pythia-exp / trainer_state.json
TinyPixel's picture
Upload folder using huggingface_hub
1301935
raw
history blame
31.4 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9987368421052631,
"eval_steps": 500,
"global_step": 593,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.5783,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 2.4573,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 2.4966,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 2.6148,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 2.4502,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 2.4416,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 2.3624,
"step": 14
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 2.3526,
"step": 16
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 2.3868,
"step": 18
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 2.402,
"step": 20
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 2.3276,
"step": 22
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 2.331,
"step": 24
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 2.2648,
"step": 26
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 2.2885,
"step": 28
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 2.3286,
"step": 30
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 2.3401,
"step": 32
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 2.241,
"step": 34
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 2.3439,
"step": 36
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 2.3157,
"step": 38
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 2.223,
"step": 40
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 2.186,
"step": 42
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 2.334,
"step": 44
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 2.0672,
"step": 46
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 2.1664,
"step": 48
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 2.0729,
"step": 50
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 2.2502,
"step": 52
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 2.4421,
"step": 54
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 2.4158,
"step": 56
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 2.3928,
"step": 58
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 2.3709,
"step": 60
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 2.1882,
"step": 62
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 2.3892,
"step": 64
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 2.3375,
"step": 66
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 2.3935,
"step": 68
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 2.3748,
"step": 70
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 2.2778,
"step": 72
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 2.3611,
"step": 74
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 2.2275,
"step": 76
