longt5_xl_gov_memsum_bp_5 / trainer_state.json
learn3r's picture
End of training
f6c33a3
{
"best_metric": 0.9812858700752258,
"best_model_checkpoint": "/exports/eddie/scratch/s1970716/models/summarization/longt5_xl_gov_memsum_bp_5/checkpoint-545",
"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": 2.3199,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.001,
"loss": 2.6972,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 0.001,
"loss": 2.4846,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 0.001,
"loss": 2.2489,
"step": 8
},
{
"epoch": 0.04,
"learning_rate": 0.001,
"loss": 1.7989,
"step": 10
},
{
"epoch": 0.04,
"learning_rate": 0.001,
"loss": 2.0537,
"step": 12
},
{
"epoch": 0.05,
"learning_rate": 0.001,
"loss": 1.82,
"step": 14
},
{
"epoch": 0.06,
"learning_rate": 0.001,
"loss": 1.6399,
"step": 16
},
{
"epoch": 0.07,
"learning_rate": 0.001,
"loss": 1.6058,
"step": 18
},
{
"epoch": 0.07,
"learning_rate": 0.001,
"loss": 1.4554,
"step": 20
},
{
"epoch": 0.08,
"learning_rate": 0.001,
"loss": 1.3491,
"step": 22
},
{
"epoch": 0.09,
"learning_rate": 0.001,
"loss": 1.382,
"step": 24
},
{
"epoch": 0.1,
"learning_rate": 0.001,
"loss": 1.4308,
"step": 26
},
{
"epoch": 0.1,
"learning_rate": 0.001,
"loss": 1.3403,
"step": 28
},
{
"epoch": 0.11,
"learning_rate": 0.001,
"loss": 1.3476,
"step": 30
},
{
"epoch": 0.12,
"learning_rate": 0.001,
"loss": 1.2751,
"step": 32
},
{
"epoch": 0.12,
"learning_rate": 0.001,
"loss": 1.2912,
"step": 34
},
{
"epoch": 0.13,
"learning_rate": 0.001,
"loss": 1.3603,
"step": 36
},
{
"epoch": 0.14,
"learning_rate": 0.001,
"loss": 1.2857,
"step": 38
},
{
"epoch": 0.15,
"learning_rate": 0.001,
"loss": 1.3147,
"step": 40
},
{
"epoch": 0.15,
"learning_rate": 0.001,
"loss": 1.2518,
"step": 42
},
{
"epoch": 0.16,
"learning_rate": 0.001,
"loss": 1.3015,
"step": 44
},
{
"epoch": 0.17,
"learning_rate": 0.001,
"loss": 1.2773,
"step": 46
},
{
"epoch": 0.18,
"learning_rate": 0.001,
"loss": 1.2587,
"step": 48
},
{
"epoch": 0.18,
"learning_rate": 0.001,
"loss": 1.3195,
"step": 50
},
{
"epoch": 0.19,
"learning_rate": 0.001,
"loss": 1.3071,
"step": 52
},
{
"epoch": 0.2,
"learning_rate": 0.001,
"loss": 1.2566,
"step": 54
},
{
"epoch": 0.21,
"learning_rate": 0.001,
"loss": 1.2417,
"step": 56
},
{
"epoch": 0.21,
"learning_rate": 0.001,
"loss": 1.2736,
"step": 58
},
{
"epoch": 0.22,
"learning_rate": 0.001,
"loss": 1.3336,
"step": 60
},
{
"epoch": 0.23,
"learning_rate": 0.001,
"loss": 1.25,
"step": 62
},
{
"epoch": 0.23,
"learning_rate": 0.001,
"loss": 1.2149,
"step": 64
},
{
"epoch": 0.24,
"learning_rate": 0.001,
"loss": 1.2396,
"step": 66
},
{
"epoch": 0.25,
"learning_rate": 0.001,
"loss": 1.3529,
"step": 68
},
{
"epoch": 0.26,
"learning_rate": 0.001,
"loss": 1.5073,
"step": 70
},
{
"epoch": 0.26,
"learning_rate": 0.001,
"loss": 1.3049,
"step": 72
},
{
"epoch": 0.27,
"learning_rate": 0.001,
"loss": 1.3049,
"step": 74
},
{
"epoch": 0.28,
"learning_rate": 0.001,
"loss": 1.6649,
"step": 76
},
{
"epoch": 0.29,
"learning_rate": 0.001,
"loss": 1.2797,
"step": 78
},
{
"epoch": 0.29,
"learning_rate": 0.001,
"loss": 1.2776,
"step": 80
},
{
"epoch": 0.3,
"learning_rate": 0.001,
"loss": 1.2459,
"step": 82
},
{
"epoch": 0.31,
"learning_rate": 0.001,
"loss": 1.1837,
"step": 84
},
{
"epoch": 0.32,
"learning_rate": 0.001,
"loss": 1.224,
"step": 86
},
{
"epoch": 0.32,
"learning_rate": 0.001,
"loss": 1.3087,
"step": 88
},
{
"epoch": 0.33,
"learning_rate": 0.001,
"loss": 1.2391,
"step": 90
},
{
"epoch": 0.34,
"learning_rate": 0.001,
"loss": 1.1851,
"step": 92
},
{
"epoch": 0.34,
"learning_rate": 0.001,
"loss": 1.2348,
"step": 94
},
{
"epoch": 0.35,
"learning_rate": 0.001,
"loss": 1.1831,
"step": 96
},
{
"epoch": 0.36,
"learning_rate": 0.001,
"loss": 1.2093,
"step": 98
},
{
"epoch": 0.37,
"learning_rate": 0.001,
"loss": 1.1663,
"step": 100
},
{
"epoch": 0.37,
"learning_rate": 0.001,
"loss": 1.2066,
"step": 102
},
{
"epoch": 0.38,
"learning_rate": 0.001,
"loss": 1.1711,
"step": 104
},
{
"epoch": 0.39,
"learning_rate": 0.001,
"loss": 1.1926,
"step": 106
},
{
"epoch": 0.4,
"learning_rate": 0.001,
"loss": 1.1504,
"step": 108
},
{
"epoch": 0.4,
"learning_rate": 0.001,
"loss": 1.1984,
"step": 110
},
{
"epoch": 0.41,
"learning_rate": 0.001,
"loss": 1.2218,
"step": 112
},
{
"epoch": 0.42,
"learning_rate": 0.001,
"loss": 1.2318,
"step": 114
},
{
"epoch": 0.43,
"learning_rate": 0.001,
"loss": 1.2617,
"step": 116
},
{
"epoch": 0.43,
"learning_rate": 0.001,
"loss": 1.406,
"step": 118
},
{
"epoch": 0.44,
"learning_rate": 0.001,
"loss": 1.3139,
"step": 120
},
{
"epoch": 0.45,
"learning_rate": 0.001,
"loss": 1.2415,
"step": 122
},
{
"epoch": 0.45,
"learning_rate": 0.001,
"loss": 1.1551,
"step": 124
},
{
"epoch": 0.46,
"learning_rate": 0.001,
"loss": 1.1821,
"step": 126
},
{
"epoch": 0.47,
"learning_rate": 0.001,
"loss": 1.1638,
"step": 128
},
{
"epoch": 0.48,
"learning_rate": 0.001,
"loss": 1.1399,
"step": 130
},
{
"epoch": 0.48,
"learning_rate": 0.001,
"loss": 1.1848,
"step": 132
},
{
"epoch": 0.49,
"learning_rate": 0.001,
"loss": 1.1916,
"step": 134
},
{
"epoch": 0.5,
"learning_rate": 0.001,
"loss": 1.1594,
"step": 136
},
{
"epoch": 0.51,
"learning_rate": 0.001,
"loss": 1.1848,
"step": 138
},
{
"epoch": 0.51,
"learning_rate": 0.001,
"loss": 1.154,
"step": 140
},
{
"epoch": 0.52,
"learning_rate": 0.001,
"loss": 1.1906,
"step": 142
},
{
"epoch": 0.53,
"learning_rate": 0.001,
"loss": 1.1621,
"step": 144
},
{
"epoch": 0.54,
"learning_rate": 0.001,
"loss": 1.1693,
"step": 146
},
{
"epoch": 0.54,
"learning_rate": 0.001,
"loss": 1.1569,
"step": 148
},
{
"epoch": 0.55,
"learning_rate": 0.001,
"loss": 1.1765,
"step": 150
},
{
"epoch": 0.56,
"learning_rate": 0.001,
"loss": 1.2398,
"step": 152
},
{
"epoch": 0.56,
"learning_rate": 0.001,
"loss": 1.2043,
"step": 154
},
{
"epoch": 0.57,
"learning_rate": 0.001,
"loss": 1.1911,
"step": 156
},
{
"epoch": 0.58,
"learning_rate": 0.001,
"loss": 1.1335,
"step": 158
},
{
"epoch": 0.59,
"learning_rate": 0.001,
"loss": 1.1646,
"step": 160
},
{
"epoch": 0.59,
"learning_rate": 0.001,
"loss": 1.2031,
"step": 162
},
{
"epoch": 0.6,
"learning_rate": 0.001,
"loss": 1.1645,
"step": 164
},
{
"epoch": 0.61,
"learning_rate": 0.001,
"loss": 1.1557,
"step": 166
},
{
"epoch": 0.62,
"learning_rate": 0.001,
"loss": 1.1505,
"step": 168
},
{
"epoch": 0.62,
"learning_rate": 0.001,
"loss": 1.1983,
"step": 170
},
{
"epoch": 0.63,
"learning_rate": 0.001,
"loss": 1.2098,
