0.5197,
"step": 4220
},
{
"epoch": 0.58,
"learning_rate": 0.0004,
"loss": 0.541,
"step": 4230
},
{
"epoch": 0.58,
"learning_rate": 0.0004,
"loss": 0.5453,
"step": 4240
},
{
"epoch": 0.58,
"learning_rate": 0.0004,
"loss": 0.5305,
"step": 4250
},
{
"epoch": 0.59,
"learning_rate": 0.0004,
"loss": 0.5402,
"step": 4260
},
{
"epoch": 0.59,
"learning_rate": 0.0004,
"loss": 0.533,
"step": 4270
},
{
"epoch": 0.59,
"learning_rate": 0.0004,
"loss": 0.5434,
"step": 4280
},
{
"epoch": 0.59,
"learning_rate": 0.0004,
"loss": 0.5453,
"step": 4290
},
{
"epoch": 0.59,
"learning_rate": 0.0004,
"loss": 0.5623,
"step": 4300
},
{
"epoch": 0.59,
"learning_rate": 0.0004,
"loss": 0.5416,
"step": 4310
},
{
"epoch": 0.59,
"learning_rate": 0.0004,
"loss": 0.5291,
"step": 4320
},
{
"epoch": 0.6,
"learning_rate": 0.0004,
"loss": 0.55,
"step": 4330
},
{
"epoch": 0.6,
"learning_rate": 0.0004,
"loss": 0.5325,
"step": 4340
},
{
"epoch": 0.6,
"learning_rate": 0.0004,
"loss": 0.5287,
"step": 4350
},
{
"epoch": 0.6,
"learning_rate": 0.0004,
"loss": 0.5207,
"step": 4360
},
{
"epoch": 0.6,
"learning_rate": 0.0004,
"loss": 0.5536,
"step": 4370
},
{
"epoch": 0.6,
"learning_rate": 0.0004,
"loss": 0.5495,
"step": 4380
},
{
"epoch": 0.6,
"learning_rate": 0.0004,
"loss": 0.5408,
"step": 4390
},
{
"epoch": 0.61,
"learning_rate": 0.0004,
"loss": 0.5391,
"step": 4400
},
{
"epoch": 0.61,
"learning_rate": 0.0004,
"loss": 0.5366,
"step": 4410
},
{
"epoch": 0.61,
"learning_rate": 0.0004,
"loss": 0.5355,
"step": 4420
},
{
"epoch": 0.61,
"learning_rate": 0.0004,
"loss": 0.5398,
"step": 4430
},
{
"epoch": 0.61,
"learning_rate": 0.0004,
"loss": 0.5378,
"step": 4440
},
{
"epoch": 0.61,
"learning_rate": 0.0004,
"loss": 0.5508,
"step": 4450
},
{
"epoch": 0.61,
"learning_rate": 0.0004,
"loss": 0.5188,
"step": 4460
},
{
"epoch": 0.61,
"learning_rate": 0.0004,
"loss": 0.539,
"step": 4470
},
{
"epoch": 0.62,
"learning_rate": 0.0004,
"loss": 0.5391,
"step": 4480
},
{
"epoch": 0.62,
"learning_rate": 0.0004,
"loss": 0.5352,
"step": 4490
},
{
"epoch": 0.62,
"learning_rate": 0.0004,
"loss": 0.55,
"step": 4500
},
{
"epoch": 0.62,
"learning_rate": 0.0004,
"loss": 0.5444,
"step": 4510
},
{
"epoch": 0.62,
"learning_rate": 0.0004,
"loss": 0.5212,
"step": 4520
},
{
"epoch": 0.62,
"learning_rate": 0.0004,
"loss": 0.5293,
"step": 4530
},
{
"epoch": 0.62,
"learning_rate": 0.0004,
"loss": 0.544,
"step": 4540
},
{
"epoch": 0.63,
"learning_rate": 0.0004,
"loss": 0.5524,
"step": 4550
},
{
"epoch": 0.63,
"learning_rate": 0.0004,
"loss": 0.539,
"step": 4560
},
{
"epoch": 0.63,
"learning_rate": 0.0004,
"loss": 0.533,
"step": 4570
},
{
"epoch": 0.63,
"learning_rate": 0.0004,
"loss": 0.5288,
"step": 4580
},
{
"epoch": 0.63,
"learning_rate": 0.0004,
"loss": 0.5078,
"step": 4590
},
{
"epoch": 0.63,
"learning_rate": 0.0004,
"loss": 0.5397,
"step": 4600
},
{
"epoch": 0.63,
"learning_rate": 0.0004,
"loss": 0.541,
"step": 4610
},
{
"epoch": 0.64,
"learning_rate": 0.0004,
"loss": 0.5461,
"step": 4620
},
{
"epoch": 0.64,
"learning_rate": 0.0004,
"loss": 0.5524,
"step": 4630
},
{
"epoch": 0.64,
"learning_rate": 0.0004,
"loss": 0.5428,
"step": 4640
},
{
"epoch": 0.64,
"learning_rate": 0.0004,
"loss": 0.5352,
"step": 4650
},
{
"epoch": 0.64,
"learning_rate": 0.0004,
"loss": 0.5264,
"step": 4660
},
{
"epoch": 0.64,
"learning_rate": 0.0004,
"loss": 0.5436,
"step": 4670
},
{
"epoch": 0.64,
"learning_rate": 0.0004,
"loss": 0.5402,
"step": 4680
},
{
"epoch": 0.65,
"learning_rate": 0.0004,
"loss": 0.5353,
"step": 4690
},
{
"epoch": 0.65,
