learn3r's picture
End of training
21a0014
{
"best_metric": 1.2379964590072632,
"best_model_checkpoint": "/home/co-ou1/rds/hpc-work/models/longt5_xl_govreport_memsum_4096/longt5_xl_govreport_4096_memsum_e10/checkpoint-136",
"epoch": 9.967934035730647,
"eval_steps": 500,
"global_step": 680,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 0.001,
"loss": 1.9479,
"step": 2
},
{
"epoch": 0.06,
"learning_rate": 0.001,
"loss": 1.8801,
"step": 4
},
{
"epoch": 0.09,
"learning_rate": 0.001,
"loss": 1.9402,
"step": 6
},
{
"epoch": 0.12,
"learning_rate": 0.001,
"loss": 2.1078,
"step": 8
},
{
"epoch": 0.15,
"learning_rate": 0.001,
"loss": 1.8636,
"step": 10
},
{
"epoch": 0.18,
"learning_rate": 0.001,
"loss": 1.8213,
"step": 12
},
{
"epoch": 0.21,
"learning_rate": 0.001,
"loss": 1.7018,
"step": 14
},
{
"epoch": 0.23,
"learning_rate": 0.001,
"loss": 1.6419,
"step": 16
},
{
"epoch": 0.26,
"learning_rate": 0.001,
"loss": 1.7423,
"step": 18
},
{
"epoch": 0.29,
"learning_rate": 0.001,
"loss": 1.6169,
"step": 20
},
{
"epoch": 0.32,
"learning_rate": 0.001,
"loss": 1.5792,
"step": 22
},
{
"epoch": 0.35,
"learning_rate": 0.001,
"loss": 1.5335,
"step": 24
},
{
"epoch": 0.38,
"learning_rate": 0.001,
"loss": 1.5094,
"step": 26
},
{
"epoch": 0.41,
"learning_rate": 0.001,
"loss": 1.5508,
"step": 28
},
{
"epoch": 0.44,
"learning_rate": 0.001,
"loss": 1.5831,
"step": 30
},
{
"epoch": 0.47,
"learning_rate": 0.001,
"loss": 1.5058,
"step": 32
},
{
"epoch": 0.5,
"learning_rate": 0.001,
"loss": 1.4895,
"step": 34
},
{
"epoch": 0.53,
"learning_rate": 0.001,
"loss": 1.4856,
"step": 36
},
{
"epoch": 0.56,
"learning_rate": 0.001,
"loss": 1.4648,
"step": 38
},
{
"epoch": 0.59,
"learning_rate": 0.001,
"loss": 1.4736,
"step": 40
},
{
"epoch": 0.62,
"learning_rate": 0.001,
"loss": 1.5697,
"step": 42
},
{
"epoch": 0.64,
"learning_rate": 0.001,
"loss": 1.485,
"step": 44
},
{
"epoch": 0.67,
"learning_rate": 0.001,
"loss": 1.5146,
"step": 46
},
{
"epoch": 0.7,
"learning_rate": 0.001,
"loss": 1.5171,
"step": 48
},
{
"epoch": 0.73,
"learning_rate": 0.001,
"loss": 1.5701,
"step": 50
},
{
"epoch": 0.76,
"learning_rate": 0.001,
"loss": 1.5421,
"step": 52
},
{
"epoch": 0.79,
"learning_rate": 0.001,
"loss": 1.483,
"step": 54
},
{
"epoch": 0.82,
"learning_rate": 0.001,
"loss": 1.4603,
"step": 56
},
{
"epoch": 0.85,
"learning_rate": 0.001,
"loss": 1.4263,
"step": 58
},
{
"epoch": 0.88,
"learning_rate": 0.001,
"loss": 1.4241,
"step": 60
},
{
"epoch": 0.91,
"learning_rate": 0.001,
"loss": 1.486,
"step": 62
},
{
"epoch": 0.94,
"learning_rate": 0.001,
"loss": 1.4382,
"step": 64
},
{
"epoch": 0.97,
"learning_rate": 0.001,
"loss": 1.49,
"step": 66
},
{
"epoch": 1.0,
"learning_rate": 0.001,
"loss": 1.4775,
"step": 68
},
{
"epoch": 1.0,
"eval_loss": 1.271297812461853,
"eval_runtime": 153.4507,
"eval_samples_per_second": 6.334,
"eval_steps_per_second": 0.795,
"step": 68
},
{
"epoch": 1.03,
"learning_rate": 0.001,
"loss": 1.4238,
"step": 70
},
{
"epoch": 1.06,
"learning_rate": 0.001,
"loss": 1.3785,
"step": 72
},
{
"epoch": 1.08,
"learning_rate": 0.001,
"loss": 1.3935,
"step": 74
},
{
"epoch": 1.11,
"learning_rate": 0.001,
"loss": 1.378,
"step": 76
},
{
"epoch": 1.14,
"learning_rate": 0.001,
"loss": 1.3352,
"step": 78
},
{
"epoch": 1.17,
"learning_rate": 0.001,
"loss": 1.3528,
"step": 80
},
{
"epoch": 1.2,
"learning_rate": 0.001,