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 2.3741,
"step": 78
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 2.2285,
"step": 80
},
{
"epoch": 0.14,
"learning_rate": 0.0002,
"loss": 2.4529,
"step": 82
},
{
"epoch": 0.14,
"learning_rate": 0.0002,
"loss": 2.1483,
"step": 84
},
{
"epoch": 0.14,
"learning_rate": 0.0002,
"loss": 2.1816,
"step": 86
},
{
"epoch": 0.15,
"learning_rate": 0.0002,
"loss": 2.1476,
"step": 88
},
{
"epoch": 0.15,
"learning_rate": 0.0002,
"loss": 2.0401,
"step": 90
},
{
"epoch": 0.15,
"learning_rate": 0.0002,
"loss": 2.1427,
"step": 92
},
{
"epoch": 0.16,
"learning_rate": 0.0002,
"loss": 2.0895,
"step": 94
},
{
"epoch": 0.16,
"learning_rate": 0.0002,
"loss": 2.2566,
"step": 96
},
{
"epoch": 0.17,
"learning_rate": 0.0002,
"loss": 1.9703,
"step": 98
},
{
"epoch": 0.17,
"learning_rate": 0.0002,
"loss": 2.1,
"step": 100
},
{
"epoch": 0.17,
"learning_rate": 0.0002,
"loss": 2.0304,
"step": 102
},
{
"epoch": 0.18,
"learning_rate": 0.0002,
"loss": 2.2995,
"step": 104
},
{
"epoch": 0.18,
"learning_rate": 0.0002,
"loss": 2.5125,
"step": 106
},
{
"epoch": 0.18,
"learning_rate": 0.0002,
"loss": 2.4695,
"step": 108
},
{
"epoch": 0.19,
"learning_rate": 0.0002,
"loss": 2.3123,
"step": 110
},
{
"epoch": 0.19,
"learning_rate": 0.0002,
"loss": 2.2879,
"step": 112
},
{
"epoch": 0.19,
"learning_rate": 0.0002,
"loss": 2.4215,
"step": 114
},
{
"epoch": 0.2,
"learning_rate": 0.0002,
"loss": 2.4717,
"step": 116
},
{
"epoch": 0.2,
"learning_rate": 0.0002,
"loss": 2.3825,
"step": 118
},
{
"epoch": 0.2,
"learning_rate": 0.0002,
"loss": 2.2808,
"step": 120
},
{
"epoch": 0.21,
"learning_rate": 0.0002,
"loss": 2.288,
"step": 122
},
{
"epoch": 0.21,
"learning_rate": 0.0002,
"loss": 2.2785,
"step": 124
},
{
"epoch": 0.21,
"learning_rate": 0.0002,
"loss": 2.2727,
"step": 126
},
{
"epoch": 0.22,
"learning_rate": 0.0002,
"loss": 2.1756,
"step": 128
},
{
"epoch": 0.22,
"learning_rate": 0.0002,
"loss": 2.2791,
"step": 130
},
{
"epoch": 0.22,
"learning_rate": 0.0002,
"loss": 2.358,
"step": 132
},
{
"epoch": 0.23,
"learning_rate": 0.0002,
"loss": 2.2445,
"step": 134
},
{
"epoch": 0.23,
"learning_rate": 0.0002,
"loss": 2.2988,
"step": 136
},
{
"epoch": 0.23,
"learning_rate": 0.0002,
"loss": 2.3197,
"step": 138
},
{
"epoch": 0.24,
"learning_rate": 0.0002,
"loss": 2.1261,
"step": 140
},
{
"epoch": 0.24,
"learning_rate": 0.0002,
"loss": 2.0944,
"step": 142
},
{
"epoch": 0.24,
"learning_rate": 0.0002,
"loss": 2.3349,
"step": 144
},
{
"epoch": 0.25,
"learning_rate": 0.0002,
"loss": 2.228,
"step": 146
},
{
"epoch": 0.25,
"learning_rate": 0.0002,
"loss": 2.0624,
"step": 148
},
{
"epoch": 0.25,
"learning_rate": 0.0002,
"loss": 2.1346,
"step": 150
},
{
"epoch": 0.26,
"learning_rate": 0.0002,
"loss": 2.184,
"step": 152
},
{
"epoch": 0.26,
"learning_rate": 0.0002,
"loss": 2.3299,
"step": 154
},
{
"epoch": 0.26,
"learning_rate": 0.0002,
"loss": 2.3675,
"step": 156
},
{
"epoch": 0.27,
