longt5_xl_gov_bp_15 / trainer_state.json
learn3r's picture
End of training
04936ff
{
"best_metric": 1.7125847339630127,
"best_model_checkpoint": "/exports/eddie/scratch/s1970716/models/summarization/longt5_xl_gov_bp_15/checkpoint-136",
"epoch": 4.985679917516325,
"eval_steps": 500,
"global_step": 680,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.001,
"loss": 0.1935,
"step": 2
},
{
"epoch": 0.03,
"learning_rate": 0.001,
"loss": 0.2072,
"step": 4
},
{
"epoch": 0.04,
"learning_rate": 0.001,
"loss": 0.2097,
"step": 6
},
{
"epoch": 0.06,
"learning_rate": 0.001,
"loss": 0.2016,
"step": 8
},
{
"epoch": 0.07,
"learning_rate": 0.001,
"loss": 0.2148,
"step": 10
},
{
"epoch": 0.09,
"learning_rate": 0.001,
"loss": 0.2136,
"step": 12
},
{
"epoch": 0.1,
"learning_rate": 0.001,
"loss": 0.2247,
"step": 14
},
{
"epoch": 0.12,
"learning_rate": 0.001,
"loss": 0.2131,
"step": 16
},
{
"epoch": 0.13,
"learning_rate": 0.001,
"loss": 0.2157,
"step": 18
},
{
"epoch": 0.15,
"learning_rate": 0.001,
"loss": 0.2204,
"step": 20
},
{
"epoch": 0.16,
"learning_rate": 0.001,
"loss": 0.2181,
"step": 22
},
{
"epoch": 0.18,
"learning_rate": 0.001,
"loss": 0.1961,
"step": 24
},
{
"epoch": 0.19,
"learning_rate": 0.001,
"loss": 0.1996,
"step": 26
},
{
"epoch": 0.21,
"learning_rate": 0.001,
"loss": 0.218,
"step": 28
},
{
"epoch": 0.22,
"learning_rate": 0.001,
"loss": 0.217,
"step": 30
},
{
"epoch": 0.23,
"learning_rate": 0.001,
"loss": 0.2044,
"step": 32
},
{
"epoch": 0.25,
"learning_rate": 0.001,
"loss": 0.2035,
"step": 34
},
{
"epoch": 0.26,
"learning_rate": 0.001,
"loss": 0.2145,
"step": 36
},
{
"epoch": 0.28,
"learning_rate": 0.001,
"loss": 0.2148,
"step": 38
},
{
"epoch": 0.29,
"learning_rate": 0.001,
"loss": 0.2195,
"step": 40
},
{
"epoch": 0.31,
"learning_rate": 0.001,
"loss": 0.2347,
"step": 42
},
{
"epoch": 0.32,
"learning_rate": 0.001,
"loss": 0.2083,
"step": 44
},
{
"epoch": 0.34,
"learning_rate": 0.001,
"loss": 0.2264,
"step": 46
},
{
"epoch": 0.35,
"learning_rate": 0.001,
"loss": 0.197,
"step": 48
},
{
"epoch": 0.37,
"learning_rate": 0.001,
"loss": 0.2207,
"step": 50
},
{
"epoch": 0.38,
"learning_rate": 0.001,
"loss": 0.2241,
"step": 52
},
{
"epoch": 0.4,
"learning_rate": 0.001,
"loss": 0.1997,
"step": 54
},
{
"epoch": 0.41,
"learning_rate": 0.001,
"loss": 0.2641,
"step": 56
},
{
"epoch": 0.43,
"learning_rate": 0.001,
"loss": 0.1875,
"step": 58
},
{
"epoch": 0.44,
"learning_rate": 0.001,
"loss": 0.1974,
"step": 60
},
{
"epoch": 0.45,
"learning_rate": 0.001,
"loss": 0.2131,
"step": 62
},
{
"epoch": 0.47,
"learning_rate": 0.001,
"loss": 0.2072,
"step": 64
},
{
"epoch": 0.48,
"learning_rate": 0.001,
"loss": 0.2014,
"step": 66
},
{
"epoch": 0.5,
"learning_rate": 0.001,
"loss": 0.1985,
"step": 68
},
{
"epoch": 0.51,
"learning_rate": 0.001,
"loss": 0.2064,
"step": 70
},
{
"epoch": 0.53,
"learning_rate": 0.001,
"loss": 0.2072,
"step": 72
},
{
"epoch": 0.54,
"learning_rate": 0.001,
"loss": 0.2162,
"step": 74
},
{
"epoch": 0.56,
"learning_rate": 0.001,
"loss": 0.2205,
"step": 76
},
{
"epoch": 0.57,
"learning_rate": 0.001,
"loss": 0.2205,
"step": 78
},
{
"epoch": 0.59,
"learning_rate": 0.001,
"loss": 0.2001,
"step": 80
},
{
"epoch": 0.6,
"learning_rate": 0.001,
"loss": 0.2086,
"step": 82
},
{
