longt5_xl_gov_memsum_bp_10 / trainer_state.json
learn3r's picture
End of training
32d841f
raw
history blame
73.3 kB
{
"best_metric": 1.1440205574035645,
"best_model_checkpoint": "/exports/eddie/scratch/s1970716/models/summarization/longt5_xl_gov_memsum_bp_10/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": 0.4576,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.001,
"loss": 0.4467,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 0.001,
"loss": 0.4584,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 0.001,
"loss": 0.4524,
"step": 8
},
{
"epoch": 0.04,
"learning_rate": 0.001,
"loss": 0.442,
"step": 10
},
{
"epoch": 0.04,
"learning_rate": 0.001,
"loss": 0.4661,
"step": 12
},
{
"epoch": 0.05,
"learning_rate": 0.001,
"loss": 0.4156,
"step": 14
},
{
"epoch": 0.06,
"learning_rate": 0.001,
"loss": 0.4305,
"step": 16
},
{
"epoch": 0.07,
"learning_rate": 0.001,
"loss": 0.4481,
"step": 18
},
{
"epoch": 0.07,
"learning_rate": 0.001,
"loss": 0.438,
"step": 20
},
{
"epoch": 0.08,
"learning_rate": 0.001,
"loss": 0.4379,
"step": 22
},
{
"epoch": 0.09,
"learning_rate": 0.001,
"loss": 0.4451,
"step": 24
},
{
"epoch": 0.1,
"learning_rate": 0.001,
"loss": 0.4514,
"step": 26
},
{
"epoch": 0.1,
"learning_rate": 0.001,
"loss": 0.4609,
"step": 28
},
{
"epoch": 0.11,
"learning_rate": 0.001,
"loss": 0.4606,
"step": 30
},
{
"epoch": 0.12,
"learning_rate": 0.001,
"loss": 0.4187,
"step": 32
},
{
"epoch": 0.12,
"learning_rate": 0.001,
"loss": 0.4167,
"step": 34
},
{
"epoch": 0.13,
"learning_rate": 0.001,
"loss": 0.4537,
"step": 36
},
{
"epoch": 0.14,
"learning_rate": 0.001,
"loss": 0.4346,
"step": 38
},
{
"epoch": 0.15,
"learning_rate": 0.001,
"loss": 0.4076,
"step": 40
},
{
"epoch": 0.15,
"learning_rate": 0.001,
"loss": 0.425,
"step": 42
},
{
"epoch": 0.16,
"learning_rate": 0.001,
"loss": 0.4528,
"step": 44
},
{
"epoch": 0.17,
"learning_rate": 0.001,
"loss": 0.4113,
"step": 46
},
{
"epoch": 0.18,
"learning_rate": 0.001,
"loss": 0.4102,
"step": 48
},
{
"epoch": 0.18,
"learning_rate": 0.001,
"loss": 0.4566,
"step": 50
},
{
"epoch": 0.19,
"learning_rate": 0.001,
"loss": 0.4094,
"step": 52
},
{
"epoch": 0.2,
"learning_rate": 0.001,
"loss": 0.4526,
"step": 54
},
{
"epoch": 0.21,
"learning_rate": 0.001,
"loss": 0.3933,
"step": 56
},
{
"epoch": 0.21,
"learning_rate": 0.001,
"loss": 0.4001,
"step": 58
},
{
"epoch": 0.22,
"learning_rate": 0.001,
"loss": 0.4151,
"step": 60
},
{
"epoch": 0.23,
"learning_rate": 0.001,
"loss": 0.4658,
"step": 62
},
{
"epoch": 0.23,
"learning_rate": 0.001,
"loss": 0.433,
"step": 64
},
{
"epoch": 0.24,
"learning_rate": 0.001,
"loss": 0.4107,
"step": 66
},
{
"epoch": 0.25,
"learning_rate": 0.001,
"loss": 0.4278,
"step": 68
},
{
"epoch": 0.26,
"learning_rate": 0.001,
"loss": 0.5057,
"step": 70
},
{
"epoch": 0.26,
"learning_rate": 0.001,
"loss": 0.4444,
"step": 72
},
{
"epoch": 0.27,
"learning_rate": 0.001,
"loss": 0.4374,
"step": 74
},
{
"epoch": 0.28,
"learning_rate": 0.001,
"loss": 0.4697,
"step": 76
},
{
"epoch": 0.29,
"learning_rate": 0.001,
"loss": 0.421,
"step": 78
},
{
"epoch": 0.29,
"learning_rate": 0.001,
"loss": 0.4495,
"step": 80
},
{
"epoch": 0.3,
"learning_rate": 0.001,
"loss": 0.4596,
"step": 82
},
{
"epoch": 0.31,
"learning_rate": 0.001,
"loss": 0.4083,
"step": 84
},
{
"epoch": 0.32,
"learning_rate": 0.001,
"loss": 0.4435,
"step": 86
},
{
"epoch": 0.32,
"learning_rate": 0.001,
"loss": 0.4814,
"step": 88
},
{
"epoch": 0.33,
"learning_rate": 0.001,
"loss": 0.4491,
"step": 90
},
{
"epoch": 0.34,
"learning_rate": 0.001,
"loss": 0.439,
"step": 92
},
{
"epoch": 0.34,
"learning_rate": 0.001,
"loss": 0.4386,
"step": 94
},
{
"epoch": 0.35,
"learning_rate": 0.001,
"loss": 0.4229,
"step": 96
},
{
"epoch": 0.36,
"learning_rate": 0.001,
"loss": 0.4522,
"step": 98
},
{
"epoch": 0.37,
"learning_rate": 0.001,
"loss": 0.4331,
"step": 100
},
{
"epoch": 0.37,
"learning_rate": 0.001,
"loss": 0.4555,
"step": 102
},
{
"epoch": 0.38,
"learning_rate": 0.001,
"loss": 0.4376,
"step": 104
},
{
"epoch": 0.39,
"learning_rate": 0.001,
"loss": 0.4271,
"step": 106
},
{
"epoch": 0.4,
"learning_rate": 0.001,
"loss": 0.4094,
"step": 108
},
{
"epoch": 0.4,
"learning_rate": 0.001,
"loss": 0.4338,
"step": 110
},
{
"epoch": 0.41,
"learning_rate": 0.001,
"loss": 0.4111,
"step": 112
},
{
"epoch": 0.42,
"learning_rate": 0.001,
"loss": 0.4415,
"step": 114
},
{
"epoch": 0.43,
"learning_rate": 0.001,
"loss": 0.4416,
"step": 116
},
{
"epoch": 0.43,
"learning_rate": 0.001,
"loss": 0.442,
"step": 118
},
{
"epoch": 0.44,
"learning_rate": 0.001,
"loss": 0.4403,
"step": 120
},
{
"epoch": 0.45,
"learning_rate": 0.001,
"loss": 0.4654,
"step": 122
},
{
"epoch": 0.45,
"learning_rate": 0.001,
"loss": 0.4456,
"step": 124
},
{
"epoch": 0.46,
"learning_rate": 0.001,
"loss": 0.4327,
"step": 126
},
{
"epoch": 0.47,
"learning_rate": 0.001,
"loss": 0.4275,
"step": 128
},
{
"epoch": 0.48,
"learning_rate": 0.001,
"loss": 0.4047,
"step": 130
},
{
"epoch": 0.48,
"learning_rate": 0.001,
"loss": 0.4297,
"step": 132
},
{
"epoch": 0.49,
"learning_rate": 0.001,
"loss": 0.4154,
"step": 134
},
{
"epoch": 0.5,
"learning_rate": 0.001,
"loss": 0.4057,
"step": 136
},
{
"epoch": 0.51,
"learning_rate": 0.001,
"loss": 0.4195,
"step": 138
},
{
"epoch": 0.51,
"learning_rate": 0.001,
"loss": 0.4255,
"step": 140
},
{
"epoch": 0.52,
"learning_rate": 0.001,
"loss": 0.4299,
"step": 142
},
{
"epoch": 0.53,
"learning_rate": 0.001,
"loss": 0.4292,
"step": 144
},
{
"epoch": 0.54,
"learning_rate": 0.001,
"loss": 0.4303,
"step": 146
},
{
"epoch": 0.54,
"learning_rate": 0.001,
"loss": 0.4493,
"step": 148
},
{
"epoch": 0.55,
"learning_rate": 0.001,
"loss": 0.4053,
"step": 150
},
{
"epoch": 0.56,
"learning_rate": 0.001,
"loss": 0.4609,
"step": 152
},
{
"epoch": 0.56,
"learning_rate": 0.001,
"loss": 0.4361,
"step": 154
},
{
"epoch": 0.57,
"learning_rate": 0.001,
"loss": 0.4576,
"step": 156
},
{
"epoch": 0.58,
"learning_rate": 0.001,
"loss": 0.406,
"step": 158
},
{
"epoch": 0.59,
"learning_rate": 0.001,
"loss": 0.4255,
"step": 160
},
{
"epoch": 0.59,
"learning_rate": 0.001,
"loss": 0.4329,
"step": 162
},
{
"epoch": 0.6,
"learning_rate": 0.001,
"loss": 0.4671,
"step": 164
},
{
"epoch": 0.61,
"learning_rate": 0.001,
"loss": 0.4617,
"step": 166
},
{
"epoch": 0.62,
"learning_rate": 0.001,
"loss": 0.4204,
"step": 168
},
{
"epoch": 0.62,
"learning_rate": 0.001,
"loss": 0.44,
"step": 170
},
{
"epoch": 0.63,
"learning_rate": 0.001,
"loss": 0.4166,