"step": 172
},
{
"epoch": 0.64,
"learning_rate": 0.001,
"loss": 1.1767,
"step": 174
},
{
"epoch": 0.65,
"learning_rate": 0.001,
"loss": 1.169,
"step": 176
},
{
"epoch": 0.65,
"learning_rate": 0.001,
"loss": 1.1461,
"step": 178
},
{
"epoch": 0.66,
"learning_rate": 0.001,
"loss": 1.2169,
"step": 180
},
{
"epoch": 0.67,
"learning_rate": 0.001,
"loss": 1.1584,
"step": 182
},
{
"epoch": 0.67,
"learning_rate": 0.001,
"loss": 1.1539,
"step": 184
},
{
"epoch": 0.68,
"learning_rate": 0.001,
"loss": 1.1421,
"step": 186
},
{
"epoch": 0.69,
"learning_rate": 0.001,
"loss": 1.1412,
"step": 188
},
{
"epoch": 0.7,
"learning_rate": 0.001,
"loss": 1.1248,
"step": 190
},
{
"epoch": 0.7,
"learning_rate": 0.001,
"loss": 1.1653,
"step": 192
},
{
"epoch": 0.71,
"learning_rate": 0.001,
"loss": 1.1376,
"step": 194
},
{
"epoch": 0.72,
"learning_rate": 0.001,
"loss": 1.1727,
"step": 196
},
{
"epoch": 0.73,
"learning_rate": 0.001,
"loss": 1.1851,
"step": 198
},
{
"epoch": 0.73,
"learning_rate": 0.001,
"loss": 1.1614,
"step": 200
},
{
"epoch": 0.74,
"learning_rate": 0.001,
"loss": 1.1994,
"step": 202
},
{
"epoch": 0.75,
"learning_rate": 0.001,
"loss": 1.1541,
"step": 204
},
{
"epoch": 0.76,
"learning_rate": 0.001,
"loss": 1.175,
"step": 206
},
{
"epoch": 0.76,
"learning_rate": 0.001,
"loss": 1.1941,
"step": 208
},
{
"epoch": 0.77,
"learning_rate": 0.001,
"loss": 1.1663,
"step": 210
},
{
"epoch": 0.78,
"learning_rate": 0.001,
"loss": 1.1243,
"step": 212
},
{
"epoch": 0.78,
"learning_rate": 0.001,
"loss": 1.1465,
"step": 214
},
{
"epoch": 0.79,
"learning_rate": 0.001,
"loss": 1.1616,
"step": 216
},
{
"epoch": 0.8,
"learning_rate": 0.001,
"loss": 1.1697,
"step": 218
},
{
"epoch": 0.81,
"learning_rate": 0.001,
"loss": 1.1376,
"step": 220
},
{
"epoch": 0.81,
"learning_rate": 0.001,
"loss": 1.1699,
"step": 222
},
{
"epoch": 0.82,
"learning_rate": 0.001,
"loss": 1.1619,
"step": 224
},
{
"epoch": 0.83,
"learning_rate": 0.001,
"loss": 1.1349,
"step": 226
},
{
"epoch": 0.84,
"learning_rate": 0.001,
"loss": 1.1263,
"step": 228
},
{
"epoch": 0.84,
"learning_rate": 0.001,
"loss": 1.1304,
"step": 230
},
{
"epoch": 0.85,
"learning_rate": 0.001,
"loss": 1.13,
"step": 232
},
{
"epoch": 0.86,
"learning_rate": 0.001,
"loss": 1.1442,
"step": 234
},
{
"epoch": 0.87,
"learning_rate": 0.001,
"loss": 1.1331,
"step": 236
},
{
"epoch": 0.87,
"learning_rate": 0.001,
"loss": 1.0813,
"step": 238
},
{
"epoch": 0.88,
"learning_rate": 0.001,
"loss": 1.107,
"step": 240
},
{
"epoch": 0.89,
"learning_rate": 0.001,
"loss": 1.1646,
"step": 242
},
{
"epoch": 0.89,
"learning_rate": 0.001,
"loss": 1.1712,
"step": 244
},
{
"epoch": 0.9,
"learning_rate": 0.001,
"loss": 1.1394,
"step": 246
},
{
"epoch": 0.91,
"learning_rate": 0.001,
"loss": 1.1199,
"step": 248
},
{
"epoch": 0.92,
"learning_rate": 0.001,
"loss": 1.1012,
"step": 250
},
{
"epoch": 0.92,
"learning_rate": 0.001,
"loss": 1.1548,
"step": 252
},
{
"epoch": 0.93,
"learning_rate": 0.001,
"loss": 1.099,
"step": 254
},
{
"epoch": 0.94,
"learning_rate": 0.001,
"loss": 1.1112,
"step": 256
},
{
"epoch": 0.95,
"learning_rate": 0.001,
"loss": 1.1163,
"step": 258
},
{
"epoch": 0.95,
"learning_rate": 0.001,
"loss": 1.1469,
"step": 260
},
{
"epoch": 0.96,
"learning_rate": 0.001,
"loss": 1.1138,
"step": 262
},
{
"epoch": 0.97,
"learning_rate": 0.001,
"loss": 1.1227,
"step": 264
},
{
"epoch": 0.98,
"learning_rate": 0.001,
"loss": 1.1265,
"step": 266
},
{
"epoch": 0.98,
"learning_rate": 0.001,
"loss": 1.1456,
"step": 268
},
{
"epoch": 0.99,
"learning_rate": 0.001,
"loss": 1.1151,
"step": 270
},
{
"epoch": 1.0,
"learning_rate": 0.001,
"loss": 1.1562,
"step": 272
},
{
"epoch": 1.0,
"eval_gen_len": 1844.1543209876543,
"eval_loss": 1.0104926824569702,
"eval_rouge1": 37.2934,
"eval_rouge2": 18.6683,
"eval_rougeL": 24.0563,
"eval_rougeLsum": 35.6575,
"eval_runtime": 10962.7631,
"eval_samples_per_second": 0.089,
"eval_steps_per_second": 0.011,
"step": 272
},
{
"epoch": 1.0,
"learning_rate": 0.001,
"loss": 1.0421,
"step": 274
},
{
"epoch": 1.01,
"learning_rate": 0.001,
"loss": 0.9781,
"step": 276
},
{
"epoch": 1.02,
"learning_rate": 0.001,
"loss": 0.9783,
"step": 278
},
{
"epoch": 1.03,
"learning_rate": 0.001,
"loss": 1.0039,
"step": 280
},
{
"epoch": 1.03,
"learning_rate": 0.001,
"loss": 0.9628,
"step": 282
},
{
"epoch": 1.04,
"learning_rate": 0.001,
"loss": 0.9647,
"step": 284
},
{
"epoch": 1.05,
"learning_rate": 0.001,
"loss": 0.935,
"step": 286
},
{
"epoch": 1.06,
"learning_rate": 0.001,
"loss": 0.9836,
"step": 288
},
{
"epoch": 1.06,
"learning_rate": 0.001,
"loss": 1.0144,
"step": 290
},
{
"epoch": 1.07,
"learning_rate": 0.001,
"loss": 0.9635,
"step": 292
},
{
"epoch": 1.08,
"learning_rate": 0.001,
"loss": 0.937,
"step": 294
},
{
"epoch": 1.09,
"learning_rate": 0.001,
"loss": 0.9641,
"step": 296
},
{
"epoch": 1.09,
"learning_rate": 0.001,
"loss": 0.9916,
"step": 298
},
{
"epoch": 1.1,
"learning_rate": 0.001,
"loss": 0.9986,
"step": 300
},
{
"epoch": 1.11,
"learning_rate": 0.001,
"loss": 0.9728,
"step": 302
},
{
"epoch": 1.11,
"learning_rate": 0.001,
"loss": 0.9489,
"step": 304
},
{
"epoch": 1.12,
"learning_rate": 0.001,
"loss": 0.9865,
"step": 306
},
{
"epoch": 1.13,
"learning_rate": 0.001,
"loss": 0.9924,
"step": 308
},
{
"epoch": 1.14,
"learning_rate": 0.001,
"loss": 0.9788,
"step": 310
},
{
"epoch": 1.14,
"learning_rate": 0.001,
"loss": 0.9855,
"step": 312
},
{
"epoch": 1.15,
"learning_rate": 0.001,
"loss": 0.9811,
"step": 314
},
{
"epoch": 1.16,
"learning_rate": 0.001,
"loss": 0.992,
"step": 316
},
{
"epoch": 1.17,
"learning_rate": 0.001,
"loss": 0.9494,
"step": 318
},
{
"epoch": 1.17,
"learning_rate": 0.001,
"loss": 0.9712,
"step": 320
},
{
"epoch": 1.18,
"learning_rate": 0.001,
"loss": 0.9647,
"step": 322
},
{
"epoch": 1.19,
"learning_rate": 0.001,
"loss": 0.9791,
"step": 324
},
{
"epoch": 1.2,
"learning_rate": 0.001,
"loss": 0.9906,
"step": 326
},
{
"epoch": 1.2,
"learning_rate": 0.001,
"loss": 1.0004,
"step": 328
},
{
"epoch": 1.21,
"learning_rate": 0.001,
"loss": 1.001,
"step": 330
},
{
"epoch": 1.22,
"learning_rate": 0.001,
"loss": 0.9532,
"step": 332
},
{
"epoch": 1.22,
"learning_rate": 0.001,
"loss": 0.9923,
"step": 334
},
{
"epoch": 1.23,
"learning_rate": 0.001,
"loss": 1.0033,
"step": 336
},
{
"epoch": 1.24,
"learning_rate": 0.001,
"loss": 0.9464,
"step": 338
},
{
"epoch": 1.25,
"learning_rate": 0.001,
"loss": 0.9697,
"step": 340
},
{
"epoch": 1.25,
"learning_rate": 0.001,