"learning_rate": 0.0004,
"loss": 0.5155,
"step": 4700
},
{
"epoch": 0.65,
"learning_rate": 0.0004,
"loss": 0.5484,
"step": 4710
},
{
"epoch": 0.65,
"learning_rate": 0.0004,
"loss": 0.5634,
"step": 4720
},
{
"epoch": 0.65,
"learning_rate": 0.0004,
"loss": 0.5414,
"step": 4730
},
{
"epoch": 0.65,
"learning_rate": 0.0004,
"loss": 0.5566,
"step": 4740
},
{
"epoch": 0.65,
"learning_rate": 0.0004,
"loss": 0.5365,
"step": 4750
},
{
"epoch": 0.65,
"learning_rate": 0.0004,
"loss": 0.5352,
"step": 4760
},
{
"epoch": 0.66,
"learning_rate": 0.0004,
"loss": 0.5372,
"step": 4770
},
{
"epoch": 0.66,
"learning_rate": 0.0004,
"loss": 0.5374,
"step": 4780
},
{
"epoch": 0.66,
"learning_rate": 0.0004,
"loss": 0.5376,
"step": 4790
},
{
"epoch": 0.66,
"learning_rate": 0.0004,
"loss": 0.5338,
"step": 4800
},
{
"epoch": 0.66,
"learning_rate": 0.0004,
"loss": 0.5446,
"step": 4810
},
{
"epoch": 0.66,
"learning_rate": 0.0004,
"loss": 0.5394,
"step": 4820
},
{
"epoch": 0.66,
"learning_rate": 0.0004,
"loss": 0.5255,
"step": 4830
},
{
"epoch": 0.67,
"learning_rate": 0.0004,
"loss": 0.5203,
"step": 4840
},
{
"epoch": 0.67,
"learning_rate": 0.0004,
"loss": 0.5401,
"step": 4850
},
{
"epoch": 0.67,
"learning_rate": 0.0004,
"loss": 0.539,
"step": 4860
},
{
"epoch": 0.67,
"learning_rate": 0.0004,
"loss": 0.5341,
"step": 4870
},
{
"epoch": 0.67,
"learning_rate": 0.0004,
"loss": 0.5309,
"step": 4880
},
{
"epoch": 0.67,
"learning_rate": 0.0004,
"loss": 0.5272,
"step": 4890
},
{
"epoch": 0.67,
"learning_rate": 0.0004,
"loss": 0.5432,
"step": 4900
},
{
"epoch": 0.68,
"learning_rate": 0.0004,
"loss": 0.5432,
"step": 4910
},
{
"epoch": 0.68,
"learning_rate": 0.0004,
"loss": 0.5228,
"step": 4920
},
{
"epoch": 0.68,
"learning_rate": 0.0004,
"loss": 0.5361,
"step": 4930
},
{
"epoch": 0.68,
"learning_rate": 0.0004,
"loss": 0.5275,
"step": 4940
},
{
"epoch": 0.68,
"learning_rate": 0.0004,
"loss": 0.5315,
"step": 4950
},
{
"epoch": 0.68,
"learning_rate": 0.0004,
"loss": 0.5289,
"step": 4960
},
{
"epoch": 0.68,
"learning_rate": 0.0004,
"loss": 0.5473,
"step": 4970
},
{
"epoch": 0.69,
"learning_rate": 0.0004,
"loss": 0.5315,
"step": 4980
},
{
"epoch": 0.69,
"learning_rate": 0.0004,
"loss": 0.5326,
"step": 4990
},
{
"epoch": 0.69,
"learning_rate": 0.0004,
"loss": 0.5083,
"step": 5000
},
{
"epoch": 0.69,
"learning_rate": 0.0004,
"loss": 0.5256,
"step": 5010
},
{
"epoch": 0.69,
"learning_rate": 0.0004,
"loss": 0.5264,
"step": 5020
},
{
"epoch": 0.69,
"learning_rate": 0.0004,
"loss": 0.5248,
"step": 5030
},
{
"epoch": 0.69,
"learning_rate": 0.0004,
"loss": 0.5353,
"step": 5040
},
{
"epoch": 0.69,
"learning_rate": 0.0004,
"loss": 0.5302,
"step": 5050
},
{
"epoch": 0.7,
"learning_rate": 0.0004,
"loss": 0.5262,
"step": 5060
},
{
"epoch": 0.7,
"learning_rate": 0.0004,
"loss": 0.5296,
"step": 5070
},
{
"epoch": 0.7,
"learning_rate": 0.0004,
"loss": 0.5231,
"step": 5080
},
{
"epoch": 0.7,
"learning_rate": 0.0004,
"loss": 0.5276,
"step": 5090
},
{
"epoch": 0.7,
"learning_rate": 0.0004,
"loss": 0.53,
"step": 5100
},
{
"epoch": 0.7,
"learning_rate": 0.0004,
"loss": 0.537,
"step": 5110
},
{
"epoch": 0.7,
"learning_rate": 0.0004,
"loss": 0.5207,
"step": 5120
},
{
"epoch": 0.71,
"learning_rate": 0.0004,
"loss": 0.5055,
"step": 5130
},
{
"epoch": 0.71,
"learning_rate": 0.0004,
"loss": 0.5222,
"step": 5140
},
{
"epoch": 0.71,
"learning_rate": 0.0004,
"loss": 0.5062,
"step": 5150
},
{
"epoch": 0.71,
"learning_rate": 0.0004,
"loss": 0.5285,
"step": 5160
},
{
"epoch": 0.71,
"learning_rate": 0.0004,
"loss": 0.5419,
"step": 5170