"step": 172
},
{
"epoch": 0.64,
"learning_rate": 0.001,
"loss": 0.4144,
"step": 174
},
{
"epoch": 0.65,
"learning_rate": 0.001,
"loss": 0.4431,
"step": 176
},
{
"epoch": 0.65,
"learning_rate": 0.001,
"loss": 0.4399,
"step": 178
},
{
"epoch": 0.66,
"learning_rate": 0.001,
"loss": 0.4468,
"step": 180
},
{
"epoch": 0.67,
"learning_rate": 0.001,
"loss": 0.4192,
"step": 182
},
{
"epoch": 0.67,
"learning_rate": 0.001,
"loss": 0.4608,
"step": 184
},
{
"epoch": 0.68,
"learning_rate": 0.001,
"loss": 0.4633,
"step": 186
},
{
"epoch": 0.69,
"learning_rate": 0.001,
"loss": 0.4237,
"step": 188
},
{
"epoch": 0.7,
"learning_rate": 0.001,
"loss": 0.3871,
"step": 190
},
{
"epoch": 0.7,
"learning_rate": 0.001,
"loss": 0.4211,
"step": 192
},
{
"epoch": 0.71,
"learning_rate": 0.001,
"loss": 0.4225,
"step": 194
},
{
"epoch": 0.72,
"learning_rate": 0.001,
"loss": 0.3983,
"step": 196
},
{
"epoch": 0.73,
"learning_rate": 0.001,
"loss": 0.4437,
"step": 198
},
{
"epoch": 0.73,
"learning_rate": 0.001,
"loss": 0.4283,
"step": 200
},
{
"epoch": 0.74,
"learning_rate": 0.001,
"loss": 0.4463,
"step": 202
},
{
"epoch": 0.75,
"learning_rate": 0.001,
"loss": 0.4407,
"step": 204
},
{
"epoch": 0.76,
"learning_rate": 0.001,
"loss": 0.4646,
"step": 206
},
{
"epoch": 0.76,
"learning_rate": 0.001,
"loss": 0.4605,
"step": 208
},
{
"epoch": 0.77,
"learning_rate": 0.001,
"loss": 0.4258,
"step": 210
},
{
"epoch": 0.78,
"learning_rate": 0.001,
"loss": 0.4109,
"step": 212
},
{
"epoch": 0.78,
"learning_rate": 0.001,
"loss": 0.4132,
"step": 214
},
{
"epoch": 0.79,
"learning_rate": 0.001,
"loss": 0.44,
"step": 216
},
{
"epoch": 0.8,
"learning_rate": 0.001,
"loss": 0.4173,
"step": 218
},
{
"epoch": 0.81,
"learning_rate": 0.001,
"loss": 0.4336,
"step": 220
},
{
"epoch": 0.81,
"learning_rate": 0.001,
"loss": 0.4323,
"step": 222
},
{
"epoch": 0.82,
"learning_rate": 0.001,
"loss": 0.4677,
"step": 224
},
{
"epoch": 0.83,
"learning_rate": 0.001,
"loss": 0.4291,
"step": 226
},
{
"epoch": 0.84,
"learning_rate": 0.001,
"loss": 0.4324,
"step": 228
},
{
"epoch": 0.84,
"learning_rate": 0.001,
"loss": 0.4253,
"step": 230
},
{
"epoch": 0.85,
"learning_rate": 0.001,
"loss": 0.398,
"step": 232
},
{
"epoch": 0.86,
"learning_rate": 0.001,
"loss": 0.4411,
"step": 234
},
{
"epoch": 0.87,
"learning_rate": 0.001,
"loss": 0.398,
"step": 236
},
{
"epoch": 0.87,
"learning_rate": 0.001,
"loss": 0.4181,
"step": 238
},
{
"epoch": 0.88,
"learning_rate": 0.001,
"loss": 0.4602,
"step": 240
},
{
"epoch": 0.89,
"learning_rate": 0.001,
"loss": 0.4488,
"step": 242
},
{
"epoch": 0.89,
"learning_rate": 0.001,
"loss": 0.4604,
"step": 244
},
{
"epoch": 0.9,
"learning_rate": 0.001,
"loss": 0.4673,
"step": 246
},
{
"epoch": 0.91,
"learning_rate": 0.001,
"loss": 0.4142,
"step": 248
},
{
"epoch": 0.92,
"learning_rate": 0.001,
"loss": 0.4012,
"step": 250
},
{
"epoch": 0.92,
"learning_rate": 0.001,
"loss": 0.4294,
"step": 252
},
{
"epoch": 0.93,
"learning_rate": 0.001,
"loss": 0.424,
"step": 254
},
{
"epoch": 0.94,
"learning_rate": 0.001,
"loss": 0.439,
"step": 256
},
{
"epoch": 0.95,
"learning_rate": 0.001,
"loss": 0.4476,
"step": 258
},
{
"epoch": 0.95,
"learning_rate": 0.001,
"loss": 0.4294,
"step": 260
},
{
"epoch": 0.96,
"learning_rate": 0.001,
"loss": 0.398,
"step": 262
},
{
"epoch": 0.97,
"learning_rate": 0.001,
"loss": 0.4405,
"step": 264
},
{
"epoch": 0.98,
"learning_rate": 0.001,
"loss": 0.4197,
"step": 266
},
{
"epoch": 0.98,
"learning_rate": 0.001,
"loss": 0.4488,
"step": 268
},
{
"epoch": 0.99,
"learning_rate": 0.001,
"loss": 0.4436,
"step": 270
},
{
"epoch": 1.0,
"learning_rate": 0.001,
"loss": 0.4356,
"step": 272
},
{
"epoch": 1.0,
"eval_gen_len": 712.0164609053498,
"eval_loss": 1.1440205574035645,
"eval_rouge1": 67.1508,
"eval_rouge2": 38.9594,
"eval_rougeL": 36.6571,
"eval_rougeLsum": 64.7944,
"eval_runtime": 5794.9642,
"eval_samples_per_second": 0.168,
"eval_steps_per_second": 0.021,
"step": 272
},
{
"epoch": 1.0,
"learning_rate": 0.001,
"loss": 0.3734,
"step": 274
},
{
"epoch": 1.01,
"learning_rate": 0.001,
"loss": 0.3162,
"step": 276
},
{
"epoch": 1.02,
"learning_rate": 0.001,
"loss": 0.3175,
"step": 278
},
{
"epoch": 1.03,
"learning_rate": 0.001,
"loss": 0.3533,
"step": 280
},
{
"epoch": 1.03,
"learning_rate": 0.001,
"loss": 0.2951,
"step": 282
},
{
"epoch": 1.04,
"learning_rate": 0.001,
"loss": 0.3072,
"step": 284
},
{
"epoch": 1.05,
"learning_rate": 0.001,
"loss": 0.2774,
"step": 286
},
{
"epoch": 1.06,
"learning_rate": 0.001,
"loss": 0.3012,
"step": 288
},
{
"epoch": 1.06,
"learning_rate": 0.001,
"loss": 0.3223,
"step": 290
},
{
"epoch": 1.07,
"learning_rate": 0.001,
"loss": 0.2957,
"step": 292
},
{
"epoch": 1.08,
"learning_rate": 0.001,
"loss": 0.287,
"step": 294
},
{
"epoch": 1.09,
"learning_rate": 0.001,
"loss": 0.3065,
"step": 296
},
{
"epoch": 1.09,
"learning_rate": 0.001,
"loss": 0.3109,
"step": 298
},
{
"epoch": 1.1,
"learning_rate": 0.001,
"loss": 0.3126,
"step": 300
},
{
"epoch": 1.11,
"learning_rate": 0.001,
"loss": 0.308,
"step": 302
},
{
"epoch": 1.11,
"learning_rate": 0.001,
"loss": 0.2987,
"step": 304
},
{
"epoch": 1.12,
"learning_rate": 0.001,
"loss": 0.3094,
"step": 306
},
{
"epoch": 1.13,
"learning_rate": 0.001,
"loss": 0.3168,
"step": 308
},
{
"epoch": 1.14,
"learning_rate": 0.001,
"loss": 0.3298,
"step": 310
},
{
"epoch": 1.14,
"learning_rate": 0.001,
"loss": 0.324,
"step": 312
},
{
"epoch": 1.15,
"learning_rate": 0.001,
"loss": 0.3354,
"step": 314
},
{
"epoch": 1.16,
"learning_rate": 0.001,
"loss": 0.3159,
"step": 316
},
{
"epoch": 1.17,
"learning_rate": 0.001,
"loss": 0.2974,
"step": 318
},
{
"epoch": 1.17,
"learning_rate": 0.001,
"loss": 0.3357,
"step": 320
},
{
"epoch": 1.18,
"learning_rate": 0.001,
"loss": 0.3316,
"step": 322
},
{
"epoch": 1.19,
"learning_rate": 0.001,
"loss": 0.3178,
"step": 324
},
{
"epoch": 1.2,
"learning_rate": 0.001,
"loss": 0.3221,
"step": 326
},
{
"epoch": 1.2,
"learning_rate": 0.001,
"loss": 0.327,
"step": 328
},
{
"epoch": 1.21,
"learning_rate": 0.001,
"loss": 0.3247,
"step": 330
},
{
"epoch": 1.22,
"learning_rate": 0.001,
"loss": 0.3374,
"step": 332
},
{
"epoch": 1.22,
"learning_rate": 0.001,
"loss": 0.3361,
"step": 334
},
{
"epoch": 1.23,
"learning_rate": 0.001,
"loss": 0.3316,
"step": 336
},
{
"epoch": 1.24,
"learning_rate": 0.001,
"loss": 0.3189,
"step": 338
},
{
"epoch": 1.25,
"learning_rate": 0.001,
"loss": 0.3211,
"step": 340
},
{
"epoch": 1.25,
"learning_rate": 0.001,
