Text Generation
Transformers
PyTorch
English
llama
finance
llms
text-generation-inference
finma-7b-nlp / trainer_state.json
jiminHuang's picture
Upload folder using huggingface_hub
429f23d
raw
history blame
44.5 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.8001484046500122,
"global_step": 3639,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2.253431117230021e-06,
"loss": 3.9812,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 3.7916371566987085e-06,
"loss": 0.5473,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 4.506862234460042e-06,
"loss": 0.3243,
"step": 30
},
{
"epoch": 0.02,
"learning_rate": 4.977968949561282e-06,
"loss": 0.3058,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 5.3298431961673955e-06,
"loss": 0.2495,
"step": 50
},
{
"epoch": 0.03,
"learning_rate": 5.610809355829126e-06,
"loss": 0.3345,
"step": 60
},
{
"epoch": 0.03,
"learning_rate": 5.844707706136422e-06,
"loss": 0.2784,
"step": 70
},
{
"epoch": 0.04,
"learning_rate": 6.04506827392873e-06,
"loss": 0.2421,
"step": 80
},
{
"epoch": 0.04,
"learning_rate": 6.220313630636092e-06,
"loss": 0.2661,
"step": 90
},
{
"epoch": 0.05,
"learning_rate": 6.376044588167711e-06,
"loss": 0.2831,
"step": 100
},
{
"epoch": 0.05,
"learning_rate": 6.516174989029968e-06,
"loss": 0.2793,
"step": 110
},
{
"epoch": 0.06,
"learning_rate": 6.643547802988659e-06,
"loss": 0.2488,
"step": 120
},
{
"epoch": 0.06,
"learning_rate": 6.7602933516900655e-06,
"loss": 0.2379,
"step": 130
},
{
"epoch": 0.07,
"learning_rate": 6.868049235636083e-06,
"loss": 0.2388,
"step": 140
},
{
"epoch": 0.07,
"learning_rate": 6.968101466168447e-06,
"loss": 0.2273,
"step": 150
},
{
"epoch": 0.08,
"learning_rate": 7.061478425531149e-06,
"loss": 0.2571,
"step": 160
},
{
"epoch": 0.08,
"learning_rate": 7.149015395297812e-06,
"loss": 0.2466,
"step": 170
},
{
"epoch": 0.09,
"learning_rate": 7.231400066791303e-06,
"loss": 0.2315,
"step": 180
},
{
"epoch": 0.09,
"learning_rate": 7.309205386775784e-06,
"loss": 0.2101,
"step": 190
},
{
"epoch": 0.1,
"learning_rate": 7.375715089769526e-06,
"loss": 0.2425,
"step": 200
},
{
"epoch": 0.1,
"learning_rate": 7.44608846772297e-06,
"loss": 0.243,
"step": 210
},
{
"epoch": 0.11,
"learning_rate": 7.513093380702437e-06,
"loss": 0.2521,
"step": 220
},
{
"epoch": 0.11,
"learning_rate": 7.57703761945179e-06,
"loss": 0.2401,
"step": 230
},
{
"epoch": 0.12,
"learning_rate": 7.638188625267883e-06,
"loss": 0.2342,
"step": 240
},
{
"epoch": 0.12,
"learning_rate": 7.696780248446552e-06,
"loss": 0.2439,
"step": 250
},
{
"epoch": 0.13,
"learning_rate": 7.753018148386997e-06,
"loss": 0.2553,
"step": 260
},
{
"epoch": 0.13,
"learning_rate": 7.80708415034011e-06,
"loss": 0.2547,
"step": 270
},
{
"epoch": 0.14,
"learning_rate": 7.859139791732239e-06,
"loss": 0.2316,
"step": 280
},
{
"epoch": 0.14,
"learning_rate": 7.909329232496527e-06,
"loss": 0.2227,
"step": 290
},
{
"epoch": 0.15,
"learning_rate": 7.957781661555314e-06,
"loss": 0.21,
"step": 300
},
{
"epoch": 0.15,
"learning_rate": 8e-06,
"loss": 0.2145,
"step": 310
},
{
"epoch": 0.16,
"learning_rate": 7.98611111111111e-06,
"loss": 0.2101,
"step": 320
},
{
"epoch": 0.16,
"learning_rate": 7.972222222222223e-06,
"loss": 0.1999,
"step": 330
},
{
"epoch": 0.17,
"learning_rate": 7.958333333333333e-06,
"loss": 0.2254,
"step": 340
},
{
"epoch": 0.17,
"learning_rate": 7.944444444444444e-06,
"loss": 0.2597,
"step": 350
},
{
"epoch": 0.18,
"learning_rate": 7.930555555555554e-06,
"loss": 0.1814,
"step": 360
},
{
"epoch": 0.18,
"learning_rate": 7.916666666666667e-06,
"loss": 0.2173,
"step": 370
},
{
"epoch": 0.19,
"learning_rate": 7.902777777777777e-06,
"loss": 0.2136,
"step": 380
},
{
"epoch": 0.19,
"learning_rate": 7.88888888888889e-06,
"loss": 0.2015,
"step": 390
},
{
"epoch": 0.2,
"learning_rate": 7.875e-06,
"loss": 0.2059,
"step": 400
},
{
"epoch": 0.2,
"learning_rate": 7.86111111111111e-06,
"loss": 0.23,
"step": 410
},
{
"epoch": 0.21,
"learning_rate": 7.847222222222221e-06,
"loss": 0.166,
"step": 420
},
{
"epoch": 0.21,
"learning_rate": 7.833333333333333e-06,
"loss": 0.2403,
"step": 430
},
{
"epoch": 0.22,