},
{
"epoch": 0.71,
"learning_rate": 0.0004,
"loss": 0.5356,
"step": 5180
},
{
"epoch": 0.71,
"learning_rate": 0.0004,
"loss": 0.5237,
"step": 5190
},
{
"epoch": 0.72,
"learning_rate": 0.0004,
"loss": 0.5516,
"step": 5200
},
{
"epoch": 0.72,
"learning_rate": 0.0004,
"loss": 0.5375,
"step": 5210
},
{
"epoch": 0.72,
"learning_rate": 0.0004,
"loss": 0.5193,
"step": 5220
},
{
"epoch": 0.72,
"learning_rate": 0.0004,
"loss": 0.5165,
"step": 5230
},
{
"epoch": 0.72,
"learning_rate": 0.0004,
"loss": 0.5263,
"step": 5240
},
{
"epoch": 0.72,
"learning_rate": 0.0004,
"loss": 0.5101,
"step": 5250
},
{
"epoch": 0.72,
"learning_rate": 0.0004,
"loss": 0.5258,
"step": 5260
},
{
"epoch": 0.73,
"learning_rate": 0.0004,
"loss": 0.5206,
"step": 5270
},
{
"epoch": 0.73,
"learning_rate": 0.0004,
"loss": 0.5226,
"step": 5280
},
{
"epoch": 0.73,
"learning_rate": 0.0004,
"loss": 0.5244,
"step": 5290
},
{
"epoch": 0.73,
"learning_rate": 0.0004,
"loss": 0.5103,
"step": 5300
},
{
"epoch": 0.73,
"learning_rate": 0.0004,
"loss": 0.5365,
"step": 5310
},
{
"epoch": 0.73,
"learning_rate": 0.0004,
"loss": 0.5152,
"step": 5320
},
{
"epoch": 0.73,
"learning_rate": 0.0004,
"loss": 0.5316,
"step": 5330
},
{
"epoch": 0.73,
"learning_rate": 0.0004,
"loss": 0.5429,
"step": 5340
},
{
"epoch": 0.74,
"learning_rate": 0.0004,
"loss": 0.5204,
"step": 5350
},
{
"epoch": 0.74,
"learning_rate": 0.0004,
"loss": 0.5362,
"step": 5360
},
{
"epoch": 0.74,
"learning_rate": 0.0004,
"loss": 0.5296,
"step": 5370
},
{
"epoch": 0.74,
"learning_rate": 0.0004,
"loss": 0.5302,
"step": 5380
},
{
"epoch": 0.74,
"learning_rate": 0.0004,
"loss": 0.5276,
"step": 5390
},
{
"epoch": 0.74,
"learning_rate": 0.0004,
"loss": 0.5247,
"step": 5400
},
{
"epoch": 0.74,
"learning_rate": 0.0004,
"loss": 0.5216,
"step": 5410
},
{
"epoch": 0.75,
"learning_rate": 0.0004,
"loss": 0.5397,
"step": 5420
},
{
"epoch": 0.75,
"learning_rate": 0.0004,
"loss": 0.5137,
"step": 5430
},
{
"epoch": 0.75,
"learning_rate": 0.0004,
"loss": 0.5194,
"step": 5440
},
{
"epoch": 0.75,
"learning_rate": 0.0004,
"loss": 0.5208,
"step": 5450
},
{
"epoch": 0.75,
"learning_rate": 0.0004,
"loss": 0.506,
"step": 5460
},
{
"epoch": 0.75,
"learning_rate": 0.0004,
"loss": 0.5002,
"step": 5470
},
{
"epoch": 0.75,
"learning_rate": 0.0004,
"loss": 0.5337,
"step": 5480
},
{
"epoch": 0.76,
"learning_rate": 0.0004,
"loss": 0.5241,
"step": 5490
},
{
"epoch": 0.76,
"learning_rate": 0.0004,
"loss": 0.5517,
"step": 5500
},
{
"epoch": 0.76,
"learning_rate": 0.0004,
"loss": 0.5073,
"step": 5510
},
{
"epoch": 0.76,
"learning_rate": 0.0004,
"loss": 0.5424,
"step": 5520
},
{
"epoch": 0.76,
"learning_rate": 0.0004,
"loss": 0.5254,
"step": 5530
},
{
"epoch": 0.76,
"learning_rate": 0.0004,
"loss": 0.5248,
"step": 5540
},
{
"epoch": 0.76,
"learning_rate": 0.0004,
"loss": 0.5214,
"step": 5550
},
{
"epoch": 0.76,
"learning_rate": 0.0004,
"loss": 0.5372,
"step": 5560
},
{
"epoch": 0.77,
"learning_rate": 0.0004,
"loss": 0.5317,
"step": 5570
},
{
"epoch": 0.77,
"learning_rate": 0.0004,
"loss": 0.5149,
"step": 5580
},
{
"epoch": 0.77,
"learning_rate": 0.0004,
"loss": 0.5194,
"step": 5590
},
{
"epoch": 0.77,
"learning_rate": 0.0004,
"loss": 0.5223,
"step": 5600
},
{
"epoch": 0.77,
"learning_rate": 0.0004,
"loss": 0.5353,
"step": 5610
},
{
"epoch": 0.77,
"learning_rate": 0.0004,
"loss": 0.5325,
"step": 5620
},
{
"epoch": 0.77,
"learning_rate": 0.0004,
"loss": 0.5255,
"step": 5630
},
{
"epoch": 0.78,
"learning_rate": 0.0004,
"loss": 0.512,
"step": 5640
},
{
"epoch": 0.78,