"loss": 0.3119,
"step": 342
},
{
"epoch": 1.26,
"learning_rate": 0.001,
"loss": 0.339,
"step": 344
},
{
"epoch": 1.27,
"learning_rate": 0.001,
"loss": 0.3156,
"step": 346
},
{
"epoch": 1.28,
"learning_rate": 0.001,
"loss": 0.3219,
"step": 348
},
{
"epoch": 1.28,
"learning_rate": 0.001,
"loss": 0.2999,
"step": 350
},
{
"epoch": 1.29,
"learning_rate": 0.001,
"loss": 0.3302,
"step": 352
},
{
"epoch": 1.3,
"learning_rate": 0.001,
"loss": 0.3146,
"step": 354
},
{
"epoch": 1.31,
"learning_rate": 0.001,
"loss": 0.3098,
"step": 356
},
{
"epoch": 1.31,
"learning_rate": 0.001,
"loss": 0.3258,
"step": 358
},
{
"epoch": 1.32,
"learning_rate": 0.001,
"loss": 0.3241,
"step": 360
},
{
"epoch": 1.33,
"learning_rate": 0.001,
"loss": 0.3108,
"step": 362
},
{
"epoch": 1.33,
"learning_rate": 0.001,
"loss": 0.3348,
"step": 364
},
{
"epoch": 1.34,
"learning_rate": 0.001,
"loss": 0.3309,
"step": 366
},
{
"epoch": 1.35,
"learning_rate": 0.001,
"loss": 0.3277,
"step": 368
},
{
"epoch": 1.36,
"learning_rate": 0.001,
"loss": 0.3426,
"step": 370
},
{
"epoch": 1.36,
"learning_rate": 0.001,
"loss": 0.3218,
"step": 372
},
{
"epoch": 1.37,
"learning_rate": 0.001,
"loss": 0.3433,
"step": 374
},
{
"epoch": 1.38,
"learning_rate": 0.001,
"loss": 0.3297,
"step": 376
},
{
"epoch": 1.39,
"learning_rate": 0.001,
"loss": 0.3283,
"step": 378
},
{
"epoch": 1.39,
"learning_rate": 0.001,
"loss": 0.3371,
"step": 380
},
{
"epoch": 1.4,
"learning_rate": 0.001,
"loss": 0.3409,
"step": 382
},
{
"epoch": 1.41,
"learning_rate": 0.001,
"loss": 0.3483,
"step": 384
},
{
"epoch": 1.42,
"learning_rate": 0.001,
"loss": 0.3222,
"step": 386
},
{
"epoch": 1.42,
"learning_rate": 0.001,
"loss": 0.3127,
"step": 388
},
{
"epoch": 1.43,
"learning_rate": 0.001,
"loss": 0.3214,
"step": 390
},
{
"epoch": 1.44,
"learning_rate": 0.001,
"loss": 0.3306,
"step": 392
},
{
"epoch": 1.44,
"learning_rate": 0.001,
"loss": 0.3064,
"step": 394
},
{
"epoch": 1.45,
"learning_rate": 0.001,
"loss": 0.2994,
"step": 396
},
{
"epoch": 1.46,
"learning_rate": 0.001,
"loss": 0.3373,
"step": 398
},
{
"epoch": 1.47,
"learning_rate": 0.001,
"loss": 0.3316,
"step": 400
},
{
"epoch": 1.47,
"learning_rate": 0.001,
"loss": 0.3248,
"step": 402
},
{
"epoch": 1.48,
"learning_rate": 0.001,
"loss": 0.3224,
"step": 404
},
{
"epoch": 1.49,
"learning_rate": 0.001,
"loss": 0.3295,
"step": 406
},
{
"epoch": 1.5,
"learning_rate": 0.001,
"loss": 0.3198,
"step": 408
},
{
"epoch": 1.5,
"learning_rate": 0.001,
"loss": 0.3353,
"step": 410
},
{
"epoch": 1.51,
"learning_rate": 0.001,
"loss": 0.3478,
"step": 412
},
{
"epoch": 1.52,
"learning_rate": 0.001,
"loss": 0.3194,
"step": 414
},
{
"epoch": 1.53,
"learning_rate": 0.001,
"loss": 0.3241,
"step": 416
},
{
"epoch": 1.53,
"learning_rate": 0.001,
"loss": 0.3211,
"step": 418
},
{
"epoch": 1.54,
"learning_rate": 0.001,
"loss": 0.3366,
"step": 420
},
{
"epoch": 1.55,
"learning_rate": 0.001,
"loss": 0.319,
"step": 422
},
{
"epoch": 1.55,
"learning_rate": 0.001,
"loss": 0.3222,
"step": 424
},
{
"epoch": 1.56,
"learning_rate": 0.001,
"loss": 0.3984,
"step": 426
},
{
"epoch": 1.57,
"learning_rate": 0.001,
"loss": 0.3117,
"step": 428
},
{
"epoch": 1.58,
"learning_rate": 0.001,
"loss": 0.3524,
"step": 430
},
{
"epoch": 1.58,
"learning_rate": 0.001,
"loss": 0.3503,
"step": 432
},
{
"epoch": 1.59,
"learning_rate": 0.001,
"loss": 0.3354,
"step": 434
},
{
"epoch": 1.6,
"learning_rate": 0.001,
"loss": 0.3306,
"step": 436
},
{
"epoch": 1.61,
"learning_rate": 0.001,
"loss": 0.336,
"step": 438
},
{
"epoch": 1.61,
"learning_rate": 0.001,
"loss": 0.3556,
"step": 440
},
{
"epoch": 1.62,
"learning_rate": 0.001,
"loss": 0.3452,
"step": 442
},
{
"epoch": 1.63,
"learning_rate": 0.001,
"loss": 0.346,
"step": 444
},
{
"epoch": 1.64,
"learning_rate": 0.001,
"loss": 0.3346,
"step": 446
},
{
"epoch": 1.64,
"learning_rate": 0.001,
"loss": 0.328,
"step": 448
},
{
"epoch": 1.65,
"learning_rate": 0.001,
"loss": 0.3441,
"step": 450
},
{
"epoch": 1.66,
"learning_rate": 0.001,
"loss": 0.3379,
"step": 452
},
{
"epoch": 1.66,
"learning_rate": 0.001,
"loss": 0.3721,
"step": 454
},
{
"epoch": 1.67,
"learning_rate": 0.001,
"loss": 0.3235,
"step": 456
},
{
"epoch": 1.68,
"learning_rate": 0.001,
"loss": 0.325,
"step": 458
},
{
"epoch": 1.69,
"learning_rate": 0.001,
"loss": 0.3409,
"step": 460
},
{
"epoch": 1.69,
"learning_rate": 0.001,
"loss": 0.348,
"step": 462
},
{
"epoch": 1.7,
"learning_rate": 0.001,
"loss": 0.3537,
"step": 464
},
{
"epoch": 1.71,
"learning_rate": 0.001,
"loss": 0.3519,
"step": 466
},
{
"epoch": 1.72,
"learning_rate": 0.001,
"loss": 0.3673,
"step": 468
},
{
"epoch": 1.72,
"learning_rate": 0.001,
"loss": 0.35,
"step": 470
},
{
"epoch": 1.73,
"learning_rate": 0.001,
"loss": 0.3329,
"step": 472
},
{
"epoch": 1.74,
"learning_rate": 0.001,
"loss": 0.3367,
"step": 474
},
{
"epoch": 1.75,
"learning_rate": 0.001,
"loss": 0.3464,
"step": 476
},
{
"epoch": 1.75,
"learning_rate": 0.001,
"loss": 0.3241,
"step": 478
},
{
"epoch": 1.76,
"learning_rate": 0.001,
"loss": 0.328,
"step": 480
},
{
"epoch": 1.77,
"learning_rate": 0.001,
"loss": 0.3553,
"step": 482
},
{
"epoch": 1.77,
"learning_rate": 0.001,
"loss": 0.3468,
"step": 484
},
{
"epoch": 1.78,
"learning_rate": 0.001,
"loss": 0.3232,
"step": 486
},
{
"epoch": 1.79,
"learning_rate": 0.001,
"loss": 0.3397,
"step": 488
},
{
"epoch": 1.8,
"learning_rate": 0.001,
"loss": 0.3248,
"step": 490
},
{
"epoch": 1.8,
"learning_rate": 0.001,
"loss": 0.3359,
"step": 492
},
{
"epoch": 1.81,
"learning_rate": 0.001,
"loss": 0.3472,
"step": 494
},
{
"epoch": 1.82,
"learning_rate": 0.001,
"loss": 0.362,
"step": 496
},
{
"epoch": 1.83,
"learning_rate": 0.001,
"loss": 0.3249,
"step": 498
},
{
"epoch": 1.83,
"learning_rate": 0.001,
"loss": 0.3396,
"step": 500
},
{
"epoch": 1.84,
"learning_rate": 0.001,
"loss": 0.3258,
"step": 502
},
{
"epoch": 1.85,
"learning_rate": 0.001,
"loss": 0.3325,
"step": 504
},
{
"epoch": 1.86,
"learning_rate": 0.001,
"loss": 0.3458,
"step": 506
},
{
"epoch": 1.86,
"learning_rate": 0.001,
"loss": 0.348,
"step": 508
},
{
"epoch": 1.87,
"learning_rate": 0.001,
"loss": 0.328,
"step": 510
},
{
"epoch": 1.88,
"learning_rate": 0.001,
"loss": 0.3431,
"step": 512
},
{
"epoch": 1.88,
"learning_rate": 0.001,
"loss": 0.3471,
"step": 514
},
{
"epoch": 1.89,
"learning_rate": 0.001,
"loss": 0.3412,
"step": 516
},
{
"epoch": 1.9,
"learning_rate": 0.001,
"loss": 0.3562,
"step": 518
},
{
"epoch": 1.91,
"learning_rate": 0.001,
