longt5_xl_gov_5 / trainer_state.json
learn3r's picture
End of training
1b92866
{
"best_metric": 1.4141343832015991,
"best_model_checkpoint": "/exports/eddie/scratch/s1970716/models/summarization/longt5_xl_gov_5/checkpoint-272",
"epoch": 4.9859655152660824,
"eval_steps": 500,
"global_step": 680,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.001,
"loss": 2.5533,
"step": 2
},
{
"epoch": 0.03,
"learning_rate": 0.001,
"loss": 3.3547,
"step": 4
},
{
"epoch": 0.04,
"learning_rate": 0.001,
"loss": 2.3004,
"step": 6
},
{
"epoch": 0.06,
"learning_rate": 0.001,
"loss": 1.8304,
"step": 8
},
{
"epoch": 0.07,
"learning_rate": 0.001,
"loss": 2.1026,
"step": 10
},
{
"epoch": 0.09,
"learning_rate": 0.001,
"loss": 2.2411,
"step": 12
},
{
"epoch": 0.1,
"learning_rate": 0.001,
"loss": 2.0959,
"step": 14
},
{
"epoch": 0.12,
"learning_rate": 0.001,
"loss": 1.8304,
"step": 16
},
{
"epoch": 0.13,
"learning_rate": 0.001,
"loss": 1.7896,
"step": 18
},
{
"epoch": 0.15,
"learning_rate": 0.001,
"loss": 1.7457,
"step": 20
},
{
"epoch": 0.16,
"learning_rate": 0.001,
"loss": 1.7814,
"step": 22
},
{
"epoch": 0.18,
"learning_rate": 0.001,
"loss": 1.7677,
"step": 24
},
{
"epoch": 0.19,
"learning_rate": 0.001,
"loss": 1.8154,
"step": 26
},
{
"epoch": 0.21,
"learning_rate": 0.001,
"loss": 1.7556,
"step": 28
},
{
"epoch": 0.22,
"learning_rate": 0.001,
"loss": 1.9631,
"step": 30
},
{
"epoch": 0.23,
"learning_rate": 0.001,
"loss": 2.0997,
"step": 32
},
{
"epoch": 0.25,
"learning_rate": 0.001,
"loss": 2.0355,
"step": 34
},
{
"epoch": 0.26,
"learning_rate": 0.001,
"loss": 2.1162,
"step": 36
},
{
"epoch": 0.28,
"learning_rate": 0.001,
"loss": 2.0213,
"step": 38
},
{
"epoch": 0.29,
"learning_rate": 0.001,
"loss": 1.9922,
"step": 40
},
{
"epoch": 0.31,
"learning_rate": 0.001,
"loss": 2.0452,
"step": 42
},
{
"epoch": 0.32,
"learning_rate": 0.001,
"loss": 1.961,
"step": 44
},
{
"epoch": 0.34,
"learning_rate": 0.001,
"loss": 1.8321,
"step": 46
},
{
"epoch": 0.35,
"learning_rate": 0.001,
"loss": 1.8563,
"step": 48
},
{
"epoch": 0.37,
"learning_rate": 0.001,
"loss": 2.2232,
"step": 50
},
{
"epoch": 0.38,
"learning_rate": 0.001,
"loss": 2.0869,
"step": 52
},
{
"epoch": 0.4,
"learning_rate": 0.001,
"loss": 2.3297,
"step": 54
},
{
"epoch": 0.41,
"learning_rate": 0.001,
"loss": 2.353,
"step": 56
},
{
"epoch": 0.43,
"learning_rate": 0.001,
"loss": 1.975,
"step": 58
},
{
"epoch": 0.44,
"learning_rate": 0.001,
"loss": 1.9746,
"step": 60
},
{
"epoch": 0.45,
"learning_rate": 0.001,
"loss": 1.703,
"step": 62
},
{
"epoch": 0.47,
"learning_rate": 0.001,
"loss": 1.8029,
"step": 64
},
{
"epoch": 0.48,
"learning_rate": 0.001,
"loss": 1.8786,
"step": 66
},
{
"epoch": 0.5,
"learning_rate": 0.001,
"loss": 1.8229,
"step": 68
},
{
"epoch": 0.51,
"learning_rate": 0.001,
"loss": 1.8989,
"step": 70
},
{
"epoch": 0.53,
"learning_rate": 0.001,
"loss": 1.7729,
"step": 72
},
{
"epoch": 0.54,
"learning_rate": 0.001,
"loss": 1.7334,
"step": 74
},
{
"epoch": 0.56,
"learning_rate": 0.001,
"loss": 1.9054,
"step": 76
},
{
"epoch": 0.57,
"learning_rate": 0.001,
"loss": 1.8183,
"step": 78
},
{
"epoch": 0.59,
"learning_rate": 0.001,
"loss": 1.7589,
"step": 80
},
{
"epoch": 0.6,
"learning_rate": 0.001,
"loss": 1.6687,
"step": 82
},
{
"epoch": 0.62,
"learning_rate": 0.001,
"loss": 1.681,
"step": 84
},
{
"epoch": 0.63,