"learning_rate": 0.0002,
"loss": 2.3509,
"step": 158
},
{
"epoch": 0.27,
"learning_rate": 0.0002,
"loss": 2.3118,
"step": 160
},
{
"epoch": 0.27,
"learning_rate": 0.0002,
"loss": 2.1703,
"step": 162
},
{
"epoch": 0.28,
"learning_rate": 0.0002,
"loss": 2.3061,
"step": 164
},
{
"epoch": 0.28,
"learning_rate": 0.0002,
"loss": 2.4734,
"step": 166
},
{
"epoch": 0.28,
"learning_rate": 0.0002,
"loss": 2.2738,
"step": 168
},
{
"epoch": 0.29,
"learning_rate": 0.0002,
"loss": 2.3078,
"step": 170
},
{
"epoch": 0.29,
"learning_rate": 0.0002,
"loss": 2.4708,
"step": 172
},
{
"epoch": 0.29,
"learning_rate": 0.0002,
"loss": 2.296,
"step": 174
},
{
"epoch": 0.3,
"learning_rate": 0.0002,
"loss": 2.35,
"step": 176
},
{
"epoch": 0.3,
"learning_rate": 0.0002,
"loss": 2.2687,
"step": 178
},
{
"epoch": 0.3,
"learning_rate": 0.0002,
"loss": 2.1999,
"step": 180
},
{
"epoch": 0.31,
"learning_rate": 0.0002,
"loss": 2.2523,
"step": 182
},
{
"epoch": 0.31,
"learning_rate": 0.0002,
"loss": 2.1825,
"step": 184
},
{
"epoch": 0.31,
"learning_rate": 0.0002,
"loss": 2.1927,
"step": 186
},
{
"epoch": 0.32,
"learning_rate": 0.0002,
"loss": 2.0817,
"step": 188
},
{
"epoch": 0.32,
"learning_rate": 0.0002,
"loss": 2.164,
"step": 190
},
{
"epoch": 0.32,
"learning_rate": 0.0002,
"loss": 2.206,
"step": 192
},
{
"epoch": 0.33,
"learning_rate": 0.0002,
"loss": 2.1514,
"step": 194
},
{
"epoch": 0.33,
"learning_rate": 0.0002,
"loss": 2.1729,
"step": 196
},
{
"epoch": 0.33,
"learning_rate": 0.0002,
"loss": 2.0873,
"step": 198
},
{
"epoch": 0.34,
"learning_rate": 0.0002,
"loss": 2.1265,
"step": 200
},
{
"epoch": 0.34,
"learning_rate": 0.0002,
"loss": 2.2295,
"step": 202
},
{
"epoch": 0.34,
"learning_rate": 0.0002,
"loss": 2.3636,
"step": 204
},
{
"epoch": 0.35,
"learning_rate": 0.0002,
"loss": 2.3608,
"step": 206
},
{
"epoch": 0.35,
"learning_rate": 0.0002,
"loss": 2.3285,
"step": 208
},
{
"epoch": 0.35,
"learning_rate": 0.0002,
"loss": 2.396,
"step": 210
},
{
"epoch": 0.36,
"learning_rate": 0.0002,
"loss": 2.3376,
"step": 212
},
{
"epoch": 0.36,
"learning_rate": 0.0002,
"loss": 2.3553,
"step": 214
},
{
"epoch": 0.36,
"learning_rate": 0.0002,
"loss": 2.3033,
"step": 216
},
{
"epoch": 0.37,
"learning_rate": 0.0002,
"loss": 2.1905,
"step": 218
},
{
"epoch": 0.37,
"learning_rate": 0.0002,
"loss": 2.3655,
"step": 220
},
{
"epoch": 0.37,
"learning_rate": 0.0002,
"loss": 2.27,
"step": 222
},
{
"epoch": 0.38,
"learning_rate": 0.0002,
"loss": 2.1489,
"step": 224
},
{
"epoch": 0.38,
"learning_rate": 0.0002,
"loss": 2.1379,
"step": 226
},
{
"epoch": 0.38,
"learning_rate": 0.0002,
"loss": 2.2362,
"step": 228
},
{
"epoch": 0.39,
"learning_rate": 0.0002,
"loss": 2.1208,
"step": 230
},
{
"epoch": 0.39,
"learning_rate": 0.0002,
"loss": 2.082,
"step": 232
},
{
"epoch": 0.39,
"learning_rate": 0.0002,
"loss": 2.1259,
"step": 234
},
{
"epoch": 0.4,
"learning_rate": 0.0002,
"loss": 2.1136,
"step": 236
},
{
"epoch": 0.4,