"loss": 0.3314,
"step": 520
},
{
"epoch": 1.91,
"learning_rate": 0.001,
"loss": 0.3507,
"step": 522
},
{
"epoch": 1.92,
"learning_rate": 0.001,
"loss": 0.3274,
"step": 524
},
{
"epoch": 1.93,
"learning_rate": 0.001,
"loss": 0.341,
"step": 526
},
{
"epoch": 1.94,
"learning_rate": 0.001,
"loss": 0.3253,
"step": 528
},
{
"epoch": 1.94,
"learning_rate": 0.001,
"loss": 0.3335,
"step": 530
},
{
"epoch": 1.95,
"learning_rate": 0.001,
"loss": 0.3452,
"step": 532
},
{
"epoch": 1.96,
"learning_rate": 0.001,
"loss": 0.3294,
"step": 534
},
{
"epoch": 1.97,
"learning_rate": 0.001,
"loss": 0.3334,
"step": 536
},
{
"epoch": 1.97,
"learning_rate": 0.001,
"loss": 0.3498,
"step": 538
},
{
"epoch": 1.98,
"learning_rate": 0.001,
"loss": 0.3573,
"step": 540
},
{
"epoch": 1.99,
"learning_rate": 0.001,
"loss": 0.3638,
"step": 542
},
{
"epoch": 1.99,
"learning_rate": 0.001,
"loss": 0.3485,
"step": 544
},
{
"epoch": 2.0,
"eval_gen_len": 808.4393004115226,
"eval_loss": 1.2622333765029907,
"eval_rouge1": 66.9296,
"eval_rouge2": 38.7595,
"eval_rougeL": 36.4964,
"eval_rougeLsum": 64.6309,
"eval_runtime": 6721.27,
"eval_samples_per_second": 0.145,
"eval_steps_per_second": 0.018,
"step": 545
},
{
"epoch": 2.0,
"learning_rate": 0.001,
"loss": 0.3388,
"step": 546
},
{
"epoch": 2.01,
"learning_rate": 0.001,
"loss": 0.2616,
"step": 548
},
{
"epoch": 2.02,
"learning_rate": 0.001,
"loss": 0.2541,
"step": 550
},
{
"epoch": 2.02,
"learning_rate": 0.001,
"loss": 0.218,
"step": 552
},
{
"epoch": 2.03,
"learning_rate": 0.001,
"loss": 0.236,
"step": 554
},
{
"epoch": 2.04,
"learning_rate": 0.001,
"loss": 0.2427,
"step": 556
},
{
"epoch": 2.05,
"learning_rate": 0.001,
"loss": 0.2696,
"step": 558
},
{
"epoch": 2.05,
"learning_rate": 0.001,
"loss": 0.2491,
"step": 560
},
{
"epoch": 2.06,
"learning_rate": 0.001,
"loss": 0.2558,
"step": 562
},
{
"epoch": 2.07,
"learning_rate": 0.001,
"loss": 0.2377,
"step": 564
},
{
"epoch": 2.08,
"learning_rate": 0.001,
"loss": 0.2352,
"step": 566
},
{
"epoch": 2.08,
"learning_rate": 0.001,
"loss": 0.2495,
"step": 568
},
{
"epoch": 2.09,
"learning_rate": 0.001,
"loss": 0.2297,
"step": 570
},
{
"epoch": 2.1,
"learning_rate": 0.001,
"loss": 0.2388,
"step": 572
},
{
"epoch": 2.1,
"learning_rate": 0.001,
"loss": 0.2546,
"step": 574
},
{
"epoch": 2.11,
"learning_rate": 0.001,
"loss": 0.2517,
"step": 576
},
{
"epoch": 2.12,
"learning_rate": 0.001,
"loss": 0.2429,
"step": 578
},
{
"epoch": 2.13,
"learning_rate": 0.001,
"loss": 0.242,
"step": 580
},
{
"epoch": 2.13,
"learning_rate": 0.001,
"loss": 0.2522,
"step": 582
},
{
"epoch": 2.14,
"learning_rate": 0.001,
"loss": 0.2755,
"step": 584
},
{
"epoch": 2.15,
"learning_rate": 0.001,
"loss": 0.2646,
"step": 586
},
{
"epoch": 2.16,
"learning_rate": 0.001,
"loss": 0.2645,
"step": 588
},
{
"epoch": 2.16,
"learning_rate": 0.001,
"loss": 0.2544,
"step": 590
},
{
"epoch": 2.17,
"learning_rate": 0.001,
"loss": 0.2482,
"step": 592
},
{
"epoch": 2.18,
"learning_rate": 0.001,
"loss": 0.2406,
"step": 594
},
{
"epoch": 2.19,
"learning_rate": 0.001,
"loss": 0.2621,
"step": 596
},
{
"epoch": 2.19,
"learning_rate": 0.001,
"loss": 0.2566,
"step": 598
},
{
"epoch": 2.2,
"learning_rate": 0.001,
"loss": 0.2569,
"step": 600
},
{
"epoch": 2.21,
"learning_rate": 0.001,
"loss": 0.244,
"step": 602
},
{
"epoch": 2.21,
"learning_rate": 0.001,
"loss": 0.252,
"step": 604
},
{
"epoch": 2.22,
"learning_rate": 0.001,
"loss": 0.2394,
"step": 606
},
{
"epoch": 2.23,
"learning_rate": 0.001,
"loss": 0.2569,
"step": 608
},
{
"epoch": 2.24,
"learning_rate": 0.001,
"loss": 0.253,
"step": 610
},
{
"epoch": 2.24,
"learning_rate": 0.001,
"loss": 0.2411,
"step": 612
},
{
"epoch": 2.25,
"learning_rate": 0.001,
"loss": 0.25,
"step": 614
},
{
"epoch": 2.26,
"learning_rate": 0.001,
"loss": 0.2603,
"step": 616
},
{
"epoch": 2.27,
"learning_rate": 0.001,
"loss": 0.2519,
"step": 618
},
{
"epoch": 2.27,
"learning_rate": 0.001,
"loss": 0.2544,
"step": 620
},
{
"epoch": 2.28,
"learning_rate": 0.001,
"loss": 0.2607,
"step": 622
},
{
"epoch": 2.29,
"learning_rate": 0.001,
"loss": 0.2485,
"step": 624
},
{
"epoch": 2.3,
"learning_rate": 0.001,
"loss": 0.2663,
"step": 626
},
{
"epoch": 2.3,
"learning_rate": 0.001,
"loss": 0.274,
"step": 628
},
{
"epoch": 2.31,
"learning_rate": 0.001,
"loss": 0.2734,
"step": 630
},
{
"epoch": 2.32,
"learning_rate": 0.001,
"loss": 0.2636,
"step": 632
},
{
"epoch": 2.32,
"learning_rate": 0.001,
"loss": 0.2637,
"step": 634
},
{
"epoch": 2.33,
"learning_rate": 0.001,
"loss": 0.2611,
"step": 636
},
{
"epoch": 2.34,
"learning_rate": 0.001,
"loss": 0.2808,
"step": 638
},
{
"epoch": 2.35,
"learning_rate": 0.001,
"loss": 0.2477,
"step": 640
},
{
"epoch": 2.35,
"learning_rate": 0.001,
"loss": 0.2528,
"step": 642
},
{
"epoch": 2.36,
"learning_rate": 0.001,
"loss": 0.2527,
"step": 644
},
{
"epoch": 2.37,
"learning_rate": 0.001,
"loss": 0.2714,
"step": 646
},
{
"epoch": 2.38,
"learning_rate": 0.001,
"loss": 0.2747,
"step": 648
},
{
"epoch": 2.38,
"learning_rate": 0.001,
"loss": 0.2745,
"step": 650
},
{
"epoch": 2.39,
"learning_rate": 0.001,
"loss": 0.2577,
"step": 652
},
{
"epoch": 2.4,
"learning_rate": 0.001,
"loss": 0.2748,
"step": 654
},
{
"epoch": 2.4,
"learning_rate": 0.001,
"loss": 0.2689,
"step": 656
},
{
"epoch": 2.41,
"learning_rate": 0.001,
"loss": 0.2519,
"step": 658
},
{
"epoch": 2.42,
"learning_rate": 0.001,
"loss": 0.2479,
"step": 660
},
{
"epoch": 2.43,
"learning_rate": 0.001,
"loss": 0.2743,
"step": 662
},
{
"epoch": 2.43,
"learning_rate": 0.001,
"loss": 0.278,
"step": 664
},
{
"epoch": 2.44,
"learning_rate": 0.001,
"loss": 0.2815,
"step": 666
},
{
"epoch": 2.45,
"learning_rate": 0.001,
"loss": 0.2685,
"step": 668
},
{
"epoch": 2.46,
"learning_rate": 0.001,
"loss": 0.2479,
"step": 670
},
{
"epoch": 2.46,
"learning_rate": 0.001,
"loss": 0.2634,
"step": 672
},
{
"epoch": 2.47,
"learning_rate": 0.001,
"loss": 0.2602,
"step": 674
},
{
"epoch": 2.48,
"learning_rate": 0.001,
"loss": 0.2601,
"step": 676
},
{
"epoch": 2.49,
"learning_rate": 0.001,
"loss": 0.2703,
"step": 678
},
{
"epoch": 2.49,
"learning_rate": 0.001,
"loss": 0.286,
"step": 680
},
{
"epoch": 2.5,
"learning_rate": 0.001,
"loss": 0.2569,
"step": 682
},
{
"epoch": 2.51,
"learning_rate": 0.001,
"loss": 0.2592,
"step": 684
},
{
"epoch": 2.51,
"learning_rate": 0.001,
"loss": 0.2703,
"step": 686
},
{
"epoch": 2.52,
"learning_rate": 0.001,
"loss": 0.2776,
"step": 688
},
{
"epoch": 2.53,