"learning_rate": 7.819444444444444e-06,
"loss": 0.2111,
"step": 440
},
{
"epoch": 0.22,
"learning_rate": 7.805555555555555e-06,
"loss": 0.2309,
"step": 450
},
{
"epoch": 0.23,
"learning_rate": 7.791666666666667e-06,
"loss": 0.2117,
"step": 460
},
{
"epoch": 0.23,
"learning_rate": 7.777777777777777e-06,
"loss": 0.2085,
"step": 470
},
{
"epoch": 0.24,
"learning_rate": 7.76388888888889e-06,
"loss": 0.1904,
"step": 480
},
{
"epoch": 0.24,
"learning_rate": 7.75e-06,
"loss": 0.1954,
"step": 490
},
{
"epoch": 0.25,
"learning_rate": 7.736111111111111e-06,
"loss": 0.2056,
"step": 500
},
{
"epoch": 0.25,
"learning_rate": 7.722222222222222e-06,
"loss": 0.169,
"step": 510
},
{
"epoch": 0.26,
"learning_rate": 7.708333333333332e-06,
"loss": 0.1814,
"step": 520
},
{
"epoch": 0.26,
"learning_rate": 7.694444444444444e-06,
"loss": 0.21,
"step": 530
},
{
"epoch": 0.27,
"learning_rate": 7.680555555555555e-06,
"loss": 0.2285,
"step": 540
},
{
"epoch": 0.27,
"learning_rate": 7.666666666666667e-06,
"loss": 0.2074,
"step": 550
},
{
"epoch": 0.28,
"learning_rate": 7.652777777777778e-06,
"loss": 0.173,
"step": 560
},
{
"epoch": 0.28,
"learning_rate": 7.638888888888888e-06,
"loss": 0.187,
"step": 570
},
{
"epoch": 0.29,
"learning_rate": 7.625e-06,
"loss": 0.2002,
"step": 580
},
{
"epoch": 0.29,
"learning_rate": 7.6111111111111104e-06,
"loss": 0.2257,
"step": 590
},
{
"epoch": 0.3,
"learning_rate": 7.597222222222222e-06,
"loss": 0.2068,
"step": 600
},
{
"epoch": 0.3,
"learning_rate": 7.5833333333333324e-06,
"loss": 0.1968,
"step": 610
},
{
"epoch": 0.31,
"learning_rate": 7.569444444444445e-06,
"loss": 0.2122,
"step": 620
},
{
"epoch": 0.31,
"learning_rate": 7.555555555555555e-06,
"loss": 0.2306,
"step": 630
},
{
"epoch": 0.32,
"learning_rate": 7.541666666666667e-06,
"loss": 0.2108,
"step": 640
},
{
"epoch": 0.32,
"learning_rate": 7.527777777777777e-06,
"loss": 0.1923,
"step": 650
},
{
"epoch": 0.33,
"learning_rate": 7.513888888888889e-06,
"loss": 0.1989,
"step": 660
},
{
"epoch": 0.33,
"learning_rate": 7.499999999999999e-06,
"loss": 0.2179,
"step": 670
},
{
"epoch": 0.34,
"learning_rate": 7.486111111111111e-06,
"loss": 0.1915,
"step": 680
},
{
"epoch": 0.34,
"learning_rate": 7.472222222222222e-06,
"loss": 0.1965,
"step": 690
},
{
"epoch": 0.35,
"learning_rate": 7.458333333333333e-06,
"loss": 0.2425,
"step": 700
},
{
"epoch": 0.35,
"learning_rate": 7.444444444444444e-06,
"loss": 0.1933,
"step": 710
},
{
"epoch": 0.36,
"learning_rate": 7.430555555555555e-06,
"loss": 0.2314,
"step": 720
},
{
"epoch": 0.36,
"learning_rate": 7.416666666666666e-06,
"loss": 0.1901,
"step": 730
},
{
"epoch": 0.37,
"learning_rate": 7.402777777777778e-06,
"loss": 0.1852,
"step": 740
},
{
"epoch": 0.37,
"learning_rate": 7.388888888888889e-06,
"loss": 0.201,
"step": 750
},
{
"epoch": 0.38,
"learning_rate": 7.375e-06,
"loss": 0.1636,
"step": 760
},
{
"epoch": 0.38,
"learning_rate": 7.36111111111111e-06,
"loss": 0.184,
"step": 770
},
{
"epoch": 0.39,
"learning_rate": 7.347222222222222e-06,
"loss": 0.1618,
"step": 780
},
{
"epoch": 0.39,
"learning_rate": 7.333333333333332e-06,
"loss": 0.1867,
"step": 790
},
{
"epoch": 0.4,
"learning_rate": 7.3194444444444446e-06,
"loss": 0.1877,
"step": 800
},
{
"epoch": 0.4,
"learning_rate": 7.305555555555555e-06,
"loss": 0.1569,
"step": 810
},
{
"epoch": 0.41,
"learning_rate": 7.291666666666667e-06,
"loss": 0.1651,
"step": 820
},
{
"epoch": 0.41,
"learning_rate": 7.277777777777777e-06,
"loss": 0.215,
"step": 830
},
{
"epoch": 0.42,
"learning_rate": 7.263888888888889e-06,
"loss": 0.1609,
"step": 840
},
{
"epoch": 0.42,
"learning_rate": 7.25e-06,
"loss": 0.1935,
"step": 850
},
{
"epoch": 0.43,
"learning_rate": 7.236111111111111e-06,
"loss": 0.1688,
"step": 860
},
{
"epoch": 0.43,
"learning_rate": 7.222222222222222e-06,
"loss": 0.1645,
"step": 870
},
{
"epoch": 0.44,
"learning_rate": 7.208333333333333e-06,
"loss": 0.162,
"step": 880
},
{
"epoch": 0.44,
"learning_rate": 7.194444444444444e-06,
"loss": 0.1467,
"step": 890
},
{
"epoch": 0.45,
"learning_rate": 7.180555555555555e-06,
"loss": 0.1579,
"step": 900
},
{
"epoch": 0.45,
"learning_rate": 7.166666666666667e-06,
