longt5_xl_gov_memsum_bp_15 / trainer_state.json
learn3r's picture
End of training
92a6484
{
"best_metric": 3.273071765899658,
"best_model_checkpoint": "/exports/eddie/scratch/s1970716/models/summarization/longt5_xl_gov_memsum_bp_15/checkpoint-272",
"epoch": 4.9859655152660824,
"eval_steps": 500,
"global_step": 1360,
"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": 0.1372,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.001,
"loss": 0.1402,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 0.001,
"loss": 0.1467,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 0.001,
"loss": 0.141,
"step": 8
},
{
"epoch": 0.04,
"learning_rate": 0.001,
"loss": 0.1431,
"step": 10
},
{
"epoch": 0.04,
"learning_rate": 0.001,
"loss": 0.1558,
"step": 12
},
{
"epoch": 0.05,
"learning_rate": 0.001,
"loss": 0.134,
"step": 14
},
{
"epoch": 0.06,
"learning_rate": 0.001,
"loss": 0.1347,
"step": 16
},
{
"epoch": 0.07,
"learning_rate": 0.001,
"loss": 0.1346,
"step": 18
},
{
"epoch": 0.07,
"learning_rate": 0.001,
"loss": 0.1297,
"step": 20
},
{
"epoch": 0.08,
"learning_rate": 0.001,
"loss": 0.1366,
"step": 22
},
{
"epoch": 0.09,
"learning_rate": 0.001,
"loss": 0.1401,
"step": 24
},
{
"epoch": 0.1,
"learning_rate": 0.001,
"loss": 0.1446,
"step": 26
},
{
"epoch": 0.1,
"learning_rate": 0.001,
"loss": 0.1523,
"step": 28
},
{
"epoch": 0.11,
"learning_rate": 0.001,
"loss": 0.1502,
"step": 30
},
{
"epoch": 0.12,
"learning_rate": 0.001,
"loss": 0.1315,
"step": 32
},
{
"epoch": 0.12,
"learning_rate": 0.001,
"loss": 0.1223,
"step": 34
},
{
"epoch": 0.13,
"learning_rate": 0.001,
"loss": 0.1407,
"step": 36
},
{
"epoch": 0.14,
"learning_rate": 0.001,
"loss": 0.1402,
"step": 38
},
{
"epoch": 0.15,
"learning_rate": 0.001,
"loss": 0.127,
"step": 40
},
{
"epoch": 0.15,
"learning_rate": 0.001,
"loss": 0.1314,
"step": 42
},
{
"epoch": 0.16,
"learning_rate": 0.001,
"loss": 0.1481,
"step": 44
},
{
"epoch": 0.17,
"learning_rate": 0.001,
"loss": 0.1307,
"step": 46
},
{
"epoch": 0.18,
"learning_rate": 0.001,
"loss": 0.1248,
"step": 48
},
{
"epoch": 0.18,
"learning_rate": 0.001,
"loss": 0.1447,
"step": 50
},
{
"epoch": 0.19,
"learning_rate": 0.001,
"loss": 0.131,
"step": 52
},
{
"epoch": 0.2,
"learning_rate": 0.001,
"loss": 0.1443,
"step": 54
},
{
"epoch": 0.21,
"learning_rate": 0.001,
"loss": 0.1274,
"step": 56
},
{
"epoch": 0.21,
"learning_rate": 0.001,
"loss": 0.1302,
"step": 58
},
{
"epoch": 0.22,
"learning_rate": 0.001,
"loss": 0.1289,
"step": 60
},
{
"epoch": 0.23,
"learning_rate": 0.001,
"loss": 0.1391,
"step": 62
},
{
"epoch": 0.23,
"learning_rate": 0.001,
"loss": 0.1415,
"step": 64
},
{
"epoch": 0.24,
"learning_rate": 0.001,
"loss": 0.1283,
"step": 66
},
{
"epoch": 0.25,
"learning_rate": 0.001,
"loss": 0.1269,
"step": 68
},
{
"epoch": 0.26,
"learning_rate": 0.001,
"loss": 0.1641,
"step": 70
},
{
"epoch": 0.26,
"learning_rate": 0.001,
"loss": 0.1453,
"step": 72
},
{
"epoch": 0.27,
"learning_rate": 0.001,
"loss": 0.1446,
"step": 74
},
{
"epoch": 0.28,
"learning_rate": 0.001,
"loss": 0.1514,
"step": 76
},
{
"epoch": 0.29,
"learning_rate": 0.001,
"loss": 0.138,
"step": 78
},
{
"epoch": 0.29,
"learning_rate": 0.001,
"loss": 0.1419,
"step": 80
},
{
"epoch": 0.3,
"learning_rate": 0.001,
"loss": 0.1535,
"step": 82
},
{
"epoch": 0.31,
"learning_rate": 0.001,
"loss": 0.1333,
"step": 84
},
{
"epoch": 0.32,
"learning_rate": 0.001,
"loss": 0.1401,
"step": 86
},
{
"epoch": 0.32,
"learning_rate": 0.001,
"loss": 0.1583,
"step": 88
},
{
"epoch": 0.33,
"learning_rate": 0.001,
"loss": 0.1433,
"step": 90
},
{
"epoch": 0.34,
"learning_rate": 0.001,
"loss": 0.1311,
"step": 92
},
{
"epoch": 0.34,
"learning_rate": 0.001,
"loss": 0.1309,
"step": 94
},
{
"epoch": 0.35,
"learning_rate": 0.001,
"loss": 0.1351,
"step": 96
},
{
"epoch": 0.36,
"learning_rate": 0.001,
"loss": 0.1521,
"step": 98
},
{
"epoch": 0.37,
"learning_rate": 0.001,
"loss": 0.1404,
"step": 100
},
{
"epoch": 0.37,
"learning_rate": 0.001,
"loss": 0.1423,
"step": 102
},
{
"epoch": 0.38,
"learning_rate": 0.001,
"loss": 0.1435,
"step": 104
},
{
"epoch": 0.39,
"learning_rate": 0.001,
"loss": 0.1381,
"step": 106
},
{
"epoch": 0.4,
"learning_rate": 0.001,
"loss": 0.1346,
"step": 108
},
{
"epoch": 0.4,
"learning_rate": 0.001,
"loss": 0.1384,
"step": 110
},
{
"epoch": 0.41,
"learning_rate": 0.001,
"loss": 0.1258,
"step": 112
},
{
"epoch": 0.42,
"learning_rate": 0.001,
"loss": 0.1363,
"step": 114
},
{
"epoch": 0.43,
"learning_rate": 0.001,
"loss": 0.1393,
"step": 116
},
{
"epoch": 0.43,
"learning_rate": 0.001,
"loss": 0.1394,
"step": 118
},
{
"epoch": 0.44,
"learning_rate": 0.001,
"loss": 0.1373,
"step": 120
},
{
"epoch": 0.45,
"learning_rate": 0.001,
"loss": 0.1444,
"step": 122
},
{
"epoch": 0.45,
"learning_rate": 0.001,
"loss": 0.1469,
"step": 124
},
{
"epoch": 0.46,
"learning_rate": 0.001,
"loss": 0.1419,
"step": 126
},
{
"epoch": 0.47,
"learning_rate": 0.001,
"loss": 0.1412,
"step": 128
},
{
"epoch": 0.48,
"learning_rate": 0.001,
"loss": 0.1218,
"step": 130
},
{
"epoch": 0.48,
"learning_rate": 0.001,
"loss": 0.1341,
"step": 132
},
{
"epoch": 0.49,
"learning_rate": 0.001,
"loss": 0.1274,
"step": 134
},
{
"epoch": 0.5,
"learning_rate": 0.001,
"loss": 0.1241,
"step": 136
},
{
"epoch": 0.51,
"learning_rate": 0.001,
"loss": 0.1271,
"step": 138
},
{
"epoch": 0.51,
"learning_rate": 0.001,
"loss": 0.1362,
"step": 140
},
{
"epoch": 0.52,
"learning_rate": 0.001,
"loss": 0.1389,
"step": 142
},
{
"epoch": 0.53,
"learning_rate": 0.001,
"loss": 0.1365,
"step": 144
},
{
"epoch": 0.54,
"learning_rate": 0.001,
"loss": 0.1441,
"step": 146
},
{
"epoch": 0.54,
"learning_rate": 0.001,
"loss": 0.1503,
"step": 148
},
{
"epoch": 0.55,
"learning_rate": 0.001,
"loss": 0.1237,
"step": 150
},
{
"epoch": 0.56,
"learning_rate": 0.001,
"loss": 0.1476,
"step": 152
},
{
"epoch": 0.56,
"learning_rate": 0.001,
"loss": 0.1423,
"step": 154
},
{
"epoch": 0.57,
"learning_rate": 0.001,
"loss": 0.1528,
"step": 156
},
{
"epoch": 0.58,
"learning_rate": 0.001,
"loss": 0.1256,
"step": 158
},
{
"epoch": 0.59,
"learning_rate": 0.001,
"loss": 0.131,
"step": 160
},
{
"epoch": 0.59,
"learning_rate": 0.001,
"loss": 0.1385,
"step": 162
},
{
"epoch": 0.6,
"learning_rate": 0.001,
"loss": 0.1539,
"step": 164
},
{
"epoch": 0.61,
"learning_rate": 0.001,
"loss": 0.1607,
"step": 166
},
{
"epoch": 0.62,
"learning_rate": 0.001,
"loss": 0.1405,
"step": 168
},
{
"epoch": 0.62,
"learning_rate": 0.001,
"loss": 0.1434,
"step": 170