"loss": 0.978,
"step": 342
},
{
"epoch": 1.26,
"learning_rate": 0.001,
"loss": 0.9997,
"step": 344
},
{
"epoch": 1.27,
"learning_rate": 0.001,
"loss": 0.9763,
"step": 346
},
{
"epoch": 1.28,
"learning_rate": 0.001,
"loss": 0.9878,
"step": 348
},
{
"epoch": 1.28,
"learning_rate": 0.001,
"loss": 0.9629,
"step": 350
},
{
"epoch": 1.29,
"learning_rate": 0.001,
"loss": 0.9588,
"step": 352
},
{
"epoch": 1.3,
"learning_rate": 0.001,
"loss": 0.9859,
"step": 354
},
{
"epoch": 1.31,
"learning_rate": 0.001,
"loss": 0.9473,
"step": 356
},
{
"epoch": 1.31,
"learning_rate": 0.001,
"loss": 1.01,
"step": 358
},
{
"epoch": 1.32,
"learning_rate": 0.001,
"loss": 0.9728,
"step": 360
},
{
"epoch": 1.33,
"learning_rate": 0.001,
"loss": 0.9789,
"step": 362
},
{
"epoch": 1.33,
"learning_rate": 0.001,
"loss": 0.9787,
"step": 364
},
{
"epoch": 1.34,
"learning_rate": 0.001,
"loss": 0.9864,
"step": 366
},
{
"epoch": 1.35,
"learning_rate": 0.001,
"loss": 0.9918,
"step": 368
},
{
"epoch": 1.36,
"learning_rate": 0.001,
"loss": 0.9948,
"step": 370
},
{
"epoch": 1.36,
"learning_rate": 0.001,
"loss": 0.9881,
"step": 372
},
{
"epoch": 1.37,
"learning_rate": 0.001,
"loss": 1.0027,
"step": 374
},
{
"epoch": 1.38,
"learning_rate": 0.001,
"loss": 0.9659,
"step": 376
},
{
"epoch": 1.39,
"learning_rate": 0.001,
"loss": 0.9712,
"step": 378
},
{
"epoch": 1.39,
"learning_rate": 0.001,
"loss": 0.9983,
"step": 380
},
{
"epoch": 1.4,
"learning_rate": 0.001,
"loss": 0.9956,
"step": 382
},
{
"epoch": 1.41,
"learning_rate": 0.001,
"loss": 1.0098,
"step": 384
},
{
"epoch": 1.42,
"learning_rate": 0.001,
"loss": 0.995,
"step": 386
},
{
"epoch": 1.42,
"learning_rate": 0.001,
"loss": 0.9596,
"step": 388
},
{
"epoch": 1.43,
"learning_rate": 0.001,
"loss": 0.9629,
"step": 390
},
{
"epoch": 1.44,
"learning_rate": 0.001,
"loss": 0.9696,
"step": 392
},
{
"epoch": 1.44,
"learning_rate": 0.001,
"loss": 0.9701,
"step": 394
},
{
"epoch": 1.45,
"learning_rate": 0.001,
"loss": 0.9607,
"step": 396
},
{
"epoch": 1.46,
"learning_rate": 0.001,
"loss": 0.9868,
"step": 398
},
{
"epoch": 1.47,
"learning_rate": 0.001,
"loss": 0.993,
"step": 400
},
{
"epoch": 1.47,
"learning_rate": 0.001,
"loss": 0.9637,
"step": 402
},
{
"epoch": 1.48,
"learning_rate": 0.001,
"loss": 0.9746,
"step": 404
},
{
"epoch": 1.49,
"learning_rate": 0.001,
"loss": 1.0091,
"step": 406
},
{
"epoch": 1.5,
"learning_rate": 0.001,
"loss": 0.9819,
"step": 408
},
{
"epoch": 1.5,
"learning_rate": 0.001,
"loss": 0.9772,
"step": 410
},
{
"epoch": 1.51,
"learning_rate": 0.001,
"loss": 0.9933,
"step": 412
},
{
"epoch": 1.52,
"learning_rate": 0.001,
"loss": 0.9852,
"step": 414
},
{
"epoch": 1.53,
"learning_rate": 0.001,
"loss": 0.9918,
"step": 416
},
{
"epoch": 1.53,
"learning_rate": 0.001,
"loss": 0.9583,
"step": 418
},
{
"epoch": 1.54,
"learning_rate": 0.001,
"loss": 0.9896,
"step": 420
},
{
"epoch": 1.55,
"learning_rate": 0.001,
"loss": 0.9684,
"step": 422
},
{
"epoch": 1.55,
"learning_rate": 0.001,
"loss": 0.9797,
"step": 424
},
{
"epoch": 1.56,
"learning_rate": 0.001,
"loss": 1.004,
"step": 426
},
{
"epoch": 1.57,
"learning_rate": 0.001,
"loss": 0.9716,
"step": 428
},
{
"epoch": 1.58,
"learning_rate": 0.001,
"loss": 1.0082,
"step": 430
},
{
"epoch": 1.58,
"learning_rate": 0.001,
"loss": 1.0011,
"step": 432
},
{
"epoch": 1.59,
"learning_rate": 0.001,
"loss": 0.9768,
"step": 434
},
{
"epoch": 1.6,
"learning_rate": 0.001,
"loss": 0.9363,
"step": 436
},
{
"epoch": 1.61,
"learning_rate": 0.001,
"loss": 1.0039,
"step": 438
},
{
"epoch": 1.61,
"learning_rate": 0.001,
"loss": 1.0078,
"step": 440
},
{
"epoch": 1.62,
"learning_rate": 0.001,
"loss": 0.9949,
"step": 442
},
{
"epoch": 1.63,
"learning_rate": 0.001,
"loss": 1.0016,
"step": 444
},
{
"epoch": 1.64,
"learning_rate": 0.001,
"loss": 0.9501,
"step": 446
},
{
"epoch": 1.64,
"learning_rate": 0.001,
"loss": 0.9875,
"step": 448
},
{
"epoch": 1.65,
"learning_rate": 0.001,
"loss": 0.9951,
"step": 450
},
{
"epoch": 1.66,
"learning_rate": 0.001,
"loss": 0.9695,
"step": 452
},
{
"epoch": 1.66,
"learning_rate": 0.001,
"loss": 1.0316,
"step": 454
},
{
"epoch": 1.67,
"learning_rate": 0.001,
"loss": 0.9619,
"step": 456
},
{
"epoch": 1.68,
"learning_rate": 0.001,
"loss": 0.9537,
"step": 458
},
{
"epoch": 1.69,
"learning_rate": 0.001,
"loss": 1.0,
"step": 460
},
{
"epoch": 1.69,
"learning_rate": 0.001,
"loss": 0.9789,
"step": 462
},
{
"epoch": 1.7,
"learning_rate": 0.001,
"loss": 0.997,
"step": 464
},
{
"epoch": 1.71,
"learning_rate": 0.001,
"loss": 0.9777,
"step": 466
},
{
"epoch": 1.72,
"learning_rate": 0.001,
"loss": 0.9825,
"step": 468
},
{
"epoch": 1.72,
"learning_rate": 0.001,
"loss": 1.0084,
"step": 470
},
{
"epoch": 1.73,
"learning_rate": 0.001,
"loss": 0.9607,
"step": 472
},
{
"epoch": 1.74,
"learning_rate": 0.001,
"loss": 1.0183,
"step": 474
},
{
"epoch": 1.75,
"learning_rate": 0.001,
"loss": 0.9916,
"step": 476
},
{
"epoch": 1.75,
"learning_rate": 0.001,
"loss": 1.0227,
"step": 478
},
{
"epoch": 1.76,
"learning_rate": 0.001,
"loss": 0.956,
"step": 480
},
{
"epoch": 1.77,
"learning_rate": 0.001,
"loss": 0.9916,
"step": 482
},
{
"epoch": 1.77,
"learning_rate": 0.001,
"loss": 0.9962,
"step": 484
},
{
"epoch": 1.78,
"learning_rate": 0.001,
"loss": 0.9903,
"step": 486
},
{
"epoch": 1.79,
"learning_rate": 0.001,
"loss": 0.9831,
"step": 488
},
{
"epoch": 1.8,
"learning_rate": 0.001,
"loss": 0.9933,
"step": 490
},
{
"epoch": 1.8,
"learning_rate": 0.001,
"loss": 0.9936,
"step": 492
},
{
"epoch": 1.81,
"learning_rate": 0.001,
"loss": 0.9966,
"step": 494
},
{
"epoch": 1.82,
"learning_rate": 0.001,
"loss": 0.9907,
"step": 496
},
{
"epoch": 1.83,
"learning_rate": 0.001,
"loss": 0.9722,
"step": 498
},
{
"epoch": 1.83,
"learning_rate": 0.001,
"loss": 0.9932,
"step": 500
},
{
"epoch": 1.84,
"learning_rate": 0.001,
"loss": 0.9702,
"step": 502
},
{
"epoch": 1.85,
"learning_rate": 0.001,
"loss": 0.9874,
"step": 504
},
{
"epoch": 1.86,
"learning_rate": 0.001,
"loss": 0.9871,
"step": 506
},
{
"epoch": 1.86,
"learning_rate": 0.001,
"loss": 1.0175,
"step": 508
},
{
"epoch": 1.87,
"learning_rate": 0.001,
"loss": 0.97,
"step": 510
},
{
"epoch": 1.88,
"learning_rate": 0.001,
"loss": 0.9787,
"step": 512
},
{
"epoch": 1.88,
"learning_rate": 0.001,
"loss": 0.9891,
"step": 514
},
{
"epoch": 1.89,
"learning_rate": 0.001,
"loss": 0.9447,
"step": 516
},
{
"epoch": 1.9,
"learning_rate": 0.001,
"loss": 0.983,
"step": 518
},
{
"epoch": 1.91,
"learning_rate": 0.001,