"loss": 0.1774,
"step": 910
},
{
"epoch": 0.46,
"learning_rate": 7.1527777777777775e-06,
"loss": 0.1931,
"step": 920
},
{
"epoch": 0.46,
"learning_rate": 7.138888888888889e-06,
"loss": 0.1505,
"step": 930
},
{
"epoch": 0.47,
"learning_rate": 7.1249999999999995e-06,
"loss": 0.1632,
"step": 940
},
{
"epoch": 0.47,
"learning_rate": 7.11111111111111e-06,
"loss": 0.169,
"step": 950
},
{
"epoch": 0.47,
"learning_rate": 7.097222222222222e-06,
"loss": 0.1762,
"step": 960
},
{
"epoch": 0.48,
"learning_rate": 7.083333333333333e-06,
"loss": 0.1838,
"step": 970
},
{
"epoch": 0.48,
"learning_rate": 7.0694444444444444e-06,
"loss": 0.1622,
"step": 980
},
{
"epoch": 0.49,
"learning_rate": 7.055555555555555e-06,
"loss": 0.1562,
"step": 990
},
{
"epoch": 0.49,
"learning_rate": 7.0416666666666664e-06,
"loss": 0.1475,
"step": 1000
},
{
"epoch": 0.5,
"learning_rate": 7.027777777777777e-06,
"loss": 0.1557,
"step": 1010
},
{
"epoch": 0.5,
"learning_rate": 7.013888888888889e-06,
"loss": 0.1851,
"step": 1020
},
{
"epoch": 0.51,
"learning_rate": 7e-06,
"loss": 0.1607,
"step": 1030
},
{
"epoch": 0.51,
"learning_rate": 6.9861111111111105e-06,
"loss": 0.1541,
"step": 1040
},
{
"epoch": 0.52,
"learning_rate": 6.972222222222222e-06,
"loss": 0.1509,
"step": 1050
},
{
"epoch": 0.52,
"learning_rate": 6.9583333333333325e-06,
"loss": 0.1754,
"step": 1060
},
{
"epoch": 0.53,
"learning_rate": 6.944444444444444e-06,
"loss": 0.205,
"step": 1070
},
{
"epoch": 0.53,
"learning_rate": 6.930555555555555e-06,
"loss": 0.2037,
"step": 1080
},
{
"epoch": 0.54,
"learning_rate": 6.916666666666667e-06,
"loss": 0.1424,
"step": 1090
},
{
"epoch": 0.54,
"learning_rate": 6.902777777777777e-06,
"loss": 0.1594,
"step": 1100
},
{
"epoch": 0.55,
"learning_rate": 6.888888888888889e-06,
"loss": 0.1838,
"step": 1110
},
{
"epoch": 0.55,
"learning_rate": 6.874999999999999e-06,
"loss": 0.1626,
"step": 1120
},
{
"epoch": 0.56,
"learning_rate": 6.86111111111111e-06,
"loss": 0.1689,
"step": 1130
},
{
"epoch": 0.56,
"learning_rate": 6.847222222222222e-06,
"loss": 0.1548,
"step": 1140
},
{
"epoch": 0.57,
"learning_rate": 6.833333333333333e-06,
"loss": 0.1435,
"step": 1150
},
{
"epoch": 0.57,
"learning_rate": 6.819444444444444e-06,
"loss": 0.1939,
"step": 1160
},
{
"epoch": 0.58,
"learning_rate": 6.805555555555555e-06,
"loss": 0.1802,
"step": 1170
},
{
"epoch": 0.58,
"learning_rate": 6.791666666666666e-06,
"loss": 0.1865,
"step": 1180
},
{
"epoch": 0.59,
"learning_rate": 6.777777777777778e-06,
"loss": 0.18,
"step": 1190
},
{
"epoch": 0.59,
"learning_rate": 6.763888888888889e-06,
"loss": 0.1862,
"step": 1200
},
{
"epoch": 0.6,
"learning_rate": 6.75e-06,
"loss": 0.183,
"step": 1210
},
{
"epoch": 0.6,
"eval_loss": 0.234619140625,
"eval_runtime": 601.4014,
"eval_samples_per_second": 39.832,
"eval_steps_per_second": 4.98,
"step": 1213
},
{
"epoch": 0.6,
"learning_rate": 6.73611111111111e-06,
"loss": 0.1954,
"step": 1220
},
{
"epoch": 0.61,
"learning_rate": 6.722222222222222e-06,
"loss": 0.1433,
"step": 1230
},
{
"epoch": 0.61,
"learning_rate": 6.708333333333332e-06,
"loss": 0.1732,
"step": 1240
},
{
"epoch": 0.62,
"learning_rate": 6.694444444444445e-06,
"loss": 0.1985,
"step": 1250
},
{
"epoch": 0.62,
"learning_rate": 6.680555555555555e-06,
"loss": 0.1786,
"step": 1260
},
{
"epoch": 0.63,
"learning_rate": 6.666666666666667e-06,
"loss": 0.167,
"step": 1270
},
{
"epoch": 0.63,
"learning_rate": 6.652777777777777e-06,
"loss": 0.1548,
"step": 1280
},
{
"epoch": 0.64,
"learning_rate": 6.638888888888889e-06,
"loss": 0.1559,
"step": 1290
},
{
"epoch": 0.64,
"learning_rate": 6.625e-06,
"loss": 0.176,
"step": 1300
},
{
"epoch": 0.65,
"learning_rate": 6.611111111111111e-06,
"loss": 0.1687,
"step": 1310
},
{
"epoch": 0.65,
"learning_rate": 6.597222222222222e-06,
"loss": 0.1497,
"step": 1320
},
{
"epoch": 0.66,
"learning_rate": 6.583333333333333e-06,
"loss": 0.1891,
"step": 1330
},
{
"epoch": 0.66,
"learning_rate": 6.569444444444444e-06,
"loss": 0.1783,
"step": 1340
},
{
"epoch": 0.67,
"learning_rate": 6.555555555555555e-06,
"loss": 0.168,
"step": 1350
},
{
"epoch": 0.67,
"learning_rate": 6.541666666666667e-06,
"loss": 0.1871,