"learning_rate": 0.0002,
"loss": 2.2157,
"step": 238
},
{
"epoch": 0.4,
"learning_rate": 0.0002,
"loss": 2.1296,
"step": 240
},
{
"epoch": 0.41,
"learning_rate": 0.0002,
"loss": 2.1879,
"step": 242
},
{
"epoch": 0.41,
"learning_rate": 0.0002,
"loss": 2.0323,
"step": 244
},
{
"epoch": 0.41,
"learning_rate": 0.0002,
"loss": 2.0867,
"step": 246
},
{
"epoch": 0.42,
"learning_rate": 0.0002,
"loss": 2.0557,
"step": 248
},
{
"epoch": 0.42,
"learning_rate": 0.0002,
"loss": 2.0231,
"step": 250
},
{
"epoch": 0.42,
"learning_rate": 0.0002,
"loss": 2.3236,
"step": 252
},
{
"epoch": 0.43,
"learning_rate": 0.0002,
"loss": 2.1812,
"step": 254
},
{
"epoch": 0.43,
"learning_rate": 0.0002,
"loss": 2.3149,
"step": 256
},
{
"epoch": 0.43,
"learning_rate": 0.0002,
"loss": 2.3427,
"step": 258
},
{
"epoch": 0.44,
"learning_rate": 0.0002,
"loss": 2.3397,
"step": 260
},
{
"epoch": 0.44,
"learning_rate": 0.0002,
"loss": 2.3995,
"step": 262
},
{
"epoch": 0.44,
"learning_rate": 0.0002,
"loss": 2.1924,
"step": 264
},
{
"epoch": 0.45,
"learning_rate": 0.0002,
"loss": 2.3778,
"step": 266
},
{
"epoch": 0.45,
"learning_rate": 0.0002,
"loss": 2.352,
"step": 268
},
{
"epoch": 0.45,
"learning_rate": 0.0002,
"loss": 2.2351,
"step": 270
},
{
"epoch": 0.46,
"learning_rate": 0.0002,
"loss": 2.3896,
"step": 272
},
{
"epoch": 0.46,
"learning_rate": 0.0002,
"loss": 2.2889,
"step": 274
},
{
"epoch": 0.46,
"learning_rate": 0.0002,
"loss": 2.1375,
"step": 276
},
{
"epoch": 0.47,
"learning_rate": 0.0002,
"loss": 2.2754,
"step": 278
},
{
"epoch": 0.47,
"learning_rate": 0.0002,
"loss": 2.2113,
"step": 280
},
{
"epoch": 0.47,
"learning_rate": 0.0002,
"loss": 2.2846,
"step": 282
},
{
"epoch": 0.48,
"learning_rate": 0.0002,
"loss": 2.1576,
"step": 284
},
{
"epoch": 0.48,
"learning_rate": 0.0002,
"loss": 2.2513,
"step": 286
},
{
"epoch": 0.49,
"learning_rate": 0.0002,
"loss": 2.1719,
"step": 288
},
{
"epoch": 0.49,
"learning_rate": 0.0002,
"loss": 2.0947,
"step": 290
},
{
"epoch": 0.49,
"learning_rate": 0.0002,
"loss": 2.2087,
"step": 292
},
{
"epoch": 0.5,
"learning_rate": 0.0002,
"loss": 2.19,
"step": 294
},
{
"epoch": 0.5,
"learning_rate": 0.0002,
"loss": 2.1734,
"step": 296
},
{
"epoch": 0.5,
"learning_rate": 0.0002,
"loss": 1.9482,
"step": 298
},
{
"epoch": 0.51,
"learning_rate": 0.0002,
"loss": 2.0103,
"step": 300
},
{
"epoch": 0.51,
"learning_rate": 0.0002,
"loss": 2.1587,
"step": 302
},
{
"epoch": 0.51,
"learning_rate": 0.0002,
"loss": 2.2392,
"step": 304
},
{
"epoch": 0.52,
"learning_rate": 0.0002,
"loss": 2.266,
"step": 306
},
{
"epoch": 0.52,
"learning_rate": 0.0002,
"loss": 2.3388,
"step": 308
},
{
"epoch": 0.52,
"learning_rate": 0.0002,
"loss": 2.2842,
"step": 310
},
{
"epoch": 0.53,
"learning_rate": 0.0002,
"loss": 2.3084,
"step": 312
},
{
"epoch": 0.53,
"learning_rate": 0.0002,
"loss": 2.3003,
"step": 314
},
{
"epoch": 0.53,
"learning_rate": 0.0002,
"loss": 2.0881,
"step": 316
},
{
"epoch": 0.54,
"learning_rate": 0.0002,