"loss": 1.3692,
"step": 82
},
{
"epoch": 1.23,
"learning_rate": 0.001,
"loss": 1.3507,
"step": 84
},
{
"epoch": 1.26,
"learning_rate": 0.001,
"loss": 1.3181,
"step": 86
},
{
"epoch": 1.29,
"learning_rate": 0.001,
"loss": 1.3247,
"step": 88
},
{
"epoch": 1.32,
"learning_rate": 0.001,
"loss": 1.3432,
"step": 90
},
{
"epoch": 1.35,
"learning_rate": 0.001,
"loss": 1.3365,
"step": 92
},
{
"epoch": 1.38,
"learning_rate": 0.001,
"loss": 1.3728,
"step": 94
},
{
"epoch": 1.41,
"learning_rate": 0.001,
"loss": 1.3642,
"step": 96
},
{
"epoch": 1.44,
"learning_rate": 0.001,
"loss": 1.3179,
"step": 98
},
{
"epoch": 1.47,
"learning_rate": 0.001,
"loss": 1.313,
"step": 100
},
{
"epoch": 1.5,
"learning_rate": 0.001,
"loss": 1.3392,
"step": 102
},
{
"epoch": 1.52,
"learning_rate": 0.001,
"loss": 1.3346,
"step": 104
},
{
"epoch": 1.55,
"learning_rate": 0.001,
"loss": 1.3572,
"step": 106
},
{
"epoch": 1.58,
"learning_rate": 0.001,
"loss": 1.3391,
"step": 108
},
{
"epoch": 1.61,
"learning_rate": 0.001,
"loss": 1.3429,
"step": 110
},
{
"epoch": 1.64,
"learning_rate": 0.001,
"loss": 1.3276,
"step": 112
},
{
"epoch": 1.67,
"learning_rate": 0.001,
"loss": 1.3346,
"step": 114
},
{
"epoch": 1.7,
"learning_rate": 0.001,
"loss": 1.3235,
"step": 116
},
{
"epoch": 1.73,
"learning_rate": 0.001,
"loss": 1.3446,
"step": 118
},
{
"epoch": 1.76,
"learning_rate": 0.001,
"loss": 1.3429,
"step": 120
},
{
"epoch": 1.79,
"learning_rate": 0.001,
"loss": 1.3465,
"step": 122
},
{
"epoch": 1.82,
"learning_rate": 0.001,
"loss": 1.3436,
"step": 124
},
{
"epoch": 1.85,
"learning_rate": 0.001,
"loss": 1.316,
"step": 126
},
{
"epoch": 1.88,
"learning_rate": 0.001,
"loss": 1.3354,
"step": 128
},
{
"epoch": 1.91,
"learning_rate": 0.001,
"loss": 1.3252,
"step": 130
},
{
"epoch": 1.93,
"learning_rate": 0.001,
"loss": 1.2983,
"step": 132
},
{
"epoch": 1.96,
"learning_rate": 0.001,
"loss": 1.3305,
"step": 134
},
{
"epoch": 1.99,
"learning_rate": 0.001,
"loss": 1.3081,
"step": 136
},
{
"epoch": 1.99,
"eval_loss": 1.2379964590072632,
"eval_runtime": 153.5844,
"eval_samples_per_second": 6.329,
"eval_steps_per_second": 0.794,
"step": 136
},
{
"epoch": 2.02,
"learning_rate": 0.001,
"loss": 1.2313,
"step": 138
},
{
"epoch": 2.05,
"learning_rate": 0.001,
"loss": 1.1831,
"step": 140
},
{
"epoch": 2.08,
"learning_rate": 0.001,
"loss": 1.2066,
"step": 142
},
{
"epoch": 2.11,
"learning_rate": 0.001,
"loss": 1.1643,
"step": 144
},
{
"epoch": 2.14,
"learning_rate": 0.001,
"loss": 1.1896,
"step": 146
},
{
"epoch": 2.17,
"learning_rate": 0.001,
"loss": 1.2158,
"step": 148
},
{
"epoch": 2.2,
"learning_rate": 0.001,
"loss": 1.1846,
"step": 150
},
{
"epoch": 2.23,
"learning_rate": 0.001,
"loss": 1.1914,
"step": 152
},
{
"epoch": 2.26,
"learning_rate": 0.001,
"loss": 1.1673,
"step": 154
},
{
"epoch": 2.29,
"learning_rate": 0.001,
"loss": 1.1649,
"step": 156
},
{
"epoch": 2.32,
"learning_rate": 0.001,
"loss": 1.1992,
"step": 158
},
{
"epoch": 2.35,
"learning_rate": 0.001,
"loss": 1.1898,
"step": 160
},
{
"epoch": 2.37,
"learning_rate": 0.001,
"loss": 1.1869,
"step": 162
},
{
"epoch": 2.4,
"learning_rate": 0.001,
"loss": 1.2013,
"step": 164
},
{
"epoch": 2.43,
"learning_rate": 0.001,
"loss": 1.1587,
"step": 166
},
{
"epoch": 2.46,
"learning_rate": 0.001,
"loss": 1.1765,
"step": 168
},
{
"epoch": 2.49,
"learning_rate": 0.001,