"learning_rate": 0.001,
"loss": 0.2701,
"step": 690
},
{
"epoch": 2.54,
"learning_rate": 0.001,
"loss": 0.277,
"step": 692
},
{
"epoch": 2.54,
"learning_rate": 0.001,
"loss": 0.2904,
"step": 694
},
{
"epoch": 2.55,
"learning_rate": 0.001,
"loss": 0.2483,
"step": 696
},
{
"epoch": 2.56,
"learning_rate": 0.001,
"loss": 0.254,
"step": 698
},
{
"epoch": 2.57,
"learning_rate": 0.001,
"loss": 0.2639,
"step": 700
},
{
"epoch": 2.57,
"learning_rate": 0.001,
"loss": 0.2731,
"step": 702
},
{
"epoch": 2.58,
"learning_rate": 0.001,
"loss": 0.2528,
"step": 704
},
{
"epoch": 2.59,
"learning_rate": 0.001,
"loss": 0.2544,
"step": 706
},
{
"epoch": 2.6,
"learning_rate": 0.001,
"loss": 0.2564,
"step": 708
},
{
"epoch": 2.6,
"learning_rate": 0.001,
"loss": 0.2779,
"step": 710
},
{
"epoch": 2.61,
"learning_rate": 0.001,
"loss": 0.2774,
"step": 712
},
{
"epoch": 2.62,
"learning_rate": 0.001,
"loss": 0.2521,
"step": 714
},
{
"epoch": 2.62,
"learning_rate": 0.001,
"loss": 0.2784,
"step": 716
},
{
"epoch": 2.63,
"learning_rate": 0.001,
"loss": 0.2565,
"step": 718
},
{
"epoch": 2.64,
"learning_rate": 0.001,
"loss": 0.2832,
"step": 720
},
{
"epoch": 2.65,
"learning_rate": 0.001,
"loss": 0.2757,
"step": 722
},
{
"epoch": 2.65,
"learning_rate": 0.001,
"loss": 0.2725,
"step": 724
},
{
"epoch": 2.66,
"learning_rate": 0.001,
"loss": 0.2794,
"step": 726
},
{
"epoch": 2.67,
"learning_rate": 0.001,
"loss": 0.2485,
"step": 728
},
{
"epoch": 2.68,
"learning_rate": 0.001,
"loss": 0.2842,
"step": 730
},
{
"epoch": 2.68,
"learning_rate": 0.001,
"loss": 0.2784,
"step": 732
},
{
"epoch": 2.69,
"learning_rate": 0.001,
"loss": 0.2825,
"step": 734
},
{
"epoch": 2.7,
"learning_rate": 0.001,
"loss": 0.2517,
"step": 736
},
{
"epoch": 2.71,
"learning_rate": 0.001,
"loss": 0.277,
"step": 738
},
{
"epoch": 2.71,
"learning_rate": 0.001,
"loss": 0.2731,
"step": 740
},
{
"epoch": 2.72,
"learning_rate": 0.001,
"loss": 0.2611,
"step": 742
},
{
"epoch": 2.73,
"learning_rate": 0.001,
"loss": 0.2789,
"step": 744
},
{
"epoch": 2.73,
"learning_rate": 0.001,
"loss": 0.2765,
"step": 746
},
{
"epoch": 2.74,
"learning_rate": 0.001,
"loss": 0.2876,
"step": 748
},
{
"epoch": 2.75,
"learning_rate": 0.001,
"loss": 0.2776,
"step": 750
},
{
"epoch": 2.76,
"learning_rate": 0.001,
"loss": 0.2867,
"step": 752
},
{
"epoch": 2.76,
"learning_rate": 0.001,
"loss": 0.2517,
"step": 754
},
{
"epoch": 2.77,
"learning_rate": 0.001,
"loss": 0.2721,
"step": 756
},
{
"epoch": 2.78,
"learning_rate": 0.001,
"loss": 0.2823,
"step": 758
},
{
"epoch": 2.79,
"learning_rate": 0.001,
"loss": 0.2809,
"step": 760
},
{
"epoch": 2.79,
"learning_rate": 0.001,
"loss": 0.2774,
"step": 762
},
{
"epoch": 2.8,
"learning_rate": 0.001,
"loss": 0.2485,
"step": 764
},
{
"epoch": 2.81,
"learning_rate": 0.001,
"loss": 0.2752,
"step": 766
},
{
"epoch": 2.82,
"learning_rate": 0.001,
"loss": 0.2618,
"step": 768
},
{
"epoch": 2.82,
"learning_rate": 0.001,
"loss": 0.28,
"step": 770
},
{
"epoch": 2.83,
"learning_rate": 0.001,
"loss": 0.2973,
"step": 772
},
{
"epoch": 2.84,
"learning_rate": 0.001,
"loss": 0.2859,
"step": 774
},
{
"epoch": 2.84,
"learning_rate": 0.001,
"loss": 0.2809,
"step": 776
},
{
"epoch": 2.85,
"learning_rate": 0.001,
"loss": 0.2807,
"step": 778
},
{
"epoch": 2.86,
"learning_rate": 0.001,
"loss": 0.2846,
"step": 780
},
{
"epoch": 2.87,
"learning_rate": 0.001,
"loss": 0.2901,
"step": 782
},
{
"epoch": 2.87,
"learning_rate": 0.001,
"loss": 0.2935,
"step": 784
},
{
"epoch": 2.88,
"learning_rate": 0.001,
"loss": 0.2833,
"step": 786
},
{
"epoch": 2.89,
"learning_rate": 0.001,
"loss": 0.2746,
"step": 788
},
{
"epoch": 2.9,
"learning_rate": 0.001,
"loss": 0.2783,
"step": 790
},
{
"epoch": 2.9,
"learning_rate": 0.001,
"loss": 0.282,
"step": 792
},
{
"epoch": 2.91,
"learning_rate": 0.001,
"loss": 0.2933,
"step": 794
},
{
"epoch": 2.92,
"learning_rate": 0.001,
"loss": 0.2693,
"step": 796
},
{
"epoch": 2.93,
"learning_rate": 0.001,
"loss": 0.2489,
"step": 798
},
{
"epoch": 2.93,
"learning_rate": 0.001,
"loss": 0.275,
"step": 800
},
{
"epoch": 2.94,
"learning_rate": 0.001,
"loss": 0.2739,
"step": 802
},
{
"epoch": 2.95,
"learning_rate": 0.001,
"loss": 0.2766,
"step": 804
},
{
"epoch": 2.95,
"learning_rate": 0.001,
"loss": 0.2692,
"step": 806
},
{
"epoch": 2.96,
"learning_rate": 0.001,
"loss": 0.2635,
"step": 808
},
{
"epoch": 2.97,
"learning_rate": 0.001,
"loss": 0.2801,
"step": 810
},
{
"epoch": 2.98,
"learning_rate": 0.001,
"loss": 0.2836,
"step": 812
},
{
"epoch": 2.98,
"learning_rate": 0.001,
"loss": 0.2707,
"step": 814
},
{
"epoch": 2.99,
"learning_rate": 0.001,
"loss": 0.3019,
"step": 816
},
{
"epoch": 3.0,
"learning_rate": 0.001,
"loss": 0.2933,
"step": 818
},
{
"epoch": 3.0,
"eval_gen_len": 976.033950617284,
"eval_loss": 1.380370855331421,
"eval_rouge1": 65.3911,
"eval_rouge2": 38.0875,
"eval_rougeL": 35.5935,
"eval_rougeLsum": 63.1902,
"eval_runtime": 8154.8246,
"eval_samples_per_second": 0.119,
"eval_steps_per_second": 0.015,
"step": 818
},
{
"epoch": 3.01,
"learning_rate": 0.001,
"loss": 0.2089,
"step": 820
},
{
"epoch": 3.01,
"learning_rate": 0.001,
"loss": 0.2027,
"step": 822
},
{
"epoch": 3.02,
"learning_rate": 0.001,
"loss": 0.1992,
"step": 824
},
{
"epoch": 3.03,
"learning_rate": 0.001,
"loss": 0.2119,
"step": 826
},
{
"epoch": 3.04,
"learning_rate": 0.001,
"loss": 0.2031,
"step": 828
},
{
"epoch": 3.04,
"learning_rate": 0.001,
"loss": 0.189,
"step": 830
},
{
"epoch": 3.05,
"learning_rate": 0.001,
"loss": 0.1996,
"step": 832
},
{
"epoch": 3.06,
"learning_rate": 0.001,
"loss": 0.1896,
"step": 834
},
{
"epoch": 3.06,
"learning_rate": 0.001,
"loss": 0.2085,
"step": 836
},
{
"epoch": 3.07,
"learning_rate": 0.001,
"loss": 0.2106,
"step": 838
},
{
"epoch": 3.08,
"learning_rate": 0.001,
"loss": 0.2056,
"step": 840
},
{
"epoch": 3.09,
"learning_rate": 0.001,
"loss": 0.1977,
"step": 842
},
{
"epoch": 3.09,
"learning_rate": 0.001,
"loss": 0.1966,
"step": 844
},
{
"epoch": 3.1,
"learning_rate": 0.001,
"loss": 0.2076,
"step": 846
},
{
"epoch": 3.11,
"learning_rate": 0.001,
"loss": 0.1946,
"step": 848
},
{
"epoch": 3.12,
"learning_rate": 0.001,
"loss": 0.2358,
"step": 850
},
{
"epoch": 3.12,
"learning_rate": 0.001,
"loss": 0.2011,
"step": 852
},
{
"epoch": 3.13,
"learning_rate": 0.001,
"loss": 0.2039,
"step": 854
},
{
"epoch": 3.14,
"learning_rate": 0.001,
"loss": 0.2098,
"step": 856
},
{
"epoch": 3.15,
"learning_rate": 0.001,
"loss": 0.1953,
"step": 858
},
{
"epoch": 3.15,