"epoch": 0.62,
"learning_rate": 0.001,
"loss": 0.2142,
"step": 84
},
{
"epoch": 0.63,
"learning_rate": 0.001,
"loss": 0.2012,
"step": 86
},
{
"epoch": 0.65,
"learning_rate": 0.001,
"loss": 0.1926,
"step": 88
},
{
"epoch": 0.66,
"learning_rate": 0.001,
"loss": 0.2085,
"step": 90
},
{
"epoch": 0.67,
"learning_rate": 0.001,
"loss": 0.2074,
"step": 92
},
{
"epoch": 0.69,
"learning_rate": 0.001,
"loss": 0.2134,
"step": 94
},
{
"epoch": 0.7,
"learning_rate": 0.001,
"loss": 0.1889,
"step": 96
},
{
"epoch": 0.72,
"learning_rate": 0.001,
"loss": 0.1875,
"step": 98
},
{
"epoch": 0.73,
"learning_rate": 0.001,
"loss": 0.2052,
"step": 100
},
{
"epoch": 0.75,
"learning_rate": 0.001,
"loss": 0.2122,
"step": 102
},
{
"epoch": 0.76,
"learning_rate": 0.001,
"loss": 0.2106,
"step": 104
},
{
"epoch": 0.78,
"learning_rate": 0.001,
"loss": 0.1914,
"step": 106
},
{
"epoch": 0.79,
"learning_rate": 0.001,
"loss": 0.2059,
"step": 108
},
{
"epoch": 0.81,
"learning_rate": 0.001,
"loss": 0.2391,
"step": 110
},
{
"epoch": 0.82,
"learning_rate": 0.001,
"loss": 0.297,
"step": 112
},
{
"epoch": 0.84,
"learning_rate": 0.001,
"loss": 0.2019,
"step": 114
},
{
"epoch": 0.85,
"learning_rate": 0.001,
"loss": 0.2156,
"step": 116
},
{
"epoch": 0.87,
"learning_rate": 0.001,
"loss": 0.1945,
"step": 118
},
{
"epoch": 0.88,
"learning_rate": 0.001,
"loss": 0.2096,
"step": 120
},
{
"epoch": 0.89,
"learning_rate": 0.001,
"loss": 0.2158,
"step": 122
},
{
"epoch": 0.91,
"learning_rate": 0.001,
"loss": 0.2265,
"step": 124
},
{
"epoch": 0.92,
"learning_rate": 0.001,
"loss": 0.2038,
"step": 126
},
{
"epoch": 0.94,
"learning_rate": 0.001,
"loss": 0.2048,
"step": 128
},
{
"epoch": 0.95,
"learning_rate": 0.001,
"loss": 0.2135,
"step": 130
},
{
"epoch": 0.97,
"learning_rate": 0.001,
"loss": 0.1989,
"step": 132
},
{
"epoch": 0.98,
"learning_rate": 0.001,
"loss": 0.2039,
"step": 134
},
{
"epoch": 1.0,
"learning_rate": 0.001,
"loss": 0.2051,
"step": 136
},
{
"epoch": 1.0,
"eval_loss": 1.7125847339630127,
"eval_runtime": 354.3186,
"eval_samples_per_second": 2.743,
"eval_steps_per_second": 1.372,
"step": 136
},
{
"epoch": 1.01,
"learning_rate": 0.001,
"loss": 0.1717,
"step": 138
},
{
"epoch": 1.03,
"learning_rate": 0.001,
"loss": 0.1722,
"step": 140
},
{
"epoch": 1.04,
"learning_rate": 0.001,
"loss": 0.1431,
"step": 142
},
{
"epoch": 1.06,
"learning_rate": 0.001,
"loss": 0.1416,
"step": 144
},
{
"epoch": 1.07,
"learning_rate": 0.001,
"loss": 0.1589,
"step": 146
},
{
"epoch": 1.09,
"learning_rate": 0.001,
"loss": 0.1494,
"step": 148
},
{
"epoch": 1.1,
"learning_rate": 0.001,
"loss": 0.1536,
"step": 150
},
{
"epoch": 1.11,
"learning_rate": 0.001,
"loss": 0.1567,
"step": 152
},
{
"epoch": 1.13,
"learning_rate": 0.001,
"loss": 0.1583,
"step": 154
},
{
"epoch": 1.14,
"learning_rate": 0.001,
"loss": 0.1631,
"step": 156
},
{
"epoch": 1.16,
"learning_rate": 0.001,
"loss": 0.1567,
"step": 158
},
{
"epoch": 1.17,
"learning_rate": 0.001,
"loss": 0.1541,
"step": 160
},
{
"epoch": 1.19,
"learning_rate": 0.001,
"loss": 0.1592,
"step": 162
},
{
"epoch": 1.2,
"learning_rate": 0.001,
"loss": 0.1612,
"step": 164
},
{
"epoch": 1.22,
"learning_rate": 0.001,
"loss": 0.1683,
"step": 166
},
{
"epoch": 1.23,
"learning_rate": 0.001,
"loss": 0.1575,
"step": 168
