krakowiak-7b / trainer_state.json
szymonrucinski's picture
Update to 3rd epoch (#3)
3c6a2d8
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.3383947939262475,
"global_step": 3000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.5637,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.3117,
"step": 20
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.2738,
"step": 30
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.2728,
"step": 40
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 1.2202,
"step": 50
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 1.2241,
"step": 60
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 1.1647,
"step": 70
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 1.1426,
"step": 80
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 1.1432,
"step": 90
},
{
"epoch": 0.14,
"learning_rate": 0.0002,
"loss": 1.1319,
"step": 100
},
{
"epoch": 0.16,
"learning_rate": 0.0002,
"loss": 1.1882,
"step": 110
},
{
"epoch": 0.17,
"learning_rate": 0.0002,
"loss": 1.116,
"step": 120
},
{
"epoch": 0.19,
"learning_rate": 0.0002,
"loss": 1.1072,
"step": 130
},
{
"epoch": 0.2,
"learning_rate": 0.0002,
"loss": 1.1417,
"step": 140
},
{
"epoch": 0.22,
"learning_rate": 0.0002,
"loss": 1.1102,
"step": 150
},
{
"epoch": 0.23,
"learning_rate": 0.0002,
"loss": 1.1567,
"step": 160
},
{
"epoch": 0.25,
"learning_rate": 0.0002,
"loss": 1.1167,
"step": 170
},
{
"epoch": 0.26,
"learning_rate": 0.0002,
"loss": 1.0849,
"step": 180
},
{
"epoch": 0.27,
"learning_rate": 0.0002,
"loss": 1.1045,
"step": 190
},
{
"epoch": 0.29,
"learning_rate": 0.0002,
"loss": 1.0925,
"step": 200
},
{
"epoch": 0.3,
"learning_rate": 0.0002,
"loss": 1.1588,
"step": 210
},
{
"epoch": 0.32,
"learning_rate": 0.0002,
"loss": 1.1013,
"step": 220
},
{
"epoch": 0.33,
"learning_rate": 0.0002,
"loss": 1.0684,
"step": 230
},
{
"epoch": 0.35,
"learning_rate": 0.0002,
"loss": 1.0887,
"step": 240
},
{
"epoch": 0.36,
"learning_rate": 0.0002,
"loss": 1.0598,
"step": 250
},
{
"epoch": 0.38,
"learning_rate": 0.0002,
"loss": 1.153,
"step": 260
},
{
"epoch": 0.39,
"learning_rate": 0.0002,
"loss": 1.0932,
"step": 270
},
{
"epoch": 0.4,
"learning_rate": 0.0002,
"loss": 1.0747,
"step": 280
},
{
"epoch": 0.42,
"learning_rate": 0.0002,
"loss": 1.0729,
"step": 290
},
{
"epoch": 0.43,
"learning_rate": 0.0002,
"loss": 1.0683,
"step": 300
},
{
"epoch": 0.45,
"learning_rate": 0.0002,
"loss": 1.1444,
"step": 310
},
{
"epoch": 0.46,
"learning_rate": 0.0002,
"loss": 1.0992,
"step": 320
},
{
"epoch": 0.48,
"learning_rate": 0.0002,
"loss": 1.0648,
"step": 330
},
{
"epoch": 0.49,
"learning_rate": 0.0002,
"loss": 1.0701,
"step": 340
},
{
"epoch": 0.51,
"learning_rate": 0.0002,
"loss": 1.0628,
"step": 350
},
{
"epoch": 0.52,
"learning_rate": 0.0002,
"loss": 1.1322,
"step": 360
},
{