"loss": 1.1673,
"step": 170
},
{
"epoch": 2.52,
"learning_rate": 0.001,
"loss": 1.1936,
"step": 172
},
{
"epoch": 2.55,
"learning_rate": 0.001,
"loss": 1.1892,
"step": 174
},
{
"epoch": 2.58,
"learning_rate": 0.001,
"loss": 1.1734,
"step": 176
},
{
"epoch": 2.61,
"learning_rate": 0.001,
"loss": 1.1765,
"step": 178
},
{
"epoch": 2.64,
"learning_rate": 0.001,
"loss": 1.1952,
"step": 180
},
{
"epoch": 2.67,
"learning_rate": 0.001,
"loss": 1.217,
"step": 182
},
{
"epoch": 2.7,
"learning_rate": 0.001,
"loss": 1.2099,
"step": 184
},
{
"epoch": 2.73,
"learning_rate": 0.001,
"loss": 1.1728,
"step": 186
},
{
"epoch": 2.76,
"learning_rate": 0.001,
"loss": 1.1885,
"step": 188
},
{
"epoch": 2.79,
"learning_rate": 0.001,
"loss": 1.1913,
"step": 190
},
{
"epoch": 2.81,
"learning_rate": 0.001,
"loss": 1.2063,
"step": 192
},
{
"epoch": 2.84,
"learning_rate": 0.001,
"loss": 1.1895,
"step": 194
},
{
"epoch": 2.87,
"learning_rate": 0.001,
"loss": 1.2323,
"step": 196
},
{
"epoch": 2.9,
"learning_rate": 0.001,
"loss": 1.2043,
"step": 198
},
{
"epoch": 2.93,
"learning_rate": 0.001,
"loss": 1.1987,
"step": 200
},
{
"epoch": 2.96,
"learning_rate": 0.001,
"loss": 1.1732,
"step": 202
},
{
"epoch": 2.99,
"learning_rate": 0.001,
"loss": 1.1811,
"step": 204
},
{
"epoch": 2.99,
"eval_loss": 1.2455540895462036,
"eval_runtime": 153.2109,
"eval_samples_per_second": 6.344,
"eval_steps_per_second": 0.796,
"step": 204
},
{
"epoch": 3.02,
"learning_rate": 0.001,
"loss": 1.0865,
"step": 206
},
{
"epoch": 3.05,
"learning_rate": 0.001,
"loss": 1.0674,
"step": 208
},
{
"epoch": 3.08,
"learning_rate": 0.001,
"loss": 1.0233,
"step": 210
},
{
"epoch": 3.11,
"learning_rate": 0.001,
"loss": 1.0369,
"step": 212
},
{
"epoch": 3.14,
"learning_rate": 0.001,
"loss": 1.0632,
"step": 214
},
{
"epoch": 3.17,
"learning_rate": 0.001,
"loss": 1.0417,
"step": 216
},
{
"epoch": 3.2,
"learning_rate": 0.001,
"loss": 1.0477,
"step": 218
},
{
"epoch": 3.22,
"learning_rate": 0.001,
"loss": 1.0429,
"step": 220
},
{
"epoch": 3.25,
"learning_rate": 0.001,
"loss": 1.0446,
"step": 222
},
{
"epoch": 3.28,
"learning_rate": 0.001,
"loss": 1.0587,
"step": 224
},
{
"epoch": 3.31,
"learning_rate": 0.001,
"loss": 1.0881,
"step": 226
},
{
"epoch": 3.34,
"learning_rate": 0.001,
"loss": 1.062,
"step": 228
},
{
"epoch": 3.37,
"learning_rate": 0.001,
"loss": 1.0618,
"step": 230
},
{
"epoch": 3.4,
"learning_rate": 0.001,
"loss": 1.0801,
"step": 232
},
{
"epoch": 3.43,
"learning_rate": 0.001,
"loss": 1.0601,
"step": 234
},
{
"epoch": 3.46,
"learning_rate": 0.001,
"loss": 1.0444,
"step": 236
},
{
"epoch": 3.49,
"learning_rate": 0.001,
"loss": 1.052,
"step": 238
},
{
"epoch": 3.52,
"learning_rate": 0.001,
"loss": 1.0677,
"step": 240
},
{
"epoch": 3.55,
"learning_rate": 0.001,
"loss": 1.074,
"step": 242
},
{
"epoch": 3.58,
"learning_rate": 0.001,
"loss": 1.0589,
"step": 244
},
{
"epoch": 3.61,
"learning_rate": 0.001,
"loss": 1.0767,
"step": 246
},
{
"epoch": 3.64,
"learning_rate": 0.001,
"loss": 1.094,
"step": 248
},
{
"epoch": 3.66,
"learning_rate": 0.001,
"loss": 1.0783,
"step": 250
},
{
"epoch": 3.69,
"learning_rate": 0.001,
"loss": 1.0683,
"step": 252
},
{
"epoch": 3.72,
"learning_rate": 0.001,
"loss": 1.0594,
"step": 254
},
{
"epoch": 3.75,
"learning_rate": 0.001,
"loss": 1.063,
"step": 256
},
{
"epoch": 3.78,
"learning_rate": 0.001,
"loss": 1.0745,