},
{
"epoch": 1.25,
"learning_rate": 0.001,
"loss": 0.1564,
"step": 170
},
{
"epoch": 1.26,
"learning_rate": 0.001,
"loss": 0.1624,
"step": 172
},
{
"epoch": 1.28,
"learning_rate": 0.001,
"loss": 0.1662,
"step": 174
},
{
"epoch": 1.29,
"learning_rate": 0.001,
"loss": 0.1549,
"step": 176
},
{
"epoch": 1.31,
"learning_rate": 0.001,
"loss": 0.1519,
"step": 178
},
{
"epoch": 1.32,
"learning_rate": 0.001,
"loss": 0.1587,
"step": 180
},
{
"epoch": 1.33,
"learning_rate": 0.001,
"loss": 0.1622,
"step": 182
},
{
"epoch": 1.35,
"learning_rate": 0.001,
"loss": 0.1697,
"step": 184
},
{
"epoch": 1.36,
"learning_rate": 0.001,
"loss": 0.1581,
"step": 186
},
{
"epoch": 1.38,
"learning_rate": 0.001,
"loss": 0.162,
"step": 188
},
{
"epoch": 1.39,
"learning_rate": 0.001,
"loss": 0.1593,
"step": 190
},
{
"epoch": 1.41,
"learning_rate": 0.001,
"loss": 0.1753,
"step": 192
},
{
"epoch": 1.42,
"learning_rate": 0.001,
"loss": 0.1586,
"step": 194
},
{
"epoch": 1.44,
"learning_rate": 0.001,
"loss": 0.1558,
"step": 196
},
{
"epoch": 1.45,
"learning_rate": 0.001,
"loss": 0.1432,
"step": 198
},
{
"epoch": 1.47,
"learning_rate": 0.001,
"loss": 0.1625,
"step": 200
},
{
"epoch": 1.48,
"learning_rate": 0.001,
"loss": 0.1589,
"step": 202
},
{
"epoch": 1.5,
"learning_rate": 0.001,
"loss": 0.1588,
"step": 204
},
{
"epoch": 1.51,
"learning_rate": 0.001,
"loss": 0.1616,
"step": 206
},
{
"epoch": 1.53,
"learning_rate": 0.001,
"loss": 0.188,
"step": 208
},
{
"epoch": 1.54,
"learning_rate": 0.001,
"loss": 0.152,
"step": 210
},
{
"epoch": 1.55,
"learning_rate": 0.001,
"loss": 0.1489,
"step": 212
},
{
"epoch": 1.57,
"learning_rate": 0.001,
"loss": 0.1553,
"step": 214
},
{
"epoch": 1.58,
"learning_rate": 0.001,
"loss": 0.1607,
"step": 216
},
{
"epoch": 1.6,
"learning_rate": 0.001,
"loss": 0.169,
"step": 218
},
{
"epoch": 1.61,
"learning_rate": 0.001,
"loss": 0.1749,
"step": 220
},
{
"epoch": 1.63,
"learning_rate": 0.001,
"loss": 0.1723,
"step": 222
},
{
"epoch": 1.64,
"learning_rate": 0.001,
"loss": 0.1662,
"step": 224
},
{
"epoch": 1.66,
"learning_rate": 0.001,
"loss": 0.1672,
"step": 226
},
{
"epoch": 1.67,
"learning_rate": 0.001,
"loss": 0.1756,
"step": 228
},
{
"epoch": 1.69,
"learning_rate": 0.001,
"loss": 0.1626,
"step": 230
},
{
"epoch": 1.7,
"learning_rate": 0.001,
"loss": 0.1631,
"step": 232
},
{
"epoch": 1.72,
"learning_rate": 0.001,
"loss": 0.1679,
"step": 234
},
{
"epoch": 1.73,
"learning_rate": 0.001,
"loss": 0.1639,
"step": 236
},
{
"epoch": 1.74,
"learning_rate": 0.001,
"loss": 0.1532,
"step": 238
},
{
"epoch": 1.76,
"learning_rate": 0.001,
"loss": 0.1549,
"step": 240
},
{
"epoch": 1.77,
"learning_rate": 0.001,
"loss": 0.1689,
"step": 242
},
{
"epoch": 1.79,
"learning_rate": 0.001,
"loss": 0.1687,
"step": 244
},
{
"epoch": 1.8,
"learning_rate": 0.001,
"loss": 0.1645,
"step": 246
},
{
"epoch": 1.82,
"learning_rate": 0.001,
"loss": 0.1733,
"step": 248
},
{
"epoch": 1.83,
"learning_rate": 0.001,
"loss": 0.1625,
"step": 250
},
{
"epoch": 1.85,
"learning_rate": 0.001,
"loss": 0.1549,
"step": 252
},
{
"epoch": 1.86,
"learning_rate": 0.001,
"loss": 0.1617,
"step": 254
},
{
"epoch": 1.88,
"learning_rate": 0.001,
"loss": 0.1596,
"step": 256
},
{
"epoch": 1.89,
"learning_rate": 0.001,
"loss": 0.1623,
"step": 258