"learning_rate": 0.001,
"loss": 1.6948,
"step": 86
},
{
"epoch": 0.65,
"learning_rate": 0.001,
"loss": 1.6912,
"step": 88
},
{
"epoch": 0.66,
"learning_rate": 0.001,
"loss": 1.6393,
"step": 90
},
{
"epoch": 0.67,
"learning_rate": 0.001,
"loss": 1.5826,
"step": 92
},
{
"epoch": 0.69,
"learning_rate": 0.001,
"loss": 1.6758,
"step": 94
},
{
"epoch": 0.7,
"learning_rate": 0.001,
"loss": 1.7602,
"step": 96
},
{
"epoch": 0.72,
"learning_rate": 0.001,
"loss": 1.6959,
"step": 98
},
{
"epoch": 0.73,
"learning_rate": 0.001,
"loss": 1.6268,
"step": 100
},
{
"epoch": 0.75,
"learning_rate": 0.001,
"loss": 1.7449,
"step": 102
},
{
"epoch": 0.76,
"learning_rate": 0.001,
"loss": 1.7258,
"step": 104
},
{
"epoch": 0.78,
"learning_rate": 0.001,
"loss": 1.7049,
"step": 106
},
{
"epoch": 0.79,
"learning_rate": 0.001,
"loss": 1.7017,
"step": 108
},
{
"epoch": 0.81,
"learning_rate": 0.001,
"loss": 1.6686,
"step": 110
},
{
"epoch": 0.82,
"learning_rate": 0.001,
"loss": 1.6871,
"step": 112
},
{
"epoch": 0.84,
"learning_rate": 0.001,
"loss": 1.666,
"step": 114
},
{
"epoch": 0.85,
"learning_rate": 0.001,
"loss": 1.6329,
"step": 116
},
{
"epoch": 0.87,
"learning_rate": 0.001,
"loss": 1.5889,
"step": 118
},
{
"epoch": 0.88,
"learning_rate": 0.001,
"loss": 1.6058,
"step": 120
},
{
"epoch": 0.89,
"learning_rate": 0.001,
"loss": 1.685,
"step": 122
},
{
"epoch": 0.91,
"learning_rate": 0.001,
"loss": 1.6222,
"step": 124
},
{
"epoch": 0.92,
"learning_rate": 0.001,
"loss": 1.5603,
"step": 126
},
{
"epoch": 0.94,
"learning_rate": 0.001,
"loss": 1.5587,
"step": 128
},
{
"epoch": 0.95,
"learning_rate": 0.001,
"loss": 1.6439,
"step": 130
},
{
"epoch": 0.97,
"learning_rate": 0.001,
"loss": 1.5574,
"step": 132
},
{
"epoch": 0.98,
"learning_rate": 0.001,
"loss": 1.5997,
"step": 134
},
{
"epoch": 1.0,
"learning_rate": 0.001,
"loss": 1.6209,
"step": 136
},
{
"epoch": 1.0,
"eval_gen_len": 904.1995884773662,
"eval_loss": 1.5433851480484009,
"eval_rouge1": 45.0062,
"eval_rouge2": 18.1618,
"eval_rougeL": 23.3808,
"eval_rougeLsum": 41.7616,
"eval_runtime": 9841.9339,
"eval_samples_per_second": 0.099,
"eval_steps_per_second": 0.012,
"step": 136
},
{
"epoch": 1.01,
"learning_rate": 0.001,
"loss": 1.5949,
"step": 138
},
{
"epoch": 1.03,
"learning_rate": 0.001,
"loss": 1.5982,
"step": 140
},
{
"epoch": 1.04,
"learning_rate": 0.001,
"loss": 1.4492,
"step": 142
},
{
"epoch": 1.06,
"learning_rate": 0.001,
"loss": 1.4375,
"step": 144
},
{
"epoch": 1.07,
"learning_rate": 0.001,
"loss": 1.4841,
"step": 146
},
{
"epoch": 1.09,
"learning_rate": 0.001,
"loss": 1.4383,
"step": 148
},
{
"epoch": 1.1,
"learning_rate": 0.001,
"loss": 1.5149,
"step": 150
},
{
"epoch": 1.11,
"learning_rate": 0.001,
"loss": 1.4563,
"step": 152
},
{
"epoch": 1.13,
"learning_rate": 0.001,
"loss": 1.494,
"step": 154
},
{
"epoch": 1.14,
"learning_rate": 0.001,
"loss": 1.4511,
"step": 156
},
{
"epoch": 1.16,
"learning_rate": 0.001,
"loss": 1.4888,
"step": 158
},
{
"epoch": 1.17,
"learning_rate": 0.001,
"loss": 1.4213,
"step": 160
},
{
"epoch": 1.19,
"learning_rate": 0.001,
"loss": 1.485,
"step": 162
},
{
"epoch": 1.2,
"learning_rate": 0.001,
"loss": 1.5013,
"step": 164
},
{
"epoch": 1.22,
"learning_rate": 0.001,
"loss": 1.477,
"step": 166
},
{
"epoch": 1.23,
"learning_rate": 0.001,
"loss": 1.4658,
"step": 168
},
{
"epoch": 1.25,
"learning_rate": 0.001,