"step": 1360
},
{
"epoch": 0.68,
"learning_rate": 6.527777777777778e-06,
"loss": 0.1601,
"step": 1370
},
{
"epoch": 0.68,
"learning_rate": 6.513888888888889e-06,
"loss": 0.1466,
"step": 1380
},
{
"epoch": 0.69,
"learning_rate": 6.5e-06,
"loss": 0.1799,
"step": 1390
},
{
"epoch": 0.69,
"learning_rate": 6.48611111111111e-06,
"loss": 0.1448,
"step": 1400
},
{
"epoch": 0.7,
"learning_rate": 6.472222222222222e-06,
"loss": 0.1459,
"step": 1410
},
{
"epoch": 0.7,
"learning_rate": 6.458333333333333e-06,
"loss": 0.1677,
"step": 1420
},
{
"epoch": 0.71,
"learning_rate": 6.4444444444444445e-06,
"loss": 0.1878,
"step": 1430
},
{
"epoch": 0.71,
"learning_rate": 6.430555555555555e-06,
"loss": 0.1494,
"step": 1440
},
{
"epoch": 0.72,
"learning_rate": 6.4166666666666665e-06,
"loss": 0.1406,
"step": 1450
},
{
"epoch": 0.72,
"learning_rate": 6.402777777777777e-06,
"loss": 0.1538,
"step": 1460
},
{
"epoch": 0.73,
"learning_rate": 6.390277777777778e-06,
"loss": 0.169,
"step": 1470
},
{
"epoch": 0.73,
"learning_rate": 6.376388888888889e-06,
"loss": 0.1444,
"step": 1480
},
{
"epoch": 0.74,
"learning_rate": 6.3625e-06,
"loss": 0.1561,
"step": 1490
},
{
"epoch": 0.74,
"learning_rate": 6.348611111111111e-06,
"loss": 0.1493,
"step": 1500
},
{
"epoch": 0.75,
"learning_rate": 6.334722222222222e-06,
"loss": 0.1547,
"step": 1510
},
{
"epoch": 0.75,
"learning_rate": 6.320833333333333e-06,
"loss": 0.1749,
"step": 1520
},
{
"epoch": 0.76,
"learning_rate": 6.3069444444444445e-06,
"loss": 0.1903,
"step": 1530
},
{
"epoch": 0.76,
"learning_rate": 6.293055555555555e-06,
"loss": 0.18,
"step": 1540
},
{
"epoch": 0.77,
"learning_rate": 6.2791666666666665e-06,
"loss": 0.1491,
"step": 1550
},
{
"epoch": 0.77,
"learning_rate": 6.265277777777777e-06,
"loss": 0.1777,
"step": 1560
},
{
"epoch": 0.78,
"learning_rate": 6.2513888888888886e-06,
"loss": 0.1226,
"step": 1570
},
{
"epoch": 0.78,
"learning_rate": 6.237499999999999e-06,
"loss": 0.1822,
"step": 1580
},
{
"epoch": 0.79,
"learning_rate": 6.2236111111111114e-06,
"loss": 0.143,
"step": 1590
},
{
"epoch": 0.79,
"learning_rate": 6.209722222222222e-06,
"loss": 0.1411,
"step": 1600
},
{
"epoch": 0.8,
"learning_rate": 6.1958333333333334e-06,
"loss": 0.1452,
"step": 1610
},
{
"epoch": 0.8,
"learning_rate": 6.181944444444444e-06,
"loss": 0.1673,
"step": 1620
},
{
"epoch": 0.81,
"learning_rate": 6.169444444444444e-06,
"loss": 0.1706,
"step": 1630
},
{
"epoch": 0.81,
"learning_rate": 6.155555555555556e-06,
"loss": 0.1755,
"step": 1640
},
{
"epoch": 0.82,
"learning_rate": 6.141666666666667e-06,
"loss": 0.1831,
"step": 1650
},
{
"epoch": 0.82,
"learning_rate": 6.127777777777778e-06,
"loss": 0.1402,
"step": 1660
},
{
"epoch": 0.83,
"learning_rate": 6.113888888888889e-06,
"loss": 0.1434,
"step": 1670
},
{
"epoch": 0.83,
"learning_rate": 6.099999999999999e-06,
"loss": 0.1347,
"step": 1680
},
{
"epoch": 0.84,
"learning_rate": 6.086111111111111e-06,
"loss": 0.1614,
"step": 1690
},
{
"epoch": 0.84,
"learning_rate": 6.072222222222222e-06,
"loss": 0.1533,
"step": 1700
},
{
"epoch": 0.85,
"learning_rate": 6.0583333333333335e-06,
"loss": 0.1666,
"step": 1710
},
{
"epoch": 0.85,
"learning_rate": 6.044444444444444e-06,
"loss": 0.1725,
"step": 1720
},
{
"epoch": 0.86,
"learning_rate": 6.0305555555555555e-06,
"loss": 0.1819,
"step": 1730
},
{
"epoch": 0.86,
"learning_rate": 6.016666666666666e-06,
"loss": 0.1739,
"step": 1740
},
{
"epoch": 0.87,
"learning_rate": 6.0027777777777775e-06,
"loss": 0.1573,
"step": 1750
},
{
"epoch": 0.87,
"learning_rate": 5.988888888888889e-06,
"loss": 0.1458,
"step": 1760
},
{
"epoch": 0.88,
"learning_rate": 5.9749999999999995e-06,
"loss": 0.1243,
"step": 1770
},
{
"epoch": 0.88,
"learning_rate": 5.961111111111111e-06,
"loss": 0.1657,
"step": 1780
},
{
"epoch": 0.89,
"learning_rate": 5.9472222222222216e-06,
"loss": 0.1871,
"step": 1790
},
{
"epoch": 0.89,
"learning_rate": 5.933333333333333e-06,
"loss": 0.1365,
"step": 1800
},
{
"epoch": 0.9,
"learning_rate": 5.9194444444444444e-06,
"loss": 0.0987,
"step": 1810
},
{
"epoch": 0.9,
"learning_rate": 5.905555555555556e-06,
"loss": 0.1396,
"step": 1820
},
{
"epoch": 0.91,