"loss": 0.9812,
"step": 520
},
{
"epoch": 1.91,
"learning_rate": 0.001,
"loss": 0.9698,
"step": 522
},
{
"epoch": 1.92,
"learning_rate": 0.001,
"loss": 0.9583,
"step": 524
},
{
"epoch": 1.93,
"learning_rate": 0.001,
"loss": 0.9837,
"step": 526
},
{
"epoch": 1.94,
"learning_rate": 0.001,
"loss": 0.9537,
"step": 528
},
{
"epoch": 1.94,
"learning_rate": 0.001,
"loss": 0.9732,
"step": 530
},
{
"epoch": 1.95,
"learning_rate": 0.001,
"loss": 1.0053,
"step": 532
},
{
"epoch": 1.96,
"learning_rate": 0.001,
"loss": 0.9955,
"step": 534
},
{
"epoch": 1.97,
"learning_rate": 0.001,
"loss": 0.9691,
"step": 536
},
{
"epoch": 1.97,
"learning_rate": 0.001,
"loss": 0.9888,
"step": 538
},
{
"epoch": 1.98,
"learning_rate": 0.001,
"loss": 0.9976,
"step": 540
},
{
"epoch": 1.99,
"learning_rate": 0.001,
"loss": 0.9564,
"step": 542
},
{
"epoch": 1.99,
"learning_rate": 0.001,
"loss": 0.9737,
"step": 544
},
{
"epoch": 2.0,
"eval_gen_len": 1101.6059670781892,
"eval_loss": 0.9812858700752258,
"eval_rouge1": 55.1149,
"eval_rouge2": 30.149,
"eval_rougeL": 31.9694,
"eval_rougeLsum": 52.9549,
"eval_runtime": 10608.1658,
"eval_samples_per_second": 0.092,
"eval_steps_per_second": 0.012,
"step": 545
},
{
"epoch": 2.0,
"learning_rate": 0.001,
"loss": 0.9727,
"step": 546
},
{
"epoch": 2.01,
"learning_rate": 0.001,
"loss": 0.8105,
"step": 548
},
{
"epoch": 2.02,
"learning_rate": 0.001,
"loss": 0.8063,
"step": 550
},
{
"epoch": 2.02,
"learning_rate": 0.001,
"loss": 0.7334,
"step": 552
},
{
"epoch": 2.03,
"learning_rate": 0.001,
"loss": 0.7668,
"step": 554
},
{
"epoch": 2.04,
"learning_rate": 0.001,
"loss": 0.7995,
"step": 556
},
{
"epoch": 2.05,
"learning_rate": 0.001,
"loss": 0.822,
"step": 558
},
{
"epoch": 2.05,
"learning_rate": 0.001,
"loss": 0.7847,
"step": 560
},
{
"epoch": 2.06,
"learning_rate": 0.001,
"loss": 0.8024,
"step": 562
},
{
"epoch": 2.07,
"learning_rate": 0.001,
"loss": 0.7899,
"step": 564
},
{
"epoch": 2.08,
"learning_rate": 0.001,
"loss": 0.7798,
"step": 566
},
{
"epoch": 2.08,
"learning_rate": 0.001,
"loss": 0.8088,
"step": 568
},
{
"epoch": 2.09,
"learning_rate": 0.001,
"loss": 0.7578,
"step": 570
},
{
"epoch": 2.1,
"learning_rate": 0.001,
"loss": 0.7808,
"step": 572
},
{
"epoch": 2.1,
"learning_rate": 0.001,
"loss": 0.8012,
"step": 574
},
{
"epoch": 2.11,
"learning_rate": 0.001,
"loss": 0.7949,
"step": 576
},
{
"epoch": 2.12,
"learning_rate": 0.001,
"loss": 0.7711,
"step": 578
},
{
"epoch": 2.13,
"learning_rate": 0.001,
"loss": 0.7867,
"step": 580
},
{
"epoch": 2.13,
"learning_rate": 0.001,
"loss": 0.8086,
"step": 582
},
{
"epoch": 2.14,
"learning_rate": 0.001,
"loss": 0.8308,
"step": 584
},
{
"epoch": 2.15,
"learning_rate": 0.001,
"loss": 0.808,
"step": 586
},
{
"epoch": 2.16,
"learning_rate": 0.001,
"loss": 0.8161,
"step": 588
},
{
"epoch": 2.16,
"learning_rate": 0.001,
"loss": 0.8135,
"step": 590
},
{
"epoch": 2.17,
"learning_rate": 0.001,
"loss": 0.8042,
"step": 592
},
{
"epoch": 2.18,
"learning_rate": 0.001,
"loss": 0.7889,
"step": 594
},
{
"epoch": 2.19,
"learning_rate": 0.001,
"loss": 0.7815,
"step": 596
},
{
"epoch": 2.19,
"learning_rate": 0.001,
"loss": 0.8032,
"step": 598
},
{
"epoch": 2.2,
"learning_rate": 0.001,
"loss": 0.7855,
"step": 600
},
{
"epoch": 2.21,
"learning_rate": 0.001,
"loss": 0.7703,
"step": 602
},
{
"epoch": 2.21,
"learning_rate": 0.001,
"loss": 0.8073,
"step": 604
},
{
"epoch": 2.22,
"learning_rate": 0.001,
"loss": 0.7707,
"step": 606
},
{
"epoch": 2.23,
"learning_rate": 0.001,
"loss": 0.7826,
"step": 608
},
{
"epoch": 2.24,
"learning_rate": 0.001,
"loss": 0.7915,
"step": 610
},
{
"epoch": 2.24,
"learning_rate": 0.001,
"loss": 0.7906,
"step": 612
},
{
"epoch": 2.25,
"learning_rate": 0.001,
"loss": 0.7777,
"step": 614
},
{
"epoch": 2.26,
"learning_rate": 0.001,
"loss": 0.7951,
"step": 616
},
{
"epoch": 2.27,
"learning_rate": 0.001,
"loss": 0.817,
"step": 618
},
{
"epoch": 2.27,
"learning_rate": 0.001,
"loss": 0.7979,
"step": 620
},
{
"epoch": 2.28,
"learning_rate": 0.001,
"loss": 0.7882,
"step": 622
},
{
"epoch": 2.29,
"learning_rate": 0.001,
"loss": 0.7798,
"step": 624
},
{
"epoch": 2.3,
"learning_rate": 0.001,
"loss": 0.8031,
"step": 626
},
{
"epoch": 2.3,
"learning_rate": 0.001,
"loss": 0.8067,
"step": 628
},
{
"epoch": 2.31,
"learning_rate": 0.001,
"loss": 0.8181,
"step": 630
},
{
"epoch": 2.32,
"learning_rate": 0.001,
"loss": 0.7953,
"step": 632
},
{
"epoch": 2.32,
"learning_rate": 0.001,
"loss": 0.7995,
"step": 634
},
{
"epoch": 2.33,
"learning_rate": 0.001,
"loss": 0.7861,
"step": 636
},
{
"epoch": 2.34,
"learning_rate": 0.001,
"loss": 0.8293,
"step": 638
},
{
"epoch": 2.35,
"learning_rate": 0.001,
"loss": 0.7806,
"step": 640
},
{
"epoch": 2.35,
"learning_rate": 0.001,
"loss": 0.8099,
"step": 642
},
{
"epoch": 2.36,
"learning_rate": 0.001,
"loss": 0.7893,
"step": 644
},
{
"epoch": 2.37,
"learning_rate": 0.001,
"loss": 0.8101,
"step": 646
},
{
"epoch": 2.38,
"learning_rate": 0.001,
"loss": 0.8023,
"step": 648
},
{
"epoch": 2.38,
"learning_rate": 0.001,
"loss": 0.8117,
"step": 650
},
{
"epoch": 2.39,
"learning_rate": 0.001,
"loss": 0.8258,
"step": 652
},
{
"epoch": 2.4,
"learning_rate": 0.001,
"loss": 0.8189,
"step": 654
},
{
"epoch": 2.4,
"learning_rate": 0.001,
"loss": 0.8089,
"step": 656
},
{
"epoch": 2.41,
"learning_rate": 0.001,
"loss": 0.796,
"step": 658
},
{
"epoch": 2.42,
"learning_rate": 0.001,
"loss": 0.7756,
"step": 660
},
{
"epoch": 2.43,
"learning_rate": 0.001,
"loss": 0.8396,
"step": 662
},
{
"epoch": 2.43,
"learning_rate": 0.001,
"loss": 0.8046,
"step": 664
},
{
"epoch": 2.44,
"learning_rate": 0.001,
"loss": 0.8277,
"step": 666
},
{
"epoch": 2.45,
"learning_rate": 0.001,
"loss": 0.8052,
"step": 668
},
{
"epoch": 2.46,
"learning_rate": 0.001,
"loss": 0.7898,
"step": 670
},
{
"epoch": 2.46,
"learning_rate": 0.001,
"loss": 0.7836,
"step": 672
},
{
"epoch": 2.47,
"learning_rate": 0.001,
"loss": 0.8259,
"step": 674
},
{
"epoch": 2.48,
"learning_rate": 0.001,
"loss": 0.8138,
"step": 676
},
{
"epoch": 2.49,
"learning_rate": 0.001,
"loss": 0.804,
"step": 678
},
{
"epoch": 2.49,
"learning_rate": 0.001,
"loss": 0.8225,
"step": 680
},
{
"epoch": 2.5,
"learning_rate": 0.001,
"loss": 0.8042,
"step": 682
},
{
"epoch": 2.51,
"learning_rate": 0.001,
"loss": 0.8215,
"step": 684
},
{
"epoch": 2.51,
"learning_rate": 0.001,
"loss": 0.8423,
"step": 686
},
{
"epoch": 2.52,
"learning_rate": 0.001,
"loss": 0.8397,
"step": 688
},
{
"epoch": 2.53,