},
{
"epoch": 0.63,
"learning_rate": 0.001,
"loss": 0.127,
"step": 172
},
{
"epoch": 0.64,
"learning_rate": 0.001,
"loss": 0.1358,
"step": 174
},
{
"epoch": 0.65,
"learning_rate": 0.001,
"loss": 0.1407,
"step": 176
},
{
"epoch": 0.65,
"learning_rate": 0.001,
"loss": 0.1413,
"step": 178
},
{
"epoch": 0.66,
"learning_rate": 0.001,
"loss": 0.1402,
"step": 180
},
{
"epoch": 0.67,
"learning_rate": 0.001,
"loss": 0.142,
"step": 182
},
{
"epoch": 0.67,
"learning_rate": 0.001,
"loss": 0.1484,
"step": 184
},
{
"epoch": 0.68,
"learning_rate": 0.001,
"loss": 0.1524,
"step": 186
},
{
"epoch": 0.69,
"learning_rate": 0.001,
"loss": 0.1409,
"step": 188
},
{
"epoch": 0.7,
"learning_rate": 0.001,
"loss": 0.1263,
"step": 190
},
{
"epoch": 0.7,
"learning_rate": 0.001,
"loss": 0.1304,
"step": 192
},
{
"epoch": 0.71,
"learning_rate": 0.001,
"loss": 0.1314,
"step": 194
},
{
"epoch": 0.72,
"learning_rate": 0.001,
"loss": 0.1178,
"step": 196
},
{
"epoch": 0.73,
"learning_rate": 0.001,
"loss": 0.1457,
"step": 198
},
{
"epoch": 0.73,
"learning_rate": 0.001,
"loss": 0.1449,
"step": 200
},
{
"epoch": 0.74,
"learning_rate": 0.001,
"loss": 0.1443,
"step": 202
},
{
"epoch": 0.75,
"learning_rate": 0.001,
"loss": 0.145,
"step": 204
},
{
"epoch": 0.76,
"learning_rate": 0.001,
"loss": 0.1529,
"step": 206
},
{
"epoch": 0.76,
"learning_rate": 0.001,
"loss": 0.154,
"step": 208
},
{
"epoch": 0.77,
"learning_rate": 0.001,
"loss": 0.1372,
"step": 210
},
{
"epoch": 0.78,
"learning_rate": 0.001,
"loss": 0.1318,
"step": 212
},
{
"epoch": 0.78,
"learning_rate": 0.001,
"loss": 0.1328,
"step": 214
},
{
"epoch": 0.79,
"learning_rate": 0.001,
"loss": 0.1424,
"step": 216
},
{
"epoch": 0.8,
"learning_rate": 0.001,
"loss": 0.1387,
"step": 218
},
{
"epoch": 0.81,
"learning_rate": 0.001,
"loss": 0.1374,
"step": 220
},
{
"epoch": 0.81,
"learning_rate": 0.001,
"loss": 0.139,
"step": 222
},
{
"epoch": 0.82,
"learning_rate": 0.001,
"loss": 0.1497,
"step": 224
},
{
"epoch": 0.83,
"learning_rate": 0.001,
"loss": 0.1417,
"step": 226
},
{
"epoch": 0.84,
"learning_rate": 0.001,
"loss": 0.1356,
"step": 228
},
{
"epoch": 0.84,
"learning_rate": 0.001,
"loss": 0.1413,
"step": 230
},
{
"epoch": 0.85,
"learning_rate": 0.001,
"loss": 0.1242,
"step": 232
},
{
"epoch": 0.86,
"learning_rate": 0.001,
"loss": 0.1465,
"step": 234
},
{
"epoch": 0.87,
"learning_rate": 0.001,
"loss": 0.1247,
"step": 236
},
{
"epoch": 0.87,
"learning_rate": 0.001,
"loss": 0.1302,
"step": 238
},
{
"epoch": 0.88,
"learning_rate": 0.001,
"loss": 0.1546,
"step": 240
},
{
"epoch": 0.89,
"learning_rate": 0.001,
"loss": 0.1468,
"step": 242
},
{
"epoch": 0.89,
"learning_rate": 0.001,
"loss": 0.1515,
"step": 244
},
{
"epoch": 0.9,
"learning_rate": 0.001,
"loss": 0.1517,
"step": 246
},
{
"epoch": 0.91,
"learning_rate": 0.001,
"loss": 0.1363,
"step": 248
},
{
"epoch": 0.92,
"learning_rate": 0.001,
"loss": 0.1298,
"step": 250
},
{
"epoch": 0.92,
"learning_rate": 0.001,
"loss": 0.1365,
"step": 252
},
{
"epoch": 0.93,
"learning_rate": 0.001,
"loss": 0.1317,
"step": 254
},
{
"epoch": 0.94,
"learning_rate": 0.001,
"loss": 0.1502,
"step": 256
},
{
"epoch": 0.95,
"learning_rate": 0.001,
"loss": 0.1573,
"step": 258
},
{
"epoch": 0.95,
"learning_rate": 0.001,
"loss": 0.1399,
"step": 260
},
{
"epoch": 0.96,
"learning_rate": 0.001,
"loss": 0.1242,
"step": 262
},
{
"epoch": 0.97,
"learning_rate": 0.001,
"loss": 0.1524,
"step": 264
},
{
"epoch": 0.98,
"learning_rate": 0.001,
"loss": 0.1354,
"step": 266
},
{
"epoch": 0.98,
"learning_rate": 0.001,
"loss": 0.1444,
"step": 268
},
{
"epoch": 0.99,
"learning_rate": 0.001,
"loss": 0.1456,
"step": 270
},
{
"epoch": 1.0,
"learning_rate": 0.001,
"loss": 0.1366,
"step": 272
},
{
"epoch": 1.0,
"eval_gen_len": 1942.3155190133607,
"eval_loss": 3.273071765899658,
"eval_rouge1": 35.319,
"eval_rouge2": 11.8288,
"eval_rougeL": 16.3777,
"eval_rougeLsum": 33.5357,
"eval_runtime": 19826.3563,
"eval_samples_per_second": 0.049,
"eval_steps_per_second": 0.006,
"step": 272
},
{
"epoch": 1.0,
"learning_rate": 0.001,
"loss": 0.1281,
"step": 274
},
{
"epoch": 1.01,
"learning_rate": 0.001,
"loss": 0.1052,
"step": 276
},
{
"epoch": 1.02,
"learning_rate": 0.001,
"loss": 0.1044,
"step": 278
},
{
"epoch": 1.03,
"learning_rate": 0.001,
"loss": 0.1083,
"step": 280
},
{
"epoch": 1.03,
"learning_rate": 0.001,
"loss": 0.0992,
"step": 282
},
{
"epoch": 1.04,
"learning_rate": 0.001,
"loss": 0.1042,
"step": 284
},
{
"epoch": 1.05,
"learning_rate": 0.001,
"loss": 0.0948,
"step": 286
},
{
"epoch": 1.06,
"learning_rate": 0.001,
"loss": 0.0937,
"step": 288
},
{
"epoch": 1.06,
"learning_rate": 0.001,
"loss": 0.109,
"step": 290
},
{
"epoch": 1.07,
"learning_rate": 0.001,
"loss": 0.1001,
"step": 292
},
{
"epoch": 1.08,
"learning_rate": 0.001,
"loss": 0.0976,
"step": 294
},
{
"epoch": 1.09,
"learning_rate": 0.001,
"loss": 0.1048,
"step": 296
},
{
"epoch": 1.09,
"learning_rate": 0.001,
"loss": 0.1052,
"step": 298
},
{
"epoch": 1.1,
"learning_rate": 0.001,
"loss": 0.1032,
"step": 300
},
{
"epoch": 1.11,
"learning_rate": 0.001,
"loss": 0.1067,
"step": 302
},
{
"epoch": 1.11,
"learning_rate": 0.001,
"loss": 0.0975,
"step": 304
},
{
"epoch": 1.12,
"learning_rate": 0.001,
"loss": 0.1044,
"step": 306
},
{
"epoch": 1.13,
"learning_rate": 0.001,
"loss": 0.105,
"step": 308
},
{
"epoch": 1.14,
"learning_rate": 0.001,
"loss": 0.1123,
"step": 310
},
{
"epoch": 1.14,
"learning_rate": 0.001,
"loss": 0.1117,
"step": 312
},
{
"epoch": 1.15,
"learning_rate": 0.001,
"loss": 0.1119,
"step": 314
},
{
"epoch": 1.16,
"learning_rate": 0.001,
"loss": 0.1,
"step": 316
},
{
"epoch": 1.17,
"learning_rate": 0.001,
"loss": 0.0966,
"step": 318
},
{
"epoch": 1.17,
"learning_rate": 0.001,
"loss": 0.1179,
"step": 320
},
{
"epoch": 1.18,
"learning_rate": 0.001,
"loss": 0.1135,
"step": 322
},
{
"epoch": 1.19,
"learning_rate": 0.001,
"loss": 0.0997,
"step": 324
},
{
"epoch": 1.2,
"learning_rate": 0.001,
"loss": 0.1043,
"step": 326
},
{
"epoch": 1.2,
"learning_rate": 0.001,
"loss": 0.1147,
"step": 328
},
{
"epoch": 1.21,
"learning_rate": 0.001,
"loss": 0.1029,
"step": 330
},
{
"epoch": 1.22,
"learning_rate": 0.001,
"loss": 0.111,
"step": 332
},
{
"epoch": 1.22,
"learning_rate": 0.001,
"loss": 0.1095,
"step": 334
},
{
"epoch": 1.23,
"learning_rate": 0.001,
"loss": 0.11,
"step": 336
},
{
"epoch": 1.24,
"learning_rate": 0.001,
"loss": 0.107,
"step": 338
},
{
"epoch": 1.25,
"learning_rate": 0.001,
"loss": 0.1061,
"step": 340