"loss": 1.4408,
"step": 170
},
{
"epoch": 1.26,
"learning_rate": 0.001,
"loss": 1.472,
"step": 172
},
{
"epoch": 1.28,
"learning_rate": 0.001,
"loss": 1.4678,
"step": 174
},
{
"epoch": 1.29,
"learning_rate": 0.001,
"loss": 1.4211,
"step": 176
},
{
"epoch": 1.31,
"learning_rate": 0.001,
"loss": 1.4808,
"step": 178
},
{
"epoch": 1.32,
"learning_rate": 0.001,
"loss": 1.4623,
"step": 180
},
{
"epoch": 1.33,
"learning_rate": 0.001,
"loss": 1.4728,
"step": 182
},
{
"epoch": 1.35,
"learning_rate": 0.001,
"loss": 1.5118,
"step": 184
},
{
"epoch": 1.36,
"learning_rate": 0.001,
"loss": 1.5171,
"step": 186
},
{
"epoch": 1.38,
"learning_rate": 0.001,
"loss": 1.497,
"step": 188
},
{
"epoch": 1.39,
"learning_rate": 0.001,
"loss": 1.5148,
"step": 190
},
{
"epoch": 1.41,
"learning_rate": 0.001,
"loss": 1.5081,
"step": 192
},
{
"epoch": 1.42,
"learning_rate": 0.001,
"loss": 1.4425,
"step": 194
},
{
"epoch": 1.44,
"learning_rate": 0.001,
"loss": 1.4402,
"step": 196
},
{
"epoch": 1.45,
"learning_rate": 0.001,
"loss": 1.4361,
"step": 198
},
{
"epoch": 1.47,
"learning_rate": 0.001,
"loss": 1.4648,
"step": 200
},
{
"epoch": 1.48,
"learning_rate": 0.001,
"loss": 1.4701,
"step": 202
},
{
"epoch": 1.5,
"learning_rate": 0.001,
"loss": 1.4982,
"step": 204
},
{
"epoch": 1.51,
"learning_rate": 0.001,
"loss": 1.4692,
"step": 206
},
{
"epoch": 1.53,
"learning_rate": 0.001,
"loss": 1.4572,
"step": 208
},
{
"epoch": 1.54,
"learning_rate": 0.001,
"loss": 1.4563,
"step": 210
},
{
"epoch": 1.55,
"learning_rate": 0.001,
"loss": 1.4295,
"step": 212
},
{
"epoch": 1.57,
"learning_rate": 0.001,
"loss": 1.4421,
"step": 214
},
{
"epoch": 1.58,
"learning_rate": 0.001,
"loss": 1.4664,
"step": 216
},
{
"epoch": 1.6,
"learning_rate": 0.001,
"loss": 1.4408,
"step": 218
},
{
"epoch": 1.61,
"learning_rate": 0.001,
"loss": 1.4754,
"step": 220
},
{
"epoch": 1.63,
"learning_rate": 0.001,
"loss": 1.4685,
"step": 222
},
{
"epoch": 1.64,
"learning_rate": 0.001,
"loss": 1.4231,
"step": 224
},
{
"epoch": 1.66,
"learning_rate": 0.001,
"loss": 1.4786,
"step": 226
},
{
"epoch": 1.67,
"learning_rate": 0.001,
"loss": 1.4659,
"step": 228
},
{
"epoch": 1.69,
"learning_rate": 0.001,
"loss": 1.4834,
"step": 230
},
{
"epoch": 1.7,
"learning_rate": 0.001,
"loss": 1.4353,
"step": 232
},
{
"epoch": 1.72,
"learning_rate": 0.001,
"loss": 1.4318,
"step": 234
},
{
"epoch": 1.73,
"learning_rate": 0.001,
"loss": 1.4646,
"step": 236
},
{
"epoch": 1.75,
"learning_rate": 0.001,
"loss": 1.4728,
"step": 238
},
{
"epoch": 1.76,
"learning_rate": 0.001,
"loss": 1.4466,
"step": 240
},
{
"epoch": 1.77,
"learning_rate": 0.001,
"loss": 1.4871,
"step": 242
},
{
"epoch": 1.79,
"learning_rate": 0.001,
"loss": 1.4811,
"step": 244
},
{
"epoch": 1.8,
"learning_rate": 0.001,
"loss": 1.4979,
"step": 246
},
{
"epoch": 1.82,
"learning_rate": 0.001,
"loss": 1.4995,
"step": 248
},
{
"epoch": 1.83,
"learning_rate": 0.001,
"loss": 1.4496,
"step": 250
},
{
"epoch": 1.85,
"learning_rate": 0.001,
"loss": 1.4225,
"step": 252
},
{
"epoch": 1.86,
"learning_rate": 0.001,
"loss": 1.4784,
"step": 254
},
{
"epoch": 1.88,
"learning_rate": 0.001,
"loss": 1.4591,
"step": 256
},
{
"epoch": 1.89,
"learning_rate": 0.001,
"loss": 1.4277,
"step": 258
},
{
"epoch": 1.91,
"learning_rate": 0.001,
"loss": 1.4555,
"step": 260
},
{
"epoch": 1.92,
"learning_rate": 0.001,