"step": 258
},
{
"epoch": 3.81,
"learning_rate": 0.001,
"loss": 1.104,
"step": 260
},
{
"epoch": 3.84,
"learning_rate": 0.001,
"loss": 1.074,
"step": 262
},
{
"epoch": 3.87,
"learning_rate": 0.001,
"loss": 1.0787,
"step": 264
},
{
"epoch": 3.9,
"learning_rate": 0.001,
"loss": 1.0848,
"step": 266
},
{
"epoch": 3.93,
"learning_rate": 0.001,
"loss": 1.0724,
"step": 268
},
{
"epoch": 3.96,
"learning_rate": 0.001,
"loss": 1.0703,
"step": 270
},
{
"epoch": 3.99,
"learning_rate": 0.001,
"loss": 1.0752,
"step": 272
},
{
"epoch": 3.99,
"eval_loss": 1.2426340579986572,
"eval_runtime": 153.6259,
"eval_samples_per_second": 6.327,
"eval_steps_per_second": 0.794,
"step": 272
},
{
"epoch": 4.02,
"learning_rate": 0.001,
"loss": 0.988,
"step": 274
},
{
"epoch": 4.05,
"learning_rate": 0.001,
"loss": 0.9078,
"step": 276
},
{
"epoch": 4.08,
"learning_rate": 0.001,
"loss": 0.9303,
"step": 278
},
{
"epoch": 4.1,
"learning_rate": 0.001,
"loss": 0.926,
"step": 280
},
{
"epoch": 4.13,
"learning_rate": 0.001,
"loss": 0.9451,
"step": 282
},
{
"epoch": 4.16,
"learning_rate": 0.001,
"loss": 0.9417,
"step": 284
},
{
"epoch": 4.19,
"learning_rate": 0.001,
"loss": 0.9242,
"step": 286
},
{
"epoch": 4.22,
"learning_rate": 0.001,
"loss": 0.9395,
"step": 288
},
{
"epoch": 4.25,
"learning_rate": 0.001,
"loss": 0.9411,
"step": 290
},
{
"epoch": 4.28,
"learning_rate": 0.001,
"loss": 0.9406,
"step": 292
},
{
"epoch": 4.31,
"learning_rate": 0.001,
"loss": 0.9396,
"step": 294
},
{
"epoch": 4.34,
"learning_rate": 0.001,
"loss": 0.9293,
"step": 296
},
{
"epoch": 4.37,
"learning_rate": 0.001,
"loss": 0.9533,
"step": 298
},
{
"epoch": 4.4,
"learning_rate": 0.001,
"loss": 0.9388,
"step": 300
},
{
"epoch": 4.43,
"learning_rate": 0.001,
"loss": 0.955,
"step": 302
},
{
"epoch": 4.46,
"learning_rate": 0.001,
"loss": 0.939,
"step": 304
},
{
"epoch": 4.49,
"learning_rate": 0.001,
"loss": 0.9381,
"step": 306
},
{
"epoch": 4.51,
"learning_rate": 0.001,
"loss": 0.9505,
"step": 308
},
{
"epoch": 4.54,
"learning_rate": 0.001,
"loss": 0.9654,
"step": 310
},
{
"epoch": 4.57,
"learning_rate": 0.001,
"loss": 0.9406,
"step": 312
},
{
"epoch": 4.6,
"learning_rate": 0.001,
"loss": 0.9684,
"step": 314
},
{
"epoch": 4.63,
"learning_rate": 0.001,
"loss": 0.948,
"step": 316
},
{
"epoch": 4.66,
"learning_rate": 0.001,
"loss": 0.9688,
"step": 318
},
{
"epoch": 4.69,
"learning_rate": 0.001,
"loss": 0.9462,
"step": 320
},
{
"epoch": 4.72,
"learning_rate": 0.001,
"loss": 0.9646,
"step": 322
},
{
"epoch": 4.75,
"learning_rate": 0.001,
"loss": 0.9637,
"step": 324
},
{
"epoch": 4.78,
"learning_rate": 0.001,
"loss": 0.9689,
"step": 326
},
{
"epoch": 4.81,
"learning_rate": 0.001,
"loss": 0.9757,
"step": 328
},
{
"epoch": 4.84,
"learning_rate": 0.001,
"loss": 0.9552,
"step": 330
},
{
"epoch": 4.87,
"learning_rate": 0.001,
"loss": 0.9662,
"step": 332
},
{
"epoch": 4.9,
"learning_rate": 0.001,
"loss": 0.96,
"step": 334
},
{
"epoch": 4.93,
"learning_rate": 0.001,
"loss": 0.9584,
"step": 336
},
{
"epoch": 4.95,
"learning_rate": 0.001,
"loss": 0.9694,
"step": 338
},
{
"epoch": 4.98,
"learning_rate": 0.001,
"loss": 0.9663,
"step": 340
},
{
"epoch": 5.0,
"eval_loss": 1.2900694608688354,
"eval_runtime": 153.609,
"eval_samples_per_second": 6.328,
"eval_steps_per_second": 0.794,
"step": 341
},
{
"epoch": 5.01,
"learning_rate": 0.001,
"loss": 0.8915,