},
{
"epoch": 1.25,
"learning_rate": 0.001,
"loss": 0.1042,
"step": 342
},
{
"epoch": 1.26,
"learning_rate": 0.001,
"loss": 0.1179,
"step": 344
},
{
"epoch": 1.27,
"learning_rate": 0.001,
"loss": 0.1079,
"step": 346
},
{
"epoch": 1.28,
"learning_rate": 0.001,
"loss": 0.1039,
"step": 348
},
{
"epoch": 1.28,
"learning_rate": 0.001,
"loss": 0.0992,
"step": 350
},
{
"epoch": 1.29,
"learning_rate": 0.001,
"loss": 0.1146,
"step": 352
},
{
"epoch": 1.3,
"learning_rate": 0.001,
"loss": 0.1076,
"step": 354
},
{
"epoch": 1.31,
"learning_rate": 0.001,
"loss": 0.1026,
"step": 356
},
{
"epoch": 1.31,
"learning_rate": 0.001,
"loss": 0.1079,
"step": 358
},
{
"epoch": 1.32,
"learning_rate": 0.001,
"loss": 0.1053,
"step": 360
},
{
"epoch": 1.33,
"learning_rate": 0.001,
"loss": 0.1043,
"step": 362
},
{
"epoch": 1.33,
"learning_rate": 0.001,
"loss": 0.1134,
"step": 364
},
{
"epoch": 1.34,
"learning_rate": 0.001,
"loss": 0.1091,
"step": 366
},
{
"epoch": 1.35,
"learning_rate": 0.001,
"loss": 0.1065,
"step": 368
},
{
"epoch": 1.36,
"learning_rate": 0.001,
"loss": 0.1091,
"step": 370
},
{
"epoch": 1.36,
"learning_rate": 0.001,
"loss": 0.1068,
"step": 372
},
{
"epoch": 1.37,
"learning_rate": 0.001,
"loss": 0.112,
"step": 374
},
{
"epoch": 1.38,
"learning_rate": 0.001,
"loss": 0.1135,
"step": 376
},
{
"epoch": 1.39,
"learning_rate": 0.001,
"loss": 0.1081,
"step": 378
},
{
"epoch": 1.39,
"learning_rate": 0.001,
"loss": 0.1131,
"step": 380
},
{
"epoch": 1.4,
"learning_rate": 0.001,
"loss": 0.1123,
"step": 382
},
{
"epoch": 1.41,
"learning_rate": 0.001,
"loss": 0.1147,
"step": 384
},
{
"epoch": 1.42,
"learning_rate": 0.001,
"loss": 0.1007,
"step": 386
},
{
"epoch": 1.42,
"learning_rate": 0.001,
"loss": 0.1032,
"step": 388
},
{
"epoch": 1.43,
"learning_rate": 0.001,
"loss": 0.1018,
"step": 390
},
{
"epoch": 1.44,
"learning_rate": 0.001,
"loss": 0.1068,
"step": 392
},
{
"epoch": 1.44,
"learning_rate": 0.001,
"loss": 0.106,
"step": 394
},
{
"epoch": 1.45,
"learning_rate": 0.001,
"loss": 0.0998,
"step": 396
},
{
"epoch": 1.46,
"learning_rate": 0.001,
"loss": 0.1119,
"step": 398
},
{
"epoch": 1.47,
"learning_rate": 0.001,
"loss": 0.1113,
"step": 400
},
{
"epoch": 1.47,
"learning_rate": 0.001,
"loss": 0.1168,
"step": 402
},
{
"epoch": 1.48,
"learning_rate": 0.001,
"loss": 0.1039,
"step": 404
},
{
"epoch": 1.49,
"learning_rate": 0.001,
"loss": 0.116,
"step": 406
},
{
"epoch": 1.5,
"learning_rate": 0.001,
"loss": 0.1095,
"step": 408
},
{
"epoch": 1.5,
"learning_rate": 0.001,
"loss": 0.1175,
"step": 410
},
{
"epoch": 1.51,
"learning_rate": 0.001,
"loss": 0.1247,
"step": 412
},
{
"epoch": 1.52,
"learning_rate": 0.001,
"loss": 0.1084,
"step": 414
},
{
"epoch": 1.53,
"learning_rate": 0.001,
"loss": 0.1083,
"step": 416
},
{
"epoch": 1.53,
"learning_rate": 0.001,
"loss": 0.1113,
"step": 418
},
{
"epoch": 1.54,
"learning_rate": 0.001,
"loss": 0.1172,
"step": 420
},
{
"epoch": 1.55,
"learning_rate": 0.001,
"loss": 0.107,
"step": 422
},
{
"epoch": 1.55,
"learning_rate": 0.001,
"loss": 0.1081,
"step": 424
},
{
"epoch": 1.56,
"learning_rate": 0.001,
"loss": 0.1383,
"step": 426
},
{
"epoch": 1.57,
"learning_rate": 0.001,
"loss": 0.1106,
"step": 428
},
{
"epoch": 1.58,
"learning_rate": 0.001,
"loss": 0.1202,
"step": 430
},
{
"epoch": 1.58,
"learning_rate": 0.001,
"loss": 0.1141,
"step": 432
},
{
"epoch": 1.59,
"learning_rate": 0.001,
"loss": 0.1125,
"step": 434
},
{
"epoch": 1.6,
"learning_rate": 0.001,
"loss": 0.1118,
"step": 436
},
{
"epoch": 1.61,
"learning_rate": 0.001,
"loss": 0.1122,
"step": 438
},
{
"epoch": 1.61,
"learning_rate": 0.001,
"loss": 0.1249,
"step": 440
},
{
"epoch": 1.62,
"learning_rate": 0.001,
"loss": 0.1125,
"step": 442
},
{
"epoch": 1.63,
"learning_rate": 0.001,
"loss": 0.1182,
"step": 444
},
{
"epoch": 1.64,
"learning_rate": 0.001,
"loss": 0.1115,
"step": 446
},
{
"epoch": 1.64,
"learning_rate": 0.001,
"loss": 0.1109,
"step": 448
},
{
"epoch": 1.65,
"learning_rate": 0.001,
"loss": 0.1157,
"step": 450
},
{
"epoch": 1.66,
"learning_rate": 0.001,
"loss": 0.1086,
"step": 452
},
{
"epoch": 1.66,
"learning_rate": 0.001,
"loss": 0.1239,
"step": 454
},
{
"epoch": 1.67,
"learning_rate": 0.001,
"loss": 0.1146,
"step": 456
},
{
"epoch": 1.68,
"learning_rate": 0.001,
"loss": 0.1088,
"step": 458
},
{
"epoch": 1.69,
"learning_rate": 0.001,
"loss": 0.1165,
"step": 460
},
{
"epoch": 1.69,
"learning_rate": 0.001,
"loss": 0.1166,
"step": 462
},
{
"epoch": 1.7,
"learning_rate": 0.001,
"loss": 0.1243,
"step": 464
},
{
"epoch": 1.71,
"learning_rate": 0.001,
"loss": 0.1284,
"step": 466
},
{
"epoch": 1.72,
"learning_rate": 0.001,
"loss": 0.1271,
"step": 468
},
{
"epoch": 1.72,
"learning_rate": 0.001,
"loss": 0.1127,
"step": 470
},
{
"epoch": 1.73,
"learning_rate": 0.001,
"loss": 0.1107,
"step": 472
},
{
"epoch": 1.74,
"learning_rate": 0.001,
"loss": 0.1075,
"step": 474
},
{
"epoch": 1.75,
"learning_rate": 0.001,
"loss": 0.1144,
"step": 476
},
{
"epoch": 1.75,
"learning_rate": 0.001,
"loss": 0.105,
"step": 478
},
{
"epoch": 1.76,
"learning_rate": 0.001,
"loss": 0.1056,
"step": 480
},
{
"epoch": 1.77,
"learning_rate": 0.001,
"loss": 0.1146,
"step": 482
},
{
"epoch": 1.77,
"learning_rate": 0.001,
"loss": 0.1162,
"step": 484
},
{
"epoch": 1.78,
"learning_rate": 0.001,
"loss": 0.1135,
"step": 486
},
{
"epoch": 1.79,
"learning_rate": 0.001,
"loss": 0.1129,
"step": 488
},
{
"epoch": 1.8,
"learning_rate": 0.001,
"loss": 0.1055,
"step": 490
},
{
"epoch": 1.8,
"learning_rate": 0.001,
"loss": 0.1147,
"step": 492
},
{
"epoch": 1.81,
"learning_rate": 0.001,
"loss": 0.1159,
"step": 494
},
{
"epoch": 1.82,
"learning_rate": 0.001,
"loss": 0.1233,
"step": 496
},
{
"epoch": 1.83,
"learning_rate": 0.001,
"loss": 0.1092,
"step": 498
},
{
"epoch": 1.83,
"learning_rate": 0.001,
"loss": 0.1134,
"step": 500
},
{
"epoch": 1.84,
"learning_rate": 0.001,
"loss": 0.1111,
"step": 502
},
{
"epoch": 1.85,
"learning_rate": 0.001,
"loss": 0.1133,
"step": 504
},
{
"epoch": 1.86,
"learning_rate": 0.001,
"loss": 0.1194,
"step": 506
},
{
"epoch": 1.86,
"learning_rate": 0.001,
"loss": 0.1161,
"step": 508
},
{
"epoch": 1.87,
"learning_rate": 0.001,
"loss": 0.1157,
"step": 510
},
{
"epoch": 1.88,
"learning_rate": 0.001,
"loss": 0.1188,
"step": 512
},
{
"epoch": 1.88,
"learning_rate": 0.001,
"loss": 0.1199,
"step": 514
},
{
"epoch": 1.89,
"learning_rate": 0.001,
"loss": 0.1208,
"step": 516
},
{
"epoch": 1.9,
"learning_rate": 0.001,
"loss": 0.1241,