"learning_rate": 0.0004,
"loss": 0.5189,
"step": 5650
},
{
"epoch": 0.78,
"learning_rate": 0.0004,
"loss": 0.5184,
"step": 5660
},
{
"epoch": 0.78,
"learning_rate": 0.0004,
"loss": 0.5409,
"step": 5670
},
{
"epoch": 0.78,
"learning_rate": 0.0004,
"loss": 0.5241,
"step": 5680
},
{
"epoch": 0.78,
"learning_rate": 0.0004,
"loss": 0.5438,
"step": 5690
},
{
"epoch": 0.78,
"learning_rate": 0.0004,
"loss": 0.5361,
"step": 5700
},
{
"epoch": 0.79,
"learning_rate": 0.0004,
"loss": 0.5368,
"step": 5710
},
{
"epoch": 0.79,
"learning_rate": 0.0004,
"loss": 0.531,
"step": 5720
},
{
"epoch": 0.79,
"learning_rate": 0.0004,
"loss": 0.5186,
"step": 5730
},
{
"epoch": 0.79,
"learning_rate": 0.0004,
"loss": 0.5124,
"step": 5740
},
{
"epoch": 0.79,
"learning_rate": 0.0004,
"loss": 0.5053,
"step": 5750
},
{
"epoch": 0.79,
"learning_rate": 0.0004,
"loss": 0.5489,
"step": 5760
},
{
"epoch": 0.79,
"learning_rate": 0.0004,
"loss": 0.5227,
"step": 5770
},
{
"epoch": 0.8,
"learning_rate": 0.0004,
"loss": 0.533,
"step": 5780
},
{
"epoch": 0.8,
"learning_rate": 0.0004,
"loss": 0.5366,
"step": 5790
},
{
"epoch": 0.8,
"learning_rate": 0.0004,
"loss": 0.5202,
"step": 5800
},
{
"epoch": 0.8,
"learning_rate": 0.0004,
"loss": 0.5287,
"step": 5810
},
{
"epoch": 0.8,
"learning_rate": 0.0004,
"loss": 0.5121,
"step": 5820
},
{
"epoch": 0.8,
"learning_rate": 0.0004,
"loss": 0.5129,
"step": 5830
},
{
"epoch": 0.8,
"learning_rate": 0.0004,
"loss": 0.5341,
"step": 5840
},
{
"epoch": 0.8,
"learning_rate": 0.0004,
"loss": 0.5213,
"step": 5850
},
{
"epoch": 0.81,
"learning_rate": 0.0004,
"loss": 0.5382,
"step": 5860
},
{
"epoch": 0.81,
"learning_rate": 0.0004,
"loss": 0.5273,
"step": 5870
},
{
"epoch": 0.81,
"learning_rate": 0.0004,
"loss": 0.5123,
"step": 5880
},
{
"epoch": 0.81,
"learning_rate": 0.0004,
"loss": 0.516,
"step": 5890
},
{
"epoch": 0.81,
"learning_rate": 0.0004,
"loss": 0.5114,
"step": 5900
},
{
"epoch": 0.81,
"learning_rate": 0.0004,
"loss": 0.5114,
"step": 5910
},
{
"epoch": 0.81,
"learning_rate": 0.0004,
"loss": 0.5234,
"step": 5920
},
{
"epoch": 0.82,
"learning_rate": 0.0004,
"loss": 0.5261,
"step": 5930
},
{
"epoch": 0.82,
"learning_rate": 0.0004,
"loss": 0.4916,
"step": 5940
},
{
"epoch": 0.82,
"learning_rate": 0.0004,
"loss": 0.5155,
"step": 5950
},
{
"epoch": 0.82,
"learning_rate": 0.0004,
"loss": 0.534,
"step": 5960
},
{
"epoch": 0.82,
"learning_rate": 0.0004,
"loss": 0.525,
"step": 5970
},
{
"epoch": 0.82,
"learning_rate": 0.0004,
"loss": 0.5319,
"step": 5980
},
{
"epoch": 0.82,
"learning_rate": 0.0004,
"loss": 0.5112,
"step": 5990
},
{
"epoch": 0.83,
"learning_rate": 0.0004,
"loss": 0.5161,
"step": 6000
},
{
"epoch": 0.83,
"learning_rate": 0.0004,
"loss": 0.5046,
"step": 6010
},
{
"epoch": 0.83,
"learning_rate": 0.0004,
"loss": 0.5339,
"step": 6020
},
{
"epoch": 0.83,
"learning_rate": 0.0004,
"loss": 0.5197,
"step": 6030
},
{
"epoch": 0.83,
"learning_rate": 0.0004,
"loss": 0.5181,
"step": 6040
},
{
"epoch": 0.83,
"learning_rate": 0.0004,
"loss": 0.517,
"step": 6050
},
{
"epoch": 0.83,
"learning_rate": 0.0004,
"loss": 0.5166,
"step": 6060
},
{
"epoch": 0.84,
"learning_rate": 0.0004,
"loss": 0.5259,
"step": 6070
},
{
"epoch": 0.84,
"learning_rate": 0.0004,
"loss": 0.516,
"step": 6080
},
{
"epoch": 0.84,
"learning_rate": 0.0004,
"loss": 0.5026,
"step": 6090
},
{
"epoch": 0.84,
"learning_rate": 0.0004,
"loss": 0.5209,
"step": 6100
},
{
"epoch": 0.84,
"learning_rate": 0.0004,
"loss": 0.5083,
"step": 6110
},
{
"epoch": 0.84,
"learning_rate": 0.0004,
"loss": 0.543,
"step": 6120
},