"loss": 1.4385,
"step": 262
},
{
"epoch": 1.94,
"learning_rate": 0.001,
"loss": 1.4104,
"step": 264
},
{
"epoch": 1.95,
"learning_rate": 0.001,
"loss": 1.5014,
"step": 266
},
{
"epoch": 1.97,
"learning_rate": 0.001,
"loss": 1.4236,
"step": 268
},
{
"epoch": 1.98,
"learning_rate": 0.001,
"loss": 1.4521,
"step": 270
},
{
"epoch": 1.99,
"learning_rate": 0.001,
"loss": 1.418,
"step": 272
},
{
"epoch": 1.99,
"eval_gen_len": 889.25,
"eval_loss": 1.4141343832015991,
"eval_rouge1": 54.2522,
"eval_rouge2": 24.7528,
"eval_rougeL": 27.2444,
"eval_rougeLsum": 51.5916,
"eval_runtime": 9838.997,
"eval_samples_per_second": 0.099,
"eval_steps_per_second": 0.012,
"step": 272
},
{
"epoch": 2.01,
"learning_rate": 0.001,
"loss": 1.3789,
"step": 274
},
{
"epoch": 2.02,
"learning_rate": 0.001,
"loss": 1.2312,
"step": 276
},
{
"epoch": 2.04,
"learning_rate": 0.001,
"loss": 1.2565,
"step": 278
},
{
"epoch": 2.05,
"learning_rate": 0.001,
"loss": 1.277,
"step": 280
},
{
"epoch": 2.07,
"learning_rate": 0.001,
"loss": 1.2787,
"step": 282
},
{
"epoch": 2.08,
"learning_rate": 0.001,
"loss": 1.2645,
"step": 284
},
{
"epoch": 2.1,
"learning_rate": 0.001,
"loss": 1.2606,
"step": 286
},
{
"epoch": 2.11,
"learning_rate": 0.001,
"loss": 1.2462,
"step": 288
},
{
"epoch": 2.13,
"learning_rate": 0.001,
"loss": 1.2102,
"step": 290
},
{
"epoch": 2.14,
"learning_rate": 0.001,
"loss": 1.2467,
"step": 292
},
{
"epoch": 2.16,
"learning_rate": 0.001,
"loss": 1.2972,
"step": 294
},
{
"epoch": 2.17,
"learning_rate": 0.001,
"loss": 1.2813,
"step": 296
},
{
"epoch": 2.19,
"learning_rate": 0.001,
"loss": 1.241,
"step": 298
},
{
"epoch": 2.2,
"learning_rate": 0.001,
"loss": 1.2556,
"step": 300
},
{
"epoch": 2.21,
"learning_rate": 0.001,
"loss": 1.2738,
"step": 302
},
{
"epoch": 2.23,
"learning_rate": 0.001,
"loss": 1.2544,
"step": 304
},
{
"epoch": 2.24,
"learning_rate": 0.001,
"loss": 1.2378,
"step": 306
},
{
"epoch": 2.26,
"learning_rate": 0.001,
"loss": 1.2346,
"step": 308
},
{
"epoch": 2.27,
"learning_rate": 0.001,
"loss": 1.2624,
"step": 310
},
{
"epoch": 2.29,
"learning_rate": 0.001,
"loss": 1.2173,
"step": 312
},
{
"epoch": 2.3,
"learning_rate": 0.001,
"loss": 1.2658,
"step": 314
},
{
"epoch": 2.32,
"learning_rate": 0.001,
"loss": 1.2828,
"step": 316
},
{
"epoch": 2.33,
"learning_rate": 0.001,
"loss": 1.2518,
"step": 318
},
{
"epoch": 2.35,
"learning_rate": 0.001,
"loss": 1.268,
"step": 320
},
{
"epoch": 2.36,
"learning_rate": 0.001,
"loss": 1.2691,
"step": 322
},
{
"epoch": 2.38,
"learning_rate": 0.001,
"loss": 1.263,
"step": 324
},
{
"epoch": 2.39,
"learning_rate": 0.001,
"loss": 1.2906,
"step": 326
},
{
"epoch": 2.4,
"learning_rate": 0.001,
"loss": 1.2462,
"step": 328
},
{
"epoch": 2.42,
"learning_rate": 0.001,
"loss": 1.2403,
"step": 330
},
{
"epoch": 2.43,
"learning_rate": 0.001,
"loss": 1.2701,
"step": 332
},
{
"epoch": 2.45,
"learning_rate": 0.001,
"loss": 1.2649,
"step": 334
},
{
"epoch": 2.46,
"learning_rate": 0.001,
"loss": 1.2267,
"step": 336
},
{
"epoch": 2.48,
"learning_rate": 0.001,
"loss": 1.2812,
"step": 338
},
{
"epoch": 2.49,
"learning_rate": 0.001,
"loss": 1.2561,
"step": 340
},
{
"epoch": 2.51,
"learning_rate": 0.001,
"loss": 1.2614,
"step": 342
},
{
"epoch": 2.52,
"learning_rate": 0.001,
"loss": 1.2928,
"step": 344
},
{
"epoch": 2.54,
"learning_rate": 0.001,
"loss": 1.2464,