"step": 518
},
{
"epoch": 1.91,
"learning_rate": 0.001,
"loss": 0.1102,
"step": 520
},
{
"epoch": 1.91,
"learning_rate": 0.001,
"loss": 0.1149,
"step": 522
},
{
"epoch": 1.92,
"learning_rate": 0.001,
"loss": 0.1112,
"step": 524
},
{
"epoch": 1.93,
"learning_rate": 0.001,
"loss": 0.1133,
"step": 526
},
{
"epoch": 1.94,
"learning_rate": 0.001,
"loss": 0.111,
"step": 528
},
{
"epoch": 1.94,
"learning_rate": 0.001,
"loss": 0.1084,
"step": 530
},
{
"epoch": 1.95,
"learning_rate": 0.001,
"loss": 0.1163,
"step": 532
},
{
"epoch": 1.96,
"learning_rate": 0.001,
"loss": 0.114,
"step": 534
},
{
"epoch": 1.97,
"learning_rate": 0.001,
"loss": 0.1082,
"step": 536
},
{
"epoch": 1.97,
"learning_rate": 0.001,
"loss": 0.1206,
"step": 538
},
{
"epoch": 1.98,
"learning_rate": 0.001,
"loss": 0.1241,
"step": 540
},
{
"epoch": 1.99,
"learning_rate": 0.001,
"loss": 0.1262,
"step": 542
},
{
"epoch": 1.99,
"learning_rate": 0.001,
"loss": 0.1183,
"step": 544
},
{
"epoch": 2.0,
"eval_gen_len": 1867.3144912641314,
"eval_loss": 3.3957316875457764,
"eval_rouge1": 37.5265,
"eval_rouge2": 12.4932,
"eval_rougeL": 16.743,
"eval_rougeLsum": 35.7285,
"eval_runtime": 19805.0125,
"eval_samples_per_second": 0.049,
"eval_steps_per_second": 0.006,
"step": 545
},
{
"epoch": 2.0,
"learning_rate": 0.001,
"loss": 0.117,
"step": 546
},
{
"epoch": 2.01,
"learning_rate": 0.001,
"loss": 0.0959,
"step": 548
},
{
"epoch": 2.02,
"learning_rate": 0.001,
"loss": 0.0917,
"step": 550
},
{
"epoch": 2.02,
"learning_rate": 0.001,
"loss": 0.0813,
"step": 552
},
{
"epoch": 2.03,
"learning_rate": 0.001,
"loss": 0.0909,
"step": 554
},
{
"epoch": 2.04,
"learning_rate": 0.001,
"loss": 0.0853,
"step": 556
},
{
"epoch": 2.05,
"learning_rate": 0.001,
"loss": 0.0968,
"step": 558
},
{
"epoch": 2.05,
"learning_rate": 0.001,
"loss": 0.0853,
"step": 560
},
{
"epoch": 2.06,
"learning_rate": 0.001,
"loss": 0.0922,
"step": 562
},
{
"epoch": 2.07,
"learning_rate": 0.001,
"loss": 0.0869,
"step": 564
},
{
"epoch": 2.08,
"learning_rate": 0.001,
"loss": 0.0865,
"step": 566
},
{
"epoch": 2.08,
"learning_rate": 0.001,
"loss": 0.0916,
"step": 568
},
{
"epoch": 2.09,
"learning_rate": 0.001,
"loss": 0.086,
"step": 570
},
{
"epoch": 2.1,
"learning_rate": 0.001,
"loss": 0.0843,
"step": 572
},
{
"epoch": 2.1,
"learning_rate": 0.001,
"loss": 0.09,
"step": 574
},
{
"epoch": 2.11,
"learning_rate": 0.001,
"loss": 0.0856,
"step": 576
},
{
"epoch": 2.12,
"learning_rate": 0.001,
"loss": 0.0939,
"step": 578
},
{
"epoch": 2.13,
"learning_rate": 0.001,
"loss": 0.0877,
"step": 580
},
{
"epoch": 2.13,
"learning_rate": 0.001,
"loss": 0.0923,
"step": 582
},
{
"epoch": 2.14,
"learning_rate": 0.001,
"loss": 0.1027,
"step": 584
},
{
"epoch": 2.15,
"learning_rate": 0.001,
"loss": 0.0951,
"step": 586
},
{
"epoch": 2.16,
"learning_rate": 0.001,
"loss": 0.0998,
"step": 588
},
{
"epoch": 2.16,
"learning_rate": 0.001,
"loss": 0.093,
"step": 590
},
{
"epoch": 2.17,
"learning_rate": 0.001,
"loss": 0.0904,
"step": 592
},
{
"epoch": 2.18,
"learning_rate": 0.001,
"loss": 0.0837,
"step": 594
},
{
"epoch": 2.19,
"learning_rate": 0.001,
"loss": 0.0957,
"step": 596
},
{
"epoch": 2.19,
"learning_rate": 0.001,
"loss": 0.0946,
"step": 598
},
{
"epoch": 2.2,
"learning_rate": 0.001,
"loss": 0.092,
"step": 600
},
{
"epoch": 2.21,
"learning_rate": 0.001,
"loss": 0.0872,
"step": 602
},
{
"epoch": 2.21,
"learning_rate": 0.001,
"loss": 0.0913,
"step": 604
},
{
"epoch": 2.22,
"learning_rate": 0.001,
"loss": 0.0835,
"step": 606
},
{
"epoch": 2.23,
"learning_rate": 0.001,
"loss": 0.0929,
"step": 608
},
{
"epoch": 2.24,
"learning_rate": 0.001,
"loss": 0.0909,
"step": 610
},
{
"epoch": 2.24,
"learning_rate": 0.001,
"loss": 0.085,
"step": 612
},
{
"epoch": 2.25,
"learning_rate": 0.001,
"loss": 0.0869,
"step": 614
},
{
"epoch": 2.26,
"learning_rate": 0.001,
"loss": 0.0963,
"step": 616
},
{
"epoch": 2.27,
"learning_rate": 0.001,
"loss": 0.0906,
"step": 618
},
{
"epoch": 2.27,
"learning_rate": 0.001,
"loss": 0.0914,
"step": 620
},
{
"epoch": 2.28,
"learning_rate": 0.001,
"loss": 0.0947,
"step": 622
},
{
"epoch": 2.29,
"learning_rate": 0.001,
"loss": 0.0898,
"step": 624
},
{
"epoch": 2.3,
"learning_rate": 0.001,
"loss": 0.095,
"step": 626
},
{
"epoch": 2.3,
"learning_rate": 0.001,
"loss": 0.0956,
"step": 628
},
{
"epoch": 2.31,
"learning_rate": 0.001,
"loss": 0.0947,
"step": 630
},
{
"epoch": 2.32,
"learning_rate": 0.001,
"loss": 0.0923,
"step": 632
},
{
"epoch": 2.32,
"learning_rate": 0.001,
"loss": 0.097,
"step": 634
},
{
"epoch": 2.33,
"learning_rate": 0.001,
"loss": 0.0926,
"step": 636
},
{
"epoch": 2.34,
"learning_rate": 0.001,
"loss": 0.0976,
"step": 638
},
{
"epoch": 2.35,
"learning_rate": 0.001,
"loss": 0.0932,
"step": 640
},
{
"epoch": 2.35,
"learning_rate": 0.001,
"loss": 0.0891,
"step": 642
},
{
"epoch": 2.36,
"learning_rate": 0.001,
"loss": 0.0967,
"step": 644
},
{
"epoch": 2.37,
"learning_rate": 0.001,
"loss": 0.1003,
"step": 646
},
{
"epoch": 2.38,
"learning_rate": 0.001,
"loss": 0.0991,
"step": 648
},
{
"epoch": 2.38,
"learning_rate": 0.001,
"loss": 0.0949,
"step": 650
},
{
"epoch": 2.39,
"learning_rate": 0.001,
"loss": 0.0951,
"step": 652
},
{
"epoch": 2.4,
"learning_rate": 0.001,
"loss": 0.0955,
"step": 654
},
{
"epoch": 2.4,
"learning_rate": 0.001,
"loss": 0.0967,
"step": 656
},
{
"epoch": 2.41,
"learning_rate": 0.001,
"loss": 0.086,
"step": 658
},
{
"epoch": 2.42,
"learning_rate": 0.001,
"loss": 0.0951,
"step": 660
},
{
"epoch": 2.43,
"learning_rate": 0.001,
"loss": 0.1006,
"step": 662
},
{
"epoch": 2.43,
"learning_rate": 0.001,
"loss": 0.1024,
"step": 664
},
{
"epoch": 2.44,
"learning_rate": 0.001,
"loss": 0.1,
"step": 666
},
{
"epoch": 2.45,
"learning_rate": 0.001,
"loss": 0.0986,
"step": 668
},
{
"epoch": 2.46,
"learning_rate": 0.001,
"loss": 0.0938,
"step": 670
},
{
"epoch": 2.46,
"learning_rate": 0.001,
"loss": 0.0927,
"step": 672
},
{
"epoch": 2.47,
"learning_rate": 0.001,
"loss": 0.0919,
"step": 674
},
{
"epoch": 2.48,
"learning_rate": 0.001,
"loss": 0.0968,
"step": 676
},
{
"epoch": 2.49,
"learning_rate": 0.001,
"loss": 0.1024,
"step": 678
},
{
"epoch": 2.49,
"learning_rate": 0.001,
"loss": 0.0942,
"step": 680
},
{
"epoch": 2.5,
"learning_rate": 0.001,
"loss": 0.0916,
"step": 682
},
{
"epoch": 2.51,
"learning_rate": 0.001,
"loss": 0.0912,
"step": 684
},
{
"epoch": 2.51,
"learning_rate": 0.001,
"loss": 0.0991,
"step": 686
},
{
"epoch": 2.52,
"learning_rate": 0.001,
"loss": 0.0999,
"step": 688