"loss": 2.4131,
"step": 318
},
{
"epoch": 0.54,
"learning_rate": 0.0002,
"loss": 2.2047,
"step": 320
},
{
"epoch": 0.54,
"learning_rate": 0.0002,
"loss": 2.179,
"step": 322
},
{
"epoch": 0.55,
"learning_rate": 0.0002,
"loss": 2.1102,
"step": 324
},
{
"epoch": 0.55,
"learning_rate": 0.0002,
"loss": 2.1323,
"step": 326
},
{
"epoch": 0.55,
"learning_rate": 0.0002,
"loss": 2.1982,
"step": 328
},
{
"epoch": 0.56,
"learning_rate": 0.0002,
"loss": 2.2898,
"step": 330
},
{
"epoch": 0.56,
"learning_rate": 0.0002,
"loss": 2.1307,
"step": 332
},
{
"epoch": 0.56,
"learning_rate": 0.0002,
"loss": 2.0766,
"step": 334
},
{
"epoch": 0.57,
"learning_rate": 0.0002,
"loss": 2.1678,
"step": 336
},
{
"epoch": 0.57,
"learning_rate": 0.0002,
"loss": 2.1257,
"step": 338
},
{
"epoch": 0.57,
"learning_rate": 0.0002,
"loss": 1.9431,
"step": 340
},
{
"epoch": 0.58,
"learning_rate": 0.0002,
"loss": 1.9472,
"step": 342
},
{
"epoch": 0.58,
"learning_rate": 0.0002,
"loss": 2.2918,
"step": 344
},
{
"epoch": 0.58,
"learning_rate": 0.0002,
"loss": 2.101,
"step": 346
},
{
"epoch": 0.59,
"learning_rate": 0.0002,
"loss": 2.0639,
"step": 348
},
{
"epoch": 0.59,
"learning_rate": 0.0002,
"loss": 1.9682,
"step": 350
},
{
"epoch": 0.59,
"learning_rate": 0.0002,
"loss": 2.2655,
"step": 352
},
{
"epoch": 0.6,
"learning_rate": 0.0002,
"loss": 2.3279,
"step": 354
},
{
"epoch": 0.6,
"learning_rate": 0.0002,
"loss": 2.2774,
"step": 356
},
{
"epoch": 0.6,
"learning_rate": 0.0002,
"loss": 2.3199,
"step": 358
},
{
"epoch": 0.61,
"learning_rate": 0.0002,
"loss": 2.3529,
"step": 360
},
{
"epoch": 0.61,
"learning_rate": 0.0002,
"loss": 2.3515,
"step": 362
},
{
"epoch": 0.61,
"learning_rate": 0.0002,
"loss": 2.345,
"step": 364
},
{
"epoch": 0.62,
"learning_rate": 0.0002,
"loss": 2.2788,
"step": 366
},
{
"epoch": 0.62,
"learning_rate": 0.0002,
"loss": 2.3067,
"step": 368
},
{
"epoch": 0.62,
"learning_rate": 0.0002,
"loss": 2.1545,
"step": 370
},
{
"epoch": 0.63,
"learning_rate": 0.0002,
"loss": 2.1672,
"step": 372
},
{
"epoch": 0.63,
"learning_rate": 0.0002,
"loss": 2.284,
"step": 374
},
{
"epoch": 0.63,
"learning_rate": 0.0002,
"loss": 2.2464,
"step": 376
},
{
"epoch": 0.64,
"learning_rate": 0.0002,
"loss": 2.2429,
"step": 378
},
{
"epoch": 0.64,
"learning_rate": 0.0002,
"loss": 2.2511,
"step": 380
},
{
"epoch": 0.64,
"learning_rate": 0.0002,
"loss": 2.1411,
"step": 382
},
{
"epoch": 0.65,
"learning_rate": 0.0002,
"loss": 2.2592,
"step": 384
},
{
"epoch": 0.65,
"learning_rate": 0.0002,
"loss": 2.0319,
"step": 386
},
{
"epoch": 0.65,
"learning_rate": 0.0002,
"loss": 2.1651,
"step": 388
},
{
"epoch": 0.66,
"learning_rate": 0.0002,
"loss": 2.0303,
"step": 390
},
{
"epoch": 0.66,
"learning_rate": 0.0002,
"loss": 2.2386,
"step": 392
},
{
"epoch": 0.66,
"learning_rate": 0.0002,
"loss": 2.2191,
"step": 394
},
{
"epoch": 0.67,
"learning_rate": 0.0002,
"loss": 2.2744,
"step": 396
},
{
"epoch": 0.67,
"learning_rate": 0.0002,