"learning_rate": 0.001,
"loss": 0.8156,
"step": 690
},
{
"epoch": 2.54,
"learning_rate": 0.001,
"loss": 0.8208,
"step": 692
},
{
"epoch": 2.54,
"learning_rate": 0.001,
"loss": 0.8334,
"step": 694
},
{
"epoch": 2.55,
"learning_rate": 0.001,
"loss": 0.803,
"step": 696
},
{
"epoch": 2.56,
"learning_rate": 0.001,
"loss": 0.7976,
"step": 698
},
{
"epoch": 2.57,
"learning_rate": 0.001,
"loss": 0.8133,
"step": 700
},
{
"epoch": 2.57,
"learning_rate": 0.001,
"loss": 0.8321,
"step": 702
},
{
"epoch": 2.58,
"learning_rate": 0.001,
"loss": 0.7889,
"step": 704
},
{
"epoch": 2.59,
"learning_rate": 0.001,
"loss": 0.7822,
"step": 706
},
{
"epoch": 2.6,
"learning_rate": 0.001,
"loss": 0.8,
"step": 708
},
{
"epoch": 2.6,
"learning_rate": 0.001,
"loss": 0.8492,
"step": 710
},
{
"epoch": 2.61,
"learning_rate": 0.001,
"loss": 0.839,
"step": 712
},
{
"epoch": 2.62,
"learning_rate": 0.001,
"loss": 0.8013,
"step": 714
},
{
"epoch": 2.62,
"learning_rate": 0.001,
"loss": 0.8414,
"step": 716
},
{
"epoch": 2.63,
"learning_rate": 0.001,
"loss": 0.8163,
"step": 718
},
{
"epoch": 2.64,
"learning_rate": 0.001,
"loss": 0.8135,
"step": 720
},
{
"epoch": 2.65,
"learning_rate": 0.001,
"loss": 0.8302,
"step": 722
},
{
"epoch": 2.65,
"learning_rate": 0.001,
"loss": 0.8529,
"step": 724
},
{
"epoch": 2.66,
"learning_rate": 0.001,
"loss": 0.831,
"step": 726
},
{
"epoch": 2.67,
"learning_rate": 0.001,
"loss": 0.823,
"step": 728
},
{
"epoch": 2.68,
"learning_rate": 0.001,
"loss": 0.8454,
"step": 730
},
{
"epoch": 2.68,
"learning_rate": 0.001,
"loss": 0.8416,
"step": 732
},
{
"epoch": 2.69,
"learning_rate": 0.001,
"loss": 0.842,
"step": 734
},
{
"epoch": 2.7,
"learning_rate": 0.001,
"loss": 0.8027,
"step": 736
},
{
"epoch": 2.71,
"learning_rate": 0.001,
"loss": 0.8238,
"step": 738
},
{
"epoch": 2.71,
"learning_rate": 0.001,
"loss": 0.8341,
"step": 740
},
{
"epoch": 2.72,
"learning_rate": 0.001,
"loss": 0.8002,
"step": 742
},
{
"epoch": 2.73,
"learning_rate": 0.001,
"loss": 0.8104,
"step": 744
},
{
"epoch": 2.73,
"learning_rate": 0.001,
"loss": 0.8128,
"step": 746
},
{
"epoch": 2.74,
"learning_rate": 0.001,
"loss": 0.8377,
"step": 748
},
{
"epoch": 2.75,
"learning_rate": 0.001,
"loss": 0.8182,
"step": 750
},
{
"epoch": 2.76,
"learning_rate": 0.001,
"loss": 0.8378,
"step": 752
},
{
"epoch": 2.76,
"learning_rate": 0.001,
"loss": 0.7862,
"step": 754
},
{
"epoch": 2.77,
"learning_rate": 0.001,
"loss": 0.8143,
"step": 756
},
{
"epoch": 2.78,
"learning_rate": 0.001,
"loss": 0.8273,
"step": 758
},
{
"epoch": 2.79,
"learning_rate": 0.001,
"loss": 0.8292,
"step": 760
},
{
"epoch": 2.79,
"learning_rate": 0.001,
"loss": 0.8464,
"step": 762
},
{
"epoch": 2.8,
"learning_rate": 0.001,
"loss": 0.7713,
"step": 764
},
{
"epoch": 2.81,
"learning_rate": 0.001,
"loss": 0.8374,
"step": 766
},
{
"epoch": 2.82,
"learning_rate": 0.001,
"loss": 0.7977,
"step": 768
},
{
"epoch": 2.82,
"learning_rate": 0.001,
"loss": 0.8321,
"step": 770
},
{
"epoch": 2.83,
"learning_rate": 0.001,
"loss": 0.8267,
"step": 772
},
{
"epoch": 2.84,
"learning_rate": 0.001,
"loss": 0.8269,
"step": 774
},
{
"epoch": 2.84,
"learning_rate": 0.001,
"loss": 0.8103,
"step": 776
},
{
"epoch": 2.85,
"learning_rate": 0.001,
"loss": 0.8347,
"step": 778
},
{
"epoch": 2.86,
"learning_rate": 0.001,
"loss": 0.8414,
"step": 780
},
{
"epoch": 2.87,
"learning_rate": 0.001,
"loss": 0.846,
"step": 782
},
{
"epoch": 2.87,
"learning_rate": 0.001,
"loss": 0.8492,
"step": 784
},
{
"epoch": 2.88,
"learning_rate": 0.001,
"loss": 0.8423,
"step": 786
},
{
"epoch": 2.89,
"learning_rate": 0.001,
"loss": 0.8323,
"step": 788
},
{
"epoch": 2.9,
"learning_rate": 0.001,
"loss": 0.827,
"step": 790
},
{
"epoch": 2.9,
"learning_rate": 0.001,
"loss": 0.8299,
"step": 792
},
{
"epoch": 2.91,
"learning_rate": 0.001,
"loss": 0.8496,
"step": 794
},
{
"epoch": 2.92,
"learning_rate": 0.001,
"loss": 0.8063,
"step": 796
},
{
"epoch": 2.93,
"learning_rate": 0.001,
"loss": 0.7956,
"step": 798
},
{
"epoch": 2.93,
"learning_rate": 0.001,
"loss": 0.8329,
"step": 800
},
{
"epoch": 2.94,
"learning_rate": 0.001,
"loss": 0.8365,
"step": 802
},
{
"epoch": 2.95,
"learning_rate": 0.001,
"loss": 0.8389,
"step": 804
},
{
"epoch": 2.95,
"learning_rate": 0.001,
"loss": 0.8134,
"step": 806
},
{
"epoch": 2.96,
"learning_rate": 0.001,
"loss": 0.8075,
"step": 808
},
{
"epoch": 2.97,
"learning_rate": 0.001,
"loss": 0.8202,
"step": 810
},
{
"epoch": 2.98,
"learning_rate": 0.001,
"loss": 0.8388,
"step": 812
},
{
"epoch": 2.98,
"learning_rate": 0.001,
"loss": 0.8238,
"step": 814
},
{
"epoch": 2.99,
"learning_rate": 0.001,
"loss": 0.8399,
"step": 816
},
{
"epoch": 3.0,
"learning_rate": 0.001,
"loss": 0.8395,
"step": 818
},
{
"epoch": 3.0,
"eval_gen_len": 1055.9783950617284,
"eval_loss": 0.9924584031105042,
"eval_rouge1": 57.4498,
"eval_rouge2": 31.9315,
"eval_rougeL": 32.914,
"eval_rougeLsum": 55.2389,
"eval_runtime": 10052.1884,
"eval_samples_per_second": 0.097,
"eval_steps_per_second": 0.012,
"step": 818
},
{
"epoch": 3.01,
"learning_rate": 0.001,
"loss": 0.6563,
"step": 820
},
{
"epoch": 3.01,
"learning_rate": 0.001,
"loss": 0.6375,
"step": 822
},
{
"epoch": 3.02,
"learning_rate": 0.001,
"loss": 0.6286,
"step": 824
},
{
"epoch": 3.03,
"learning_rate": 0.001,
"loss": 0.6436,
"step": 826
},
{
"epoch": 3.04,
"learning_rate": 0.001,
"loss": 0.656,
"step": 828
},
{
"epoch": 3.04,
"learning_rate": 0.001,
"loss": 0.6208,
"step": 830
},
{
"epoch": 3.05,
"learning_rate": 0.001,
"loss": 0.6414,
"step": 832
},
{
"epoch": 3.06,
"learning_rate": 0.001,
"loss": 0.6238,
"step": 834
},
{
"epoch": 3.06,
"learning_rate": 0.001,
"loss": 0.6681,
"step": 836
},
{
"epoch": 3.07,
"learning_rate": 0.001,
"loss": 0.6295,
"step": 838
},
{
"epoch": 3.08,
"learning_rate": 0.001,
"loss": 0.6341,
"step": 840
},
{
"epoch": 3.09,
"learning_rate": 0.001,
"loss": 0.6603,
"step": 842
},
{
"epoch": 3.09,
"learning_rate": 0.001,
"loss": 0.6205,
"step": 844
},
{
"epoch": 3.1,
"learning_rate": 0.001,
"loss": 0.6472,
"step": 846
},
{
"epoch": 3.11,
"learning_rate": 0.001,
"loss": 0.6198,
"step": 848
},
{
"epoch": 3.12,
"learning_rate": 0.001,
"loss": 0.6945,
"step": 850
},
{
"epoch": 3.12,
"learning_rate": 0.001,
"loss": 0.6442,
"step": 852
},
{
"epoch": 3.13,
"learning_rate": 0.001,
"loss": 0.6695,
"step": 854
},
{
"epoch": 3.14,
"learning_rate": 0.001,
"loss": 0.6582,
"step": 856
},
{
"epoch": 3.15,
"learning_rate": 0.001,
"loss": 0.6469,
"step": 858
},
{