},
{
"epoch": 2.53,
"learning_rate": 0.001,
"loss": 0.096,
"step": 690
},
{
"epoch": 2.54,
"learning_rate": 0.001,
"loss": 0.0982,
"step": 692
},
{
"epoch": 2.54,
"learning_rate": 0.001,
"loss": 0.1058,
"step": 694
},
{
"epoch": 2.55,
"learning_rate": 0.001,
"loss": 0.088,
"step": 696
},
{
"epoch": 2.56,
"learning_rate": 0.001,
"loss": 0.0895,
"step": 698
},
{
"epoch": 2.57,
"learning_rate": 0.001,
"loss": 0.0914,
"step": 700
},
{
"epoch": 2.57,
"learning_rate": 0.001,
"loss": 0.0963,
"step": 702
},
{
"epoch": 2.58,
"learning_rate": 0.001,
"loss": 0.0853,
"step": 704
},
{
"epoch": 2.59,
"learning_rate": 0.001,
"loss": 0.0924,
"step": 706
},
{
"epoch": 2.6,
"learning_rate": 0.001,
"loss": 0.0928,
"step": 708
},
{
"epoch": 2.6,
"learning_rate": 0.001,
"loss": 0.1014,
"step": 710
},
{
"epoch": 2.61,
"learning_rate": 0.001,
"loss": 0.1058,
"step": 712
},
{
"epoch": 2.62,
"learning_rate": 0.001,
"loss": 0.0948,
"step": 714
},
{
"epoch": 2.62,
"learning_rate": 0.001,
"loss": 0.1025,
"step": 716
},
{
"epoch": 2.63,
"learning_rate": 0.001,
"loss": 0.0962,
"step": 718
},
{
"epoch": 2.64,
"learning_rate": 0.001,
"loss": 0.1035,
"step": 720
},
{
"epoch": 2.65,
"learning_rate": 0.001,
"loss": 0.0999,
"step": 722
},
{
"epoch": 2.65,
"learning_rate": 0.001,
"loss": 0.0957,
"step": 724
},
{
"epoch": 2.66,
"learning_rate": 0.001,
"loss": 0.0994,
"step": 726
},
{
"epoch": 2.67,
"learning_rate": 0.001,
"loss": 0.0875,
"step": 728
},
{
"epoch": 2.68,
"learning_rate": 0.001,
"loss": 0.0997,
"step": 730
},
{
"epoch": 2.68,
"learning_rate": 0.001,
"loss": 0.1021,
"step": 732
},
{
"epoch": 2.69,
"learning_rate": 0.001,
"loss": 0.102,
"step": 734
},
{
"epoch": 2.7,
"learning_rate": 0.001,
"loss": 0.0912,
"step": 736
},
{
"epoch": 2.71,
"learning_rate": 0.001,
"loss": 0.097,
"step": 738
},
{
"epoch": 2.71,
"learning_rate": 0.001,
"loss": 0.0993,
"step": 740
},
{
"epoch": 2.72,
"learning_rate": 0.001,
"loss": 0.0924,
"step": 742
},
{
"epoch": 2.73,
"learning_rate": 0.001,
"loss": 0.1004,
"step": 744
},
{
"epoch": 2.73,
"learning_rate": 0.001,
"loss": 0.0916,
"step": 746
},
{
"epoch": 2.74,
"learning_rate": 0.001,
"loss": 0.1108,
"step": 748
},
{
"epoch": 2.75,
"learning_rate": 0.001,
"loss": 0.099,
"step": 750
},
{
"epoch": 2.76,
"learning_rate": 0.001,
"loss": 0.1042,
"step": 752
},
{
"epoch": 2.76,
"learning_rate": 0.001,
"loss": 0.0911,
"step": 754
},
{
"epoch": 2.77,
"learning_rate": 0.001,
"loss": 0.0998,
"step": 756
},
{
"epoch": 2.78,
"learning_rate": 0.001,
"loss": 0.0943,
"step": 758
},
{
"epoch": 2.79,
"learning_rate": 0.001,
"loss": 0.0989,
"step": 760
},
{
"epoch": 2.79,
"learning_rate": 0.001,
"loss": 0.1013,
"step": 762
},
{
"epoch": 2.8,
"learning_rate": 0.001,
"loss": 0.0923,
"step": 764
},
{
"epoch": 2.81,
"learning_rate": 0.001,
"loss": 0.0998,
"step": 766
},
{
"epoch": 2.82,
"learning_rate": 0.001,
"loss": 0.0974,
"step": 768
},
{
"epoch": 2.82,
"learning_rate": 0.001,
"loss": 0.1011,
"step": 770
},
{
"epoch": 2.83,
"learning_rate": 0.001,
"loss": 0.112,
"step": 772
},
{
"epoch": 2.84,
"learning_rate": 0.001,
"loss": 0.1017,
"step": 774
},
{
"epoch": 2.84,
"learning_rate": 0.001,
"loss": 0.1061,
"step": 776
},
{
"epoch": 2.85,
"learning_rate": 0.001,
"loss": 0.1031,
"step": 778
},
{
"epoch": 2.86,
"learning_rate": 0.001,
"loss": 0.0998,
"step": 780
},
{
"epoch": 2.87,
"learning_rate": 0.001,
"loss": 0.1034,
"step": 782
},
{
"epoch": 2.87,
"learning_rate": 0.001,
"loss": 0.1037,
"step": 784
},
{
"epoch": 2.88,
"learning_rate": 0.001,
"loss": 0.1007,
"step": 786
},
{
"epoch": 2.89,
"learning_rate": 0.001,
"loss": 0.1005,
"step": 788
},
{
"epoch": 2.9,
"learning_rate": 0.001,
"loss": 0.1013,
"step": 790
},
{
"epoch": 2.9,
"learning_rate": 0.001,
"loss": 0.0994,
"step": 792
},
{
"epoch": 2.91,
"learning_rate": 0.001,
"loss": 0.1016,
"step": 794
},
{
"epoch": 2.92,
"learning_rate": 0.001,
"loss": 0.1009,
"step": 796
},
{
"epoch": 2.93,
"learning_rate": 0.001,
"loss": 0.0906,
"step": 798
},
{
"epoch": 2.93,
"learning_rate": 0.001,
"loss": 0.106,
"step": 800
},
{
"epoch": 2.94,
"learning_rate": 0.001,
"loss": 0.0955,
"step": 802
},
{
"epoch": 2.95,
"learning_rate": 0.001,
"loss": 0.0981,
"step": 804
},
{
"epoch": 2.95,
"learning_rate": 0.001,
"loss": 0.0964,
"step": 806
},
{
"epoch": 2.96,
"learning_rate": 0.001,
"loss": 0.095,
"step": 808
},
{
"epoch": 2.97,
"learning_rate": 0.001,
"loss": 0.1011,
"step": 810
},
{
"epoch": 2.98,
"learning_rate": 0.001,
"loss": 0.107,
"step": 812
},
{
"epoch": 2.98,
"learning_rate": 0.001,
"loss": 0.0948,
"step": 814
},
{
"epoch": 2.99,
"learning_rate": 0.001,
"loss": 0.1079,
"step": 816
},
{
"epoch": 3.0,
"learning_rate": 0.001,
"loss": 0.1072,
"step": 818
},
{
"epoch": 3.0,
"eval_gen_len": 1561.0853031860227,
"eval_loss": 3.4308173656463623,
"eval_rouge1": 41.1487,
"eval_rouge2": 13.4035,
"eval_rougeL": 17.5783,
"eval_rougeLsum": 39.1233,
"eval_runtime": 19485.5469,
"eval_samples_per_second": 0.05,
"eval_steps_per_second": 0.006,
"step": 818
},
{
"epoch": 3.01,
"learning_rate": 0.001,
"loss": 0.0861,
"step": 820
},
{
"epoch": 3.01,
"learning_rate": 0.001,
"loss": 0.0805,
"step": 822
},
{
"epoch": 3.02,
"learning_rate": 0.001,
"loss": 0.0797,
"step": 824
},
{
"epoch": 3.03,
"learning_rate": 0.001,
"loss": 0.0845,
"step": 826
},
{
"epoch": 3.04,
"learning_rate": 0.001,
"loss": 0.079,
"step": 828
},
{
"epoch": 3.04,
"learning_rate": 0.001,
"loss": 0.0743,
"step": 830
},
{
"epoch": 3.05,
"learning_rate": 0.001,
"loss": 0.0803,
"step": 832
},
{
"epoch": 3.06,
"learning_rate": 0.001,
"loss": 0.0734,
"step": 834
},
{
"epoch": 3.06,
"learning_rate": 0.001,
"loss": 0.085,
"step": 836
},
{
"epoch": 3.07,
"learning_rate": 0.001,
"loss": 0.0849,
"step": 838
},
{
"epoch": 3.08,
"learning_rate": 0.001,
"loss": 0.0821,
"step": 840
},
{
"epoch": 3.09,
"learning_rate": 0.001,
"loss": 0.0788,
"step": 842
},
{
"epoch": 3.09,
"learning_rate": 0.001,
"loss": 0.0738,
"step": 844
},
{
"epoch": 3.1,
"learning_rate": 0.001,
"loss": 0.0764,
"step": 846
},
{
"epoch": 3.11,
"learning_rate": 0.001,
"loss": 0.0778,
"step": 848
},
{
"epoch": 3.12,
"learning_rate": 0.001,
"loss": 0.0932,
"step": 850
},
{
"epoch": 3.12,
"learning_rate": 0.001,
"loss": 0.0779,
"step": 852
},
{
"epoch": 3.13,
"learning_rate": 0.001,
"loss": 0.0783,
"step": 854
},
{
"epoch": 3.14,
"learning_rate": 0.001,
"loss": 0.0797,
"step": 856
},
{
"epoch": 3.15,
"learning_rate": 0.001,
"loss": 0.0769,