"epoch": 0.54,
"learning_rate": 0.0002,
"loss": 1.0736,
"step": 370
},
{
"epoch": 0.55,
"learning_rate": 0.0002,
"loss": 1.0485,
"step": 380
},
{
"epoch": 0.56,
"learning_rate": 0.0002,
"loss": 1.0571,
"step": 390
},
{
"epoch": 0.58,
"learning_rate": 0.0002,
"loss": 1.076,
"step": 400
},
{
"epoch": 0.59,
"learning_rate": 0.0002,
"loss": 1.1234,
"step": 410
},
{
"epoch": 0.61,
"learning_rate": 0.0002,
"loss": 1.0641,
"step": 420
},
{
"epoch": 0.62,
"learning_rate": 0.0002,
"loss": 1.0724,
"step": 430
},
{
"epoch": 0.64,
"learning_rate": 0.0002,
"loss": 1.0483,
"step": 440
},
{
"epoch": 0.65,
"learning_rate": 0.0002,
"loss": 1.039,
"step": 450
},
{
"epoch": 0.67,
"learning_rate": 0.0002,
"loss": 1.1064,
"step": 460
},
{
"epoch": 0.68,
"learning_rate": 0.0002,
"loss": 1.0551,
"step": 470
},
{
"epoch": 0.69,
"learning_rate": 0.0002,
"loss": 1.0224,
"step": 480
},
{
"epoch": 0.71,
"learning_rate": 0.0002,
"loss": 1.0001,
"step": 490
},
{
"epoch": 0.72,
"learning_rate": 0.0002,
"loss": 0.96,
"step": 500
},
{
"epoch": 0.74,
"learning_rate": 0.0002,
"loss": 1.0563,
"step": 510
},
{
"epoch": 0.75,
"learning_rate": 0.0002,
"loss": 1.0359,
"step": 520
},
{
"epoch": 0.77,
"learning_rate": 0.0002,
"loss": 1.0219,
"step": 530
},
{
"epoch": 0.78,
"learning_rate": 0.0002,
"loss": 1.0062,
"step": 540
},
{
"epoch": 0.8,
"learning_rate": 0.0002,
"loss": 0.948,
"step": 550
},
{
"epoch": 0.81,
"learning_rate": 0.0002,
"loss": 1.0781,
"step": 560
},
{
"epoch": 0.82,
"learning_rate": 0.0002,
"loss": 1.0279,
"step": 570
},
{
"epoch": 0.84,
"learning_rate": 0.0002,
"loss": 1.0209,
"step": 580
},
{
"epoch": 0.85,
"learning_rate": 0.0002,
"loss": 1.0166,
"step": 590
},
{
"epoch": 0.87,
"learning_rate": 0.0002,
"loss": 0.9426,
"step": 600
},
{
"epoch": 0.88,
"learning_rate": 0.0002,
"loss": 1.0778,
"step": 610
},
{
"epoch": 0.9,
"learning_rate": 0.0002,
"loss": 1.0314,
"step": 620
},
{
"epoch": 0.91,
"learning_rate": 0.0002,
"loss": 1.0092,
"step": 630
},
{
"epoch": 0.93,
"learning_rate": 0.0002,
"loss": 1.0022,
"step": 640
},
{
"epoch": 0.94,
"learning_rate": 0.0002,
"loss": 0.9352,
"step": 650
},
{
"epoch": 0.95,
"learning_rate": 0.0002,
"loss": 1.0628,
"step": 660
},
{
"epoch": 0.97,
"learning_rate": 0.0002,
"loss": 1.0157,
"step": 670
},
{
"epoch": 0.98,
"learning_rate": 0.0002,
"loss": 1.0169,
"step": 680
},
{
"epoch": 1.0,
"learning_rate": 0.0002,
"loss": 0.9608,
"step": 690
},
{
"epoch": 1.01,
"learning_rate": 0.0002,
"loss": 1.033,
"step": 700
},
{
"epoch": 1.03,
"learning_rate": 0.0002,
"loss": 1.0205,
"step": 710
},
{
"epoch": 1.04,
"learning_rate": 0.0002,
"loss": 0.9868,
"step": 720
},
{
"epoch": 1.06,
"learning_rate": 0.0002,
"loss": 0.9838,
"step": 730
},
{
"epoch": 1.07,
"learning_rate": 0.0002,
"loss": 0.925,
"step": 740
},
{
"epoch": 1.08,