{
"epoch": 0.84,
"learning_rate": 0.0004,
"loss": 0.5313,
"step": 6130
},
{
"epoch": 0.84,
"learning_rate": 0.0004,
"loss": 0.539,
"step": 6140
},
{
"epoch": 0.85,
"learning_rate": 0.0004,
"loss": 0.5165,
"step": 6150
},
{
"epoch": 0.85,
"learning_rate": 0.0004,
"loss": 0.5185,
"step": 6160
},
{
"epoch": 0.85,
"learning_rate": 0.0004,
"loss": 0.5286,
"step": 6170
},
{
"epoch": 0.85,
"learning_rate": 0.0004,
"loss": 0.5229,
"step": 6180
},
{
"epoch": 0.85,
"learning_rate": 0.0004,
"loss": 0.5128,
"step": 6190
},
{
"epoch": 0.85,
"learning_rate": 0.0004,
"loss": 0.5178,
"step": 6200
},
{
"epoch": 0.85,
"learning_rate": 0.0004,
"loss": 0.4972,
"step": 6210
},
{
"epoch": 0.86,
"learning_rate": 0.0004,
"loss": 0.5277,
"step": 6220
},
{
"epoch": 0.86,
"learning_rate": 0.0004,
"loss": 0.4977,
"step": 6230
},
{
"epoch": 0.86,
"learning_rate": 0.0004,
"loss": 0.5226,
"step": 6240
},
{
"epoch": 0.86,
"learning_rate": 0.0004,
"loss": 0.5125,
"step": 6250
},
{
"epoch": 0.86,
"learning_rate": 0.0004,
"loss": 0.5209,
"step": 6260
},
{
"epoch": 0.86,
"learning_rate": 0.0004,
"loss": 0.4912,
"step": 6270
},
{
"epoch": 0.86,
"learning_rate": 0.0004,
"loss": 0.4965,
"step": 6280
},
{
"epoch": 0.87,
"learning_rate": 0.0004,
"loss": 0.511,
"step": 6290
},
{
"epoch": 0.87,
"learning_rate": 0.0004,
"loss": 0.506,
"step": 6300
},
{
"epoch": 0.87,
"learning_rate": 0.0004,
"loss": 0.529,
"step": 6310
},
{
"epoch": 0.87,
"learning_rate": 0.0004,
"loss": 0.5106,
"step": 6320
},
{
"epoch": 0.87,
"learning_rate": 0.0004,
"loss": 0.5028,
"step": 6330
},
{
"epoch": 0.87,
"learning_rate": 0.0004,
"loss": 0.5159,
"step": 6340
},
{
"epoch": 0.87,
"learning_rate": 0.0004,
"loss": 0.5232,
"step": 6350
},
{
"epoch": 0.88,
"learning_rate": 0.0004,
"loss": 0.52,
"step": 6360
},
{
"epoch": 0.88,
"learning_rate": 0.0004,
"loss": 0.5273,
"step": 6370
},
{
"epoch": 0.88,
"learning_rate": 0.0004,
"loss": 0.5095,
"step": 6380
},
{
"epoch": 0.88,
"learning_rate": 0.0004,
"loss": 0.5151,
"step": 6390
},
{
"epoch": 0.88,
"learning_rate": 0.0004,
"loss": 0.5207,
"step": 6400
},
{
"epoch": 0.88,
"learning_rate": 0.0004,
"loss": 0.5113,
"step": 6410
},
{
"epoch": 0.88,
"learning_rate": 0.0004,
"loss": 0.5193,
"step": 6420
},
{
"epoch": 0.88,
"learning_rate": 0.0004,
"loss": 0.5304,
"step": 6430
},
{
"epoch": 0.89,
"learning_rate": 0.0004,
"loss": 0.5271,
"step": 6440
},
{
"epoch": 0.89,
"learning_rate": 0.0004,
"loss": 0.5155,
"step": 6450
},
{
"epoch": 0.89,
"learning_rate": 0.0004,
"loss": 0.5228,
"step": 6460
},
{
"epoch": 0.89,
"learning_rate": 0.0004,
"loss": 0.5087,
"step": 6470
},
{
"epoch": 0.89,
"learning_rate": 0.0004,
"loss": 0.5199,
"step": 6480
},
{
"epoch": 0.89,
"learning_rate": 0.0004,
"loss": 0.5059,
"step": 6490
},
{
"epoch": 0.89,
"learning_rate": 0.0004,
"loss": 0.5128,
"step": 6500
},
{
"epoch": 0.9,
"learning_rate": 0.0004,
"loss": 0.536,
"step": 6510
},
{
"epoch": 0.9,
"learning_rate": 0.0004,
"loss": 0.5008,
"step": 6520
},
{
"epoch": 0.9,
"learning_rate": 0.0004,
"loss": 0.5167,
"step": 6530
},
{
"epoch": 0.9,
"learning_rate": 0.0004,
"loss": 0.5151,
"step": 6540
},
{
"epoch": 0.9,
"learning_rate": 0.0004,
"loss": 0.5151,
"step": 6550
},
{
"epoch": 0.9,
"learning_rate": 0.0004,
"loss": 0.507,
"step": 6560
},
{
"epoch": 0.9,
"learning_rate": 0.0004,
"loss": 0.5274,
"step": 6570
},
{
"epoch": 0.91,
"learning_rate": 0.0004,
"loss": 0.5088,
"step": 6580
},
{
"epoch": 0.91,
"learning_rate": 0.0004,
"loss": 0.5268,
"step": 6590
},
{
"epoch": 0.91,
"learning_rate": 0.0004,