"step": 858
},
{
"epoch": 3.15,
"learning_rate": 0.001,
"loss": 0.0806,
"step": 860
},
{
"epoch": 3.16,
"learning_rate": 0.001,
"loss": 0.0821,
"step": 862
},
{
"epoch": 3.17,
"learning_rate": 0.001,
"loss": 0.0799,
"step": 864
},
{
"epoch": 3.17,
"learning_rate": 0.001,
"loss": 0.0802,
"step": 866
},
{
"epoch": 3.18,
"learning_rate": 0.001,
"loss": 0.0809,
"step": 868
},
{
"epoch": 3.19,
"learning_rate": 0.001,
"loss": 0.0834,
"step": 870
},
{
"epoch": 3.2,
"learning_rate": 0.001,
"loss": 0.0782,
"step": 872
},
{
"epoch": 3.2,
"learning_rate": 0.001,
"loss": 0.077,
"step": 874
},
{
"epoch": 3.21,
"learning_rate": 0.001,
"loss": 0.0845,
"step": 876
},
{
"epoch": 3.22,
"learning_rate": 0.001,
"loss": 0.0859,
"step": 878
},
{
"epoch": 3.23,
"learning_rate": 0.001,
"loss": 0.0881,
"step": 880
},
{
"epoch": 3.23,
"learning_rate": 0.001,
"loss": 0.0873,
"step": 882
},
{
"epoch": 3.24,
"learning_rate": 0.001,
"loss": 0.0844,
"step": 884
},
{
"epoch": 3.25,
"learning_rate": 0.001,
"loss": 0.0827,
"step": 886
},
{
"epoch": 3.26,
"learning_rate": 0.001,
"loss": 0.0861,
"step": 888
},
{
"epoch": 3.26,
"learning_rate": 0.001,
"loss": 0.0778,
"step": 890
},
{
"epoch": 3.27,
"learning_rate": 0.001,
"loss": 0.0798,
"step": 892
},
{
"epoch": 3.28,
"learning_rate": 0.001,
"loss": 0.0836,
"step": 894
},
{
"epoch": 3.28,
"learning_rate": 0.001,
"loss": 0.0871,
"step": 896
},
{
"epoch": 3.29,
"learning_rate": 0.001,
"loss": 0.0841,
"step": 898
},
{
"epoch": 3.3,
"learning_rate": 0.001,
"loss": 0.0908,
"step": 900
},
{
"epoch": 3.31,
"learning_rate": 0.001,
"loss": 0.0805,
"step": 902
},
{
"epoch": 3.31,
"learning_rate": 0.001,
"loss": 0.0838,
"step": 904
},
{
"epoch": 3.32,
"learning_rate": 0.001,
"loss": 0.0807,
"step": 906
},
{
"epoch": 3.33,
"learning_rate": 0.001,
"loss": 0.0823,
"step": 908
},
{
"epoch": 3.34,
"learning_rate": 0.001,
"loss": 0.0801,
"step": 910
},
{
"epoch": 3.34,
"learning_rate": 0.001,
"loss": 0.0908,
"step": 912
},
{
"epoch": 3.35,
"learning_rate": 0.001,
"loss": 0.0811,
"step": 914
},
{
"epoch": 3.36,
"learning_rate": 0.001,
"loss": 0.0848,
"step": 916
},
{
"epoch": 3.37,
"learning_rate": 0.001,
"loss": 0.0864,
"step": 918
},
{
"epoch": 3.37,
"learning_rate": 0.001,
"loss": 0.0875,
"step": 920
},
{
"epoch": 3.38,
"learning_rate": 0.001,
"loss": 0.0909,
"step": 922
},
{
"epoch": 3.39,
"learning_rate": 0.001,
"loss": 0.0823,
"step": 924
},
{
"epoch": 3.39,
"learning_rate": 0.001,
"loss": 0.0839,
"step": 926
},
{
"epoch": 3.4,
"learning_rate": 0.001,
"loss": 0.0892,
"step": 928
},
{
"epoch": 3.41,
"learning_rate": 0.001,
"loss": 0.0874,
"step": 930
},
{
"epoch": 3.42,
"learning_rate": 0.001,
"loss": 0.0823,
"step": 932
},
{
"epoch": 3.42,
"learning_rate": 0.001,
"loss": 0.0899,
"step": 934
},
{
"epoch": 3.43,
"learning_rate": 0.001,
"loss": 0.085,
"step": 936
},
{
"epoch": 3.44,
"learning_rate": 0.001,
"loss": 0.0866,
"step": 938
},
{
"epoch": 3.45,
"learning_rate": 0.001,
"loss": 0.0826,
"step": 940
},
{
"epoch": 3.45,
"learning_rate": 0.001,
"loss": 0.0877,
"step": 942
},
{
"epoch": 3.46,
"learning_rate": 0.001,
"loss": 0.0875,
"step": 944
},
{
"epoch": 3.47,
"learning_rate": 0.001,
"loss": 0.0855,
"step": 946
},
{
"epoch": 3.48,
"learning_rate": 0.001,
"loss": 0.0828,
"step": 948
},
{
"epoch": 3.48,
"learning_rate": 0.001,
"loss": 0.0937,
"step": 950
},
{
"epoch": 3.49,
"learning_rate": 0.001,
"loss": 0.0819,
"step": 952
},
{
"epoch": 3.5,
"learning_rate": 0.001,
"loss": 0.0794,
"step": 954
},
{
"epoch": 3.5,
"learning_rate": 0.001,
"loss": 0.0811,
"step": 956
},
{
"epoch": 3.51,
"learning_rate": 0.001,
"loss": 0.0835,
"step": 958
},
{
"epoch": 3.52,
"learning_rate": 0.001,
"loss": 0.0824,
"step": 960
},
{
"epoch": 3.53,
"learning_rate": 0.001,
"loss": 0.0799,
"step": 962
},
{
"epoch": 3.53,
"learning_rate": 0.001,
"loss": 0.0818,
"step": 964
},
{
"epoch": 3.54,
"learning_rate": 0.001,
"loss": 0.0798,
"step": 966
},
{
"epoch": 3.55,
"learning_rate": 0.001,
"loss": 0.0901,
"step": 968
},
{
"epoch": 3.56,
"learning_rate": 0.001,
"loss": 0.0868,
"step": 970
},
{
"epoch": 3.56,
"learning_rate": 0.001,
"loss": 0.0829,
"step": 972
},
{
"epoch": 3.57,
"learning_rate": 0.001,
"loss": 0.0882,
"step": 974
},
{
"epoch": 3.58,
"learning_rate": 0.001,
"loss": 0.0864,
"step": 976
},
{
"epoch": 3.59,
"learning_rate": 0.001,
"loss": 0.0862,
"step": 978
},
{
"epoch": 3.59,
"learning_rate": 0.001,
"loss": 0.0869,
"step": 980
},
{
"epoch": 3.6,
"learning_rate": 0.001,
"loss": 0.089,
"step": 982
},
{
"epoch": 3.61,
"learning_rate": 0.001,
"loss": 0.0905,
"step": 984
},
{
"epoch": 3.61,
"learning_rate": 0.001,
"loss": 0.0858,
"step": 986
},
{
"epoch": 3.62,
"learning_rate": 0.001,
"loss": 0.0837,
"step": 988
},
{
"epoch": 3.63,
"learning_rate": 0.001,
"loss": 0.0888,
"step": 990
},
{
"epoch": 3.64,
"learning_rate": 0.001,
"loss": 0.0937,
"step": 992
},
{
"epoch": 3.64,
"learning_rate": 0.001,
"loss": 0.0889,
"step": 994
},
{
"epoch": 3.65,
"learning_rate": 0.001,
"loss": 0.0871,
"step": 996
},
{
"epoch": 3.66,
"learning_rate": 0.001,
"loss": 0.0848,
"step": 998
},
{
"epoch": 3.67,
"learning_rate": 0.001,
"loss": 0.0873,
"step": 1000
},
{
"epoch": 3.67,
"learning_rate": 0.001,
"loss": 0.0847,
"step": 1002
},
{
"epoch": 3.68,
"learning_rate": 0.001,
"loss": 0.078,
"step": 1004
},
{
"epoch": 3.69,
"learning_rate": 0.001,
"loss": 0.0847,
"step": 1006
},
{
"epoch": 3.7,
"learning_rate": 0.001,
"loss": 0.0854,
"step": 1008
},
{
"epoch": 3.7,
"learning_rate": 0.001,
"loss": 0.0861,
"step": 1010
},
{
"epoch": 3.71,
"learning_rate": 0.001,
"loss": 0.0825,
"step": 1012
},
{
"epoch": 3.72,
"learning_rate": 0.001,
"loss": 0.0869,
"step": 1014
},
{
"epoch": 3.72,
"learning_rate": 0.001,
"loss": 0.0861,
"step": 1016
},
{
"epoch": 3.73,
"learning_rate": 0.001,
"loss": 0.0933,
"step": 1018
},
{
"epoch": 3.74,
"learning_rate": 0.001,
"loss": 0.0833,
"step": 1020
},
{
"epoch": 3.75,
"learning_rate": 0.001,
"loss": 0.0848,
"step": 1022
},
{
"epoch": 3.75,
"learning_rate": 0.001,
"loss": 0.0896,
"step": 1024
},
{
"epoch": 3.76,
"learning_rate": 0.001,
"loss": 0.096,
"step": 1026
},
{
"epoch": 3.77,
"learning_rate": 0.001,
"loss": 0.0931,
"step": 1028
},
{
"epoch": 3.78,
"learning_rate": 0.001,
"loss": 0.0901,
"step": 1030
},
{
"epoch": 3.78,
"learning_rate": 0.001,
"loss": 0.088,
"step": 1032
},
{
"epoch": 3.79,
"learning_rate": 0.001,
"loss": 0.0956,
"step": 1034
},
{
"epoch": 3.8,
"learning_rate": 0.001,