"learning_rate": 0.0002,
"loss": 1.0044,
"step": 750
},
{
"epoch": 1.1,
"learning_rate": 0.0002,
"loss": 1.0188,
"step": 760
},
{
"epoch": 1.11,
"learning_rate": 0.0002,
"loss": 0.9815,
"step": 770
},
{
"epoch": 1.13,
"learning_rate": 0.0002,
"loss": 0.9745,
"step": 780
},
{
"epoch": 1.14,
"learning_rate": 0.0002,
"loss": 0.9249,
"step": 790
},
{
"epoch": 1.16,
"learning_rate": 0.0002,
"loss": 1.0042,
"step": 800
},
{
"epoch": 1.17,
"learning_rate": 0.0002,
"loss": 0.9997,
"step": 810
},
{
"epoch": 1.19,
"learning_rate": 0.0002,
"loss": 0.9889,
"step": 820
},
{
"epoch": 1.2,
"learning_rate": 0.0002,
"loss": 0.9679,
"step": 830
},
{
"epoch": 1.21,
"learning_rate": 0.0002,
"loss": 0.9192,
"step": 840
},
{
"epoch": 1.23,
"learning_rate": 0.0002,
"loss": 1.0285,
"step": 850
},
{
"epoch": 1.24,
"learning_rate": 0.0002,
"loss": 1.0116,
"step": 860
},
{
"epoch": 1.26,
"learning_rate": 0.0002,
"loss": 0.9794,
"step": 870
},
{
"epoch": 1.27,
"learning_rate": 0.0002,
"loss": 0.974,
"step": 880
},
{
"epoch": 1.29,
"learning_rate": 0.0002,
"loss": 0.9272,
"step": 890
},
{
"epoch": 1.3,
"learning_rate": 0.0002,
"loss": 1.016,
"step": 900
},
{
"epoch": 1.32,
"learning_rate": 0.0002,
"loss": 1.0145,
"step": 910
},
{
"epoch": 1.33,
"learning_rate": 0.0002,
"loss": 0.9856,
"step": 920
},
{
"epoch": 1.34,
"learning_rate": 0.0002,
"loss": 0.9517,
"step": 930
},
{
"epoch": 1.36,
"learning_rate": 0.0002,
"loss": 0.9321,
"step": 940
},
{
"epoch": 1.37,
"learning_rate": 0.0002,
"loss": 1.0238,
"step": 950
},
{
"epoch": 1.39,
"learning_rate": 0.0002,
"loss": 1.0162,
"step": 960
},
{
"epoch": 1.4,
"learning_rate": 0.0002,
"loss": 0.9882,
"step": 970
},
{
"epoch": 1.42,
"learning_rate": 0.0002,
"loss": 0.9704,
"step": 980
},
{
"epoch": 1.43,
"learning_rate": 0.0002,
"loss": 0.9221,
"step": 990
},
{
"epoch": 1.45,
"learning_rate": 0.0002,
"loss": 1.0302,
"step": 1000
},
{
"epoch": 1.46,
"learning_rate": 0.0002,
"loss": 1.0084,
"step": 1010
},
{
"epoch": 1.48,
"learning_rate": 0.0002,
"loss": 0.9829,
"step": 1020
},
{
"epoch": 1.49,
"learning_rate": 0.0002,
"loss": 0.9673,
"step": 1030
},
{
"epoch": 1.5,
"learning_rate": 0.0002,
"loss": 0.9238,
"step": 1040
},
{
"epoch": 1.52,
"learning_rate": 0.0002,
"loss": 1.0006,
"step": 1050
},
{
"epoch": 1.53,
"learning_rate": 0.0002,
"loss": 0.9912,
"step": 1060
},
{
"epoch": 1.55,
"learning_rate": 0.0002,
"loss": 0.973,
"step": 1070
},
{
"epoch": 1.56,
"learning_rate": 0.0002,
"loss": 0.961,
"step": 1080
},
{
"epoch": 1.58,
"learning_rate": 0.0002,
"loss": 0.9109,
"step": 1090
},
{
"epoch": 1.59,
"learning_rate": 0.0002,
"loss": 0.9946,
"step": 1100
},
{
"epoch": 1.61,
"learning_rate": 0.0002,
"loss": 0.9957,
"step": 1110
},
{
"epoch": 1.62,
"learning_rate": 0.0002,
"loss": 0.9628,
"step": 1120
},
{
"epoch": 1.63,
"learning_rate": 0.0002,