"epoch": 3.15,
"learning_rate": 0.001,
"loss": 0.6245,
"step": 860
},
{
"epoch": 3.16,
"learning_rate": 0.001,
"loss": 0.661,
"step": 862
},
{
"epoch": 3.17,
"learning_rate": 0.001,
"loss": 0.6581,
"step": 864
},
{
"epoch": 3.17,
"learning_rate": 0.001,
"loss": 0.6608,
"step": 866
},
{
"epoch": 3.18,
"learning_rate": 0.001,
"loss": 0.656,
"step": 868
},
{
"epoch": 3.19,
"learning_rate": 0.001,
"loss": 0.6667,
"step": 870
},
{
"epoch": 3.2,
"learning_rate": 0.001,
"loss": 0.6452,
"step": 872
},
{
"epoch": 3.2,
"learning_rate": 0.001,
"loss": 0.6257,
"step": 874
},
{
"epoch": 3.21,
"learning_rate": 0.001,
"loss": 0.6919,
"step": 876
},
{
"epoch": 3.22,
"learning_rate": 0.001,
"loss": 0.676,
"step": 878
},
{
"epoch": 3.23,
"learning_rate": 0.001,
"loss": 0.6648,
"step": 880
},
{
"epoch": 3.23,
"learning_rate": 0.001,
"loss": 0.6758,
"step": 882
},
{
"epoch": 3.24,
"learning_rate": 0.001,
"loss": 0.645,
"step": 884
},
{
"epoch": 3.25,
"learning_rate": 0.001,
"loss": 0.639,
"step": 886
},
{
"epoch": 3.26,
"learning_rate": 0.001,
"loss": 0.6595,
"step": 888
},
{
"epoch": 3.26,
"learning_rate": 0.001,
"loss": 0.6605,
"step": 890
},
{
"epoch": 3.27,
"learning_rate": 0.001,
"loss": 0.657,
"step": 892
},
{
"epoch": 3.28,
"learning_rate": 0.001,
"loss": 0.6793,
"step": 894
},
{
"epoch": 3.28,
"learning_rate": 0.001,
"loss": 0.6917,
"step": 896
},
{
"epoch": 3.29,
"learning_rate": 0.001,
"loss": 0.6472,
"step": 898
},
{
"epoch": 3.3,
"learning_rate": 0.001,
"loss": 0.7147,
"step": 900
},
{
"epoch": 3.31,
"learning_rate": 0.001,
"loss": 0.652,
"step": 902
},
{
"epoch": 3.31,
"learning_rate": 0.001,
"loss": 0.662,
"step": 904
},
{
"epoch": 3.32,
"learning_rate": 0.001,
"loss": 0.6623,
"step": 906
},
{
"epoch": 3.33,
"learning_rate": 0.001,
"loss": 0.6747,
"step": 908
},
{
"epoch": 3.34,
"learning_rate": 0.001,
"loss": 0.6829,
"step": 910
},
{
"epoch": 3.34,
"learning_rate": 0.001,
"loss": 0.676,
"step": 912
},
{
"epoch": 3.35,
"learning_rate": 0.001,
"loss": 0.6552,
"step": 914
},
{
"epoch": 3.36,
"learning_rate": 0.001,
"loss": 0.6817,
"step": 916
},
{
"epoch": 3.37,
"learning_rate": 0.001,
"loss": 0.6693,
"step": 918
},
{
"epoch": 3.37,
"learning_rate": 0.001,
"loss": 0.6744,
"step": 920
},
{
"epoch": 3.38,
"learning_rate": 0.001,
"loss": 0.7078,
"step": 922
},
{
"epoch": 3.39,
"learning_rate": 0.001,
"loss": 0.6591,
"step": 924
},
{
"epoch": 3.39,
"learning_rate": 0.001,
"loss": 0.6899,
"step": 926
},
{
"epoch": 3.4,
"learning_rate": 0.001,
"loss": 0.7025,
"step": 928
},
{
"epoch": 3.41,
"learning_rate": 0.001,
"loss": 0.6988,
"step": 930
},
{
"epoch": 3.42,
"learning_rate": 0.001,
"loss": 0.6642,
"step": 932
},
{
"epoch": 3.42,
"learning_rate": 0.001,
"loss": 0.6947,
"step": 934
},
{
"epoch": 3.43,
"learning_rate": 0.001,
"loss": 0.6867,
"step": 936
},
{
"epoch": 3.44,
"learning_rate": 0.001,
"loss": 0.6942,
"step": 938
},
{
"epoch": 3.45,
"learning_rate": 0.001,
"loss": 0.6566,
"step": 940
},
{
"epoch": 3.45,
"learning_rate": 0.001,
"loss": 0.6515,
"step": 942
},
{
"epoch": 3.46,
"learning_rate": 0.001,
"loss": 0.7037,
"step": 944
},
{
"epoch": 3.47,
"learning_rate": 0.001,
"loss": 0.67,
"step": 946
},
{
"epoch": 3.48,
"learning_rate": 0.001,
"loss": 0.6649,
"step": 948
},
{
"epoch": 3.48,
"learning_rate": 0.001,
"loss": 0.6978,
"step": 950
},
{
"epoch": 3.49,
"learning_rate": 0.001,
"loss": 0.6685,
"step": 952
},
{
"epoch": 3.5,
"learning_rate": 0.001,
"loss": 0.7003,
"step": 954
},
{
"epoch": 3.5,
"learning_rate": 0.001,
"loss": 0.6769,
"step": 956
},
{
"epoch": 3.51,
"learning_rate": 0.001,
"loss": 0.675,
"step": 958
},
{
"epoch": 3.52,
"learning_rate": 0.001,
"loss": 0.6938,
"step": 960
},
{
"epoch": 3.53,
"learning_rate": 0.001,
"loss": 0.6757,
"step": 962
},
{
"epoch": 3.53,
"learning_rate": 0.001,
"loss": 0.684,
"step": 964
},
{
"epoch": 3.54,
"learning_rate": 0.001,
"loss": 0.6674,
"step": 966
},
{
"epoch": 3.55,
"learning_rate": 0.001,
"loss": 0.7103,
"step": 968
},
{
"epoch": 3.56,
"learning_rate": 0.001,
"loss": 0.6688,
"step": 970
},
{
"epoch": 3.56,
"learning_rate": 0.001,
"loss": 0.6543,
"step": 972
},
{
"epoch": 3.57,
"learning_rate": 0.001,
"loss": 0.7131,
"step": 974
},
{
"epoch": 3.58,
"learning_rate": 0.001,
"loss": 0.6909,
"step": 976
},
{
"epoch": 3.59,
"learning_rate": 0.001,
"loss": 0.6693,
"step": 978
},
{
"epoch": 3.59,
"learning_rate": 0.001,
"loss": 0.6899,
"step": 980
},
{
"epoch": 3.6,
"learning_rate": 0.001,
"loss": 0.6903,
"step": 982
},
{
"epoch": 3.61,
"learning_rate": 0.001,
"loss": 0.6849,
"step": 984
},
{
"epoch": 3.61,
"learning_rate": 0.001,
"loss": 0.6801,
"step": 986
},
{
"epoch": 3.62,
"learning_rate": 0.001,
"loss": 0.6933,
"step": 988
},
{
"epoch": 3.63,
"learning_rate": 0.001,
"loss": 0.698,
"step": 990
},
{
"epoch": 3.64,
"learning_rate": 0.001,
"loss": 0.7244,
"step": 992
},
{
"epoch": 3.64,
"learning_rate": 0.001,
"loss": 0.7065,
"step": 994
},
{
"epoch": 3.65,
"learning_rate": 0.001,
"loss": 0.6869,
"step": 996
},
{
"epoch": 3.66,
"learning_rate": 0.001,
"loss": 0.6686,
"step": 998
},
{
"epoch": 3.67,
"learning_rate": 0.001,
"loss": 0.7052,
"step": 1000
},
{
"epoch": 3.67,
"learning_rate": 0.001,
"loss": 0.6706,
"step": 1002
},
{
"epoch": 3.68,
"learning_rate": 0.001,
"loss": 0.6616,
"step": 1004
},
{
"epoch": 3.69,
"learning_rate": 0.001,
"loss": 0.6894,
"step": 1006
},
{
"epoch": 3.7,
"learning_rate": 0.001,
"loss": 0.6906,
"step": 1008
},
{
"epoch": 3.7,
"learning_rate": 0.001,
"loss": 0.6715,
"step": 1010
},
{
"epoch": 3.71,
"learning_rate": 0.001,
"loss": 0.6508,
"step": 1012
},
{
"epoch": 3.72,
"learning_rate": 0.001,
"loss": 0.7055,
"step": 1014
},
{
"epoch": 3.72,
"learning_rate": 0.001,
"loss": 0.6837,
"step": 1016
},
{
"epoch": 3.73,
"learning_rate": 0.001,
"loss": 0.6924,
"step": 1018
},
{
"epoch": 3.74,
"learning_rate": 0.001,
"loss": 0.6774,
"step": 1020
},
{
"epoch": 3.75,
"learning_rate": 0.001,
"loss": 0.7043,
"step": 1022
},
{
"epoch": 3.75,
"learning_rate": 0.001,
"loss": 0.7119,
"step": 1024
},
{
"epoch": 3.76,
"learning_rate": 0.001,
"loss": 0.7059,
"step": 1026
},
{
"epoch": 3.77,
"learning_rate": 0.001,
"loss": 0.7113,
"step": 1028
},
{
"epoch": 3.78,
"learning_rate": 0.001,
"loss": 0.7124,
"step": 1030
},
{
"epoch": 3.78,
"learning_rate": 0.001,
"loss": 0.6883,
"step": 1032
},
{
"epoch": 3.79,
"learning_rate": 0.001,
"loss": 0.7274,
"step": 1034
},
{
"epoch": 3.8,
"learning_rate": 0.001,
"loss": 0.7102,