},
{
"epoch": 1.91,
"learning_rate": 0.001,
"loss": 0.1689,
"step": 260
},
{
"epoch": 1.92,
"learning_rate": 0.001,
"loss": 0.1577,
"step": 262
},
{
"epoch": 1.94,
"learning_rate": 0.001,
"loss": 0.1512,
"step": 264
},
{
"epoch": 1.95,
"learning_rate": 0.001,
"loss": 0.1663,
"step": 266
},
{
"epoch": 1.96,
"learning_rate": 0.001,
"loss": 0.1556,
"step": 268
},
{
"epoch": 1.98,
"learning_rate": 0.001,
"loss": 0.1615,
"step": 270
},
{
"epoch": 1.99,
"learning_rate": 0.001,
"loss": 0.1732,
"step": 272
},
{
"epoch": 1.99,
"eval_loss": 1.8856897354125977,
"eval_runtime": 354.3228,
"eval_samples_per_second": 2.743,
"eval_steps_per_second": 1.372,
"step": 272
},
{
"epoch": 2.01,
"learning_rate": 0.001,
"loss": 0.1571,
"step": 274
},
{
"epoch": 2.02,
"learning_rate": 0.001,
"loss": 0.117,
"step": 276
},
{
"epoch": 2.04,
"learning_rate": 0.001,
"loss": 0.1197,
"step": 278
},
{
"epoch": 2.05,
"learning_rate": 0.001,
"loss": 0.1262,
"step": 280
},
{
"epoch": 2.07,
"learning_rate": 0.001,
"loss": 0.1274,
"step": 282
},
{
"epoch": 2.08,
"learning_rate": 0.001,
"loss": 0.1226,
"step": 284
},
{
"epoch": 2.1,
"learning_rate": 0.001,
"loss": 0.1207,
"step": 286
},
{
"epoch": 2.11,
"learning_rate": 0.001,
"loss": 0.1218,
"step": 288
},
{
"epoch": 2.13,
"learning_rate": 0.001,
"loss": 0.1203,
"step": 290
},
{
"epoch": 2.14,
"learning_rate": 0.001,
"loss": 0.1253,
"step": 292
},
{
"epoch": 2.16,
"learning_rate": 0.001,
"loss": 0.1635,
"step": 294
},
{
"epoch": 2.17,
"learning_rate": 0.001,
"loss": 0.1241,
"step": 296
},
{
"epoch": 2.18,
"learning_rate": 0.001,
"loss": 0.1257,
"step": 298
},
{
"epoch": 2.2,
"learning_rate": 0.001,
"loss": 0.1215,
"step": 300
},
{
"epoch": 2.21,
"learning_rate": 0.001,
"loss": 0.1229,
"step": 302
},
{
"epoch": 2.23,
"learning_rate": 0.001,
"loss": 0.1224,
"step": 304
},
{
"epoch": 2.24,
"learning_rate": 0.001,
"loss": 0.1223,
"step": 306
},
{
"epoch": 2.26,
"learning_rate": 0.001,
"loss": 0.1214,
"step": 308
},
{
"epoch": 2.27,
"learning_rate": 0.001,
"loss": 0.1255,
"step": 310
},
{
"epoch": 2.29,
"learning_rate": 0.001,
"loss": 0.1265,
"step": 312
},
{
"epoch": 2.3,
"learning_rate": 0.001,
"loss": 0.1344,
"step": 314
},
{
"epoch": 2.32,
"learning_rate": 0.001,
"loss": 0.1316,
"step": 316
},
{
"epoch": 2.33,
"learning_rate": 0.001,
"loss": 0.1356,
"step": 318
},
{
"epoch": 2.35,
"learning_rate": 0.001,
"loss": 0.1403,
"step": 320
},
{
"epoch": 2.36,
"learning_rate": 0.001,
"loss": 0.1411,
"step": 322
},
{
"epoch": 2.38,
"learning_rate": 0.001,
"loss": 0.1294,
"step": 324
},
{
"epoch": 2.39,
"learning_rate": 0.001,
"loss": 0.1306,
"step": 326
},
{
"epoch": 2.4,
"learning_rate": 0.001,
"loss": 0.1288,
"step": 328
},
{
"epoch": 2.42,
"learning_rate": 0.001,
"loss": 0.1198,
"step": 330
},
{
"epoch": 2.43,
"learning_rate": 0.001,
"loss": 0.1341,
"step": 332
},
{
"epoch": 2.45,
"learning_rate": 0.001,
"loss": 0.1369,
"step": 334
},
{
"epoch": 2.46,
"learning_rate": 0.001,
"loss": 0.1242,
"step": 336
},
{
"epoch": 2.48,
"learning_rate": 0.001,
"loss": 0.1249,
"step": 338
},
{
"epoch": 2.49,
"learning_rate": 0.001,
"loss": 0.1975,
"step": 340
},
{
"epoch": 2.51,
"learning_rate": 0.001,
"loss": 0.1143,
"step": 342
},
{
"epoch": 2.52,
"learning_rate": 0.001,