"step": 342
},
{
"epoch": 5.04,
"learning_rate": 0.001,
"loss": 0.8169,
"step": 344
},
{
"epoch": 5.07,
"learning_rate": 0.001,
"loss": 0.8109,
"step": 346
},
{
"epoch": 5.1,
"learning_rate": 0.001,
"loss": 0.8339,
"step": 348
},
{
"epoch": 5.13,
"learning_rate": 0.001,
"loss": 0.8303,
"step": 350
},
{
"epoch": 5.16,
"learning_rate": 0.001,
"loss": 0.8237,
"step": 352
},
{
"epoch": 5.19,
"learning_rate": 0.001,
"loss": 0.8227,
"step": 354
},
{
"epoch": 5.22,
"learning_rate": 0.001,
"loss": 0.8495,
"step": 356
},
{
"epoch": 5.25,
"learning_rate": 0.001,
"loss": 0.8487,
"step": 358
},
{
"epoch": 5.28,
"learning_rate": 0.001,
"loss": 0.8412,
"step": 360
},
{
"epoch": 5.31,
"learning_rate": 0.001,
"loss": 0.8089,
"step": 362
},
{
"epoch": 5.34,
"learning_rate": 0.001,
"loss": 0.838,
"step": 364
},
{
"epoch": 5.37,
"learning_rate": 0.001,
"loss": 0.8485,
"step": 366
},
{
"epoch": 5.39,
"learning_rate": 0.001,
"loss": 0.8291,
"step": 368
},
{
"epoch": 5.42,
"learning_rate": 0.001,
"loss": 0.8407,
"step": 370
},
{
"epoch": 5.45,
"learning_rate": 0.001,
"loss": 0.852,
"step": 372
},
{
"epoch": 5.48,
"learning_rate": 0.001,
"loss": 0.8438,
"step": 374
},
{
"epoch": 5.51,
"learning_rate": 0.001,
"loss": 0.849,
"step": 376
},
{
"epoch": 5.54,
"learning_rate": 0.001,
"loss": 0.8397,
"step": 378
},
{
"epoch": 5.57,
"learning_rate": 0.001,
"loss": 0.8717,
"step": 380
},
{
"epoch": 5.6,
"learning_rate": 0.001,
"loss": 0.8536,
"step": 382
},
{
"epoch": 5.63,
"learning_rate": 0.001,
"loss": 0.8602,
"step": 384
},
{
"epoch": 5.66,
"learning_rate": 0.001,
"loss": 0.8661,
"step": 386
},
{
"epoch": 5.69,
"learning_rate": 0.001,
"loss": 0.8613,
"step": 388
},
{
"epoch": 5.72,
"learning_rate": 0.001,
"loss": 0.8651,
"step": 390
},
{
"epoch": 5.75,
"learning_rate": 0.001,
"loss": 0.8626,
"step": 392
},
{
"epoch": 5.78,
"learning_rate": 0.001,
"loss": 0.8669,
"step": 394
},
{
"epoch": 5.8,
"learning_rate": 0.001,
"loss": 0.8642,
"step": 396
},
{
"epoch": 5.83,
"learning_rate": 0.001,
"loss": 0.8689,
"step": 398
},
{
"epoch": 5.86,
"learning_rate": 0.001,
"loss": 0.8696,
"step": 400
},
{
"epoch": 5.89,
"learning_rate": 0.001,
"loss": 0.8443,
"step": 402
},
{
"epoch": 5.92,
"learning_rate": 0.001,
"loss": 0.8539,
"step": 404
},
{
"epoch": 5.95,
"learning_rate": 0.001,
"loss": 0.8647,
"step": 406
},
{
"epoch": 5.98,
"learning_rate": 0.001,
"loss": 0.8607,
"step": 408
},
{
"epoch": 6.0,
"eval_loss": 1.3395987749099731,
"eval_runtime": 153.1153,
"eval_samples_per_second": 6.348,
"eval_steps_per_second": 0.797,
"step": 409
},
{
"epoch": 6.01,
"learning_rate": 0.001,
"loss": 0.8252,
"step": 410
},
{
"epoch": 6.04,
"learning_rate": 0.001,
"loss": 0.7173,
"step": 412
},
{
"epoch": 6.07,
"learning_rate": 0.001,
"loss": 0.7206,
"step": 414
},
{
"epoch": 6.1,
"learning_rate": 0.001,
"loss": 0.7364,
"step": 416
},
{
"epoch": 6.13,
"learning_rate": 0.001,
"loss": 0.7132,
"step": 418
},
{
"epoch": 6.16,
"learning_rate": 0.001,
"loss": 0.7353,
"step": 420
},
{
"epoch": 6.19,
"learning_rate": 0.001,
"loss": 0.7392,
"step": 422
},
{
"epoch": 6.22,
"learning_rate": 0.001,
"loss": 0.7394,
"step": 424
},
{
"epoch": 6.24,
"learning_rate": 0.001,
"loss": 0.7684,
"step": 426
},
{
"epoch": 6.27,
"learning_rate": 0.001,
"loss": 0.7543,
"step": 428
},
{
"epoch": 6.3,
"learning_rate": 0.001,
"loss": 0.7392,