"step": 1036
},
{
"epoch": 3.81,
"learning_rate": 0.001,
"loss": 0.7152,
"step": 1038
},
{
"epoch": 3.81,
"learning_rate": 0.001,
"loss": 0.7076,
"step": 1040
},
{
"epoch": 3.82,
"learning_rate": 0.001,
"loss": 0.7049,
"step": 1042
},
{
"epoch": 3.83,
"learning_rate": 0.001,
"loss": 0.6826,
"step": 1044
},
{
"epoch": 3.83,
"learning_rate": 0.001,
"loss": 0.7086,
"step": 1046
},
{
"epoch": 3.84,
"learning_rate": 0.001,
"loss": 0.6887,
"step": 1048
},
{
"epoch": 3.85,
"learning_rate": 0.001,
"loss": 0.6971,
"step": 1050
},
{
"epoch": 3.86,
"learning_rate": 0.001,
"loss": 0.697,
"step": 1052
},
{
"epoch": 3.86,
"learning_rate": 0.001,
"loss": 0.7221,
"step": 1054
},
{
"epoch": 3.87,
"learning_rate": 0.001,
"loss": 0.7126,
"step": 1056
},
{
"epoch": 3.88,
"learning_rate": 0.001,
"loss": 0.6873,
"step": 1058
},
{
"epoch": 3.89,
"learning_rate": 0.001,
"loss": 0.7034,
"step": 1060
},
{
"epoch": 3.89,
"learning_rate": 0.001,
"loss": 0.744,
"step": 1062
},
{
"epoch": 3.9,
"learning_rate": 0.001,
"loss": 0.7147,
"step": 1064
},
{
"epoch": 3.91,
"learning_rate": 0.001,
"loss": 0.6817,
"step": 1066
},
{
"epoch": 3.92,
"learning_rate": 0.001,
"loss": 0.6888,
"step": 1068
},
{
"epoch": 3.92,
"learning_rate": 0.001,
"loss": 0.6823,
"step": 1070
},
{
"epoch": 3.93,
"learning_rate": 0.001,
"loss": 0.7153,
"step": 1072
},
{
"epoch": 3.94,
"learning_rate": 0.001,
"loss": 0.686,
"step": 1074
},
{
"epoch": 3.94,
"learning_rate": 0.001,
"loss": 0.7071,
"step": 1076
},
{
"epoch": 3.95,
"learning_rate": 0.001,
"loss": 0.7163,
"step": 1078
},
{
"epoch": 3.96,
"learning_rate": 0.001,
"loss": 0.6945,
"step": 1080
},
{
"epoch": 3.97,
"learning_rate": 0.001,
"loss": 0.7562,
"step": 1082
},
{
"epoch": 3.97,
"learning_rate": 0.001,
"loss": 0.7305,
"step": 1084
},
{
"epoch": 3.98,
"learning_rate": 0.001,
"loss": 0.7067,
"step": 1086
},
{
"epoch": 3.99,
"learning_rate": 0.001,
"loss": 0.6829,
"step": 1088
},
{
"epoch": 4.0,
"learning_rate": 0.001,
"loss": 0.7353,
"step": 1090
},
{
"epoch": 4.0,
"eval_gen_len": 829.2880658436214,
"eval_loss": 1.0404338836669922,
"eval_rouge1": 67.3946,
"eval_rouge2": 39.2034,
"eval_rougeL": 36.8583,
"eval_rougeLsum": 64.9879,
"eval_runtime": 6999.2115,
"eval_samples_per_second": 0.139,
"eval_steps_per_second": 0.017,
"step": 1091
},
{
"epoch": 4.0,
"learning_rate": 0.001,
"loss": 0.6303,
"step": 1092
},
{
"epoch": 4.01,
"learning_rate": 0.001,
"loss": 0.535,
"step": 1094
},
{
"epoch": 4.02,
"learning_rate": 0.001,
"loss": 0.4868,
"step": 1096
},
{
"epoch": 4.03,
"learning_rate": 0.001,
"loss": 0.5172,
"step": 1098
},
{
"epoch": 4.03,
"learning_rate": 0.001,
"loss": 0.5108,
"step": 1100
},
{
"epoch": 4.04,
"learning_rate": 0.001,
"loss": 0.4989,
"step": 1102
},
{
"epoch": 4.05,
"learning_rate": 0.001,
"loss": 0.5296,
"step": 1104
},
{
"epoch": 4.05,
"learning_rate": 0.001,
"loss": 0.5606,
"step": 1106
},
{
"epoch": 4.06,
"learning_rate": 0.001,
"loss": 0.5346,
"step": 1108
},
{
"epoch": 4.07,
"learning_rate": 0.001,
"loss": 0.5484,
"step": 1110
},
{
"epoch": 4.08,
"learning_rate": 0.001,
"loss": 0.533,
"step": 1112
},
{
"epoch": 4.08,
"learning_rate": 0.001,
"loss": 0.5309,
"step": 1114
},
{
"epoch": 4.09,
"learning_rate": 0.001,
"loss": 0.5183,
"step": 1116
},
{
"epoch": 4.1,
"learning_rate": 0.001,
"loss": 0.5669,
"step": 1118
},
{
"epoch": 4.11,
"learning_rate": 0.001,
"loss": 0.5189,
"step": 1120
},
{
"epoch": 4.11,
"learning_rate": 0.001,
"loss": 0.5508,
"step": 1122
},
{
"epoch": 4.12,
"learning_rate": 0.001,
"loss": 0.5614,
"step": 1124
},
{
"epoch": 4.13,
"learning_rate": 0.001,
"loss": 0.5692,
"step": 1126
},
{
"epoch": 4.14,
"learning_rate": 0.001,
"loss": 0.5357,
"step": 1128
},
{
"epoch": 4.14,
"learning_rate": 0.001,
"loss": 0.5575,
"step": 1130
},
{
"epoch": 4.15,
"learning_rate": 0.001,
"loss": 0.5544,
"step": 1132
},
{
"epoch": 4.16,
"learning_rate": 0.001,
"loss": 0.5574,
"step": 1134
},
{
"epoch": 4.16,
"learning_rate": 0.001,
"loss": 0.5483,
"step": 1136
},
{
"epoch": 4.17,
"learning_rate": 0.001,
"loss": 0.5498,
"step": 1138
},
{
"epoch": 4.18,
"learning_rate": 0.001,
"loss": 0.5183,
"step": 1140
},
{
"epoch": 4.19,
"learning_rate": 0.001,
"loss": 0.5401,
"step": 1142
},
{
"epoch": 4.19,
"learning_rate": 0.001,
"loss": 0.5577,
"step": 1144
},
{
"epoch": 4.2,
"learning_rate": 0.001,
"loss": 0.5699,
"step": 1146
},
{
"epoch": 4.21,
"learning_rate": 0.001,
"loss": 0.546,
"step": 1148
},
{
"epoch": 4.22,
"learning_rate": 0.001,
"loss": 0.533,
"step": 1150
},
{
"epoch": 4.22,
"learning_rate": 0.001,
"loss": 0.5452,
"step": 1152
},
{
"epoch": 4.23,
"learning_rate": 0.001,
"loss": 0.5434,
"step": 1154
},
{
"epoch": 4.24,
"learning_rate": 0.001,
"loss": 0.5656,
"step": 1156
},
{
"epoch": 4.25,
"learning_rate": 0.001,
"loss": 0.5462,
"step": 1158
},
{
"epoch": 4.25,
"learning_rate": 0.001,
"loss": 0.5493,
"step": 1160
},
{
"epoch": 4.26,
"learning_rate": 0.001,
"loss": 0.5453,
"step": 1162
},
{
"epoch": 4.27,
"learning_rate": 0.001,
"loss": 0.523,
"step": 1164
},
{
"epoch": 4.27,
"learning_rate": 0.001,
"loss": 0.599,
"step": 1166
},
{
"epoch": 4.28,
"learning_rate": 0.001,
"loss": 0.5457,
"step": 1168
},
{
"epoch": 4.29,
"learning_rate": 0.001,
"loss": 0.5434,
"step": 1170
},
{
"epoch": 4.3,
"learning_rate": 0.001,
"loss": 0.5643,
"step": 1172
},
{
"epoch": 4.3,
"learning_rate": 0.001,
"loss": 0.5501,
"step": 1174
},
{
"epoch": 4.31,
"learning_rate": 0.001,
"loss": 0.5868,
"step": 1176
},
{
"epoch": 4.32,
"learning_rate": 0.001,
"loss": 0.5707,
"step": 1178
},
{
"epoch": 4.33,
"learning_rate": 0.001,
"loss": 0.5549,
"step": 1180
},
{
"epoch": 4.33,
"learning_rate": 0.001,
"loss": 0.5543,
"step": 1182
},
{
"epoch": 4.34,
"learning_rate": 0.001,
"loss": 0.5891,
"step": 1184
},
{
"epoch": 4.35,
"learning_rate": 0.001,
"loss": 0.5512,
"step": 1186
},
{
"epoch": 4.36,
"learning_rate": 0.001,
"loss": 0.566,
"step": 1188
},
{
"epoch": 4.36,
"learning_rate": 0.001,
"loss": 0.5539,
"step": 1190
},
{
"epoch": 4.37,
"learning_rate": 0.001,
"loss": 0.5184,
"step": 1192
},
{
"epoch": 4.38,
"learning_rate": 0.001,
"loss": 0.5576,
"step": 1194
},
{
"epoch": 4.38,
"learning_rate": 0.001,
"loss": 0.5915,
"step": 1196
},
{
"epoch": 4.39,
"learning_rate": 0.001,
"loss": 0.5504,
"step": 1198
},
{
"epoch": 4.4,
"learning_rate": 0.001,
"loss": 0.5772,
"step": 1200
},
{
"epoch": 4.41,
"learning_rate": 0.001,
"loss": 0.5741,
"step": 1202
},
{
"epoch": 4.41,
"learning_rate": 0.001,