"loss": 0.0867,
"step": 1036
},
{
"epoch": 3.81,
"learning_rate": 0.001,
"loss": 0.0801,
"step": 1038
},
{
"epoch": 3.81,
"learning_rate": 0.001,
"loss": 0.0922,
"step": 1040
},
{
"epoch": 3.82,
"learning_rate": 0.001,
"loss": 0.0925,
"step": 1042
},
{
"epoch": 3.83,
"learning_rate": 0.001,
"loss": 0.0975,
"step": 1044
},
{
"epoch": 3.83,
"learning_rate": 0.001,
"loss": 0.0977,
"step": 1046
},
{
"epoch": 3.84,
"learning_rate": 0.001,
"loss": 0.0881,
"step": 1048
},
{
"epoch": 3.85,
"learning_rate": 0.001,
"loss": 0.0903,
"step": 1050
},
{
"epoch": 3.86,
"learning_rate": 0.001,
"loss": 0.0895,
"step": 1052
},
{
"epoch": 3.86,
"learning_rate": 0.001,
"loss": 0.0948,
"step": 1054
},
{
"epoch": 3.87,
"learning_rate": 0.001,
"loss": 0.0963,
"step": 1056
},
{
"epoch": 3.88,
"learning_rate": 0.001,
"loss": 0.0846,
"step": 1058
},
{
"epoch": 3.89,
"learning_rate": 0.001,
"loss": 0.0868,
"step": 1060
},
{
"epoch": 3.89,
"learning_rate": 0.001,
"loss": 0.0916,
"step": 1062
},
{
"epoch": 3.9,
"learning_rate": 0.001,
"loss": 0.0816,
"step": 1064
},
{
"epoch": 3.91,
"learning_rate": 0.001,
"loss": 0.0853,
"step": 1066
},
{
"epoch": 3.92,
"learning_rate": 0.001,
"loss": 0.0869,
"step": 1068
},
{
"epoch": 3.92,
"learning_rate": 0.001,
"loss": 0.0836,
"step": 1070
},
{
"epoch": 3.93,
"learning_rate": 0.001,
"loss": 0.09,
"step": 1072
},
{
"epoch": 3.94,
"learning_rate": 0.001,
"loss": 0.0865,
"step": 1074
},
{
"epoch": 3.94,
"learning_rate": 0.001,
"loss": 0.0937,
"step": 1076
},
{
"epoch": 3.95,
"learning_rate": 0.001,
"loss": 0.0877,
"step": 1078
},
{
"epoch": 3.96,
"learning_rate": 0.001,
"loss": 0.0895,
"step": 1080
},
{
"epoch": 3.97,
"learning_rate": 0.001,
"loss": 0.0967,
"step": 1082
},
{
"epoch": 3.97,
"learning_rate": 0.001,
"loss": 0.1025,
"step": 1084
},
{
"epoch": 3.98,
"learning_rate": 0.001,
"loss": 0.0893,
"step": 1086
},
{
"epoch": 3.99,
"learning_rate": 0.001,
"loss": 0.0881,
"step": 1088
},
{
"epoch": 4.0,
"learning_rate": 0.001,
"loss": 0.0909,
"step": 1090
},
{
"epoch": 4.0,
"eval_gen_len": 1429.4604316546763,
"eval_loss": 3.6077892780303955,
"eval_rouge1": 41.2814,
"eval_rouge2": 13.3137,
"eval_rougeL": 17.9878,
"eval_rougeLsum": 39.2664,
"eval_runtime": 18644.4183,
"eval_samples_per_second": 0.052,
"eval_steps_per_second": 0.007,
"step": 1091
},
{
"epoch": 4.0,
"learning_rate": 0.001,
"loss": 0.0861,
"step": 1092
},
{
"epoch": 4.01,
"learning_rate": 0.001,
"loss": 0.0728,
"step": 1094
},
{
"epoch": 4.02,
"learning_rate": 0.001,
"loss": 0.0644,
"step": 1096
},
{
"epoch": 4.03,
"learning_rate": 0.001,
"loss": 0.0696,
"step": 1098
},
{
"epoch": 4.03,
"learning_rate": 0.001,
"loss": 0.0744,
"step": 1100
},
{
"epoch": 4.04,
"learning_rate": 0.001,
"loss": 0.0636,
"step": 1102
},
{
"epoch": 4.05,
"learning_rate": 0.001,
"loss": 0.0731,
"step": 1104
},
{
"epoch": 4.05,
"learning_rate": 0.001,
"loss": 0.0759,
"step": 1106
},
{
"epoch": 4.06,
"learning_rate": 0.001,
"loss": 0.0737,
"step": 1108
},
{
"epoch": 4.07,
"learning_rate": 0.001,
"loss": 0.0763,
"step": 1110
},
{
"epoch": 4.08,
"learning_rate": 0.001,
"loss": 0.0729,
"step": 1112
},
{
"epoch": 4.08,
"learning_rate": 0.001,
"loss": 0.0723,
"step": 1114
},
{
"epoch": 4.09,
"learning_rate": 0.001,
"loss": 0.0739,
"step": 1116
},
{
"epoch": 4.1,
"learning_rate": 0.001,
"loss": 0.0832,
"step": 1118
},
{
"epoch": 4.11,
"learning_rate": 0.001,
"loss": 0.0719,
"step": 1120
},
{
"epoch": 4.11,
"learning_rate": 0.001,
"loss": 0.0756,
"step": 1122
},
{
"epoch": 4.12,
"learning_rate": 0.001,
"loss": 0.0776,
"step": 1124
},
{
"epoch": 4.13,
"learning_rate": 0.001,
"loss": 0.0752,
"step": 1126
},
{
"epoch": 4.14,
"learning_rate": 0.001,
"loss": 0.0765,
"step": 1128
},
{
"epoch": 4.14,
"learning_rate": 0.001,
"loss": 0.0705,
"step": 1130
},
{
"epoch": 4.15,
"learning_rate": 0.001,
"loss": 0.0758,
"step": 1132
},
{
"epoch": 4.16,
"learning_rate": 0.001,
"loss": 0.0705,
"step": 1134
},
{
"epoch": 4.16,
"learning_rate": 0.001,
"loss": 0.0725,
"step": 1136
},
{
"epoch": 4.17,
"learning_rate": 0.001,
"loss": 0.0729,
"step": 1138
},
{
"epoch": 4.18,
"learning_rate": 0.001,
"loss": 0.0706,
"step": 1140
},
{
"epoch": 4.19,
"learning_rate": 0.001,
"loss": 0.0751,
"step": 1142
},
{
"epoch": 4.19,
"learning_rate": 0.001,
"loss": 0.0761,
"step": 1144
},
{
"epoch": 4.2,
"learning_rate": 0.001,
"loss": 0.078,
"step": 1146
},
{
"epoch": 4.21,
"learning_rate": 0.001,
"loss": 0.0743,
"step": 1148
},
{
"epoch": 4.22,
"learning_rate": 0.001,
"loss": 0.0713,
"step": 1150
},
{
"epoch": 4.22,
"learning_rate": 0.001,
"loss": 0.07,
"step": 1152
},
{
"epoch": 4.23,
"learning_rate": 0.001,
"loss": 0.0712,
"step": 1154
},
{
"epoch": 4.24,
"learning_rate": 0.001,
"loss": 0.0808,
"step": 1156
},
{
"epoch": 4.25,
"learning_rate": 0.001,
"loss": 0.0746,
"step": 1158
},
{
"epoch": 4.25,
"learning_rate": 0.001,
"loss": 0.0677,
"step": 1160
},
{
"epoch": 4.26,
"learning_rate": 0.001,
"loss": 0.073,
"step": 1162
},
{
"epoch": 4.27,
"learning_rate": 0.001,
"loss": 0.0719,
"step": 1164
},
{
"epoch": 4.27,
"learning_rate": 0.001,
"loss": 0.0817,
"step": 1166
},
{
"epoch": 4.28,
"learning_rate": 0.001,
"loss": 0.0773,
"step": 1168
},
{
"epoch": 4.29,
"learning_rate": 0.001,
"loss": 0.0763,
"step": 1170
},
{
"epoch": 4.3,
"learning_rate": 0.001,
"loss": 0.0777,
"step": 1172
},
{
"epoch": 4.3,
"learning_rate": 0.001,
"loss": 0.074,
"step": 1174
},
{
"epoch": 4.31,
"learning_rate": 0.001,
"loss": 0.0836,
"step": 1176
},
{
"epoch": 4.32,
"learning_rate": 0.001,
"loss": 0.0737,
"step": 1178
},
{
"epoch": 4.33,
"learning_rate": 0.001,
"loss": 0.0746,
"step": 1180
},
{
"epoch": 4.33,
"learning_rate": 0.001,
"loss": 0.0751,
"step": 1182
},
{
"epoch": 4.34,
"learning_rate": 0.001,
"loss": 0.081,
"step": 1184
},
{
"epoch": 4.35,
"learning_rate": 0.001,
"loss": 0.0726,
"step": 1186
},
{
"epoch": 4.36,
"learning_rate": 0.001,
"loss": 0.0768,
"step": 1188
},
{
"epoch": 4.36,
"learning_rate": 0.001,
"loss": 0.0785,
"step": 1190
},
{
"epoch": 4.37,
"learning_rate": 0.001,
"loss": 0.0703,
"step": 1192
},
{
"epoch": 4.38,
"learning_rate": 0.001,
"loss": 0.0708,
"step": 1194
},
{
"epoch": 4.38,
"learning_rate": 0.001,
"loss": 0.0789,
"step": 1196
},
{
"epoch": 4.39,
"learning_rate": 0.001,
"loss": 0.072,
"step": 1198
},
{
"epoch": 4.4,
"learning_rate": 0.001,
"loss": 0.078,
"step": 1200
},
{
"epoch": 4.41,
"learning_rate": 0.001,
"loss": 0.0791,
"step": 1202
},
{
"epoch": 4.41,