"step": 346
},
{
"epoch": 2.55,
"learning_rate": 0.001,
"loss": 1.2291,
"step": 348
},
{
"epoch": 2.57,
"learning_rate": 0.001,
"loss": 1.2535,
"step": 350
},
{
"epoch": 2.58,
"learning_rate": 0.001,
"loss": 1.2453,
"step": 352
},
{
"epoch": 2.6,
"learning_rate": 0.001,
"loss": 1.2154,
"step": 354
},
{
"epoch": 2.61,
"learning_rate": 0.001,
"loss": 1.3274,
"step": 356
},
{
"epoch": 2.62,
"learning_rate": 0.001,
"loss": 1.2851,
"step": 358
},
{
"epoch": 2.64,
"learning_rate": 0.001,
"loss": 1.253,
"step": 360
},
{
"epoch": 2.65,
"learning_rate": 0.001,
"loss": 1.2939,
"step": 362
},
{
"epoch": 2.67,
"learning_rate": 0.001,
"loss": 1.2554,
"step": 364
},
{
"epoch": 2.68,
"learning_rate": 0.001,
"loss": 1.2893,
"step": 366
},
{
"epoch": 2.7,
"learning_rate": 0.001,
"loss": 1.2668,
"step": 368
},
{
"epoch": 2.71,
"learning_rate": 0.001,
"loss": 1.2619,
"step": 370
},
{
"epoch": 2.73,
"learning_rate": 0.001,
"loss": 1.2303,
"step": 372
},
{
"epoch": 2.74,
"learning_rate": 0.001,
"loss": 1.2802,
"step": 374
},
{
"epoch": 2.76,
"learning_rate": 0.001,
"loss": 1.2482,
"step": 376
},
{
"epoch": 2.77,
"learning_rate": 0.001,
"loss": 1.2512,
"step": 378
},
{
"epoch": 2.79,
"learning_rate": 0.001,
"loss": 1.3013,
"step": 380
},
{
"epoch": 2.8,
"learning_rate": 0.001,
"loss": 1.2722,
"step": 382
},
{
"epoch": 2.82,
"learning_rate": 0.001,
"loss": 1.2711,
"step": 384
},
{
"epoch": 2.83,
"learning_rate": 0.001,
"loss": 1.2437,
"step": 386
},
{
"epoch": 2.84,
"learning_rate": 0.001,
"loss": 1.2389,
"step": 388
},
{
"epoch": 2.86,
"learning_rate": 0.001,
"loss": 1.2792,
"step": 390
},
{
"epoch": 2.87,
"learning_rate": 0.001,
"loss": 1.3103,
"step": 392
},
{
"epoch": 2.89,
"learning_rate": 0.001,
"loss": 1.3027,
"step": 394
},
{
"epoch": 2.9,
"learning_rate": 0.001,
"loss": 1.2437,
"step": 396
},
{
"epoch": 2.92,
"learning_rate": 0.001,
"loss": 1.2682,
"step": 398
},
{
"epoch": 2.93,
"learning_rate": 0.001,
"loss": 1.2591,
"step": 400
},
{
"epoch": 2.95,
"learning_rate": 0.001,
"loss": 1.2806,
"step": 402
},
{
"epoch": 2.96,
"learning_rate": 0.001,
"loss": 1.2288,
"step": 404
},
{
"epoch": 2.98,
"learning_rate": 0.001,
"loss": 1.2457,
"step": 406
},
{
"epoch": 2.99,
"learning_rate": 0.001,
"loss": 1.2626,
"step": 408
},
{
"epoch": 3.0,
"eval_gen_len": 878.4094650205761,
"eval_loss": 1.4249345064163208,
"eval_rouge1": 52.4332,
"eval_rouge2": 23.708,
"eval_rougeL": 27.2902,
"eval_rougeLsum": 49.8071,
"eval_runtime": 9854.5185,
"eval_samples_per_second": 0.099,
"eval_steps_per_second": 0.012,
"step": 409
},
{
"epoch": 3.01,
"learning_rate": 0.001,
"loss": 1.1762,
"step": 410
},
{
"epoch": 3.02,
"learning_rate": 0.001,
"loss": 1.1034,
"step": 412
},
{
"epoch": 3.04,
"learning_rate": 0.001,
"loss": 1.0806,
"step": 414
},
{
"epoch": 3.05,
"learning_rate": 0.001,
"loss": 1.0266,
"step": 416
},
{
"epoch": 3.06,
"learning_rate": 0.001,
"loss": 1.0486,
"step": 418
},
{
"epoch": 3.08,
"learning_rate": 0.001,
"loss": 1.0534,
"step": 420
},
{
"epoch": 3.09,
"learning_rate": 0.001,
"loss": 1.0261,
"step": 422
},
{
"epoch": 3.11,
"learning_rate": 0.001,
"loss": 1.0433,
"step": 424
},
{
"epoch": 3.12,
"learning_rate": 0.001,
"loss": 1.0878,
"step": 426
},
{
"epoch": 3.14,
"learning_rate": 0.001,
"loss": 1.0971,
"step": 428
},
{
"epoch": 3.15,
"learning_rate": 0.001,
"loss": 1.0331,