"loss": 0.5175,
"step": 6600
},
{
"epoch": 0.91,
"learning_rate": 0.0004,
"loss": 0.5205,
"step": 6610
},
{
"epoch": 0.91,
"learning_rate": 0.0004,
"loss": 0.5267,
"step": 6620
},
{
"epoch": 0.91,
"learning_rate": 0.0004,
"loss": 0.5122,
"step": 6630
},
{
"epoch": 0.91,
"learning_rate": 0.0004,
"loss": 0.5058,
"step": 6640
},
{
"epoch": 0.91,
"learning_rate": 0.0004,
"loss": 0.5131,
"step": 6650
},
{
"epoch": 0.92,
"learning_rate": 0.0004,
"loss": 0.5009,
"step": 6660
},
{
"epoch": 0.92,
"learning_rate": 0.0004,
"loss": 0.5174,
"step": 6670
},
{
"epoch": 0.92,
"learning_rate": 0.0004,
"loss": 0.4971,
"step": 6680
},
{
"epoch": 0.92,
"learning_rate": 0.0004,
"loss": 0.5045,
"step": 6690
},
{
"epoch": 0.92,
"learning_rate": 0.0004,
"loss": 0.5129,
"step": 6700
},
{
"epoch": 0.92,
"learning_rate": 0.0004,
"loss": 0.5183,
"step": 6710
},
{
"epoch": 0.92,
"learning_rate": 0.0004,
"loss": 0.5168,
"step": 6720
},
{
"epoch": 0.93,
"learning_rate": 0.0004,
"loss": 0.5219,
"step": 6730
},
{
"epoch": 0.93,
"learning_rate": 0.0004,
"loss": 0.4939,
"step": 6740
},
{
"epoch": 0.93,
"learning_rate": 0.0004,
"loss": 0.5048,
"step": 6750
},
{
"epoch": 0.93,
"learning_rate": 0.0004,
"loss": 0.5144,
"step": 6760
},
{
"epoch": 0.93,
"learning_rate": 0.0004,
"loss": 0.4923,
"step": 6770
},
{
"epoch": 0.93,
"learning_rate": 0.0004,
"loss": 0.5264,
"step": 6780
},
{
"epoch": 0.93,
"learning_rate": 0.0004,
"loss": 0.5089,
"step": 6790
},
{
"epoch": 0.94,
"learning_rate": 0.0004,
"loss": 0.4996,
"step": 6800
},
{
"epoch": 0.94,
"learning_rate": 0.0004,
"loss": 0.5014,
"step": 6810
},
{
"epoch": 0.94,
"learning_rate": 0.0004,
"loss": 0.5054,
"step": 6820
},
{
"epoch": 0.94,
"learning_rate": 0.0004,
"loss": 0.5125,
"step": 6830
},
{
"epoch": 0.94,
"learning_rate": 0.0004,
"loss": 0.508,
"step": 6840
},
{
"epoch": 0.94,
"learning_rate": 0.0004,
"loss": 0.5164,
"step": 6850
},
{
"epoch": 0.94,
"learning_rate": 0.0004,
"loss": 0.5086,
"step": 6860
},
{
"epoch": 0.95,
"learning_rate": 0.0004,
"loss": 0.5078,
"step": 6870
},
{
"epoch": 0.95,
"learning_rate": 0.0004,
"loss": 0.5094,
"step": 6880
},
{
"epoch": 0.95,
"learning_rate": 0.0004,
"loss": 0.4825,
"step": 6890
},
{
"epoch": 0.95,
"learning_rate": 0.0004,
"loss": 0.5068,
"step": 6900
},
{
"epoch": 0.95,
"learning_rate": 0.0004,
"loss": 0.524,
"step": 6910
},
{
"epoch": 0.95,
"learning_rate": 0.0004,
"loss": 0.5097,
"step": 6920
},
{
"epoch": 0.95,
"learning_rate": 0.0004,
"loss": 0.5109,
"step": 6930
},
{
"epoch": 0.95,
"learning_rate": 0.0004,
"loss": 0.5073,
"step": 6940
},
{
"epoch": 0.96,
"learning_rate": 0.0004,
"loss": 0.5154,
"step": 6950
},
{
"epoch": 0.96,
"learning_rate": 0.0004,
"loss": 0.5133,
"step": 6960
},
{
"epoch": 0.96,
"learning_rate": 0.0004,
"loss": 0.5203,
"step": 6970
},
{
"epoch": 0.96,
"learning_rate": 0.0004,
"loss": 0.5185,
"step": 6980
},
{
"epoch": 0.96,
"learning_rate": 0.0004,
"loss": 0.5115,
"step": 6990
},
{
"epoch": 0.96,
"learning_rate": 0.0004,
"loss": 0.5172,
"step": 7000
},
{
"epoch": 0.96,
"learning_rate": 0.0004,
"loss": 0.5361,
"step": 7010
},
{
"epoch": 0.97,
"learning_rate": 0.0004,
"loss": 0.5243,
"step": 7020
},
{
"epoch": 0.97,
"learning_rate": 0.0004,
"loss": 0.4933,
"step": 7030
},
{
"epoch": 0.97,
"learning_rate": 0.0004,
"loss": 0.5159,
"step": 7040
},
{
"epoch": 0.97,
"learning_rate": 0.0004,
"loss": 0.5087,
"step": 7050
},
{
"epoch": 0.97,
"learning_rate": 0.0004,
"loss": 0.4991,
"step": 7060
},
{
"epoch": 0.97,
"learning_rate": 0.0004,
"loss": 0.5025,
"step": 7070
},
{