"loss": 0.9551,
"step": 1130
},
{
"epoch": 1.65,
"learning_rate": 0.0002,
"loss": 0.9382,
"step": 1140
},
{
"epoch": 1.66,
"learning_rate": 0.0002,
"loss": 1.0101,
"step": 1150
},
{
"epoch": 1.68,
"learning_rate": 0.0002,
"loss": 0.982,
"step": 1160
},
{
"epoch": 1.69,
"learning_rate": 0.0002,
"loss": 0.9751,
"step": 1170
},
{
"epoch": 1.71,
"learning_rate": 0.0002,
"loss": 0.9605,
"step": 1180
},
{
"epoch": 1.72,
"learning_rate": 0.0002,
"loss": 0.9216,
"step": 1190
},
{
"epoch": 1.74,
"learning_rate": 0.0002,
"loss": 0.9855,
"step": 1200
},
{
"epoch": 1.75,
"learning_rate": 0.0002,
"loss": 0.9885,
"step": 1210
},
{
"epoch": 1.76,
"learning_rate": 0.0002,
"loss": 0.9678,
"step": 1220
},
{
"epoch": 1.78,
"learning_rate": 0.0002,
"loss": 0.9642,
"step": 1230
},
{
"epoch": 1.79,
"learning_rate": 0.0002,
"loss": 0.9125,
"step": 1240
},
{
"epoch": 1.81,
"learning_rate": 0.0002,
"loss": 0.9917,
"step": 1250
},
{
"epoch": 1.82,
"learning_rate": 0.0002,
"loss": 0.9832,
"step": 1260
},
{
"epoch": 1.84,
"learning_rate": 0.0002,
"loss": 0.9619,
"step": 1270
},
{
"epoch": 1.85,
"learning_rate": 0.0002,
"loss": 0.9523,
"step": 1280
},
{
"epoch": 1.87,
"learning_rate": 0.0002,
"loss": 0.9244,
"step": 1290
},
{
"epoch": 1.88,
"learning_rate": 0.0002,
"loss": 0.9929,
"step": 1300
},
{
"epoch": 1.89,
"learning_rate": 0.0002,
"loss": 0.9795,
"step": 1310
},
{
"epoch": 1.91,
"learning_rate": 0.0002,
"loss": 0.9674,
"step": 1320
},
{
"epoch": 1.92,
"learning_rate": 0.0002,
"loss": 0.9671,
"step": 1330
},
{
"epoch": 1.94,
"learning_rate": 0.0002,
"loss": 0.9089,
"step": 1340
},
{
"epoch": 1.95,
"learning_rate": 0.0002,
"loss": 0.9829,
"step": 1350
},
{
"epoch": 1.97,
"learning_rate": 0.0002,
"loss": 0.9712,
"step": 1360
},
{
"epoch": 1.98,
"learning_rate": 0.0002,
"loss": 0.9626,
"step": 1370
},
{
"epoch": 2.0,
"learning_rate": 0.0002,
"loss": 0.9273,
"step": 1380
},
{
"epoch": 2.01,
"learning_rate": 0.0002,
"loss": 0.96,
"step": 1390
},
{
"epoch": 2.02,
"learning_rate": 0.0002,
"loss": 0.9706,
"step": 1400
},
{
"epoch": 2.04,
"learning_rate": 0.0002,
"loss": 0.9352,
"step": 1410
},
{
"epoch": 2.05,
"learning_rate": 0.0002,
"loss": 0.9279,
"step": 1420
},
{
"epoch": 2.07,
"learning_rate": 0.0002,
"loss": 0.8945,
"step": 1430
},
{
"epoch": 2.08,
"learning_rate": 0.0002,
"loss": 0.9358,
"step": 1440
},
{
"epoch": 2.1,
"learning_rate": 0.0002,
"loss": 0.9542,
"step": 1450
},
{
"epoch": 2.11,
"learning_rate": 0.0002,
"loss": 0.9328,
"step": 1460
},
{
"epoch": 2.13,
"learning_rate": 0.0002,
"loss": 0.91,
"step": 1470
},
{
"epoch": 2.14,
"learning_rate": 0.0002,
"loss": 0.8871,
"step": 1480
},
{
"epoch": 2.15,
"learning_rate": 0.0002,
"loss": 0.9231,
"step": 1490
},
{
"epoch": 2.17,
"learning_rate": 0.0002,
"loss": 0.9682,
"step": 1500
},
{
"epoch": 2.18,