"step": 430
},
{
"epoch": 3.17,
"learning_rate": 0.001,
"loss": 1.0837,
"step": 432
},
{
"epoch": 3.18,
"learning_rate": 0.001,
"loss": 1.0788,
"step": 434
},
{
"epoch": 3.2,
"learning_rate": 0.001,
"loss": 1.0536,
"step": 436
},
{
"epoch": 3.21,
"learning_rate": 0.001,
"loss": 1.0676,
"step": 438
},
{
"epoch": 3.23,
"learning_rate": 0.001,
"loss": 1.0809,
"step": 440
},
{
"epoch": 3.24,
"learning_rate": 0.001,
"loss": 1.0762,
"step": 442
},
{
"epoch": 3.26,
"learning_rate": 0.001,
"loss": 1.0679,
"step": 444
},
{
"epoch": 3.27,
"learning_rate": 0.001,
"loss": 1.0514,
"step": 446
},
{
"epoch": 3.28,
"learning_rate": 0.001,
"loss": 1.1013,
"step": 448
},
{
"epoch": 3.3,
"learning_rate": 0.001,
"loss": 1.0957,
"step": 450
},
{
"epoch": 3.31,
"learning_rate": 0.001,
"loss": 1.0706,
"step": 452
},
{
"epoch": 3.33,
"learning_rate": 0.001,
"loss": 1.0755,
"step": 454
},
{
"epoch": 3.34,
"learning_rate": 0.001,
"loss": 1.0774,
"step": 456
},
{
"epoch": 3.36,
"learning_rate": 0.001,
"loss": 1.0796,
"step": 458
},
{
"epoch": 3.37,
"learning_rate": 0.001,
"loss": 1.0908,
"step": 460
},
{
"epoch": 3.39,
"learning_rate": 0.001,
"loss": 1.1043,
"step": 462
},
{
"epoch": 3.4,
"learning_rate": 0.001,
"loss": 1.0982,
"step": 464
},
{
"epoch": 3.42,
"learning_rate": 0.001,
"loss": 1.0942,
"step": 466
},
{
"epoch": 3.43,
"learning_rate": 0.001,
"loss": 1.0975,
"step": 468
},
{
"epoch": 3.45,
"learning_rate": 0.001,
"loss": 1.0786,
"step": 470
},
{
"epoch": 3.46,
"learning_rate": 0.001,
"loss": 1.1133,
"step": 472
},
{
"epoch": 3.48,
"learning_rate": 0.001,
"loss": 1.0705,
"step": 474
},
{
"epoch": 3.49,
"learning_rate": 0.001,
"loss": 1.1205,
"step": 476
},
{
"epoch": 3.5,
"learning_rate": 0.001,
"loss": 1.117,
"step": 478
},
{
"epoch": 3.52,
"learning_rate": 0.001,
"loss": 1.1035,
"step": 480
},
{
"epoch": 3.53,
"learning_rate": 0.001,
"loss": 1.0684,
"step": 482
},
{
"epoch": 3.55,
"learning_rate": 0.001,
"loss": 1.0812,
"step": 484
},
{
"epoch": 3.56,
"learning_rate": 0.001,
"loss": 1.0383,
"step": 486
},
{
"epoch": 3.58,
"learning_rate": 0.001,
"loss": 1.1239,
"step": 488
},
{
"epoch": 3.59,
"learning_rate": 0.001,
"loss": 1.1189,
"step": 490
},
{
"epoch": 3.61,
"learning_rate": 0.001,
"loss": 1.0958,
"step": 492
},
{
"epoch": 3.62,
"learning_rate": 0.001,
"loss": 1.0997,
"step": 494
},
{
"epoch": 3.64,
"learning_rate": 0.001,
"loss": 1.1264,
"step": 496
},
{
"epoch": 3.65,
"learning_rate": 0.001,
"loss": 1.1033,
"step": 498
},
{
"epoch": 3.67,
"learning_rate": 0.001,
"loss": 1.0644,
"step": 500
},
{
"epoch": 3.68,
"learning_rate": 0.001,
"loss": 1.0705,
"step": 502
},
{
"epoch": 3.7,
"learning_rate": 0.001,
"loss": 1.0929,
"step": 504
},
{
"epoch": 3.71,
"learning_rate": 0.001,
"loss": 1.0478,
"step": 506
},
{
"epoch": 3.72,
"learning_rate": 0.001,
"loss": 1.1277,
"step": 508
},
{
"epoch": 3.74,
"learning_rate": 0.001,
"loss": 1.0987,
"step": 510
},
{
"epoch": 3.75,
"learning_rate": 0.001,
"loss": 1.105,
"step": 512
},
{
"epoch": 3.77,
"learning_rate": 0.001,
"loss": 1.1306,
"step": 514
},
{
"epoch": 3.78,
"learning_rate": 0.001,
"loss": 1.1151,
"step": 516
},
{
"epoch": 3.8,
"learning_rate": 0.001,
"loss": 1.1238,
"step": 518
},
{
"epoch": 3.81,
"learning_rate": 0.001,
"loss": 1.1157,
"step": 520
},
{
"epoch": 3.83,
"learning_rate": 0.001,
"loss": 1.1197,
"step": 522