"learning_rate": 0.001,
"loss": 0.196,
"step": 860
},
{
"epoch": 3.16,
"learning_rate": 0.001,
"loss": 0.2122,
"step": 862
},
{
"epoch": 3.17,
"learning_rate": 0.001,
"loss": 0.2076,
"step": 864
},
{
"epoch": 3.17,
"learning_rate": 0.001,
"loss": 0.2093,
"step": 866
},
{
"epoch": 3.18,
"learning_rate": 0.001,
"loss": 0.213,
"step": 868
},
{
"epoch": 3.19,
"learning_rate": 0.001,
"loss": 0.2213,
"step": 870
},
{
"epoch": 3.2,
"learning_rate": 0.001,
"loss": 0.1936,
"step": 872
},
{
"epoch": 3.2,
"learning_rate": 0.001,
"loss": 0.1946,
"step": 874
},
{
"epoch": 3.21,
"learning_rate": 0.001,
"loss": 0.2242,
"step": 876
},
{
"epoch": 3.22,
"learning_rate": 0.001,
"loss": 0.2156,
"step": 878
},
{
"epoch": 3.23,
"learning_rate": 0.001,
"loss": 0.2178,
"step": 880
},
{
"epoch": 3.23,
"learning_rate": 0.001,
"loss": 0.2119,
"step": 882
},
{
"epoch": 3.24,
"learning_rate": 0.001,
"loss": 0.2021,
"step": 884
},
{
"epoch": 3.25,
"learning_rate": 0.001,
"loss": 0.1916,
"step": 886
},
{
"epoch": 3.26,
"learning_rate": 0.001,
"loss": 0.217,
"step": 888
},
{
"epoch": 3.26,
"learning_rate": 0.001,
"loss": 0.2018,
"step": 890
},
{
"epoch": 3.27,
"learning_rate": 0.001,
"loss": 0.2048,
"step": 892
},
{
"epoch": 3.28,
"learning_rate": 0.001,
"loss": 0.2264,
"step": 894
},
{
"epoch": 3.28,
"learning_rate": 0.001,
"loss": 0.2287,
"step": 896
},
{
"epoch": 3.29,
"learning_rate": 0.001,
"loss": 0.2083,
"step": 898
},
{
"epoch": 3.3,
"learning_rate": 0.001,
"loss": 0.2398,
"step": 900
},
{
"epoch": 3.31,
"learning_rate": 0.001,
"loss": 0.2016,
"step": 902
},
{
"epoch": 3.31,
"learning_rate": 0.001,
"loss": 0.2082,
"step": 904
},
{
"epoch": 3.32,
"learning_rate": 0.001,
"loss": 0.2098,
"step": 906
},
{
"epoch": 3.33,
"learning_rate": 0.001,
"loss": 0.2164,
"step": 908
},
{
"epoch": 3.34,
"learning_rate": 0.001,
"loss": 0.2072,
"step": 910
},
{
"epoch": 3.34,
"learning_rate": 0.001,
"loss": 0.2274,
"step": 912
},
{
"epoch": 3.35,
"learning_rate": 0.001,
"loss": 0.2134,
"step": 914
},
{
"epoch": 3.36,
"learning_rate": 0.001,
"loss": 0.2193,
"step": 916
},
{
"epoch": 3.37,
"learning_rate": 0.001,
"loss": 0.2157,
"step": 918
},
{
"epoch": 3.37,
"learning_rate": 0.001,
"loss": 0.2156,
"step": 920
},
{
"epoch": 3.38,
"learning_rate": 0.001,
"loss": 0.2256,
"step": 922
},
{
"epoch": 3.39,
"learning_rate": 0.001,
"loss": 0.2126,
"step": 924
},
{
"epoch": 3.39,
"learning_rate": 0.001,
"loss": 0.2128,
"step": 926
},
{
"epoch": 3.4,
"learning_rate": 0.001,
"loss": 0.2318,
"step": 928
},
{
"epoch": 3.41,
"learning_rate": 0.001,
"loss": 0.2406,
"step": 930
},
{
"epoch": 3.42,
"learning_rate": 0.001,
"loss": 0.216,
"step": 932
},
{
"epoch": 3.42,
"learning_rate": 0.001,
"loss": 0.2316,
"step": 934
},
{
"epoch": 3.43,
"learning_rate": 0.001,
"loss": 0.2221,
"step": 936
},
{
"epoch": 3.44,
"learning_rate": 0.001,
"loss": 0.2177,
"step": 938
},
{
"epoch": 3.45,
"learning_rate": 0.001,
"loss": 0.2091,
"step": 940
},
{
"epoch": 3.45,
"learning_rate": 0.001,
"loss": 0.2198,
"step": 942
},
{
"epoch": 3.46,
"learning_rate": 0.001,
"loss": 0.2361,
"step": 944
},
{
"epoch": 3.47,
"learning_rate": 0.001,
"loss": 0.2279,
"step": 946
},
{
"epoch": 3.48,
"learning_rate": 0.001,
"loss": 0.213,
"step": 948
},
{
"epoch": 3.48,
"learning_rate": 0.001,
"loss": 0.2299,
"step": 950
},
{
"epoch": 3.49,
"learning_rate": 0.001,
"loss": 0.2116,
"step": 952
},
{
"epoch": 3.5,
"learning_rate": 0.001,
"loss": 0.2074,
"step": 954
},
{
"epoch": 3.5,
"learning_rate": 0.001,
"loss": 0.215,
"step": 956
},
{
"epoch": 3.51,
"learning_rate": 0.001,
"loss": 0.2226,
"step": 958
},
{
"epoch": 3.52,
"learning_rate": 0.001,
"loss": 0.2182,
"step": 960
},
{
"epoch": 3.53,
"learning_rate": 0.001,
"loss": 0.2098,
"step": 962
},
{
"epoch": 3.53,
"learning_rate": 0.001,
"loss": 0.2102,
"step": 964
},
{
"epoch": 3.54,
"learning_rate": 0.001,
"loss": 0.2144,
"step": 966
},
{
"epoch": 3.55,
"learning_rate": 0.001,
"loss": 0.2381,
"step": 968
},
{
"epoch": 3.56,
"learning_rate": 0.001,
"loss": 0.2146,
"step": 970
},
{
"epoch": 3.56,
"learning_rate": 0.001,
"loss": 0.2139,
"step": 972
},
{
"epoch": 3.57,
"learning_rate": 0.001,
"loss": 0.2351,
"step": 974
},
{
"epoch": 3.58,
"learning_rate": 0.001,
"loss": 0.2255,
"step": 976
},
{
"epoch": 3.59,
"learning_rate": 0.001,
"loss": 0.2112,
"step": 978
},
{
"epoch": 3.59,
"learning_rate": 0.001,
"loss": 0.2247,
"step": 980
},
{
"epoch": 3.6,
"learning_rate": 0.001,
"loss": 0.2221,
"step": 982
},
{
"epoch": 3.61,
"learning_rate": 0.001,
"loss": 0.2252,
"step": 984
},
{
"epoch": 3.61,
"learning_rate": 0.001,
"loss": 0.2238,
"step": 986
},
{
"epoch": 3.62,
"learning_rate": 0.001,
"loss": 0.226,
"step": 988
},
{
"epoch": 3.63,
"learning_rate": 0.001,
"loss": 0.2295,
"step": 990
},
{
"epoch": 3.64,
"learning_rate": 0.001,
"loss": 0.2435,
"step": 992
},
{
"epoch": 3.64,
"learning_rate": 0.001,
"loss": 0.2331,
"step": 994
},
{
"epoch": 3.65,
"learning_rate": 0.001,
"loss": 0.232,
"step": 996
},
{
"epoch": 3.66,
"learning_rate": 0.001,
"loss": 0.219,
"step": 998
},
{
"epoch": 3.67,
"learning_rate": 0.001,
"loss": 0.2229,
"step": 1000
},
{
"epoch": 3.67,
"learning_rate": 0.001,
"loss": 0.2223,
"step": 1002
},
{
"epoch": 3.68,
"learning_rate": 0.001,
"loss": 0.2039,
"step": 1004
},
{
"epoch": 3.69,
"learning_rate": 0.001,
"loss": 0.2172,
"step": 1006
},
{
"epoch": 3.7,
"learning_rate": 0.001,
"loss": 0.2247,
"step": 1008
},
{
"epoch": 3.7,
"learning_rate": 0.001,
"loss": 0.2175,
"step": 1010
},
{
"epoch": 3.71,
"learning_rate": 0.001,
"loss": 0.2136,
"step": 1012
},
{
"epoch": 3.72,
"learning_rate": 0.001,
"loss": 0.2242,
"step": 1014
},
{
"epoch": 3.72,
"learning_rate": 0.001,
"loss": 0.2148,
"step": 1016
},
{
"epoch": 3.73,
"learning_rate": 0.001,
"loss": 0.2243,
"step": 1018
},
{
"epoch": 3.74,
"learning_rate": 0.001,
"loss": 0.2145,
"step": 1020
},
{
"epoch": 3.75,
"learning_rate": 0.001,
"loss": 0.2261,
"step": 1022
},
{
"epoch": 3.75,
"learning_rate": 0.001,
"loss": 0.2366,
"step": 1024
},
{
"epoch": 3.76,
"learning_rate": 0.001,
"loss": 0.2486,
"step": 1026
},
{
"epoch": 3.77,
"learning_rate": 0.001,
"loss": 0.2361,
"step": 1028
},
{
"epoch": 3.78,
"learning_rate": 0.001,
"loss": 0.2382,
"step": 1030
},
{
"epoch": 3.78,
"learning_rate": 0.001,
"loss": 0.2278,
"step": 1032
},
{
"epoch": 3.79,
"learning_rate": 0.001,
"loss": 0.2466,
"step": 1034
},
{
"epoch": 3.8,
"learning_rate": 0.001,
"loss": 0.2241,