"epoch": 0.97,
"learning_rate": 0.0004,
"loss": 0.5142,
"step": 7080
},
{
"epoch": 0.98,
"learning_rate": 0.0004,
"loss": 0.4961,
"step": 7090
},
{
"epoch": 0.98,
"learning_rate": 0.0004,
"loss": 0.5148,
"step": 7100
},
{
"epoch": 0.98,
"learning_rate": 0.0004,
"loss": 0.4982,
"step": 7110
},
{
"epoch": 0.98,
"learning_rate": 0.0004,
"loss": 0.5185,
"step": 7120
},
{
"epoch": 0.98,
"learning_rate": 0.0004,
"loss": 0.5072,
"step": 7130
},
{
"epoch": 0.98,
"learning_rate": 0.0004,
"loss": 0.4863,
"step": 7140
},
{
"epoch": 0.98,
"learning_rate": 0.0004,
"loss": 0.5181,
"step": 7150
},
{
"epoch": 0.99,
"learning_rate": 0.0004,
"loss": 0.5071,
"step": 7160
},
{
"epoch": 0.99,
"learning_rate": 0.0004,
"loss": 0.4807,
"step": 7170
},
{
"epoch": 0.99,
"learning_rate": 0.0004,
"loss": 0.5052,
"step": 7180
},
{
"epoch": 0.99,
"learning_rate": 0.0004,
"loss": 0.5187,
"step": 7190
},
{
"epoch": 0.99,
"learning_rate": 0.0004,
"loss": 0.5243,
"step": 7200
},
{
"epoch": 0.99,
"learning_rate": 0.0004,
"loss": 0.5058,
"step": 7210
},
{
"epoch": 0.99,
"learning_rate": 0.0004,
"loss": 0.4977,
"step": 7220
},
{
"epoch": 0.99,
"learning_rate": 0.0004,
"loss": 0.5155,
"step": 7230
},
{
"epoch": 1.0,
"learning_rate": 0.0004,
"loss": 0.5198,
"step": 7240
},
{
"epoch": 1.0,
"learning_rate": 0.0004,
"loss": 0.5313,
"step": 7250
},
{
"epoch": 1.0,
"learning_rate": 0.0004,
"loss": 0.5083,
"step": 7260
},
{
"epoch": 1.0,
"learning_rate": 0.0004,
"loss": 0.5122,
"step": 7270
},
{
"epoch": 1.0,
"learning_rate": 0.0004,
"loss": 0.5152,
"step": 7280
},
{
"epoch": 1.0,
"learning_rate": 0.0004,
"loss": 0.522,
"step": 7290
},
{
"epoch": 1.0,
"learning_rate": 0.0004,
"loss": 0.5113,
"step": 7300
},
{
"epoch": 1.01,
"learning_rate": 0.0004,
"loss": 0.5033,
"step": 7310
},
{
"epoch": 1.01,
"learning_rate": 0.0004,
"loss": 0.5097,
"step": 7320
},
{
"epoch": 1.01,
"learning_rate": 0.0004,
"loss": 0.5233,
"step": 7330
},
{
"epoch": 1.01,
"learning_rate": 0.0004,
"loss": 0.5039,
"step": 7340
},
{
"epoch": 1.01,
"learning_rate": 0.0004,
"loss": 0.5091,
"step": 7350
},
{
"epoch": 1.01,
"learning_rate": 0.0004,
"loss": 0.5215,
"step": 7360
},
{
"epoch": 1.01,
"learning_rate": 0.0004,
"loss": 0.4979,
"step": 7370
},
{
"epoch": 1.02,
"learning_rate": 0.0004,
"loss": 0.4949,
"step": 7380
},
{
"epoch": 1.02,
"learning_rate": 0.0004,
"loss": 0.5163,
"step": 7390
},
{
"epoch": 1.02,
"learning_rate": 0.0004,
"loss": 0.5033,
"step": 7400
},
{
"epoch": 1.02,
"learning_rate": 0.0004,
"loss": 0.5141,
"step": 7410
},
{
"epoch": 1.02,
"learning_rate": 0.0004,
"loss": 0.4948,
"step": 7420
},
{
"epoch": 1.02,
"learning_rate": 0.0004,
"loss": 0.4724,
"step": 7430
},
{
"epoch": 1.02,
"learning_rate": 0.0004,
"loss": 0.4959,
"step": 7440
},
{
"epoch": 1.02,
"learning_rate": 0.0004,
"loss": 0.4982,
"step": 7450
},
{
"epoch": 1.03,
"learning_rate": 0.0004,
"loss": 0.5074,
"step": 7460
},
{
"epoch": 1.03,
"learning_rate": 0.0004,
"loss": 0.5181,
"step": 7470
},
{
"epoch": 1.03,
"learning_rate": 0.0004,
"loss": 0.479,
"step": 7480
},
{
"epoch": 1.03,
"learning_rate": 0.0004,
"loss": 0.51,
"step": 7490
},
{
"epoch": 1.03,
"learning_rate": 0.0004,
"loss": 0.4975,
"step": 7500
},
{
"epoch": 1.03,
"learning_rate": 0.0004,
"loss": 0.5088,
"step": 7510
},
{
"epoch": 1.03,
"learning_rate": 0.0004,
"loss": 0.5214,
"step": 7520
},
{
"epoch": 1.04,
"learning_rate": 0.0004,
"loss": 0.5131,
"step": 7530
},
{
"epoch": 1.04,
"learning_rate": 0.0004,
"loss": 0.483,
"step": 7540
},
{
"epoch": 1.04,
"learning_rate": 0.0004,