"step": 430
},
{
"epoch": 6.33,
"learning_rate": 0.001,
"loss": 0.7445,
"step": 432
},
{
"epoch": 6.36,
"learning_rate": 0.001,
"loss": 0.7773,
"step": 434
},
{
"epoch": 6.39,
"learning_rate": 0.001,
"loss": 0.7469,
"step": 436
},
{
"epoch": 6.42,
"learning_rate": 0.001,
"loss": 0.7275,
"step": 438
},
{
"epoch": 6.45,
"learning_rate": 0.001,
"loss": 0.7775,
"step": 440
},
{
"epoch": 6.48,
"learning_rate": 0.001,
"loss": 0.7301,
"step": 442
},
{
"epoch": 6.51,
"learning_rate": 0.001,
"loss": 0.7491,
"step": 444
},
{
"epoch": 6.54,
"learning_rate": 0.001,
"loss": 0.7475,
"step": 446
},
{
"epoch": 6.57,
"learning_rate": 0.001,
"loss": 0.7629,
"step": 448
},
{
"epoch": 6.6,
"learning_rate": 0.001,
"loss": 0.7667,
"step": 450
},
{
"epoch": 6.63,
"learning_rate": 0.001,
"loss": 0.7558,
"step": 452
},
{
"epoch": 6.66,
"learning_rate": 0.001,
"loss": 0.7604,
"step": 454
},
{
"epoch": 6.68,
"learning_rate": 0.001,
"loss": 0.7602,
"step": 456
},
{
"epoch": 6.71,
"learning_rate": 0.001,
"loss": 0.7781,
"step": 458
},
{
"epoch": 6.74,
"learning_rate": 0.001,
"loss": 0.7619,
"step": 460
},
{
"epoch": 6.77,
"learning_rate": 0.001,
"loss": 0.7577,
"step": 462
},
{
"epoch": 6.8,
"learning_rate": 0.001,
"loss": 0.7469,
"step": 464
},
{
"epoch": 6.83,
"learning_rate": 0.001,
"loss": 0.7438,
"step": 466
},
{
"epoch": 6.86,
"learning_rate": 0.001,
"loss": 0.765,
"step": 468
},
{
"epoch": 6.89,
"learning_rate": 0.001,
"loss": 0.7336,
"step": 470
},
{
"epoch": 6.92,
"learning_rate": 0.001,
"loss": 0.7441,
"step": 472
},
{
"epoch": 6.95,
"learning_rate": 0.001,
"loss": 0.7552,
"step": 474
},
{
"epoch": 6.98,
"learning_rate": 0.001,
"loss": 0.7462,
"step": 476
},
{
"epoch": 6.99,
"eval_loss": 1.3746581077575684,
"eval_runtime": 153.643,
"eval_samples_per_second": 6.326,
"eval_steps_per_second": 0.794,
"step": 477
},
{
"epoch": 7.01,
"learning_rate": 0.001,
"loss": 0.7543,
"step": 478
},
{
"epoch": 7.04,
"learning_rate": 0.001,
"loss": 0.6377,
"step": 480
},
{
"epoch": 7.07,
"learning_rate": 0.001,
"loss": 0.6342,
"step": 482
},
{
"epoch": 7.09,
"learning_rate": 0.001,
"loss": 0.6417,
"step": 484
},
{
"epoch": 7.12,
"learning_rate": 0.001,
"loss": 0.6428,
"step": 486
},
{
"epoch": 7.15,
"learning_rate": 0.001,
"loss": 0.6378,
"step": 488
},
{
"epoch": 7.18,
"learning_rate": 0.001,
"loss": 0.6354,
"step": 490
},
{
"epoch": 7.21,
"learning_rate": 0.001,
"loss": 0.6492,
"step": 492
},
{
"epoch": 7.24,
"learning_rate": 0.001,
"loss": 0.643,
"step": 494
},
{
"epoch": 7.27,
"learning_rate": 0.001,
"loss": 0.65,
"step": 496
},
{
"epoch": 7.3,
"learning_rate": 0.001,
"loss": 0.6553,
"step": 498
},
{
"epoch": 7.33,
"learning_rate": 0.001,
"loss": 0.6565,
"step": 500
},
{
"epoch": 7.36,
"learning_rate": 0.001,
"loss": 0.6603,
"step": 502
},
{
"epoch": 7.39,
"learning_rate": 0.001,
"loss": 0.6753,
"step": 504
},
{
"epoch": 7.42,
"learning_rate": 0.001,
"loss": 0.646,
"step": 506
},
{
"epoch": 7.45,
"learning_rate": 0.001,
"loss": 0.6468,
"step": 508
},
{
"epoch": 7.48,
"learning_rate": 0.001,
"loss": 0.6393,
"step": 510
},
{
"epoch": 7.51,
"learning_rate": 0.001,
"loss": 0.6594,
"step": 512
},
{
"epoch": 7.53,
"learning_rate": 0.001,
"loss": 0.6491,
"step": 514
},
{
"epoch": 7.56,
"learning_rate": 0.001,
"loss": 0.6517,
"step": 516
},
{
"epoch": 7.59,
"learning_rate": 0.001,
"loss": 0.66,
"step": 518