"learning_rate": 0.0002,
"loss": 0.9527,
"step": 1510
},
{
"epoch": 2.2,
"learning_rate": 0.0002,
"loss": 0.9268,
"step": 1520
},
{
"epoch": 2.21,
"learning_rate": 0.0002,
"loss": 0.8734,
"step": 1530
},
{
"epoch": 2.23,
"learning_rate": 0.0002,
"loss": 0.9363,
"step": 1540
},
{
"epoch": 2.24,
"learning_rate": 0.0002,
"loss": 0.9615,
"step": 1550
},
{
"epoch": 2.26,
"learning_rate": 0.0002,
"loss": 0.9415,
"step": 1560
},
{
"epoch": 2.27,
"learning_rate": 0.0002,
"loss": 0.9177,
"step": 1570
},
{
"epoch": 2.28,
"learning_rate": 0.0002,
"loss": 0.9003,
"step": 1580
},
{
"epoch": 2.3,
"learning_rate": 0.0002,
"loss": 0.9628,
"step": 1590
},
{
"epoch": 2.31,
"learning_rate": 0.0002,
"loss": 0.9603,
"step": 1600
},
{
"epoch": 2.33,
"learning_rate": 0.0002,
"loss": 0.9314,
"step": 1610
},
{
"epoch": 2.34,
"learning_rate": 0.0002,
"loss": 0.9305,
"step": 1620
},
{
"epoch": 2.36,
"learning_rate": 0.0002,
"loss": 0.8867,
"step": 1630
},
{
"epoch": 2.37,
"learning_rate": 0.0002,
"loss": 0.9304,
"step": 1640
},
{
"epoch": 2.39,
"learning_rate": 0.0002,
"loss": 0.978,
"step": 1650
},
{
"epoch": 2.4,
"learning_rate": 0.0002,
"loss": 0.9338,
"step": 1660
},
{
"epoch": 2.42,
"learning_rate": 0.0002,
"loss": 0.9334,
"step": 1670
},
{
"epoch": 2.43,
"learning_rate": 0.0002,
"loss": 0.8967,
"step": 1680
},
{
"epoch": 2.44,
"learning_rate": 0.0002,
"loss": 0.9358,
"step": 1690
},
{
"epoch": 2.46,
"learning_rate": 0.0002,
"loss": 0.9557,
"step": 1700
},
{
"epoch": 2.47,
"learning_rate": 0.0002,
"loss": 0.9332,
"step": 1710
},
{
"epoch": 2.49,
"learning_rate": 0.0002,
"loss": 0.9198,
"step": 1720
},
{
"epoch": 2.5,
"learning_rate": 0.0002,
"loss": 0.8794,
"step": 1730
},
{
"epoch": 2.52,
"learning_rate": 0.0002,
"loss": 0.9247,
"step": 1740
},
{
"epoch": 2.53,
"learning_rate": 0.0002,
"loss": 0.9541,
"step": 1750
},
{
"epoch": 2.55,
"learning_rate": 0.0002,
"loss": 0.9266,
"step": 1760
},
{
"epoch": 2.56,
"learning_rate": 0.0002,
"loss": 0.908,
"step": 1770
},
{
"epoch": 2.57,
"learning_rate": 0.0002,
"loss": 0.8933,
"step": 1780
},
{
"epoch": 2.59,
"learning_rate": 0.0002,
"loss": 0.9533,
"step": 1790
},
{
"epoch": 2.6,
"learning_rate": 0.0002,
"loss": 0.9567,
"step": 1800
},
{
"epoch": 2.62,
"learning_rate": 0.0002,
"loss": 0.9514,
"step": 1810
},
{
"epoch": 2.63,
"learning_rate": 0.0002,
"loss": 0.9099,
"step": 1820
},
{
"epoch": 2.65,
"learning_rate": 0.0002,
"loss": 0.8934,
"step": 1830
},
{
"epoch": 2.66,
"learning_rate": 0.0002,
"loss": 0.9207,
"step": 1840
},
{
"epoch": 2.68,
"learning_rate": 0.0002,
"loss": 0.9655,
"step": 1850
},
{
"epoch": 2.69,
"learning_rate": 0.0002,
"loss": 0.934,
"step": 1860
},
{
"epoch": 2.7,
"learning_rate": 0.0002,
"loss": 0.9299,
"step": 1870
},
{
"epoch": 2.72,
"learning_rate": 0.0002,
"loss": 0.8832,
"step": 1880
},
{
"epoch": 2.73,
