f9749f03ca / checkpoint-2100 /trainer_state.json
philschmid's picture
philschmid HF staff
Training in progress, step 2100
73f4306
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.7,
"global_step": 2100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0003,
"loss": 9.4994,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 7.7223,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 7.3713,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 7.2695,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 7.2811,
"step": 50
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 7.2291,
"step": 60
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 7.1263,
"step": 70
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 7.0881,
"step": 80
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 6.5989,
"step": 90
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 6.0091,
"step": 100
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 5.5511,
"step": 110
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 5.3413,
"step": 120
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 5.1775,
"step": 130
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 5.104,
"step": 140
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 5.0133,
"step": 150
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 4.9843,
"step": 160
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 4.9256,
"step": 170
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 4.8692,
"step": 180
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 4.9233,
"step": 190
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 4.9139,
"step": 200
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 4.8974,
"step": 210
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 4.9036,
"step": 220
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 4.8635,
"step": 230
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 4.7883,
"step": 240
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 4.7681,
"step": 250
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 4.7572,
"step": 260
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 4.7552,
"step": 270
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 4.706,
"step": 280
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 4.7015,
"step": 290
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 4.695,
"step": 300
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 4.6808,
"step": 310
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 4.6423,
"step": 320
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 4.613,
"step": 330
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 4.5851,
"step": 340
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 4.5882,
"step": 350
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 4.6228,
"step": 360
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 4.6269,
"step": 370
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 4.5364,
"step": 380
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 4.4992,
"step": 390
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 4.4799,
"step": 400
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 4.3733,
"step": 410
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 4.1788,
"step": 420
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 3.6706,
"step": 430
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 2.8767,
"step": 440
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 2.3927,
"step": 450
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 2.3062,
"step": 460
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 2.2299,
"step": 470
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 2.1739,
"step": 480
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 2.1303,
"step": 490
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 2.1092,
"step": 500
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 2.0715,
"step": 510
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 2.0473,
"step": 520
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 2.0566,
"step": 530
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 1.9818,
"step": 540
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 1.9592,
"step": 550
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 1.8939,
"step": 560
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 1.8441,
"step": 570
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 1.808,
"step": 580
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 1.765,
"step": 590
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 1.706,
"step": 600
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 1.6328,
"step": 610
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 1.6197,
"step": 620
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 1.6106,
"step": 630
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 1.5649,
"step": 640
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 1.5001,
"step": 650
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 1.4926,
"step": 660
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 1.4682,
"step": 670
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 1.442,
"step": 680
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 1.4117,
"step": 690
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 1.379,
"step": 700
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 1.3609,
"step": 710
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 1.3224,
"step": 720
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 1.2853,
"step": 730
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 1.2762,
"step": 740
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 1.2265,
"step": 750
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 1.2232,
"step": 760
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 1.2075,
"step": 770
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 1.168,
"step": 780
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 1.1472,
"step": 790
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 1.118,
"step": 800
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 1.1228,
"step": 810
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 1.1339,
"step": 820
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 1.0853,
"step": 830
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 1.0676,
"step": 840
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 1.0905,
"step": 850
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 1.076,
"step": 860
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 1.0202,
"step": 870
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 1.0123,
"step": 880
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 0.9863,
"step": 890
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 0.9347,
"step": 900
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 0.9416,
"step": 910
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 0.9165,
"step": 920
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 0.8996,
"step": 930
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 0.8673,
"step": 940
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 0.8449,
"step": 950
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 0.8468,
"step": 960
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 0.817,
"step": 970
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 0.7947,
"step": 980
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 0.7706,
"step": 990
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 0.7357,
"step": 1000
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 0.6983,
"step": 1010
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 0.6989,
"step": 1020
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 0.6692,
"step": 1030
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.6553,
"step": 1040
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.6272,
"step": 1050
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.6092,
"step": 1060
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 0.604,
"step": 1070
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 0.6494,
"step": 1080
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 0.6155,
"step": 1090
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 0.5713,
"step": 1100
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 0.5358,
"step": 1110
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 0.5005,
"step": 1120
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 0.483,
"step": 1130
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 0.4736,
"step": 1140
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 0.4585,
"step": 1150
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.4442,
"step": 1160
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.4392,
"step": 1170
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.4084,
"step": 1180
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 0.4104,
"step": 1190
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 0.3855,
"step": 1200
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 0.3662,
"step": 1210
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.3727,
"step": 1220
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.3563,
"step": 1230
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.3297,
"step": 1240
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.314,
"step": 1250
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.2996,
"step": 1260
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.3,
"step": 1270
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.2773,
"step": 1280
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.2665,
"step": 1290
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.2646,
"step": 1300
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.2406,
"step": 1310
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.2206,
"step": 1320
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.2325,
"step": 1330
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.2152,
"step": 1340
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.2011,
"step": 1350
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.1953,
"step": 1360
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.1862,
"step": 1370
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.1814,
"step": 1380
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.1677,
"step": 1390
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.1657,
"step": 1400
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.155,
"step": 1410
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.1517,
"step": 1420
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.1481,
"step": 1430
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.1396,
"step": 1440
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.1301,
"step": 1450
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.1274,
"step": 1460
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.1244,
"step": 1470
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.1172,
"step": 1480
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.1177,
"step": 1490
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.1118,
"step": 1500
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.113,
"step": 1510
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.3687,
"step": 1520
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.1801,
"step": 1530
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.1534,
"step": 1540
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.1248,
"step": 1550
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.1091,
"step": 1560
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.0965,
"step": 1570
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 0.098,
"step": 1580
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 0.097,
"step": 1590
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 0.0885,
"step": 1600
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.0795,
"step": 1610
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.0843,
"step": 1620
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.0734,
"step": 1630
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 0.0744,
"step": 1640
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 0.0794,
"step": 1650
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 0.0708,
"step": 1660
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.1133,
"step": 1670
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.1582,
"step": 1680
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.1106,
"step": 1690
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.0904,
"step": 1700
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.0785,
"step": 1710
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.0747,
"step": 1720
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.0704,
"step": 1730
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.0634,
"step": 1740
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.0629,
"step": 1750
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 0.057,
"step": 1760
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 0.0563,
"step": 1770
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 0.054,
"step": 1780
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.0532,
"step": 1790
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.0525,
"step": 1800
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.0519,
"step": 1810
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.0478,
"step": 1820
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.0473,
"step": 1830
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.0473,
"step": 1840
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.0492,
"step": 1850
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.0451,
"step": 1860
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.0453,
"step": 1870
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.0439,
"step": 1880
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.0435,
"step": 1890
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.0435,
"step": 1900
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.0412,
"step": 1910
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.0441,
"step": 1920
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.04,
"step": 1930
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.041,
"step": 1940
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.1391,
"step": 1950
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.1502,
"step": 1960
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.0767,
"step": 1970
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.0563,
"step": 1980
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.0487,
"step": 1990
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.042,
"step": 2000
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.0388,
"step": 2010
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.0424,
"step": 2020
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.0413,
"step": 2030
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.036,
"step": 2040
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.0333,
"step": 2050
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.0334,
"step": 2060
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.0298,
"step": 2070
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.0302,
"step": 2080
},
{
"epoch": 0.7,
"learning_rate": 0.0003,
"loss": 0.0302,
"step": 2090
},
{
"epoch": 0.7,
"learning_rate": 0.0003,
"loss": 0.0293,
"step": 2100
}
],
"max_steps": 3000,
"num_train_epochs": 9223372036854775807,
"total_flos": 879394553856000.0,
"trial_name": null,
"trial_params": null
}