},
{
"epoch": 7.62,
"learning_rate": 0.001,
"loss": 0.6743,
"step": 520
},
{
"epoch": 7.65,
"learning_rate": 0.001,
"loss": 0.6568,
"step": 522
},
{
"epoch": 7.68,
"learning_rate": 0.001,
"loss": 0.6705,
"step": 524
},
{
"epoch": 7.71,
"learning_rate": 0.001,
"loss": 0.6793,
"step": 526
},
{
"epoch": 7.74,
"learning_rate": 0.001,
"loss": 0.6717,
"step": 528
},
{
"epoch": 7.77,
"learning_rate": 0.001,
"loss": 0.6836,
"step": 530
},
{
"epoch": 7.8,
"learning_rate": 0.001,
"loss": 0.6635,
"step": 532
},
{
"epoch": 7.83,
"learning_rate": 0.001,
"loss": 0.6762,
"step": 534
},
{
"epoch": 7.86,
"learning_rate": 0.001,
"loss": 0.6787,
"step": 536
},
{
"epoch": 7.89,
"learning_rate": 0.001,
"loss": 0.6886,
"step": 538
},
{
"epoch": 7.92,
"learning_rate": 0.001,
"loss": 0.6827,
"step": 540
},
{
"epoch": 7.95,
"learning_rate": 0.001,
"loss": 0.7047,
"step": 542
},
{
"epoch": 7.97,
"learning_rate": 0.001,
"loss": 0.7084,
"step": 544
},
{
"epoch": 7.99,
"eval_loss": 1.4659099578857422,
"eval_runtime": 153.344,
"eval_samples_per_second": 6.339,
"eval_steps_per_second": 0.796,
"step": 545
},
{
"epoch": 8.0,
"learning_rate": 0.001,
"loss": 0.6625,
"step": 546
},
{
"epoch": 8.03,
"learning_rate": 0.001,
"loss": 0.55,
"step": 548
},
{
"epoch": 8.06,
"learning_rate": 0.001,
"loss": 0.5624,
"step": 550
},
{
"epoch": 8.09,
"learning_rate": 0.001,
"loss": 0.5566,
"step": 552
},
{
"epoch": 8.12,
"learning_rate": 0.001,
"loss": 0.5603,
"step": 554
},
{
"epoch": 8.15,
"learning_rate": 0.001,
"loss": 0.5613,
"step": 556
},
{
"epoch": 8.18,
"learning_rate": 0.001,
"loss": 0.5507,
"step": 558
},
{
"epoch": 8.21,
"learning_rate": 0.001,
"loss": 0.5696,
"step": 560
},
{
"epoch": 8.24,
"learning_rate": 0.001,
"loss": 0.5643,
"step": 562
},
{
"epoch": 8.27,
"learning_rate": 0.001,
"loss": 0.5779,
"step": 564
},
{
"epoch": 8.3,
"learning_rate": 0.001,
"loss": 0.5716,
"step": 566
},
{
"epoch": 8.33,
"learning_rate": 0.001,
"loss": 0.5809,
"step": 568
},
{
"epoch": 8.36,
"learning_rate": 0.001,
"loss": 0.5757,
"step": 570
},
{
"epoch": 8.38,
"learning_rate": 0.001,
"loss": 0.5579,
"step": 572
},
{
"epoch": 8.41,
"learning_rate": 0.001,
"loss": 0.5724,
"step": 574
},
{
"epoch": 8.44,
"learning_rate": 0.001,
"loss": 0.5509,
"step": 576
},
{
"epoch": 8.47,
"learning_rate": 0.001,
"loss": 0.5539,
"step": 578
},
{
"epoch": 8.5,
"learning_rate": 0.001,
"loss": 0.5906,
"step": 580
},
{
"epoch": 8.53,
"learning_rate": 0.001,
"loss": 0.5943,
"step": 582
},
{
"epoch": 8.56,
"learning_rate": 0.001,
"loss": 0.6132,
"step": 584
},
{
"epoch": 8.59,
"learning_rate": 0.001,
"loss": 0.6026,
"step": 586
},
{
"epoch": 8.62,
"learning_rate": 0.001,
"loss": 0.6147,
"step": 588
},
{
"epoch": 8.65,
"learning_rate": 0.001,
"loss": 0.5925,
"step": 590
},
{
"epoch": 8.68,
"learning_rate": 0.001,
"loss": 0.5987,
"step": 592
},
{
"epoch": 8.71,
"learning_rate": 0.001,
"loss": 0.6025,
"step": 594
},
{
"epoch": 8.74,
"learning_rate": 0.001,
"loss": 0.5965,
"step": 596
},
{
"epoch": 8.77,
"learning_rate": 0.001,
"loss": 0.598,
"step": 598
},
{
"epoch": 8.8,
"learning_rate": 0.001,
"loss": 0.616,
"step": 600
},
{
"epoch": 8.82,
"learning_rate": 0.001,
"loss": 0.5976,
"step": 602
},
{
"epoch": 8.85,
"learning_rate": 0.001,
"loss": 0.5999,
"step": 604
},
{
"epoch": 8.88,
"learning_rate": 0.001,
"loss": 0.5895,
"step": 606
},
{