"learning_rate": 0.0002,
"loss": 0.9434,
"step": 1890
},
{
"epoch": 2.75,
"learning_rate": 0.0002,
"loss": 0.9503,
"step": 1900
},
{
"epoch": 2.76,
"learning_rate": 0.0002,
"loss": 0.9322,
"step": 1910
},
{
"epoch": 2.78,
"learning_rate": 0.0002,
"loss": 0.9019,
"step": 1920
},
{
"epoch": 2.79,
"learning_rate": 0.0002,
"loss": 0.8827,
"step": 1930
},
{
"epoch": 2.81,
"learning_rate": 0.0002,
"loss": 0.94,
"step": 1940
},
{
"epoch": 2.82,
"learning_rate": 0.0002,
"loss": 0.9615,
"step": 1950
},
{
"epoch": 2.83,
"learning_rate": 0.0002,
"loss": 0.926,
"step": 1960
},
{
"epoch": 2.85,
"learning_rate": 0.0002,
"loss": 0.9219,
"step": 1970
},
{
"epoch": 2.86,
"learning_rate": 0.0002,
"loss": 0.8812,
"step": 1980
},
{
"epoch": 2.88,
"learning_rate": 0.0002,
"loss": 0.9407,
"step": 1990
},
{
"epoch": 2.89,
"learning_rate": 0.0002,
"loss": 0.9679,
"step": 2000
},
{
"epoch": 2.91,
"learning_rate": 0.0002,
"loss": 0.9243,
"step": 2010
},
{
"epoch": 2.92,
"learning_rate": 0.0002,
"loss": 0.911,
"step": 2020
},
{
"epoch": 2.94,
"learning_rate": 0.0002,
"loss": 0.8796,
"step": 2030
},
{
"epoch": 2.95,
"learning_rate": 0.0002,
"loss": 0.94,
"step": 2040
},
{
"epoch": 2.96,
"learning_rate": 0.0002,
"loss": 0.9692,
"step": 2050
},
{
"epoch": 2.98,
"learning_rate": 0.0002,
"loss": 0.9006,
"step": 2060
},
{
"epoch": 2.99,
"learning_rate": 0.0002,
"loss": 0.9048,
"step": 2070
},
{
"epoch": 3.01,
"learning_rate": 0.0002,
"loss": 0.8862,
"step": 2080
},
{
"epoch": 3.02,
"learning_rate": 0.0002,
"loss": 0.9506,
"step": 2090
},
{
"epoch": 3.04,
"learning_rate": 0.0002,
"loss": 0.891,
"step": 2100
},
{
"epoch": 3.05,
"learning_rate": 0.0002,
"loss": 0.8773,
"step": 2110
},
{
"epoch": 3.07,
"learning_rate": 0.0002,
"loss": 0.8564,
"step": 2120
},
{
"epoch": 3.08,
"learning_rate": 0.0002,
"loss": 0.8797,
"step": 2130
},
{
"epoch": 3.09,
"learning_rate": 0.0002,
"loss": 0.9263,
"step": 2140
},
{
"epoch": 3.11,
"learning_rate": 0.0002,
"loss": 0.8894,
"step": 2150
},
{
"epoch": 3.12,
"learning_rate": 0.0002,
"loss": 0.8973,
"step": 2160
},
{
"epoch": 3.14,
"learning_rate": 0.0002,
"loss": 0.838,
"step": 2170
},
{
"epoch": 3.15,
"learning_rate": 0.0002,
"loss": 0.8785,
"step": 2180
},
{
"epoch": 3.17,
"learning_rate": 0.0002,
"loss": 0.9323,
"step": 2190
},
{
"epoch": 3.18,
"learning_rate": 0.0002,
"loss": 0.8981,
"step": 2200
},
{
"epoch": 3.2,
"learning_rate": 0.0002,
"loss": 0.8775,
"step": 2210
},
{
"epoch": 3.21,
"learning_rate": 0.0002,
"loss": 0.8546,
"step": 2220
},
{
"epoch": 3.22,
"learning_rate": 0.0002,
"loss": 0.8693,
"step": 2230
},
{
"epoch": 3.24,
"learning_rate": 0.0002,
"loss": 0.941,
"step": 2240
},
{
"epoch": 3.25,
"learning_rate": 0.0002,
"loss": 0.9034,
"step": 2250
},
{
"epoch": 3.27,
"learning_rate": 0.0002,
"loss": 0.8807,
"step": 2260
},
{