"loss": 0.5104,
"step": 7550
},
{
"epoch": 1.04,
"learning_rate": 0.0004,
"loss": 0.4812,
"step": 7560
},
{
"epoch": 1.04,
"learning_rate": 0.0004,
"loss": 0.5016,
"step": 7570
},
{
"epoch": 1.04,
"learning_rate": 0.0004,
"loss": 0.4848,
"step": 7580
},
{
"epoch": 1.04,
"learning_rate": 0.0004,
"loss": 0.5095,
"step": 7590
},
{
"epoch": 1.05,
"learning_rate": 0.0004,
"loss": 0.5105,
"step": 7600
},
{
"epoch": 1.05,
"learning_rate": 0.0004,
"loss": 0.503,
"step": 7610
},
{
"epoch": 1.05,
"learning_rate": 0.0004,
"loss": 0.4859,
"step": 7620
},
{
"epoch": 1.05,
"learning_rate": 0.0004,
"loss": 0.5161,
"step": 7630
},
{
"epoch": 1.05,
"learning_rate": 0.0004,
"loss": 0.5081,
"step": 7640
},
{
"epoch": 1.05,
"learning_rate": 0.0004,
"loss": 0.5174,
"step": 7650
},
{
"epoch": 1.05,
"learning_rate": 0.0004,
"loss": 0.5133,
"step": 7660
},
{
"epoch": 1.06,
"learning_rate": 0.0004,
"loss": 0.5143,
"step": 7670
},
{
"epoch": 1.06,
"learning_rate": 0.0004,
"loss": 0.4895,
"step": 7680
},
{
"epoch": 1.06,
"learning_rate": 0.0004,
"loss": 0.5093,
"step": 7690
},
{
"epoch": 1.06,
"learning_rate": 0.0004,
"loss": 0.5011,
"step": 7700
},
{
"epoch": 1.06,
"learning_rate": 0.0004,
"loss": 0.4987,
"step": 7710
},
{
"epoch": 1.06,
"learning_rate": 0.0004,
"loss": 0.5093,
"step": 7720
},
{
"epoch": 1.06,
"learning_rate": 0.0004,
"loss": 0.4935,
"step": 7730
},
{
"epoch": 1.06,
"learning_rate": 0.0004,
"loss": 0.5175,
"step": 7740
},
{
"epoch": 1.07,
"learning_rate": 0.0004,
"loss": 0.5026,
"step": 7750
},
{
"epoch": 1.07,
"learning_rate": 0.0004,
"loss": 0.4963,
"step": 7760
},
{
"epoch": 1.07,
"learning_rate": 0.0004,
"loss": 0.4784,
"step": 7770
},
{
"epoch": 1.07,
"learning_rate": 0.0004,
"loss": 0.488,
"step": 7780
},
{
"epoch": 1.07,
"learning_rate": 0.0004,
"loss": 0.4973,
"step": 7790
},
{
"epoch": 1.07,
"learning_rate": 0.0004,
"loss": 0.4876,
"step": 7800
},
{
"epoch": 1.07,
"learning_rate": 0.0004,
"loss": 0.5124,
"step": 7810
},
{
"epoch": 1.08,
"learning_rate": 0.0004,
"loss": 0.5014,
"step": 7820
},
{
"epoch": 1.08,
"learning_rate": 0.0004,
"loss": 0.4924,
"step": 7830
},
{
"epoch": 1.08,
"learning_rate": 0.0004,
"loss": 0.5041,
"step": 7840
},
{
"epoch": 1.08,
"learning_rate": 0.0004,
"loss": 0.5101,
"step": 7850
},
{
"epoch": 1.08,
"learning_rate": 0.0004,
"loss": 0.5236,
"step": 7860
},
{
"epoch": 1.08,
"learning_rate": 0.0004,
"loss": 0.5086,
"step": 7870
},
{
"epoch": 1.08,
"learning_rate": 0.0004,
"loss": 0.5032,
"step": 7880
},
{
"epoch": 1.09,
"learning_rate": 0.0004,
"loss": 0.5093,
"step": 7890
},
{
"epoch": 1.09,
"learning_rate": 0.0004,
"loss": 0.5155,
"step": 7900
},
{
"epoch": 1.09,
"learning_rate": 0.0004,
"loss": 0.5072,
"step": 7910
},
{
"epoch": 1.09,
"learning_rate": 0.0004,
"loss": 0.5199,
"step": 7920
},
{
"epoch": 1.09,
"learning_rate": 0.0004,
"loss": 0.4829,
"step": 7930
},
{
"epoch": 1.09,
"learning_rate": 0.0004,
"loss": 0.5146,
"step": 7940
},
{
"epoch": 1.09,
"learning_rate": 0.0004,
"loss": 0.504,
"step": 7950
},
{
"epoch": 1.1,
"learning_rate": 0.0004,
"loss": 0.5176,
"step": 7960
},
{
"epoch": 1.1,
"learning_rate": 0.0004,
"loss": 0.4947,
"step": 7970
},
{
"epoch": 1.1,
"learning_rate": 0.0004,
"loss": 0.5089,
"step": 7980
},
{
"epoch": 1.1,
"learning_rate": 0.0004,
"loss": 0.5092,
"step": 7990
},
{
"epoch": 1.1,
"learning_rate": 0.0004,
"loss": 0.4978,
"step": 8000
}
],
"logging_steps": 10,
"max_steps": 8000,
"num_train_epochs": 2,
"save_steps": 500,
"total_flos": 2.79870537990144e+18,
"trial_name": null,
"trial_params": null
}