"loss": 2.0435,
"step": 398
},
{
"epoch": 0.67,
"learning_rate": 0.0002,
"loss": 1.8054,
"step": 400
},
{
"epoch": 0.68,
"learning_rate": 0.0002,
"loss": 2.2516,
"step": 402
},
{
"epoch": 0.68,
"learning_rate": 0.0002,
"loss": 2.3505,
"step": 404
},
{
"epoch": 0.68,
"learning_rate": 0.0002,
"loss": 2.3588,
"step": 406
},
{
"epoch": 0.69,
"learning_rate": 0.0002,
"loss": 2.3669,
"step": 408
},
{
"epoch": 0.69,
"learning_rate": 0.0002,
"loss": 2.2353,
"step": 410
},
{
"epoch": 0.69,
"learning_rate": 0.0002,
"loss": 2.4041,
"step": 412
},
{
"epoch": 0.7,
"learning_rate": 0.0002,
"loss": 2.1972,
"step": 414
},
{
"epoch": 0.7,
"learning_rate": 0.0002,
"loss": 2.3933,
"step": 416
},
{
"epoch": 0.7,
"learning_rate": 0.0002,
"loss": 2.303,
"step": 418
},
{
"epoch": 0.71,
"learning_rate": 0.0002,
"loss": 2.3503,
"step": 420
},
{
"epoch": 0.71,
"learning_rate": 0.0002,
"loss": 2.248,
"step": 422
},
{
"epoch": 0.71,
"learning_rate": 0.0002,
"loss": 2.2381,
"step": 424
},
{
"epoch": 0.72,
"learning_rate": 0.0002,
"loss": 2.2356,
"step": 426
},
{
"epoch": 0.72,
"learning_rate": 0.0002,
"loss": 2.2037,
"step": 428
},
{
"epoch": 0.72,
"learning_rate": 0.0002,
"loss": 2.1608,
"step": 430
},
{
"epoch": 0.73,
"learning_rate": 0.0002,
"loss": 2.25,
"step": 432
},
{
"epoch": 0.73,
"learning_rate": 0.0002,
"loss": 2.2222,
"step": 434
},
{
"epoch": 0.73,
"learning_rate": 0.0002,
"loss": 2.2497,
"step": 436
},
{
"epoch": 0.74,
"learning_rate": 0.0002,
"loss": 2.1431,
"step": 438
},
{
"epoch": 0.74,
"learning_rate": 0.0002,
"loss": 2.0895,
"step": 440
},
{
"epoch": 0.74,
"learning_rate": 0.0002,
"loss": 2.0663,
"step": 442
},
{
"epoch": 0.75,
"learning_rate": 0.0002,
"loss": 2.0556,
"step": 444
},
{
"epoch": 0.75,
"learning_rate": 0.0002,
"loss": 2.0243,
"step": 446
},
{
"epoch": 0.75,
"learning_rate": 0.0002,
"loss": 2.1532,
"step": 448
},
{
"epoch": 0.76,
"learning_rate": 0.0002,
"loss": 1.8696,
"step": 450
},
{
"epoch": 0.76,
"learning_rate": 0.0002,
"loss": 2.3663,
"step": 452
},
{
"epoch": 0.76,
"learning_rate": 0.0002,
"loss": 2.2396,
"step": 454
},
{
"epoch": 0.77,
"learning_rate": 0.0002,
"loss": 2.4401,
"step": 456
},
{
"epoch": 0.77,
"learning_rate": 0.0002,
"loss": 2.2978,
"step": 458
},
{
"epoch": 0.77,
"learning_rate": 0.0002,
"loss": 2.3494,
"step": 460
},
{
"epoch": 0.78,
"learning_rate": 0.0002,
"loss": 2.3713,
"step": 462
},
{
"epoch": 0.78,
"learning_rate": 0.0002,
"loss": 2.355,
"step": 464
},
{
"epoch": 0.78,
"learning_rate": 0.0002,
"loss": 2.1954,
"step": 466
},
{
"epoch": 0.79,
"learning_rate": 0.0002,
"loss": 2.2361,
"step": 468
},
{
"epoch": 0.79,
"learning_rate": 0.0002,
"loss": 2.2835,
"step": 470
},
{
"epoch": 0.79,
"learning_rate": 0.0002,
"loss": 2.2002,
"step": 472
},
{
"epoch": 0.8,
"learning_rate": 0.0002,
"loss": 2.1734,
"step": 474
},
{
"epoch": 0.8,
"learning_rate": 0.0002,
"loss": 2.175,
"step": 476
},
{
"epoch": 0.81,
"learning_rate": 0.0002,
"loss": 2.2539,