"learning_rate": 5.8916666666666664e-06,
"loss": 0.1693,
"step": 1830
},
{
"epoch": 0.91,
"learning_rate": 5.877777777777778e-06,
"loss": 0.1391,
"step": 1840
},
{
"epoch": 0.92,
"learning_rate": 5.8638888888888885e-06,
"loss": 0.1439,
"step": 1850
},
{
"epoch": 0.92,
"learning_rate": 5.849999999999999e-06,
"loss": 0.1503,
"step": 1860
},
{
"epoch": 0.93,
"learning_rate": 5.836111111111111e-06,
"loss": 0.1359,
"step": 1870
},
{
"epoch": 0.93,
"learning_rate": 5.822222222222222e-06,
"loss": 0.1423,
"step": 1880
},
{
"epoch": 0.93,
"learning_rate": 5.808333333333333e-06,
"loss": 0.1317,
"step": 1890
},
{
"epoch": 0.94,
"learning_rate": 5.794444444444444e-06,
"loss": 0.1431,
"step": 1900
},
{
"epoch": 0.94,
"learning_rate": 5.780555555555555e-06,
"loss": 0.1235,
"step": 1910
},
{
"epoch": 0.95,
"learning_rate": 5.766666666666666e-06,
"loss": 0.1397,
"step": 1920
},
{
"epoch": 0.95,
"learning_rate": 5.752777777777778e-06,
"loss": 0.1375,
"step": 1930
},
{
"epoch": 0.96,
"learning_rate": 5.738888888888889e-06,
"loss": 0.1341,
"step": 1940
},
{
"epoch": 0.96,
"learning_rate": 5.724999999999999e-06,
"loss": 0.1408,
"step": 1950
},
{
"epoch": 0.97,
"learning_rate": 5.711111111111111e-06,
"loss": 0.1766,
"step": 1960
},
{
"epoch": 0.97,
"learning_rate": 5.697222222222221e-06,
"loss": 0.177,
"step": 1970
},
{
"epoch": 0.98,
"learning_rate": 5.683333333333334e-06,
"loss": 0.1586,
"step": 1980
},
{
"epoch": 0.98,
"learning_rate": 5.669444444444444e-06,
"loss": 0.1447,
"step": 1990
},
{
"epoch": 0.99,
"learning_rate": 5.655555555555556e-06,
"loss": 0.1452,
"step": 2000
},
{
"epoch": 0.99,
"learning_rate": 5.641666666666666e-06,
"loss": 0.1078,
"step": 2010
},
{
"epoch": 1.0,
"learning_rate": 5.627777777777778e-06,
"loss": 0.1133,
"step": 2020
},
{
"epoch": 1.0,
"learning_rate": 5.613888888888888e-06,
"loss": 0.1288,
"step": 2030
},
{
"epoch": 1.01,
"learning_rate": 5.6e-06,
"loss": 0.1128,
"step": 2040
},
{
"epoch": 1.01,
"learning_rate": 5.586111111111111e-06,
"loss": 0.1298,
"step": 2050
},
{
"epoch": 1.02,
"learning_rate": 5.572222222222222e-06,
"loss": 0.1189,
"step": 2060
},
{
"epoch": 1.02,
"learning_rate": 5.558333333333333e-06,
"loss": 0.1478,
"step": 2070
},
{
"epoch": 1.03,
"learning_rate": 5.544444444444444e-06,
"loss": 0.1179,
"step": 2080
},
{
"epoch": 1.03,
"learning_rate": 5.530555555555556e-06,
"loss": 0.1119,
"step": 2090
},
{
"epoch": 1.04,
"learning_rate": 5.516666666666667e-06,
"loss": 0.1355,
"step": 2100
},
{
"epoch": 1.04,
"learning_rate": 5.502777777777778e-06,
"loss": 0.1105,
"step": 2110
},
{
"epoch": 1.05,
"learning_rate": 5.488888888888889e-06,
"loss": 0.1289,
"step": 2120
},
{
"epoch": 1.05,
"learning_rate": 5.474999999999999e-06,
"loss": 0.1127,
"step": 2130
},
{
"epoch": 1.06,
"learning_rate": 5.461111111111111e-06,
"loss": 0.1814,
"step": 2140
},
{
"epoch": 1.06,
"learning_rate": 5.447222222222222e-06,
"loss": 0.1554,
"step": 2150
},
{
"epoch": 1.07,
"learning_rate": 5.4333333333333335e-06,
"loss": 0.1038,
"step": 2160
},
{
"epoch": 1.07,
"learning_rate": 5.419444444444444e-06,
"loss": 0.1085,
"step": 2170
},
{
"epoch": 1.08,
"learning_rate": 5.4055555555555556e-06,
"loss": 0.1364,
"step": 2180
},
{
"epoch": 1.08,
"learning_rate": 5.391666666666666e-06,
"loss": 0.1089,
"step": 2190
},
{
"epoch": 1.09,
"learning_rate": 5.377777777777778e-06,
"loss": 0.1484,
"step": 2200
},
{
"epoch": 1.09,
"learning_rate": 5.363888888888889e-06,
"loss": 0.1254,
"step": 2210
},
{
"epoch": 1.1,
"learning_rate": 5.35e-06,
"loss": 0.1228,
"step": 2220
},
{
"epoch": 1.1,
"learning_rate": 5.336111111111111e-06,
"loss": 0.154,
"step": 2230
},
{
"epoch": 1.11,
"learning_rate": 5.322222222222222e-06,
"loss": 0.1745,
"step": 2240
},
{
"epoch": 1.11,
"learning_rate": 5.308333333333333e-06,
"loss": 0.1031,
"step": 2250
},
{
"epoch": 1.12,
"learning_rate": 5.294444444444444e-06,
"loss": 0.1359,
"step": 2260
},
{
"epoch": 1.12,
"learning_rate": 5.280555555555556e-06,
"loss": 0.1194,
"step": 2270
},
{
"epoch": 1.13,
"learning_rate": 5.2666666666666665e-06,
"loss": 0.1398,
"step": 2280
},
{
"epoch": 1.13,
"learning_rate": 5.252777777777778e-06,