"epoch": 8.91,
"learning_rate": 0.001,
"loss": 0.6129,
"step": 608
},
{
"epoch": 8.94,
"learning_rate": 0.001,
"loss": 0.61,
"step": 610
},
{
"epoch": 8.97,
"learning_rate": 0.001,
"loss": 0.6155,
"step": 612
},
{
"epoch": 8.99,
"eval_loss": 1.5037193298339844,
"eval_runtime": 153.536,
"eval_samples_per_second": 6.331,
"eval_steps_per_second": 0.795,
"step": 613
},
{
"epoch": 9.0,
"learning_rate": 0.001,
"loss": 0.633,
"step": 614
},
{
"epoch": 9.03,
"learning_rate": 0.001,
"loss": 0.4917,
"step": 616
},
{
"epoch": 9.06,
"learning_rate": 0.001,
"loss": 0.4737,
"step": 618
},
{
"epoch": 9.09,
"learning_rate": 0.001,
"loss": 0.4802,
"step": 620
},
{
"epoch": 9.12,
"learning_rate": 0.001,
"loss": 0.4917,
"step": 622
},
{
"epoch": 9.15,
"learning_rate": 0.001,
"loss": 0.4999,
"step": 624
},
{
"epoch": 9.18,
"learning_rate": 0.001,
"loss": 0.5103,
"step": 626
},
{
"epoch": 9.21,
"learning_rate": 0.001,
"loss": 0.5019,
"step": 628
},
{
"epoch": 9.23,
"learning_rate": 0.001,
"loss": 0.4964,
"step": 630
},
{
"epoch": 9.26,
"learning_rate": 0.001,
"loss": 0.5142,
"step": 632
},
{
"epoch": 9.29,
"learning_rate": 0.001,
"loss": 0.515,
"step": 634
},
{
"epoch": 9.32,
"learning_rate": 0.001,
"loss": 0.5133,
"step": 636
},
{
"epoch": 9.35,
"learning_rate": 0.001,
"loss": 0.5136,
"step": 638
},
{
"epoch": 9.38,
"learning_rate": 0.001,
"loss": 0.5135,
"step": 640
},
{
"epoch": 9.41,
"learning_rate": 0.001,
"loss": 0.4979,
"step": 642
},
{
"epoch": 9.44,
"learning_rate": 0.001,
"loss": 0.5069,
"step": 644
},
{
"epoch": 9.47,
"learning_rate": 0.001,
"loss": 0.5287,
"step": 646
},
{
"epoch": 9.5,
"learning_rate": 0.001,
"loss": 0.5227,
"step": 648
},
{
"epoch": 9.53,
"learning_rate": 0.001,
"loss": 0.4968,
"step": 650
},
{
"epoch": 9.56,
"learning_rate": 0.001,
"loss": 0.5015,
"step": 652
},
{
"epoch": 9.59,
"learning_rate": 0.001,
"loss": 0.5143,
"step": 654
},
{
"epoch": 9.62,
"learning_rate": 0.001,
"loss": 0.5062,
"step": 656
},
{
"epoch": 9.65,
"learning_rate": 0.001,
"loss": 0.51,
"step": 658
},
{
"epoch": 9.67,
"learning_rate": 0.001,
"loss": 0.5293,
"step": 660
},
{
"epoch": 9.7,
"learning_rate": 0.001,
"loss": 0.5273,
"step": 662
},
{
"epoch": 9.73,
"learning_rate": 0.001,
"loss": 0.526,
"step": 664
},
{
"epoch": 9.76,
"learning_rate": 0.001,
"loss": 0.5294,
"step": 666
},
{
"epoch": 9.79,
"learning_rate": 0.001,
"loss": 0.5279,
"step": 668
},
{
"epoch": 9.82,
"learning_rate": 0.001,
"loss": 0.536,
"step": 670
},
{
"epoch": 9.85,
"learning_rate": 0.001,
"loss": 0.5446,
"step": 672
},
{
"epoch": 9.88,
"learning_rate": 0.001,
"loss": 0.5467,
"step": 674
},
{
"epoch": 9.91,
"learning_rate": 0.001,
"loss": 0.5394,
"step": 676
},
{
"epoch": 9.94,
"learning_rate": 0.001,
"loss": 0.5341,
"step": 678
},
{
"epoch": 9.97,
"learning_rate": 0.001,
"loss": 0.5435,
"step": 680
},
{
"epoch": 9.97,
"eval_loss": 1.5582315921783447,
"eval_runtime": 153.7963,
"eval_samples_per_second": 6.32,
"eval_steps_per_second": 0.793,
"step": 680
},
{
"epoch": 9.97,
"step": 680,
"total_flos": 3.0923201415995965e+18,
"train_loss": 0.9514477711390047,
"train_runtime": 93373.8295,
"train_samples_per_second": 1.87,
"train_steps_per_second": 0.007
}
],
"logging_steps": 2,
"max_steps": 680,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 3.0923201415995965e+18,
"trial_name": null,
"trial_params": null
}