"step": 1036
},
{
"epoch": 3.81,
"learning_rate": 0.001,
"loss": 0.2335,
"step": 1038
},
{
"epoch": 3.81,
"learning_rate": 0.001,
"loss": 0.2413,
"step": 1040
},
{
"epoch": 3.82,
"learning_rate": 0.001,
"loss": 0.2413,
"step": 1042
},
{
"epoch": 3.83,
"learning_rate": 0.001,
"loss": 0.2317,
"step": 1044
},
{
"epoch": 3.83,
"learning_rate": 0.001,
"loss": 0.2322,
"step": 1046
},
{
"epoch": 3.84,
"learning_rate": 0.001,
"loss": 0.2154,
"step": 1048
},
{
"epoch": 3.85,
"learning_rate": 0.001,
"loss": 0.2178,
"step": 1050
},
{
"epoch": 3.86,
"learning_rate": 0.001,
"loss": 0.22,
"step": 1052
},
{
"epoch": 3.86,
"learning_rate": 0.001,
"loss": 0.2446,
"step": 1054
},
{
"epoch": 3.87,
"learning_rate": 0.001,
"loss": 0.2386,
"step": 1056
},
{
"epoch": 3.88,
"learning_rate": 0.001,
"loss": 0.2296,
"step": 1058
},
{
"epoch": 3.89,
"learning_rate": 0.001,
"loss": 0.2303,
"step": 1060
},
{
"epoch": 3.89,
"learning_rate": 0.001,
"loss": 0.2461,
"step": 1062
},
{
"epoch": 3.9,
"learning_rate": 0.001,
"loss": 0.2198,
"step": 1064
},
{
"epoch": 3.91,
"learning_rate": 0.001,
"loss": 0.2139,
"step": 1066
},
{
"epoch": 3.92,
"learning_rate": 0.001,
"loss": 0.2213,
"step": 1068
},
{
"epoch": 3.92,
"learning_rate": 0.001,
"loss": 0.2138,
"step": 1070
},
{
"epoch": 3.93,
"learning_rate": 0.001,
"loss": 0.2335,
"step": 1072
},
{
"epoch": 3.94,
"learning_rate": 0.001,
"loss": 0.2257,
"step": 1074
},
{
"epoch": 3.94,
"learning_rate": 0.001,
"loss": 0.2317,
"step": 1076
},
{
"epoch": 3.95,
"learning_rate": 0.001,
"loss": 0.2327,
"step": 1078
},
{
"epoch": 3.96,
"learning_rate": 0.001,
"loss": 0.2282,
"step": 1080
},
{
"epoch": 3.97,
"learning_rate": 0.001,
"loss": 0.2539,
"step": 1082
},
{
"epoch": 3.97,
"learning_rate": 0.001,
"loss": 0.2497,
"step": 1084
},
{
"epoch": 3.98,
"learning_rate": 0.001,
"loss": 0.2235,
"step": 1086
},
{
"epoch": 3.99,
"learning_rate": 0.001,
"loss": 0.2262,
"step": 1088
},
{
"epoch": 4.0,
"learning_rate": 0.001,
"loss": 0.2443,
"step": 1090
},
{
"epoch": 4.0,
"eval_gen_len": 816.7253086419753,
"eval_loss": 1.4998103380203247,
"eval_rouge1": 67.0929,
"eval_rouge2": 38.0763,
"eval_rougeL": 35.8704,
"eval_rougeLsum": 64.9022,
"eval_runtime": 6494.5526,
"eval_samples_per_second": 0.15,
"eval_steps_per_second": 0.019,
"step": 1091
},
{
"epoch": 4.0,
"learning_rate": 0.001,
"loss": 0.2103,
"step": 1092
},
{
"epoch": 4.01,
"learning_rate": 0.001,
"loss": 0.1719,
"step": 1094
},
{
"epoch": 4.02,
"learning_rate": 0.001,
"loss": 0.1457,
"step": 1096
},
{
"epoch": 4.03,
"learning_rate": 0.001,
"loss": 0.1594,
"step": 1098
},
{
"epoch": 4.03,
"learning_rate": 0.001,
"loss": 0.1525,
"step": 1100
},
{
"epoch": 4.04,
"learning_rate": 0.001,
"loss": 0.1445,
"step": 1102
},
{
"epoch": 4.05,
"learning_rate": 0.001,
"loss": 0.1679,
"step": 1104
},
{
"epoch": 4.05,
"learning_rate": 0.001,
"loss": 0.1793,
"step": 1106
},
{
"epoch": 4.06,
"learning_rate": 0.001,
"loss": 0.1613,
"step": 1108
},
{
"epoch": 4.07,
"learning_rate": 0.001,
"loss": 0.1735,
"step": 1110
},
{
"epoch": 4.08,
"learning_rate": 0.001,
"loss": 0.1683,
"step": 1112
},
{
"epoch": 4.08,
"learning_rate": 0.001,
"loss": 0.1658,
"step": 1114
},
{
"epoch": 4.09,
"learning_rate": 0.001,
"loss": 0.1648,
"step": 1116
},
{
"epoch": 4.1,
"learning_rate": 0.001,
"loss": 0.1861,
"step": 1118
},
{
"epoch": 4.11,
"learning_rate": 0.001,
"loss": 0.1625,
"step": 1120
},
{
"epoch": 4.11,
"learning_rate": 0.001,
"loss": 0.1713,
"step": 1122
},
{
"epoch": 4.12,
"learning_rate": 0.001,
"loss": 0.1754,
"step": 1124
},
{
"epoch": 4.13,
"learning_rate": 0.001,
"loss": 0.1801,
"step": 1126
},
{
"epoch": 4.14,
"learning_rate": 0.001,
"loss": 0.1655,
"step": 1128
},
{
"epoch": 4.14,
"learning_rate": 0.001,
"loss": 0.1665,
"step": 1130
},
{
"epoch": 4.15,
"learning_rate": 0.001,
"loss": 0.1834,
"step": 1132
},
{
"epoch": 4.16,
"learning_rate": 0.001,
"loss": 0.1626,
"step": 1134
},
{
"epoch": 4.16,
"learning_rate": 0.001,
"loss": 0.1687,
"step": 1136
},
{
"epoch": 4.17,
"learning_rate": 0.001,
"loss": 0.1673,
"step": 1138
},
{
"epoch": 4.18,
"learning_rate": 0.001,
"loss": 0.1627,
"step": 1140
},
{
"epoch": 4.19,
"learning_rate": 0.001,
"loss": 0.1692,
"step": 1142
},
{
"epoch": 4.19,
"learning_rate": 0.001,
"loss": 0.1725,
"step": 1144
},
{
"epoch": 4.2,
"learning_rate": 0.001,
"loss": 0.1769,
"step": 1146
},
{
"epoch": 4.21,
"learning_rate": 0.001,
"loss": 0.1816,
"step": 1148
},
{
"epoch": 4.22,
"learning_rate": 0.001,
"loss": 0.1672,
"step": 1150
},
{
"epoch": 4.22,
"learning_rate": 0.001,
"loss": 0.1712,
"step": 1152
},
{
"epoch": 4.23,
"learning_rate": 0.001,
"loss": 0.1647,
"step": 1154
},
{
"epoch": 4.24,
"learning_rate": 0.001,
"loss": 0.1866,
"step": 1156
},
{
"epoch": 4.25,
"learning_rate": 0.001,
"loss": 0.1745,
"step": 1158
},
{
"epoch": 4.25,
"learning_rate": 0.001,
"loss": 0.1639,
"step": 1160
},
{
"epoch": 4.26,
"learning_rate": 0.001,
"loss": 0.1746,
"step": 1162
},
{
"epoch": 4.27,
"learning_rate": 0.001,
"loss": 0.1614,
"step": 1164
},
{
"epoch": 4.27,
"learning_rate": 0.001,
"loss": 0.1919,
"step": 1166
},
{
"epoch": 4.28,
"learning_rate": 0.001,
"loss": 0.1816,
"step": 1168
},
{
"epoch": 4.29,
"learning_rate": 0.001,
"loss": 0.1676,
"step": 1170
},
{
"epoch": 4.3,
"learning_rate": 0.001,
"loss": 0.181,
"step": 1172
},
{
"epoch": 4.3,
"learning_rate": 0.001,
"loss": 0.1734,
"step": 1174
},
{
"epoch": 4.31,
"learning_rate": 0.001,
"loss": 0.197,
"step": 1176
},
{
"epoch": 4.32,
"learning_rate": 0.001,
"loss": 0.1781,
"step": 1178
},
{
"epoch": 4.33,
"learning_rate": 0.001,
"loss": 0.1791,
"step": 1180
},
{
"epoch": 4.33,
"learning_rate": 0.001,
"loss": 0.1727,
"step": 1182
},
{
"epoch": 4.34,
"learning_rate": 0.001,
"loss": 0.1894,
"step": 1184
},
{
"epoch": 4.35,
"learning_rate": 0.001,
"loss": 0.1701,
"step": 1186
},
{
"epoch": 4.36,
"learning_rate": 0.001,
"loss": 0.1782,
"step": 1188
},
{
"epoch": 4.36,
"learning_rate": 0.001,
"loss": 0.1786,
"step": 1190
},
{
"epoch": 4.37,
"learning_rate": 0.001,
"loss": 0.1596,
"step": 1192
},
{
"epoch": 4.38,
"learning_rate": 0.001,
"loss": 0.174,
"step": 1194
},
{
"epoch": 4.38,
"learning_rate": 0.001,
"loss": 0.1921,
"step": 1196
},
{
"epoch": 4.39,
"learning_rate": 0.001,
"loss": 0.1756,
"step": 1198
},
{
"epoch": 4.4,
"learning_rate": 0.001,
"loss": 0.1912,
"step": 1200
},
{
"epoch": 4.41,
"learning_rate": 0.001,
"loss": 0.1863,
"step": 1202
},
{
"epoch": 4.41,