"epoch": 3.28,
"learning_rate": 0.0002,
"loss": 0.8535,
"step": 2270
},
{
"epoch": 3.3,
"learning_rate": 0.0002,
"loss": 0.8793,
"step": 2280
},
{
"epoch": 3.31,
"learning_rate": 0.0002,
"loss": 0.938,
"step": 2290
},
{
"epoch": 3.33,
"learning_rate": 0.0002,
"loss": 0.9041,
"step": 2300
},
{
"epoch": 3.34,
"learning_rate": 0.0002,
"loss": 0.8857,
"step": 2310
},
{
"epoch": 3.36,
"learning_rate": 0.0002,
"loss": 0.8367,
"step": 2320
},
{
"epoch": 3.37,
"learning_rate": 0.0002,
"loss": 0.8857,
"step": 2330
},
{
"epoch": 3.38,
"learning_rate": 0.0002,
"loss": 0.9411,
"step": 2340
},
{
"epoch": 3.4,
"learning_rate": 0.0002,
"loss": 0.907,
"step": 2350
},
{
"epoch": 3.41,
"learning_rate": 0.0002,
"loss": 0.8845,
"step": 2360
},
{
"epoch": 3.43,
"learning_rate": 0.0002,
"loss": 0.8558,
"step": 2370
},
{
"epoch": 3.44,
"learning_rate": 0.0002,
"loss": 0.8698,
"step": 2380
},
{
"epoch": 3.46,
"learning_rate": 0.0002,
"loss": 0.951,
"step": 2390
},
{
"epoch": 3.47,
"learning_rate": 0.0002,
"loss": 0.8948,
"step": 2400
},
{
"epoch": 3.49,
"learning_rate": 0.0002,
"loss": 0.8737,
"step": 2410
},
{
"epoch": 3.5,
"learning_rate": 0.0002,
"loss": 0.8625,
"step": 2420
},
{
"epoch": 3.51,
"learning_rate": 0.0002,
"loss": 0.8975,
"step": 2430
},
{
"epoch": 3.53,
"learning_rate": 0.0002,
"loss": 0.9429,
"step": 2440
},
{
"epoch": 3.54,
"learning_rate": 0.0002,
"loss": 0.9116,
"step": 2450
},
{
"epoch": 3.56,
"learning_rate": 0.0002,
"loss": 0.8913,
"step": 2460
},
{
"epoch": 3.57,
"learning_rate": 0.0002,
"loss": 0.8636,
"step": 2470
},
{
"epoch": 3.59,
"learning_rate": 0.0002,
"loss": 0.8751,
"step": 2480
},
{
"epoch": 3.6,
"learning_rate": 0.0002,
"loss": 0.9381,
"step": 2490
},
{
"epoch": 3.62,
"learning_rate": 0.0002,
"loss": 0.9171,
"step": 2500
},
{
"epoch": 3.63,
"learning_rate": 0.0002,
"loss": 0.8879,
"step": 2510
},
{
"epoch": 3.64,
"learning_rate": 0.0002,
"loss": 0.8706,
"step": 2520
},
{
"epoch": 3.66,
"learning_rate": 0.0002,
"loss": 0.8806,
"step": 2530
},
{
"epoch": 3.67,
"learning_rate": 0.0002,
"loss": 0.9308,
"step": 2540
},
{
"epoch": 3.69,
"learning_rate": 0.0002,
"loss": 0.8945,
"step": 2550
},
{
"epoch": 3.7,
"learning_rate": 0.0002,
"loss": 0.8851,
"step": 2560
},
{
"epoch": 3.72,
"learning_rate": 0.0002,
"loss": 0.8523,
"step": 2570
},
{
"epoch": 3.73,
"learning_rate": 0.0002,
"loss": 0.8859,
"step": 2580
},
{
"epoch": 3.75,
"learning_rate": 0.0002,
"loss": 0.9284,
"step": 2590
},
{
"epoch": 3.76,
"learning_rate": 0.0002,
"loss": 0.898,
"step": 2600
},
{
"epoch": 3.77,
"learning_rate": 0.0002,
"loss": 0.8752,
"step": 2610
},
{
"epoch": 3.79,
"learning_rate": 0.0002,
"loss": 0.8548,
"step": 2620
},
{
"epoch": 3.8,
"learning_rate": 0.0002,
"loss": 0.8768,
"step": 2630
},
{
"epoch": 3.82,
"learning_rate": 0.0002,
"loss": 0.9454,