"learning_rate": 0.001,
"loss": 0.0773,
"step": 1204
},
{
"epoch": 4.42,
"learning_rate": 0.001,
"loss": 0.0826,
"step": 1206
},
{
"epoch": 4.43,
"learning_rate": 0.001,
"loss": 0.0717,
"step": 1208
},
{
"epoch": 4.44,
"learning_rate": 0.001,
"loss": 0.0724,
"step": 1210
},
{
"epoch": 4.44,
"learning_rate": 0.001,
"loss": 0.0799,
"step": 1212
},
{
"epoch": 4.45,
"learning_rate": 0.001,
"loss": 0.0734,
"step": 1214
},
{
"epoch": 4.46,
"learning_rate": 0.001,
"loss": 0.0774,
"step": 1216
},
{
"epoch": 4.47,
"learning_rate": 0.001,
"loss": 0.0771,
"step": 1218
},
{
"epoch": 4.47,
"learning_rate": 0.001,
"loss": 0.0766,
"step": 1220
},
{
"epoch": 4.48,
"learning_rate": 0.001,
"loss": 0.0789,
"step": 1222
},
{
"epoch": 4.49,
"learning_rate": 0.001,
"loss": 0.0792,
"step": 1224
},
{
"epoch": 4.49,
"learning_rate": 0.001,
"loss": 0.0752,
"step": 1226
},
{
"epoch": 4.5,
"learning_rate": 0.001,
"loss": 0.0802,
"step": 1228
},
{
"epoch": 4.51,
"learning_rate": 0.001,
"loss": 0.0796,
"step": 1230
},
{
"epoch": 4.52,
"learning_rate": 0.001,
"loss": 0.0818,
"step": 1232
},
{
"epoch": 4.52,
"learning_rate": 0.001,
"loss": 0.0838,
"step": 1234
},
{
"epoch": 4.53,
"learning_rate": 0.001,
"loss": 0.0777,
"step": 1236
},
{
"epoch": 4.54,
"learning_rate": 0.001,
"loss": 0.0782,
"step": 1238
},
{
"epoch": 4.55,
"learning_rate": 0.001,
"loss": 0.0778,
"step": 1240
},
{
"epoch": 4.55,
"learning_rate": 0.001,
"loss": 0.077,
"step": 1242
},
{
"epoch": 4.56,
"learning_rate": 0.001,
"loss": 0.0745,
"step": 1244
},
{
"epoch": 4.57,
"learning_rate": 0.001,
"loss": 0.074,
"step": 1246
},
{
"epoch": 4.58,
"learning_rate": 0.001,
"loss": 0.0863,
"step": 1248
},
{
"epoch": 4.58,
"learning_rate": 0.001,
"loss": 0.0804,
"step": 1250
},
{
"epoch": 4.59,
"learning_rate": 0.001,
"loss": 0.0749,
"step": 1252
},
{
"epoch": 4.6,
"learning_rate": 0.001,
"loss": 0.0786,
"step": 1254
},
{
"epoch": 4.6,
"learning_rate": 0.001,
"loss": 0.0787,
"step": 1256
},
{
"epoch": 4.61,
"learning_rate": 0.001,
"loss": 0.0801,
"step": 1258
},
{
"epoch": 4.62,
"learning_rate": 0.001,
"loss": 0.0859,
"step": 1260
},
{
"epoch": 4.63,
"learning_rate": 0.001,
"loss": 0.0784,
"step": 1262
},
{
"epoch": 4.63,
"learning_rate": 0.001,
"loss": 0.0757,
"step": 1264
},
{
"epoch": 4.64,
"learning_rate": 0.001,
"loss": 0.0773,
"step": 1266
},
{
"epoch": 4.65,
"learning_rate": 0.001,
"loss": 0.0875,
"step": 1268
},
{
"epoch": 4.66,
"learning_rate": 0.001,
"loss": 0.0781,
"step": 1270
},
{
"epoch": 4.66,
"learning_rate": 0.001,
"loss": 0.0843,
"step": 1272
},
{
"epoch": 4.67,
"learning_rate": 0.001,
"loss": 0.0761,
"step": 1274
},
{
"epoch": 4.68,
"learning_rate": 0.001,
"loss": 0.0804,
"step": 1276
},
{
"epoch": 4.69,
"learning_rate": 0.001,
"loss": 0.0791,
"step": 1278
},
{
"epoch": 4.69,
"learning_rate": 0.001,
"loss": 0.0801,
"step": 1280
},
{
"epoch": 4.7,
"learning_rate": 0.001,
"loss": 0.0832,
"step": 1282
},
{
"epoch": 4.71,
"learning_rate": 0.001,
"loss": 0.0775,
"step": 1284
},
{
"epoch": 4.71,
"learning_rate": 0.001,
"loss": 0.0763,
"step": 1286
},
{
"epoch": 4.72,
"learning_rate": 0.001,
"loss": 0.0799,
"step": 1288
},
{
"epoch": 4.73,
"learning_rate": 0.001,
"loss": 0.0843,
"step": 1290
},
{
"epoch": 4.74,
"learning_rate": 0.001,
"loss": 0.0802,
"step": 1292
},
{
"epoch": 4.74,
"learning_rate": 0.001,
"loss": 0.0828,
"step": 1294
},
{
"epoch": 4.75,
"learning_rate": 0.001,
"loss": 0.0778,
"step": 1296
},
{
"epoch": 4.76,
"learning_rate": 0.001,
"loss": 0.0773,
"step": 1298
},
{
"epoch": 4.77,
"learning_rate": 0.001,
"loss": 0.0784,
"step": 1300
},
{
"epoch": 4.77,
"learning_rate": 0.001,
"loss": 0.0796,
"step": 1302
},
{
"epoch": 4.78,
"learning_rate": 0.001,
"loss": 0.079,
"step": 1304
},
{
"epoch": 4.79,
"learning_rate": 0.001,
"loss": 0.0813,
"step": 1306
},
{
"epoch": 4.8,
"learning_rate": 0.001,
"loss": 0.0812,
"step": 1308
},
{
"epoch": 4.8,
"learning_rate": 0.001,
"loss": 0.0825,
"step": 1310
},
{
"epoch": 4.81,
"learning_rate": 0.001,
"loss": 0.0753,
"step": 1312
},
{
"epoch": 4.82,
"learning_rate": 0.001,
"loss": 0.0799,
"step": 1314
},
{
"epoch": 4.82,
"learning_rate": 0.001,
"loss": 0.0745,
"step": 1316
},
{
"epoch": 4.83,
"learning_rate": 0.001,
"loss": 0.0776,
"step": 1318
},
{
"epoch": 4.84,
"learning_rate": 0.001,
"loss": 0.0835,
"step": 1320
},
{
"epoch": 4.85,
"learning_rate": 0.001,
"loss": 0.0798,
"step": 1322
},
{
"epoch": 4.85,
"learning_rate": 0.001,
"loss": 0.0777,
"step": 1324
},
{
"epoch": 4.86,
"learning_rate": 0.001,
"loss": 0.081,
"step": 1326
},
{
"epoch": 4.87,
"learning_rate": 0.001,
"loss": 0.0746,
"step": 1328
},
{
"epoch": 4.88,
"learning_rate": 0.001,
"loss": 0.0815,
"step": 1330
},
{
"epoch": 4.88,
"learning_rate": 0.001,
"loss": 0.0779,
"step": 1332
},
{
"epoch": 4.89,
"learning_rate": 0.001,
"loss": 0.0836,
"step": 1334
},
{
"epoch": 4.9,
"learning_rate": 0.001,
"loss": 0.0822,
"step": 1336
},
{
"epoch": 4.91,
"learning_rate": 0.001,
"loss": 0.0861,
"step": 1338
},
{
"epoch": 4.91,
"learning_rate": 0.001,
"loss": 0.081,
"step": 1340
},
{
"epoch": 4.92,
"learning_rate": 0.001,
"loss": 0.0849,
"step": 1342
},
{
"epoch": 4.93,
"learning_rate": 0.001,
"loss": 0.0848,
"step": 1344
},
{
"epoch": 4.93,
"learning_rate": 0.001,
"loss": 0.0832,
"step": 1346
},
{
"epoch": 4.94,
"learning_rate": 0.001,
"loss": 0.0799,
"step": 1348
},
{
"epoch": 4.95,
"learning_rate": 0.001,
"loss": 0.0833,
"step": 1350
},
{
"epoch": 4.96,
"learning_rate": 0.001,
"loss": 0.0804,
"step": 1352
},
{
"epoch": 4.96,
"learning_rate": 0.001,
"loss": 0.0844,
"step": 1354
},
{
"epoch": 4.97,
"learning_rate": 0.001,
"loss": 0.079,
"step": 1356
},
{
"epoch": 4.98,
"learning_rate": 0.001,
"loss": 0.0787,
"step": 1358
},
{
"epoch": 4.99,
"learning_rate": 0.001,
"loss": 0.0834,
"step": 1360
},
{
"epoch": 4.99,
"eval_gen_len": 1559.3237410071943,
"eval_loss": 3.8802897930145264,
"eval_rouge1": 42.0328,
"eval_rouge2": 13.9186,
"eval_rougeL": 17.8203,
"eval_rougeLsum": 39.9705,
"eval_runtime": 19337.1139,
"eval_samples_per_second": 0.05,
"eval_steps_per_second": 0.006,
"step": 1360
},
{
"epoch": 4.99,
"step": 1360,
"total_flos": 1.024762577636008e+18,
"train_loss": 0.10190736966974595,
"train_runtime": 144636.3155,
"train_samples_per_second": 0.603,
"train_steps_per_second": 0.009
}
],
"logging_steps": 2,
"max_steps": 1360,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 1.024762577636008e+18,
"trial_name": null,
"trial_params": null
}