},
{
"epoch": 3.84,
"learning_rate": 0.001,
"loss": 1.095,
"step": 524
},
{
"epoch": 3.86,
"learning_rate": 0.001,
"loss": 1.1052,
"step": 526
},
{
"epoch": 3.87,
"learning_rate": 0.001,
"loss": 1.1495,
"step": 528
},
{
"epoch": 3.89,
"learning_rate": 0.001,
"loss": 1.1081,
"step": 530
},
{
"epoch": 3.9,
"learning_rate": 0.001,
"loss": 1.1378,
"step": 532
},
{
"epoch": 3.92,
"learning_rate": 0.001,
"loss": 1.0769,
"step": 534
},
{
"epoch": 3.93,
"learning_rate": 0.001,
"loss": 1.1236,
"step": 536
},
{
"epoch": 3.94,
"learning_rate": 0.001,
"loss": 1.0993,
"step": 538
},
{
"epoch": 3.96,
"learning_rate": 0.001,
"loss": 1.0958,
"step": 540
},
{
"epoch": 3.97,
"learning_rate": 0.001,
"loss": 1.1507,
"step": 542
},
{
"epoch": 3.99,
"learning_rate": 0.001,
"loss": 1.0992,
"step": 544
},
{
"epoch": 4.0,
"eval_gen_len": 670.7047325102881,
"eval_loss": 1.4211255311965942,
"eval_rouge1": 55.2041,
"eval_rouge2": 26.5229,
"eval_rougeL": 29.9951,
"eval_rougeLsum": 52.6487,
"eval_runtime": 9282.99,
"eval_samples_per_second": 0.105,
"eval_steps_per_second": 0.013,
"step": 545
},
{
"epoch": 4.0,
"learning_rate": 0.001,
"loss": 1.0866,
"step": 546
},
{
"epoch": 4.02,
"learning_rate": 0.001,
"loss": 0.8617,
"step": 548
},
{
"epoch": 4.03,
"learning_rate": 0.001,
"loss": 0.878,
"step": 550
},
{
"epoch": 4.05,
"learning_rate": 0.001,
"loss": 0.8617,
"step": 552
},
{
"epoch": 4.06,
"learning_rate": 0.001,
"loss": 0.9181,
"step": 554
},
{
"epoch": 4.08,
"learning_rate": 0.001,
"loss": 0.9142,
"step": 556
},
{
"epoch": 4.09,
"learning_rate": 0.001,
"loss": 0.8928,
"step": 558
},
{
"epoch": 4.11,
"learning_rate": 0.001,
"loss": 0.9007,
"step": 560
},
{
"epoch": 4.12,
"learning_rate": 0.001,
"loss": 0.9425,
"step": 562
},
{
"epoch": 4.14,
"learning_rate": 0.001,
"loss": 0.9297,
"step": 564
},
{
"epoch": 4.15,
"learning_rate": 0.001,
"loss": 0.9367,
"step": 566
},
{
"epoch": 4.16,
"learning_rate": 0.001,
"loss": 0.9289,
"step": 568
},
{
"epoch": 4.18,
"learning_rate": 0.001,
"loss": 0.9027,
"step": 570
},
{
"epoch": 4.19,
"learning_rate": 0.001,
"loss": 0.9263,
"step": 572
},
{
"epoch": 4.21,
"learning_rate": 0.001,
"loss": 0.9208,
"step": 574
},
{
"epoch": 4.22,
"learning_rate": 0.001,
"loss": 0.8909,
"step": 576
},
{
"epoch": 4.24,
"learning_rate": 0.001,
"loss": 0.9407,
"step": 578
},
{
"epoch": 4.25,
"learning_rate": 0.001,
"loss": 0.9139,
"step": 580
},
{
"epoch": 4.27,
"learning_rate": 0.001,
"loss": 0.9096,
"step": 582
},
{
"epoch": 4.28,
"learning_rate": 0.001,
"loss": 0.9509,
"step": 584
},
{
"epoch": 4.3,
"learning_rate": 0.001,
"loss": 0.9396,
"step": 586
},
{
"epoch": 4.31,
"learning_rate": 0.001,
"loss": 0.9573,
"step": 588
},
{
"epoch": 4.33,
"learning_rate": 0.001,
"loss": 0.9431,
"step": 590
},
{
"epoch": 4.34,
"learning_rate": 0.001,
"loss": 0.9372,
"step": 592
},
{
"epoch": 4.36,
"learning_rate": 0.001,
"loss": 0.9375,
"step": 594
},
{
"epoch": 4.37,
"learning_rate": 0.001,
"loss": 0.9088,
"step": 596
},
{
"epoch": 4.38,
"learning_rate": 0.001,
"loss": 0.9325,
"step": 598
},
{
"epoch": 4.4,
"learning_rate": 0.001,
"loss": 0.9175,
"step": 600
},
{
"epoch": 4.41,
"learning_rate": 0.001,
"loss": 0.9467,
"step": 602
},
{
"epoch": 4.43,
"learning_rate": 0.001,
"loss": 0.9325,
"step": 604
},
{
"epoch": 4.44,
"learning_rate": 0.001,
"loss": 0.9501,
"step": 606