"loss": 0.1316,
"step": 344
},
{
"epoch": 2.54,
"learning_rate": 0.001,
"loss": 0.1282,
"step": 346
},
{
"epoch": 2.55,
"learning_rate": 0.001,
"loss": 0.1294,
"step": 348
},
{
"epoch": 2.57,
"learning_rate": 0.001,
"loss": 0.1244,
"step": 350
},
{
"epoch": 2.58,
"learning_rate": 0.001,
"loss": 0.1284,
"step": 352
},
{
"epoch": 2.6,
"learning_rate": 0.001,
"loss": 0.1301,
"step": 354
},
{
"epoch": 2.61,
"learning_rate": 0.001,
"loss": 0.139,
"step": 356
},
{
"epoch": 2.62,
"learning_rate": 0.001,
"loss": 0.1325,
"step": 358
},
{
"epoch": 2.64,
"learning_rate": 0.001,
"loss": 0.1301,
"step": 360
},
{
"epoch": 2.65,
"learning_rate": 0.001,
"loss": 0.1365,
"step": 362
},
{
"epoch": 2.67,
"learning_rate": 0.001,
"loss": 0.1253,
"step": 364
},
{
"epoch": 2.68,
"learning_rate": 0.001,
"loss": 0.1311,
"step": 366
},
{
"epoch": 2.7,
"learning_rate": 0.001,
"loss": 0.1253,
"step": 368
},
{
"epoch": 2.71,
"learning_rate": 0.001,
"loss": 0.1267,
"step": 370
},
{
"epoch": 2.73,
"learning_rate": 0.001,
"loss": 0.1338,
"step": 372
},
{
"epoch": 2.74,
"learning_rate": 0.001,
"loss": 0.1404,
"step": 374
},
{
"epoch": 2.76,
"learning_rate": 0.001,
"loss": 0.1397,
"step": 376
},
{
"epoch": 2.77,
"learning_rate": 0.001,
"loss": 0.1938,
"step": 378
},
{
"epoch": 2.79,
"learning_rate": 0.001,
"loss": 0.1278,
"step": 380
},
{
"epoch": 2.8,
"learning_rate": 0.001,
"loss": 0.1313,
"step": 382
},
{
"epoch": 2.82,
"learning_rate": 0.001,
"loss": 0.1345,
"step": 384
},
{
"epoch": 2.83,
"learning_rate": 0.001,
"loss": 0.1421,
"step": 386
},
{
"epoch": 2.84,
"learning_rate": 0.001,
"loss": 0.1352,
"step": 388
},
{
"epoch": 2.86,
"learning_rate": 0.001,
"loss": 0.1417,
"step": 390
},
{
"epoch": 2.87,
"learning_rate": 0.001,
"loss": 0.1294,
"step": 392
},
{
"epoch": 2.89,
"learning_rate": 0.001,
"loss": 0.1292,
"step": 394
},
{
"epoch": 2.9,
"learning_rate": 0.001,
"loss": 0.2719,
"step": 396
},
{
"epoch": 2.92,
"learning_rate": 0.001,
"loss": 0.2977,
"step": 398
},
{
"epoch": 2.93,
"learning_rate": 0.001,
"loss": 0.5512,
"step": 400
},
{
"epoch": 2.95,
"learning_rate": 0.001,
"loss": 0.3507,
"step": 402
},
{
"epoch": 2.96,
"learning_rate": 0.001,
"loss": 0.177,
"step": 404
},
{
"epoch": 2.98,
"learning_rate": 0.001,
"loss": 0.1911,
"step": 406
},
{
"epoch": 2.99,
"learning_rate": 0.001,
"loss": 0.1777,
"step": 408
},
{
"epoch": 3.0,
"eval_loss": 1.9036095142364502,
"eval_runtime": 354.3775,
"eval_samples_per_second": 2.743,
"eval_steps_per_second": 1.371,
"step": 409
},
{
"epoch": 3.01,
"learning_rate": 0.001,
"loss": 0.1494,
"step": 410
},
{
"epoch": 3.02,
"learning_rate": 0.001,
"loss": 0.1955,
"step": 412
},
{
"epoch": 3.04,
"learning_rate": 0.001,
"loss": 0.3844,
"step": 414
},
{
"epoch": 3.05,
"learning_rate": 0.001,
"loss": 0.2272,
"step": 416
},
{
"epoch": 3.06,
"learning_rate": 0.001,
"loss": 0.3148,
"step": 418
},
{
"epoch": 3.08,
"learning_rate": 0.001,
"loss": 0.7032,
"step": 420
},
{
"epoch": 3.09,
"learning_rate": 0.001,
"loss": 0.5363,
"step": 422
},
{
"epoch": 3.11,
"learning_rate": 0.001,
"loss": 0.2559,
"step": 424
},
{
"epoch": 3.12,
"learning_rate": 0.001,
"loss": 0.2382,
"step": 426
},
{
"epoch": 3.14,
"learning_rate": 0.001,
"loss": 0.2869,
"step": 428
},
{
"epoch": 3.15,