"loss": 0.1277,
"step": 2290
},
{
"epoch": 1.14,
"learning_rate": 5.2388888888888885e-06,
"loss": 0.1121,
"step": 2300
},
{
"epoch": 1.14,
"learning_rate": 5.224999999999999e-06,
"loss": 0.1067,
"step": 2310
},
{
"epoch": 1.15,
"learning_rate": 5.211111111111111e-06,
"loss": 0.1101,
"step": 2320
},
{
"epoch": 1.15,
"learning_rate": 5.197222222222222e-06,
"loss": 0.1192,
"step": 2330
},
{
"epoch": 1.16,
"learning_rate": 5.183333333333333e-06,
"loss": 0.1055,
"step": 2340
},
{
"epoch": 1.16,
"learning_rate": 5.169444444444444e-06,
"loss": 0.1232,
"step": 2350
},
{
"epoch": 1.17,
"learning_rate": 5.155555555555555e-06,
"loss": 0.1096,
"step": 2360
},
{
"epoch": 1.17,
"learning_rate": 5.141666666666666e-06,
"loss": 0.0831,
"step": 2370
},
{
"epoch": 1.18,
"learning_rate": 5.127777777777778e-06,
"loss": 0.149,
"step": 2380
},
{
"epoch": 1.18,
"learning_rate": 5.113888888888889e-06,
"loss": 0.1328,
"step": 2390
},
{
"epoch": 1.19,
"learning_rate": 5.0999999999999995e-06,
"loss": 0.1193,
"step": 2400
},
{
"epoch": 1.19,
"learning_rate": 5.086111111111111e-06,
"loss": 0.1222,
"step": 2410
},
{
"epoch": 1.2,
"learning_rate": 5.0722222222222215e-06,
"loss": 0.1395,
"step": 2420
},
{
"epoch": 1.2,
"eval_loss": 0.26611328125,
"eval_runtime": 595.4698,
"eval_samples_per_second": 40.229,
"eval_steps_per_second": 5.03,
"step": 2426
},
{
"epoch": 1.2,
"learning_rate": 5.058333333333334e-06,
"loss": 0.1261,
"step": 2430
},
{
"epoch": 1.21,
"learning_rate": 5.044444444444444e-06,
"loss": 0.1416,
"step": 2440
},
{
"epoch": 1.21,
"learning_rate": 5.030555555555556e-06,
"loss": 0.1453,
"step": 2450
},
{
"epoch": 1.22,
"learning_rate": 5.016666666666666e-06,
"loss": 0.114,
"step": 2460
},
{
"epoch": 1.22,
"learning_rate": 5.002777777777778e-06,
"loss": 0.133,
"step": 2470
},
{
"epoch": 1.23,
"learning_rate": 4.988888888888888e-06,
"loss": 0.1207,
"step": 2480
},
{
"epoch": 1.23,
"learning_rate": 4.975e-06,
"loss": 0.1123,
"step": 2490
},
{
"epoch": 1.24,
"learning_rate": 4.961111111111111e-06,
"loss": 0.1039,
"step": 2500
},
{
"epoch": 1.24,
"learning_rate": 4.947222222222222e-06,
"loss": 0.091,
"step": 2510
},
{
"epoch": 1.25,
"learning_rate": 4.933333333333333e-06,
"loss": 0.1588,
"step": 2520
},
{
"epoch": 1.25,
"learning_rate": 4.919444444444444e-06,
"loss": 0.098,
"step": 2530
},
{
"epoch": 1.26,
"learning_rate": 4.905555555555555e-06,
"loss": 0.1033,
"step": 2540
},
{
"epoch": 1.26,
"learning_rate": 4.891666666666667e-06,
"loss": 0.1473,
"step": 2550
},
{
"epoch": 1.27,
"learning_rate": 4.877777777777778e-06,
"loss": 0.1331,
"step": 2560
},
{
"epoch": 1.27,
"learning_rate": 4.863888888888889e-06,
"loss": 0.1196,
"step": 2570
},
{
"epoch": 1.28,
"learning_rate": 4.849999999999999e-06,
"loss": 0.1379,
"step": 2580
},
{
"epoch": 1.28,
"learning_rate": 4.836111111111111e-06,
"loss": 0.124,
"step": 2590
},
{
"epoch": 1.29,
"learning_rate": 4.822222222222222e-06,
"loss": 0.1058,
"step": 2600
},
{
"epoch": 1.29,
"learning_rate": 4.808333333333334e-06,
"loss": 0.1132,
"step": 2610
},
{
"epoch": 1.3,
"learning_rate": 4.794444444444444e-06,
"loss": 0.1077,
"step": 2620
},
{
"epoch": 1.3,
"learning_rate": 4.780555555555556e-06,
"loss": 0.1266,
"step": 2630
},
{
"epoch": 1.31,
"learning_rate": 4.766666666666666e-06,
"loss": 0.1292,
"step": 2640
},
{
"epoch": 1.31,
"learning_rate": 4.752777777777778e-06,
"loss": 0.0969,
"step": 2650
},
{
"epoch": 1.32,
"learning_rate": 4.738888888888889e-06,
"loss": 0.0946,
"step": 2660
},
{
"epoch": 1.32,
"learning_rate": 4.725e-06,
"loss": 0.1479,
"step": 2670
},
{
"epoch": 1.33,
"learning_rate": 4.711111111111111e-06,
"loss": 0.133,
"step": 2680
},
{
"epoch": 1.33,
"learning_rate": 4.697222222222222e-06,
"loss": 0.1118,
"step": 2690
},
{
"epoch": 1.34,
"learning_rate": 4.683333333333333e-06,
"loss": 0.1362,
"step": 2700
},
{
"epoch": 1.34,
"learning_rate": 4.669444444444444e-06,
"loss": 0.1384,
"step": 2710
},
{
"epoch": 1.35,
"learning_rate": 4.655555555555556e-06,
"loss": 0.1275,
"step": 2720
},
{
"epoch": 1.35,
"learning_rate": 4.6416666666666666e-06,
"loss": 0.1416,
"step": 2730
},
{
"epoch": 1.36,