},
{
"epoch": 4.46,
"learning_rate": 0.001,
"loss": 0.9185,
"step": 608
},
{
"epoch": 4.47,
"learning_rate": 0.001,
"loss": 0.9673,
"step": 610
},
{
"epoch": 4.49,
"learning_rate": 0.001,
"loss": 0.9608,
"step": 612
},
{
"epoch": 4.5,
"learning_rate": 0.001,
"loss": 0.9238,
"step": 614
},
{
"epoch": 4.52,
"learning_rate": 0.001,
"loss": 0.9645,
"step": 616
},
{
"epoch": 4.53,
"learning_rate": 0.001,
"loss": 0.9575,
"step": 618
},
{
"epoch": 4.55,
"learning_rate": 0.001,
"loss": 0.9876,
"step": 620
},
{
"epoch": 4.56,
"learning_rate": 0.001,
"loss": 0.9601,
"step": 622
},
{
"epoch": 4.58,
"learning_rate": 0.001,
"loss": 0.9555,
"step": 624
},
{
"epoch": 4.59,
"learning_rate": 0.001,
"loss": 0.9603,
"step": 626
},
{
"epoch": 4.6,
"learning_rate": 0.001,
"loss": 0.9442,
"step": 628
},
{
"epoch": 4.62,
"learning_rate": 0.001,
"loss": 0.9681,
"step": 630
},
{
"epoch": 4.63,
"learning_rate": 0.001,
"loss": 0.9681,
"step": 632
},
{
"epoch": 4.65,
"learning_rate": 0.001,
"loss": 1.0074,
"step": 634
},
{
"epoch": 4.66,
"learning_rate": 0.001,
"loss": 0.9949,
"step": 636
},
{
"epoch": 4.68,
"learning_rate": 0.001,
"loss": 0.9764,
"step": 638
},
{
"epoch": 4.69,
"learning_rate": 0.001,
"loss": 0.9612,
"step": 640
},
{
"epoch": 4.71,
"learning_rate": 0.001,
"loss": 0.9607,
"step": 642
},
{
"epoch": 4.72,
"learning_rate": 0.001,
"loss": 0.9954,
"step": 644
},
{
"epoch": 4.74,
"learning_rate": 0.001,
"loss": 1.0018,
"step": 646
},
{
"epoch": 4.75,
"learning_rate": 0.001,
"loss": 0.9353,
"step": 648
},
{
"epoch": 4.77,
"learning_rate": 0.001,
"loss": 0.9209,
"step": 650
},
{
"epoch": 4.78,
"learning_rate": 0.001,
"loss": 0.9726,
"step": 652
},
{
"epoch": 4.8,
"learning_rate": 0.001,
"loss": 0.9745,
"step": 654
},
{
"epoch": 4.81,
"learning_rate": 0.001,
"loss": 0.9479,
"step": 656
},
{
"epoch": 4.82,
"learning_rate": 0.001,
"loss": 0.9508,
"step": 658
},
{
"epoch": 4.84,
"learning_rate": 0.001,
"loss": 0.9887,
"step": 660
},
{
"epoch": 4.85,
"learning_rate": 0.001,
"loss": 0.9553,
"step": 662
},
{
"epoch": 4.87,
"learning_rate": 0.001,
"loss": 0.9733,
"step": 664
},
{
"epoch": 4.88,
"learning_rate": 0.001,
"loss": 0.9416,
"step": 666
},
{
"epoch": 4.9,
"learning_rate": 0.001,
"loss": 0.9705,
"step": 668
},
{
"epoch": 4.91,
"learning_rate": 0.001,
"loss": 0.9931,
"step": 670
},
{
"epoch": 4.93,
"learning_rate": 0.001,
"loss": 1.0008,
"step": 672
},
{
"epoch": 4.94,
"learning_rate": 0.001,
"loss": 0.9638,
"step": 674
},
{
"epoch": 4.96,
"learning_rate": 0.001,
"loss": 0.995,
"step": 676
},
{
"epoch": 4.97,
"learning_rate": 0.001,
"loss": 0.9863,
"step": 678
},
{
"epoch": 4.99,
"learning_rate": 0.001,
"loss": 0.9974,
"step": 680
},
{
"epoch": 4.99,
"eval_gen_len": 883.0462962962963,
"eval_loss": 1.45689058303833,
"eval_rouge1": 55.9961,
"eval_rouge2": 26.2205,
"eval_rougeL": 29.0409,
"eval_rougeLsum": 53.3109,
"eval_runtime": 9845.6326,
"eval_samples_per_second": 0.099,
"eval_steps_per_second": 0.012,
"step": 680
},
{
"epoch": 4.99,
"step": 680,
"total_flos": 5.765052082333483e+18,
"train_loss": 1.3253671477822697,
"train_runtime": 159961.9679,
"train_samples_per_second": 0.546,
"train_steps_per_second": 0.004
}
],
"logging_steps": 2,
"max_steps": 680,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 5.765052082333483e+18,
"trial_name": null,
"trial_params": null
}