"learning_rate": 0.001,
"loss": 0.2226,
"step": 430
},
{
"epoch": 3.17,
"learning_rate": 0.001,
"loss": 0.2641,
"step": 432
},
{
"epoch": 3.18,
"learning_rate": 0.001,
"loss": 0.1683,
"step": 434
},
{
"epoch": 3.2,
"learning_rate": 0.001,
"loss": 0.24,
"step": 436
},
{
"epoch": 3.21,
"learning_rate": 0.001,
"loss": 0.2043,
"step": 438
},
{
"epoch": 3.23,
"learning_rate": 0.001,
"loss": 0.1783,
"step": 440
},
{
"epoch": 3.24,
"learning_rate": 0.001,
"loss": 0.2701,
"step": 442
},
{
"epoch": 3.26,
"learning_rate": 0.001,
"loss": 0.3012,
"step": 444
},
{
"epoch": 3.27,
"learning_rate": 0.001,
"loss": 0.1771,
"step": 446
},
{
"epoch": 3.28,
"learning_rate": 0.001,
"loss": 0.1712,
"step": 448
},
{
"epoch": 3.3,
"learning_rate": 0.001,
"loss": 0.1225,
"step": 450
},
{
"epoch": 3.31,
"learning_rate": 0.001,
"loss": 0.2051,
"step": 452
},
{
"epoch": 3.33,
"learning_rate": 0.001,
"loss": 0.4229,
"step": 454
},
{
"epoch": 3.34,
"learning_rate": 0.001,
"loss": 0.4659,
"step": 456
},
{
"epoch": 3.36,
"learning_rate": 0.001,
"loss": 0.6107,
"step": 458
},
{
"epoch": 3.37,
"learning_rate": 0.001,
"loss": 0.4208,
"step": 460
},
{
"epoch": 3.39,
"learning_rate": 0.001,
"loss": 0.181,
"step": 462
},
{
"epoch": 3.4,
"learning_rate": 0.001,
"loss": 0.1997,
"step": 464
},
{
"epoch": 3.42,
"learning_rate": 0.001,
"loss": 0.1514,
"step": 466
},
{
"epoch": 3.43,
"learning_rate": 0.001,
"loss": 0.171,
"step": 468
},
{
"epoch": 3.45,
"learning_rate": 0.001,
"loss": 0.7932,
"step": 470
},
{
"epoch": 3.46,
"learning_rate": 0.001,
"loss": 1.6152,
"step": 472
},
{
"epoch": 3.48,
"learning_rate": 0.001,
"loss": 1.63,
"step": 474
},
{
"epoch": 3.49,
"learning_rate": 0.001,
"loss": 0.5535,
"step": 476
},
{
"epoch": 3.5,
"learning_rate": 0.001,
"loss": 0.8349,
"step": 478
},
{
"epoch": 3.52,
"learning_rate": 0.001,
"loss": 0.8509,
"step": 480
},
{
"epoch": 3.53,
"learning_rate": 0.001,
"loss": 0.3377,
"step": 482
},
{
"epoch": 3.55,
"learning_rate": 0.001,
"loss": 0.3293,
"step": 484
},
{
"epoch": 3.56,
"learning_rate": 0.001,
"loss": 0.459,
"step": 486
},
{
"epoch": 3.58,
"learning_rate": 0.001,
"loss": 0.3061,
"step": 488
},
{
"epoch": 3.59,
"learning_rate": 0.001,
"loss": 0.2499,
"step": 490
},
{
"epoch": 3.61,
"learning_rate": 0.001,
"loss": 0.1416,
"step": 492
},
{
"epoch": 3.62,
"learning_rate": 0.001,
"loss": 0.1306,
"step": 494
},
{
"epoch": 3.64,
"learning_rate": 0.001,
"loss": 0.1394,
"step": 496
},
{
"epoch": 3.65,
"learning_rate": 0.001,
"loss": 0.1228,
"step": 498
},
{
"epoch": 3.67,
"learning_rate": 0.001,
"loss": 0.1151,
"step": 500
},
{
"epoch": 3.68,
"learning_rate": 0.001,
"loss": 0.1038,
"step": 502
},
{
"epoch": 3.7,
"learning_rate": 0.001,
"loss": 0.1879,
"step": 504
},
{
"epoch": 3.71,
"learning_rate": 0.001,
"loss": 0.2733,
"step": 506
},
{
"epoch": 3.72,
"learning_rate": 0.001,
"loss": 0.2079,
"step": 508
},
{
"epoch": 3.74,
"learning_rate": 0.001,
"loss": 0.1846,
"step": 510
},
{
"epoch": 3.75,
"learning_rate": 0.001,
"loss": 0.2592,
"step": 512
},
{
"epoch": 3.77,
"learning_rate": 0.001,
"loss": 0.2491,
"step": 514
},
{
"epoch": 3.78,
"learning_rate": 0.001,
"loss": 0.1779,
"step": 516
},
{
"epoch": 3.8,
"learning_rate": 0.001,
"loss": 0.1322,
"step": 518
},
{
"epoch": 3.81,
"learning_rate": 0.001,