"learning_rate": 4.627777777777778e-06,
"loss": 0.1119,
"step": 2740
},
{
"epoch": 1.36,
"learning_rate": 4.6138888888888886e-06,
"loss": 0.1079,
"step": 2750
},
{
"epoch": 1.37,
"learning_rate": 4.599999999999999e-06,
"loss": 0.1197,
"step": 2760
},
{
"epoch": 1.37,
"learning_rate": 4.5861111111111114e-06,
"loss": 0.1115,
"step": 2770
},
{
"epoch": 1.38,
"learning_rate": 4.572222222222222e-06,
"loss": 0.1023,
"step": 2780
},
{
"epoch": 1.38,
"learning_rate": 4.5583333333333335e-06,
"loss": 0.1109,
"step": 2790
},
{
"epoch": 1.39,
"learning_rate": 4.544444444444444e-06,
"loss": 0.1184,
"step": 2800
},
{
"epoch": 1.39,
"learning_rate": 4.5305555555555555e-06,
"loss": 0.1103,
"step": 2810
},
{
"epoch": 1.4,
"learning_rate": 4.516666666666666e-06,
"loss": 0.1074,
"step": 2820
},
{
"epoch": 1.4,
"learning_rate": 4.502777777777778e-06,
"loss": 0.1139,
"step": 2830
},
{
"epoch": 1.4,
"learning_rate": 4.488888888888889e-06,
"loss": 0.1107,
"step": 2840
},
{
"epoch": 1.41,
"learning_rate": 4.4749999999999995e-06,
"loss": 0.0777,
"step": 2850
},
{
"epoch": 1.41,
"learning_rate": 4.461111111111111e-06,
"loss": 0.1348,
"step": 2860
},
{
"epoch": 1.42,
"learning_rate": 4.4472222222222215e-06,
"loss": 0.1362,
"step": 2870
},
{
"epoch": 1.42,
"learning_rate": 4.433333333333333e-06,
"loss": 0.1374,
"step": 2880
},
{
"epoch": 1.43,
"learning_rate": 4.419444444444444e-06,
"loss": 0.1135,
"step": 2890
},
{
"epoch": 1.43,
"learning_rate": 4.405555555555556e-06,
"loss": 0.1166,
"step": 2900
},
{
"epoch": 1.44,
"learning_rate": 4.391666666666666e-06,
"loss": 0.1202,
"step": 2910
},
{
"epoch": 1.44,
"learning_rate": 4.377777777777778e-06,
"loss": 0.1455,
"step": 2920
},
{
"epoch": 1.45,
"learning_rate": 4.3638888888888884e-06,
"loss": 0.0831,
"step": 2930
},
{
"epoch": 1.45,
"learning_rate": 4.35e-06,
"loss": 0.1211,
"step": 2940
},
{
"epoch": 1.46,
"learning_rate": 4.336111111111111e-06,
"loss": 0.1194,
"step": 2950
},
{
"epoch": 1.46,
"learning_rate": 4.322222222222222e-06,
"loss": 0.1124,
"step": 2960
},
{
"epoch": 1.47,
"learning_rate": 4.308333333333333e-06,
"loss": 0.0947,
"step": 2970
},
{
"epoch": 1.47,
"learning_rate": 4.294444444444444e-06,
"loss": 0.1152,
"step": 2980
},
{
"epoch": 1.48,
"learning_rate": 4.280555555555555e-06,
"loss": 0.0858,
"step": 2990
},
{
"epoch": 1.48,
"learning_rate": 4.266666666666667e-06,
"loss": 0.087,
"step": 3000
},
{
"epoch": 1.49,
"learning_rate": 4.252777777777778e-06,
"loss": 0.1237,
"step": 3010
},
{
"epoch": 1.49,
"learning_rate": 4.238888888888889e-06,
"loss": 0.0809,
"step": 3020
},
{
"epoch": 1.5,
"learning_rate": 4.224999999999999e-06,
"loss": 0.1022,
"step": 3030
},
{
"epoch": 1.5,
"learning_rate": 4.211111111111111e-06,
"loss": 0.101,
"step": 3040
},
{
"epoch": 1.51,
"learning_rate": 4.197222222222221e-06,
"loss": 0.1327,
"step": 3050
},
{
"epoch": 1.51,
"learning_rate": 4.183333333333334e-06,
"loss": 0.1056,
"step": 3060
},
{
"epoch": 1.52,
"learning_rate": 4.169444444444444e-06,
"loss": 0.1129,
"step": 3070
},
{
"epoch": 1.52,
"learning_rate": 4.155555555555556e-06,
"loss": 0.1119,
"step": 3080
},
{
"epoch": 1.53,
"learning_rate": 4.141666666666666e-06,
"loss": 0.1287,
"step": 3090
},
{
"epoch": 1.53,
"learning_rate": 4.127777777777778e-06,
"loss": 0.1179,
"step": 3100
},
{
"epoch": 1.54,
"learning_rate": 4.113888888888889e-06,
"loss": 0.1152,
"step": 3110
},
{
"epoch": 1.54,
"learning_rate": 4.1e-06,
"loss": 0.0833,
"step": 3120
},
{
"epoch": 1.55,
"learning_rate": 4.086111111111111e-06,
"loss": 0.1304,
"step": 3130
},
{
"epoch": 1.55,
"learning_rate": 4.072222222222222e-06,
"loss": 0.0813,
"step": 3140
},
{
"epoch": 1.56,
"learning_rate": 4.058333333333333e-06,
"loss": 0.1068,
"step": 3150
},
{
"epoch": 1.56,
"learning_rate": 4.044444444444444e-06,
"loss": 0.0998,
"step": 3160
},
{
"epoch": 1.57,
"learning_rate": 4.030555555555556e-06,
"loss": 0.1109,
"step": 3170
},
{
"epoch": 1.57,
"learning_rate": 4.016666666666667e-06,
"loss": 0.1193,
"step": 3180
},
{
"epoch": 1.58,
"learning_rate": 4.002777777777778e-06,
"loss": 0.1234,
"step": 3190
},
{
"epoch": 1.58,
"learning_rate": 3.988888888888889e-06,