"loss": 0.5732,
"step": 1204
},
{
"epoch": 4.42,
"learning_rate": 0.001,
"loss": 0.5857,
"step": 1206
},
{
"epoch": 4.43,
"learning_rate": 0.001,
"loss": 0.541,
"step": 1208
},
{
"epoch": 4.44,
"learning_rate": 0.001,
"loss": 0.5483,
"step": 1210
},
{
"epoch": 4.44,
"learning_rate": 0.001,
"loss": 0.6174,
"step": 1212
},
{
"epoch": 4.45,
"learning_rate": 0.001,
"loss": 0.5349,
"step": 1214
},
{
"epoch": 4.46,
"learning_rate": 0.001,
"loss": 0.5727,
"step": 1216
},
{
"epoch": 4.47,
"learning_rate": 0.001,
"loss": 0.5784,
"step": 1218
},
{
"epoch": 4.47,
"learning_rate": 0.001,
"loss": 0.5558,
"step": 1220
},
{
"epoch": 4.48,
"learning_rate": 0.001,
"loss": 0.5616,
"step": 1222
},
{
"epoch": 4.49,
"learning_rate": 0.001,
"loss": 0.5801,
"step": 1224
},
{
"epoch": 4.49,
"learning_rate": 0.001,
"loss": 0.5539,
"step": 1226
},
{
"epoch": 4.5,
"learning_rate": 0.001,
"loss": 0.5807,
"step": 1228
},
{
"epoch": 4.51,
"learning_rate": 0.001,
"loss": 0.5626,
"step": 1230
},
{
"epoch": 4.52,
"learning_rate": 0.001,
"loss": 0.6048,
"step": 1232
},
{
"epoch": 4.52,
"learning_rate": 0.001,
"loss": 0.5858,
"step": 1234
},
{
"epoch": 4.53,
"learning_rate": 0.001,
"loss": 0.5638,
"step": 1236
},
{
"epoch": 4.54,
"learning_rate": 0.001,
"loss": 0.5865,
"step": 1238
},
{
"epoch": 4.55,
"learning_rate": 0.001,
"loss": 0.5916,
"step": 1240
},
{
"epoch": 4.55,
"learning_rate": 0.001,
"loss": 0.5683,
"step": 1242
},
{
"epoch": 4.56,
"learning_rate": 0.001,
"loss": 0.5656,
"step": 1244
},
{
"epoch": 4.57,
"learning_rate": 0.001,
"loss": 0.5839,
"step": 1246
},
{
"epoch": 4.58,
"learning_rate": 0.001,
"loss": 0.601,
"step": 1248
},
{
"epoch": 4.58,
"learning_rate": 0.001,
"loss": 0.5799,
"step": 1250
},
{
"epoch": 4.59,
"learning_rate": 0.001,
"loss": 0.5705,
"step": 1252
},
{
"epoch": 4.6,
"learning_rate": 0.001,
"loss": 0.5937,
"step": 1254
},
{
"epoch": 4.6,
"learning_rate": 0.001,
"loss": 0.5636,
"step": 1256
},
{
"epoch": 4.61,
"learning_rate": 0.001,
"loss": 0.5849,
"step": 1258
},
{
"epoch": 4.62,
"learning_rate": 0.001,
"loss": 0.5945,
"step": 1260
},
{
"epoch": 4.63,
"learning_rate": 0.001,
"loss": 0.5763,
"step": 1262
},
{
"epoch": 4.63,
"learning_rate": 0.001,
"loss": 0.577,
"step": 1264
},
{
"epoch": 4.64,
"learning_rate": 0.001,
"loss": 0.5799,
"step": 1266
},
{
"epoch": 4.65,
"learning_rate": 0.001,
"loss": 0.6109,
"step": 1268
},
{
"epoch": 4.66,
"learning_rate": 0.001,
"loss": 0.5754,
"step": 1270
},
{
"epoch": 4.66,
"learning_rate": 0.001,
"loss": 0.6006,
"step": 1272
},
{
"epoch": 4.67,
"learning_rate": 0.001,
"loss": 0.5883,
"step": 1274
},
{
"epoch": 4.68,
"learning_rate": 0.001,
"loss": 0.5924,
"step": 1276
},
{
"epoch": 4.69,
"learning_rate": 0.001,
"loss": 0.5979,
"step": 1278
},
{
"epoch": 4.69,
"learning_rate": 0.001,
"loss": 0.5952,
"step": 1280
},
{
"epoch": 4.7,
"learning_rate": 0.001,
"loss": 0.6096,
"step": 1282
},
{
"epoch": 4.71,
"learning_rate": 0.001,
"loss": 0.5743,
"step": 1284
},
{
"epoch": 4.71,
"learning_rate": 0.001,
"loss": 0.5885,
"step": 1286
},
{
"epoch": 4.72,
"learning_rate": 0.001,
"loss": 0.5983,
"step": 1288
},
{
"epoch": 4.73,
"learning_rate": 0.001,
"loss": 0.6172,
"step": 1290
},
{
"epoch": 4.74,
"learning_rate": 0.001,
"loss": 0.6137,
"step": 1292
},
{
"epoch": 4.74,
"learning_rate": 0.001,
"loss": 0.5791,
"step": 1294
},
{
"epoch": 4.75,
"learning_rate": 0.001,
"loss": 0.5677,
"step": 1296
},
{
"epoch": 4.76,
"learning_rate": 0.001,
"loss": 0.5658,
"step": 1298
},
{
"epoch": 4.77,
"learning_rate": 0.001,
"loss": 0.5713,
"step": 1300
},
{
"epoch": 4.77,
"learning_rate": 0.001,
"loss": 0.6123,
"step": 1302
},
{
"epoch": 4.78,
"learning_rate": 0.001,
"loss": 0.5754,
"step": 1304
},
{
"epoch": 4.79,
"learning_rate": 0.001,
"loss": 0.5862,
"step": 1306
},
{
"epoch": 4.8,
"learning_rate": 0.001,
"loss": 0.6062,
"step": 1308
},
{
"epoch": 4.8,
"learning_rate": 0.001,
"loss": 0.5874,
"step": 1310
},
{
"epoch": 4.81,
"learning_rate": 0.001,
"loss": 0.5693,
"step": 1312
},
{
"epoch": 4.82,
"learning_rate": 0.001,
"loss": 0.5952,
"step": 1314
},
{
"epoch": 4.82,
"learning_rate": 0.001,
"loss": 0.5942,
"step": 1316
},
{
"epoch": 4.83,
"learning_rate": 0.001,
"loss": 0.6039,
"step": 1318
},
{
"epoch": 4.84,
"learning_rate": 0.001,
"loss": 0.6092,
"step": 1320
},
{
"epoch": 4.85,
"learning_rate": 0.001,
"loss": 0.5984,
"step": 1322
},
{
"epoch": 4.85,
"learning_rate": 0.001,
"loss": 0.5838,
"step": 1324
},
{
"epoch": 4.86,
"learning_rate": 0.001,
"loss": 0.6145,
"step": 1326
},
{
"epoch": 4.87,
"learning_rate": 0.001,
"loss": 0.5708,
"step": 1328
},
{
"epoch": 4.88,
"learning_rate": 0.001,
"loss": 0.5911,
"step": 1330
},
{
"epoch": 4.88,
"learning_rate": 0.001,
"loss": 0.5589,
"step": 1332
},
{
"epoch": 4.89,
"learning_rate": 0.001,
"loss": 0.6074,
"step": 1334
},
{
"epoch": 4.9,
"learning_rate": 0.001,
"loss": 0.5834,
"step": 1336
},
{
"epoch": 4.91,
"learning_rate": 0.001,
"loss": 0.625,
"step": 1338
},
{
"epoch": 4.91,
"learning_rate": 0.001,
"loss": 0.5877,
"step": 1340
},
{
"epoch": 4.92,
"learning_rate": 0.001,
"loss": 0.6212,
"step": 1342
},
{
"epoch": 4.93,
"learning_rate": 0.001,
"loss": 0.5916,
"step": 1344
},
{
"epoch": 4.93,
"learning_rate": 0.001,
"loss": 0.6018,
"step": 1346
},
{
"epoch": 4.94,
"learning_rate": 0.001,
"loss": 0.6138,
"step": 1348
},
{
"epoch": 4.95,
"learning_rate": 0.001,
"loss": 0.6121,
"step": 1350
},
{
"epoch": 4.96,
"learning_rate": 0.001,
"loss": 0.5962,
"step": 1352
},
{
"epoch": 4.96,
"learning_rate": 0.001,
"loss": 0.6013,
"step": 1354
},
{
"epoch": 4.97,
"learning_rate": 0.001,
"loss": 0.5776,
"step": 1356
},
{
"epoch": 4.98,
"learning_rate": 0.001,
"loss": 0.5763,
"step": 1358
},
{
"epoch": 4.99,
"learning_rate": 0.001,
"loss": 0.6212,
"step": 1360
},
{
"epoch": 4.99,
"eval_gen_len": 779.6152263374486,
"eval_loss": 1.0752325057983398,
"eval_rouge1": 64.5433,
"eval_rouge2": 36.9477,
"eval_rougeL": 35.3482,
"eval_rougeLsum": 62.2005,
"eval_runtime": 7358.5246,
"eval_samples_per_second": 0.132,
"eval_steps_per_second": 0.017,
"step": 1360
},
{
"epoch": 4.99,
"step": 1360,
"total_flos": 1.024762577636008e+18,
"train_loss": 0.8627048472709515,
"train_runtime": 92306.6703,
"train_samples_per_second": 0.946,
"train_steps_per_second": 0.015
}
],
"logging_steps": 2,
"max_steps": 1360,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 1.024762577636008e+18,
"trial_name": null,
"trial_params": null
}