"loss": 0.1184,
"step": 520
},
{
"epoch": 3.83,
"learning_rate": 0.001,
"loss": 0.1033,
"step": 522
},
{
"epoch": 3.84,
"learning_rate": 0.001,
"loss": 0.1199,
"step": 524
},
{
"epoch": 3.86,
"learning_rate": 0.001,
"loss": 0.1183,
"step": 526
},
{
"epoch": 3.87,
"learning_rate": 0.001,
"loss": 0.1116,
"step": 528
},
{
"epoch": 3.89,
"learning_rate": 0.001,
"loss": 0.1206,
"step": 530
},
{
"epoch": 3.9,
"learning_rate": 0.001,
"loss": 0.1044,
"step": 532
},
{
"epoch": 3.92,
"learning_rate": 0.001,
"loss": 0.0913,
"step": 534
},
{
"epoch": 3.93,
"learning_rate": 0.001,
"loss": 0.1104,
"step": 536
},
{
"epoch": 3.94,
"learning_rate": 0.001,
"loss": 0.1087,
"step": 538
},
{
"epoch": 3.96,
"learning_rate": 0.001,
"loss": 0.1048,
"step": 540
},
{
"epoch": 3.97,
"learning_rate": 0.001,
"loss": 0.1219,
"step": 542
},
{
"epoch": 3.99,
"learning_rate": 0.001,
"loss": 0.1122,
"step": 544
},
{
"epoch": 4.0,
"eval_loss": 1.9537909030914307,
"eval_runtime": 354.3096,
"eval_samples_per_second": 2.743,
"eval_steps_per_second": 1.372,
"step": 545
},
{
"epoch": 4.0,
"learning_rate": 0.001,
"loss": 0.1096,
"step": 546
},
{
"epoch": 4.02,
"learning_rate": 0.001,
"loss": 0.1053,
"step": 548
},
{
"epoch": 4.03,
"learning_rate": 0.001,
"loss": 0.1069,
"step": 550
},
{
"epoch": 4.05,
"learning_rate": 0.001,
"loss": 0.1031,
"step": 552
},
{
"epoch": 4.06,
"learning_rate": 0.001,
"loss": 0.0946,
"step": 554
},
{
"epoch": 4.08,
"learning_rate": 0.001,
"loss": 0.1018,
"step": 556
},
{
"epoch": 4.09,
"learning_rate": 0.001,
"loss": 0.0983,
"step": 558
},
{
"epoch": 4.11,
"learning_rate": 0.001,
"loss": 0.0995,
"step": 560
},
{
"epoch": 4.12,
"learning_rate": 0.001,
"loss": 0.1077,
"step": 562
},
{
"epoch": 4.14,
"learning_rate": 0.001,
"loss": 0.1014,
"step": 564
},
{
"epoch": 4.15,
"learning_rate": 0.001,
"loss": 0.1062,
"step": 566
},
{
"epoch": 4.16,
"learning_rate": 0.001,
"loss": 0.1127,
"step": 568
},
{
"epoch": 4.18,
"learning_rate": 0.001,
"loss": 0.1089,
"step": 570
},
{
"epoch": 4.19,
"learning_rate": 0.001,
"loss": 0.11,
"step": 572
},
{
"epoch": 4.21,
"learning_rate": 0.001,
"loss": 0.1049,
"step": 574
},
{
"epoch": 4.22,
"learning_rate": 0.001,
"loss": 0.1001,
"step": 576
},
{
"epoch": 4.24,
"learning_rate": 0.001,
"loss": 0.1066,
"step": 578
},
{
"epoch": 4.25,
"learning_rate": 0.001,
"loss": 0.1019,
"step": 580
},
{
"epoch": 4.27,
"learning_rate": 0.001,
"loss": 0.1003,
"step": 582
},
{
"epoch": 4.28,
"learning_rate": 0.001,
"loss": 0.1046,
"step": 584
},
{
"epoch": 4.3,
"learning_rate": 0.001,
"loss": 0.1022,
"step": 586
},
{
"epoch": 4.31,
"learning_rate": 0.001,
"loss": 0.1111,
"step": 588
},
{
"epoch": 4.33,
"learning_rate": 0.001,
"loss": 0.1093,
"step": 590
},
{
"epoch": 4.34,
"learning_rate": 0.001,
"loss": 0.1072,
"step": 592
},
{
"epoch": 4.36,
"learning_rate": 0.001,
"loss": 0.1097,
"step": 594
},
{
"epoch": 4.37,
"learning_rate": 0.001,
"loss": 0.1031,
"step": 596
},
{
"epoch": 4.38,
"learning_rate": 0.001,
"loss": 0.1074,
"step": 598
},
{
"epoch": 4.4,
"learning_rate": 0.001,
"loss": 0.1058,
"step": 600
},
{
"epoch": 4.41,
"learning_rate": 0.001,
"loss": 0.1039,
"step": 602
},
{
"epoch": 4.43,
"learning_rate": 0.001,
"loss": 0.0961,
"step": 604
},
{
"epoch": 4.44,