"learning_rate": 0.001,
"loss": 0.181,
"step": 1204
},
{
"epoch": 4.42,
"learning_rate": 0.001,
"loss": 0.191,
"step": 1206
},
{
"epoch": 4.43,
"learning_rate": 0.001,
"loss": 0.1794,
"step": 1208
},
{
"epoch": 4.44,
"learning_rate": 0.001,
"loss": 0.1734,
"step": 1210
},
{
"epoch": 4.44,
"learning_rate": 0.001,
"loss": 0.2014,
"step": 1212
},
{
"epoch": 4.45,
"learning_rate": 0.001,
"loss": 0.1676,
"step": 1214
},
{
"epoch": 4.46,
"learning_rate": 0.001,
"loss": 0.1823,
"step": 1216
},
{
"epoch": 4.47,
"learning_rate": 0.001,
"loss": 0.1859,
"step": 1218
},
{
"epoch": 4.47,
"learning_rate": 0.001,
"loss": 0.1796,
"step": 1220
},
{
"epoch": 4.48,
"learning_rate": 0.001,
"loss": 0.188,
"step": 1222
},
{
"epoch": 4.49,
"learning_rate": 0.001,
"loss": 0.1906,
"step": 1224
},
{
"epoch": 4.49,
"learning_rate": 0.001,
"loss": 0.1916,
"step": 1226
},
{
"epoch": 4.5,
"learning_rate": 0.001,
"loss": 0.1996,
"step": 1228
},
{
"epoch": 4.51,
"learning_rate": 0.001,
"loss": 0.1762,
"step": 1230
},
{
"epoch": 4.52,
"learning_rate": 0.001,
"loss": 0.1907,
"step": 1232
},
{
"epoch": 4.52,
"learning_rate": 0.001,
"loss": 0.1924,
"step": 1234
},
{
"epoch": 4.53,
"learning_rate": 0.001,
"loss": 0.1767,
"step": 1236
},
{
"epoch": 4.54,
"learning_rate": 0.001,
"loss": 0.1803,
"step": 1238
},
{
"epoch": 4.55,
"learning_rate": 0.001,
"loss": 0.1957,
"step": 1240
},
{
"epoch": 4.55,
"learning_rate": 0.001,
"loss": 0.1787,
"step": 1242
},
{
"epoch": 4.56,
"learning_rate": 0.001,
"loss": 0.1807,
"step": 1244
},
{
"epoch": 4.57,
"learning_rate": 0.001,
"loss": 0.191,
"step": 1246
},
{
"epoch": 4.58,
"learning_rate": 0.001,
"loss": 0.1993,
"step": 1248
},
{
"epoch": 4.58,
"learning_rate": 0.001,
"loss": 0.1949,
"step": 1250
},
{
"epoch": 4.59,
"learning_rate": 0.001,
"loss": 0.1812,
"step": 1252
},
{
"epoch": 4.6,
"learning_rate": 0.001,
"loss": 0.1946,
"step": 1254
},
{
"epoch": 4.6,
"learning_rate": 0.001,
"loss": 0.1852,
"step": 1256
},
{
"epoch": 4.61,
"learning_rate": 0.001,
"loss": 0.1835,
"step": 1258
},
{
"epoch": 4.62,
"learning_rate": 0.001,
"loss": 0.1912,
"step": 1260
},
{
"epoch": 4.63,
"learning_rate": 0.001,
"loss": 0.1823,
"step": 1262
},
{
"epoch": 4.63,
"learning_rate": 0.001,
"loss": 0.1811,
"step": 1264
},
{
"epoch": 4.64,
"learning_rate": 0.001,
"loss": 0.1811,
"step": 1266
},
{
"epoch": 4.65,
"learning_rate": 0.001,
"loss": 0.1988,
"step": 1268
},
{
"epoch": 4.66,
"learning_rate": 0.001,
"loss": 0.1858,
"step": 1270
},
{
"epoch": 4.66,
"learning_rate": 0.001,
"loss": 0.2041,
"step": 1272
},
{
"epoch": 4.67,
"learning_rate": 0.001,
"loss": 0.1874,
"step": 1274
},
{
"epoch": 4.68,
"learning_rate": 0.001,
"loss": 0.1994,
"step": 1276
},
{
"epoch": 4.69,
"learning_rate": 0.001,
"loss": 0.1956,
"step": 1278
},
{
"epoch": 4.69,
"learning_rate": 0.001,
"loss": 0.1976,
"step": 1280
},
{
"epoch": 4.7,
"learning_rate": 0.001,
"loss": 0.2042,
"step": 1282
},
{
"epoch": 4.71,
"learning_rate": 0.001,
"loss": 0.1852,
"step": 1284
},
{
"epoch": 4.71,
"learning_rate": 0.001,
"loss": 0.1864,
"step": 1286
},
{
"epoch": 4.72,
"learning_rate": 0.001,
"loss": 0.1945,
"step": 1288
},
{
"epoch": 4.73,
"learning_rate": 0.001,
"loss": 0.2045,
"step": 1290
},
{
"epoch": 4.74,
"learning_rate": 0.001,
"loss": 0.1939,
"step": 1292
},
{
"epoch": 4.74,
"learning_rate": 0.001,
"loss": 0.1858,
"step": 1294
},
{
"epoch": 4.75,
"learning_rate": 0.001,
"loss": 0.1842,
"step": 1296
},
{
"epoch": 4.76,
"learning_rate": 0.001,
"loss": 0.177,
"step": 1298
},
{
"epoch": 4.77,
"learning_rate": 0.001,
"loss": 0.1851,
"step": 1300
},
{
"epoch": 4.77,
"learning_rate": 0.001,
"loss": 0.186,
"step": 1302
},
{
"epoch": 4.78,
"learning_rate": 0.001,
"loss": 0.1881,
"step": 1304
},
{
"epoch": 4.79,
"learning_rate": 0.001,
"loss": 0.1925,
"step": 1306
},
{
"epoch": 4.8,
"learning_rate": 0.001,
"loss": 0.1965,
"step": 1308
},
{
"epoch": 4.8,
"learning_rate": 0.001,
"loss": 0.1902,
"step": 1310
},
{
"epoch": 4.81,
"learning_rate": 0.001,
"loss": 0.1818,
"step": 1312
},
{
"epoch": 4.82,
"learning_rate": 0.001,
"loss": 0.1968,
"step": 1314
},
{
"epoch": 4.82,
"learning_rate": 0.001,
"loss": 0.1894,
"step": 1316
},
{
"epoch": 4.83,
"learning_rate": 0.001,
"loss": 0.1948,
"step": 1318
},
{
"epoch": 4.84,
"learning_rate": 0.001,
"loss": 0.2014,
"step": 1320
},
{
"epoch": 4.85,
"learning_rate": 0.001,
"loss": 0.1881,
"step": 1322
},
{
"epoch": 4.85,
"learning_rate": 0.001,
"loss": 0.1859,
"step": 1324
},
{
"epoch": 4.86,
"learning_rate": 0.001,
"loss": 0.1987,
"step": 1326
},
{
"epoch": 4.87,
"learning_rate": 0.001,
"loss": 0.1808,
"step": 1328
},
{
"epoch": 4.88,
"learning_rate": 0.001,
"loss": 0.1878,
"step": 1330
},
{
"epoch": 4.88,
"learning_rate": 0.001,
"loss": 0.1767,
"step": 1332
},
{
"epoch": 4.89,
"learning_rate": 0.001,
"loss": 0.2004,
"step": 1334
},
{
"epoch": 4.9,
"learning_rate": 0.001,
"loss": 0.1925,
"step": 1336
},
{
"epoch": 4.91,
"learning_rate": 0.001,
"loss": 0.2075,
"step": 1338
},
{
"epoch": 4.91,
"learning_rate": 0.001,
"loss": 0.1884,
"step": 1340
},
{
"epoch": 4.92,
"learning_rate": 0.001,
"loss": 0.2032,
"step": 1342
},
{
"epoch": 4.93,
"learning_rate": 0.001,
"loss": 0.199,
"step": 1344
},
{
"epoch": 4.93,
"learning_rate": 0.001,
"loss": 0.1958,
"step": 1346
},
{
"epoch": 4.94,
"learning_rate": 0.001,
"loss": 0.1997,
"step": 1348
},
{
"epoch": 4.95,
"learning_rate": 0.001,
"loss": 0.2033,
"step": 1350
},
{
"epoch": 4.96,
"learning_rate": 0.001,
"loss": 0.1921,
"step": 1352
},
{
"epoch": 4.96,
"learning_rate": 0.001,
"loss": 0.2043,
"step": 1354
},
{
"epoch": 4.97,
"learning_rate": 0.001,
"loss": 0.1924,
"step": 1356
},
{
"epoch": 4.98,
"learning_rate": 0.001,
"loss": 0.1824,
"step": 1358
},
{
"epoch": 4.99,
"learning_rate": 0.001,
"loss": 0.2033,
"step": 1360
},
{
"epoch": 4.99,
"eval_gen_len": 1052.8816872427983,
"eval_loss": 1.550795316696167,
"eval_rouge1": 64.1251,
"eval_rouge2": 36.9601,
"eval_rougeL": 34.8068,
"eval_rougeLsum": 61.9673,
"eval_runtime": 8676.5547,
"eval_samples_per_second": 0.112,
"eval_steps_per_second": 0.014,
"step": 1360
},
{
"epoch": 4.99,
"step": 1360,
"total_flos": 1.024762577636008e+18,
"train_loss": 0.28696994373903556,
"train_runtime": 83467.5082,
"train_samples_per_second": 1.046,
"train_steps_per_second": 0.016
}
],
"logging_steps": 2,
"max_steps": 1360,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 1.024762577636008e+18,
"trial_name": null,
"trial_params": null
}