"step": 2640
},
{
"epoch": 3.83,
"learning_rate": 0.0002,
"loss": 0.8926,
"step": 2650
},
{
"epoch": 3.85,
"learning_rate": 0.0002,
"loss": 0.8801,
"step": 2660
},
{
"epoch": 3.86,
"learning_rate": 0.0002,
"loss": 0.8558,
"step": 2670
},
{
"epoch": 3.88,
"learning_rate": 0.0002,
"loss": 0.8597,
"step": 2680
},
{
"epoch": 3.89,
"learning_rate": 0.0002,
"loss": 0.9234,
"step": 2690
},
{
"epoch": 3.9,
"learning_rate": 0.0002,
"loss": 0.8973,
"step": 2700
},
{
"epoch": 3.92,
"learning_rate": 0.0002,
"loss": 0.8579,
"step": 2710
},
{
"epoch": 3.93,
"learning_rate": 0.0002,
"loss": 0.8538,
"step": 2720
},
{
"epoch": 3.95,
"learning_rate": 0.0002,
"loss": 0.8772,
"step": 2730
},
{
"epoch": 3.96,
"learning_rate": 0.0002,
"loss": 0.9341,
"step": 2740
},
{
"epoch": 3.98,
"learning_rate": 0.0002,
"loss": 0.8907,
"step": 2750
},
{
"epoch": 3.99,
"learning_rate": 0.0002,
"loss": 0.8652,
"step": 2760
},
{
"epoch": 4.01,
"learning_rate": 0.0002,
"loss": 0.8527,
"step": 2770
},
{
"epoch": 4.02,
"learning_rate": 0.0002,
"loss": 0.9176,
"step": 2780
},
{
"epoch": 4.03,
"learning_rate": 0.0002,
"loss": 0.8707,
"step": 2790
},
{
"epoch": 4.05,
"learning_rate": 0.0002,
"loss": 0.849,
"step": 2800
},
{
"epoch": 4.06,
"learning_rate": 0.0002,
"loss": 0.8208,
"step": 2810
},
{
"epoch": 4.08,
"learning_rate": 0.0002,
"loss": 0.7985,
"step": 2820
},
{
"epoch": 4.09,
"learning_rate": 0.0002,
"loss": 0.9227,
"step": 2830
},
{
"epoch": 4.11,
"learning_rate": 0.0002,
"loss": 0.8879,
"step": 2840
},
{
"epoch": 4.12,
"learning_rate": 0.0002,
"loss": 0.8378,
"step": 2850
},
{
"epoch": 4.14,
"learning_rate": 0.0002,
"loss": 0.8242,
"step": 2860
},
{
"epoch": 4.15,
"learning_rate": 0.0002,
"loss": 0.8257,
"step": 2870
},
{
"epoch": 4.16,
"learning_rate": 0.0002,
"loss": 0.9259,
"step": 2880
},
{
"epoch": 4.18,
"learning_rate": 0.0002,
"loss": 0.8598,
"step": 2890
},
{
"epoch": 4.19,
"learning_rate": 0.0002,
"loss": 0.8437,
"step": 2900
},
{
"epoch": 4.21,
"learning_rate": 0.0002,
"loss": 0.8156,
"step": 2910
},
{
"epoch": 4.22,
"learning_rate": 0.0002,
"loss": 0.8178,
"step": 2920
},
{
"epoch": 4.24,
"learning_rate": 0.0002,
"loss": 0.9162,
"step": 2930
},
{
"epoch": 4.25,
"learning_rate": 0.0002,
"loss": 0.8678,
"step": 2940
},
{
"epoch": 4.27,
"learning_rate": 0.0002,
"loss": 0.8499,
"step": 2950
},
{
"epoch": 4.28,
"learning_rate": 0.0002,
"loss": 0.8106,
"step": 2960
},
{
"epoch": 4.3,
"learning_rate": 0.0002,
"loss": 0.821,
"step": 2970
},
{
"epoch": 4.31,
"learning_rate": 0.0002,
"loss": 0.9278,
"step": 2980
},
{
"epoch": 4.32,
"learning_rate": 0.0002,
"loss": 0.865,
"step": 2990
},
{
"epoch": 4.34,
"learning_rate": 0.0002,
"loss": 0.8549,
"step": 3000
}
],
"max_steps": 5000,
"num_train_epochs": 8,
"total_flos": 6.44896481399808e+17,
"trial_name": null,
"trial_params": null
}