"learning_rate": 0.001,
"loss": 0.1057,
"step": 606
},
{
"epoch": 4.46,
"learning_rate": 0.001,
"loss": 0.1088,
"step": 608
},
{
"epoch": 4.47,
"learning_rate": 0.001,
"loss": 0.1087,
"step": 610
},
{
"epoch": 4.49,
"learning_rate": 0.001,
"loss": 0.1067,
"step": 612
},
{
"epoch": 4.5,
"learning_rate": 0.001,
"loss": 0.0966,
"step": 614
},
{
"epoch": 4.52,
"learning_rate": 0.001,
"loss": 0.1017,
"step": 616
},
{
"epoch": 4.53,
"learning_rate": 0.001,
"loss": 0.1087,
"step": 618
},
{
"epoch": 4.55,
"learning_rate": 0.001,
"loss": 0.1025,
"step": 620
},
{
"epoch": 4.56,
"learning_rate": 0.001,
"loss": 0.1061,
"step": 622
},
{
"epoch": 4.58,
"learning_rate": 0.001,
"loss": 0.1103,
"step": 624
},
{
"epoch": 4.59,
"learning_rate": 0.001,
"loss": 0.1056,
"step": 626
},
{
"epoch": 4.6,
"learning_rate": 0.001,
"loss": 0.1105,
"step": 628
},
{
"epoch": 4.62,
"learning_rate": 0.001,
"loss": 0.1114,
"step": 630
},
{
"epoch": 4.63,
"learning_rate": 0.001,
"loss": 0.1066,
"step": 632
},
{
"epoch": 4.65,
"learning_rate": 0.001,
"loss": 0.1053,
"step": 634
},
{
"epoch": 4.66,
"learning_rate": 0.001,
"loss": 0.1045,
"step": 636
},
{
"epoch": 4.68,
"learning_rate": 0.001,
"loss": 0.1089,
"step": 638
},
{
"epoch": 4.69,
"learning_rate": 0.001,
"loss": 0.1126,
"step": 640
},
{
"epoch": 4.71,
"learning_rate": 0.001,
"loss": 0.1107,
"step": 642
},
{
"epoch": 4.72,
"learning_rate": 0.001,
"loss": 0.1158,
"step": 644
},
{
"epoch": 4.74,
"learning_rate": 0.001,
"loss": 0.1194,
"step": 646
},
{
"epoch": 4.75,
"learning_rate": 0.001,
"loss": 0.1074,
"step": 648
},
{
"epoch": 4.77,
"learning_rate": 0.001,
"loss": 0.1126,
"step": 650
},
{
"epoch": 4.78,
"learning_rate": 0.001,
"loss": 0.107,
"step": 652
},
{
"epoch": 4.8,
"learning_rate": 0.001,
"loss": 0.1097,
"step": 654
},
{
"epoch": 4.81,
"learning_rate": 0.001,
"loss": 0.105,
"step": 656
},
{
"epoch": 4.82,
"learning_rate": 0.001,
"loss": 0.113,
"step": 658
},
{
"epoch": 4.84,
"learning_rate": 0.001,
"loss": 0.1082,
"step": 660
},
{
"epoch": 4.85,
"learning_rate": 0.001,
"loss": 0.1075,
"step": 662
},
{
"epoch": 4.87,
"learning_rate": 0.001,
"loss": 0.0987,
"step": 664
},
{
"epoch": 4.88,
"learning_rate": 0.001,
"loss": 0.097,
"step": 666
},
{
"epoch": 4.9,
"learning_rate": 0.001,
"loss": 0.106,
"step": 668
},
{
"epoch": 4.91,
"learning_rate": 0.001,
"loss": 0.1167,
"step": 670
},
{
"epoch": 4.93,
"learning_rate": 0.001,
"loss": 0.119,
"step": 672
},
{
"epoch": 4.94,
"learning_rate": 0.001,
"loss": 0.1125,
"step": 674
},
{
"epoch": 4.96,
"learning_rate": 0.001,
"loss": 0.1112,
"step": 676
},
{
"epoch": 4.97,
"learning_rate": 0.001,
"loss": 0.1167,
"step": 678
},
{
"epoch": 4.99,
"learning_rate": 0.001,
"loss": 0.1098,
"step": 680
},
{
"epoch": 4.99,
"eval_loss": 2.113422155380249,
"eval_runtime": 354.3609,
"eval_samples_per_second": 2.743,
"eval_steps_per_second": 1.371,
"step": 680
},
{
"epoch": 4.99,
"step": 680,
"total_flos": 5.939593565767631e+18,
"train_loss": 0.18507634396938716,
"train_runtime": 117893.9968,
"train_samples_per_second": 0.74,
"train_steps_per_second": 0.006
}
],
"logging_steps": 2,
"max_steps": 680,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 5.939593565767631e+18,
"trial_name": null,
"trial_params": null
}