"loss": 0.1049,
"step": 3200
},
{
"epoch": 1.59,
"learning_rate": 3.975e-06,
"loss": 0.1017,
"step": 3210
},
{
"epoch": 1.59,
"learning_rate": 3.9611111111111115e-06,
"loss": 0.1044,
"step": 3220
},
{
"epoch": 1.6,
"learning_rate": 3.947222222222222e-06,
"loss": 0.1263,
"step": 3230
},
{
"epoch": 1.6,
"learning_rate": 3.933333333333333e-06,
"loss": 0.1419,
"step": 3240
},
{
"epoch": 1.61,
"learning_rate": 3.919444444444444e-06,
"loss": 0.1294,
"step": 3250
},
{
"epoch": 1.61,
"learning_rate": 3.9055555555555555e-06,
"loss": 0.0939,
"step": 3260
},
{
"epoch": 1.62,
"learning_rate": 3.891666666666666e-06,
"loss": 0.1374,
"step": 3270
},
{
"epoch": 1.62,
"learning_rate": 3.8777777777777775e-06,
"loss": 0.0959,
"step": 3280
},
{
"epoch": 1.63,
"learning_rate": 3.863888888888889e-06,
"loss": 0.1009,
"step": 3290
},
{
"epoch": 1.63,
"learning_rate": 3.8499999999999996e-06,
"loss": 0.1305,
"step": 3300
},
{
"epoch": 1.64,
"learning_rate": 3.836111111111111e-06,
"loss": 0.1303,
"step": 3310
},
{
"epoch": 1.64,
"learning_rate": 3.8222222222222224e-06,
"loss": 0.1282,
"step": 3320
},
{
"epoch": 1.65,
"learning_rate": 3.808333333333333e-06,
"loss": 0.1053,
"step": 3330
},
{
"epoch": 1.65,
"learning_rate": 3.794444444444444e-06,
"loss": 0.1042,
"step": 3340
},
{
"epoch": 1.66,
"learning_rate": 3.7805555555555555e-06,
"loss": 0.0849,
"step": 3350
},
{
"epoch": 1.66,
"learning_rate": 3.7666666666666665e-06,
"loss": 0.1274,
"step": 3360
},
{
"epoch": 1.67,
"learning_rate": 3.7527777777777775e-06,
"loss": 0.1228,
"step": 3370
},
{
"epoch": 1.67,
"learning_rate": 3.738888888888889e-06,
"loss": 0.1129,
"step": 3380
},
{
"epoch": 1.68,
"learning_rate": 3.725e-06,
"loss": 0.1128,
"step": 3390
},
{
"epoch": 1.68,
"learning_rate": 3.711111111111111e-06,
"loss": 0.1317,
"step": 3400
},
{
"epoch": 1.69,
"learning_rate": 3.6972222222222224e-06,
"loss": 0.1246,
"step": 3410
},
{
"epoch": 1.69,
"learning_rate": 3.683333333333333e-06,
"loss": 0.0806,
"step": 3420
},
{
"epoch": 1.7,
"learning_rate": 3.669444444444444e-06,
"loss": 0.119,
"step": 3430
},
{
"epoch": 1.7,
"learning_rate": 3.6555555555555554e-06,
"loss": 0.0893,
"step": 3440
},
{
"epoch": 1.71,
"learning_rate": 3.6416666666666664e-06,
"loss": 0.1058,
"step": 3450
},
{
"epoch": 1.71,
"learning_rate": 3.6277777777777774e-06,
"loss": 0.0944,
"step": 3460
},
{
"epoch": 1.72,
"learning_rate": 3.613888888888889e-06,
"loss": 0.126,
"step": 3470
},
{
"epoch": 1.72,
"learning_rate": 3.6e-06,
"loss": 0.1104,
"step": 3480
},
{
"epoch": 1.73,
"learning_rate": 3.5861111111111113e-06,
"loss": 0.1108,
"step": 3490
},
{
"epoch": 1.73,
"learning_rate": 3.5722222222222223e-06,
"loss": 0.1197,
"step": 3500
},
{
"epoch": 1.74,
"learning_rate": 3.558333333333333e-06,
"loss": 0.1182,
"step": 3510
},
{
"epoch": 1.74,
"learning_rate": 3.5444444444444443e-06,
"loss": 0.0988,
"step": 3520
},
{
"epoch": 1.75,
"learning_rate": 3.5305555555555553e-06,
"loss": 0.0949,
"step": 3530
},
{
"epoch": 1.75,
"learning_rate": 3.5166666666666663e-06,
"loss": 0.1102,
"step": 3540
},
{
"epoch": 1.76,
"learning_rate": 3.5027777777777777e-06,
"loss": 0.1203,
"step": 3550
},
{
"epoch": 1.76,
"learning_rate": 3.4888888888888888e-06,
"loss": 0.1343,
"step": 3560
},
{
"epoch": 1.77,
"learning_rate": 3.4749999999999998e-06,
"loss": 0.0851,
"step": 3570
},
{
"epoch": 1.77,
"learning_rate": 3.461111111111111e-06,
"loss": 0.1181,
"step": 3580
},
{
"epoch": 1.78,
"learning_rate": 3.447222222222222e-06,
"loss": 0.0931,
"step": 3590
},
{
"epoch": 1.78,
"learning_rate": 3.433333333333333e-06,
"loss": 0.1068,
"step": 3600
},
{
"epoch": 1.79,
"learning_rate": 3.4194444444444442e-06,
"loss": 0.0884,
"step": 3610
},
{
"epoch": 1.79,
"learning_rate": 3.4055555555555552e-06,
"loss": 0.1326,
"step": 3620
},
{
"epoch": 1.8,
"learning_rate": 3.3916666666666667e-06,
"loss": 0.1307,
"step": 3630
},
{
"epoch": 1.8,
"eval_loss": 0.249267578125,
"eval_runtime": 590.255,
"eval_samples_per_second": 40.584,
"eval_steps_per_second": 5.074,
"step": 3639
}
],
"max_steps": 6063,
"num_train_epochs": 3,
"total_flos": 134441240494080.0,
"trial_name": null,
"trial_params": null
}