"step": 478
},
{
"epoch": 0.81,
"learning_rate": 0.0002,
"loss": 2.1933,
"step": 480
},
{
"epoch": 0.81,
"learning_rate": 0.0002,
"loss": 2.4237,
"step": 482
},
{
"epoch": 0.82,
"learning_rate": 0.0002,
"loss": 2.276,
"step": 484
},
{
"epoch": 0.82,
"learning_rate": 0.0002,
"loss": 2.1601,
"step": 486
},
{
"epoch": 0.82,
"learning_rate": 0.0002,
"loss": 1.9626,
"step": 488
},
{
"epoch": 0.83,
"learning_rate": 0.0002,
"loss": 1.9995,
"step": 490
},
{
"epoch": 0.83,
"learning_rate": 0.0002,
"loss": 2.1384,
"step": 492
},
{
"epoch": 0.83,
"learning_rate": 0.0002,
"loss": 2.1403,
"step": 494
},
{
"epoch": 0.84,
"learning_rate": 0.0002,
"loss": 2.2106,
"step": 496
},
{
"epoch": 0.84,
"learning_rate": 0.0002,
"loss": 2.1397,
"step": 498
},
{
"epoch": 0.84,
"learning_rate": 0.0002,
"loss": 1.8596,
"step": 500
},
{
"epoch": 0.85,
"learning_rate": 0.0002,
"loss": 2.2574,
"step": 502
},
{
"epoch": 0.85,
"learning_rate": 0.0002,
"loss": 2.4599,
"step": 504
},
{
"epoch": 0.85,
"learning_rate": 0.0002,
"loss": 2.4179,
"step": 506
},
{
"epoch": 0.86,
"learning_rate": 0.0002,
"loss": 2.4719,
"step": 508
},
{
"epoch": 0.86,
"learning_rate": 0.0002,
"loss": 2.3956,
"step": 510
},
{
"epoch": 0.86,
"learning_rate": 0.0002,
"loss": 2.2783,
"step": 512
},
{
"epoch": 0.87,
"learning_rate": 0.0002,
"loss": 2.1859,
"step": 514
},
{
"epoch": 0.87,
"learning_rate": 0.0002,
"loss": 2.2919,
"step": 516
},
{
"epoch": 0.87,
"learning_rate": 0.0002,
"loss": 2.3544,
"step": 518
},
{
"epoch": 0.88,
"learning_rate": 0.0002,
"loss": 2.2946,
"step": 520
},
{
"epoch": 0.88,
"learning_rate": 0.0002,
"loss": 2.2641,
"step": 522
},
{
"epoch": 0.88,
"learning_rate": 0.0002,
"loss": 2.3026,
"step": 524
},
{
"epoch": 0.89,
"learning_rate": 0.0002,
"loss": 2.303,
"step": 526
},
{
"epoch": 0.89,
"learning_rate": 0.0002,
"loss": 2.2672,
"step": 528
},
{
"epoch": 0.89,
"learning_rate": 0.0002,
"loss": 2.0322,
"step": 530
},
{
"epoch": 0.9,
"learning_rate": 0.0002,
"loss": 2.2123,
"step": 532
},
{
"epoch": 0.9,
"learning_rate": 0.0002,
"loss": 2.2045,
"step": 534
},
{
"epoch": 0.9,
"learning_rate": 0.0002,
"loss": 2.1314,
"step": 536
},
{
"epoch": 0.91,
"learning_rate": 0.0002,
"loss": 2.0978,
"step": 538
},
{
"epoch": 0.91,
"learning_rate": 0.0002,
"loss": 2.1141,
"step": 540
},
{
"epoch": 0.91,
"learning_rate": 0.0002,
"loss": 2.1792,
"step": 542
},
{
"epoch": 0.92,
"learning_rate": 0.0002,
"loss": 2.1708,
"step": 544
},
{
"epoch": 0.92,
"learning_rate": 0.0002,
"loss": 2.0571,
"step": 546
},
{
"epoch": 0.92,
"learning_rate": 0.0002,
"loss": 2.0905,
"step": 548
},
{
"epoch": 0.93,
"learning_rate": 0.0002,
"loss": 1.8878,
"step": 550
},
{
"epoch": 0.93,
"learning_rate": 0.0002,
"loss": 2.0614,
"step": 552
},
{
"epoch": 0.93,
"learning_rate": 0.0002,
"loss": 2.3649,
"step": 554
},
{
"epoch": 0.94,
"learning_rate": 0.0002,
"loss": 2.3329,
"step": 556
},
{
"epoch": 0.94,
"learning_rate": 0.0002,
"loss": 2.3081,
"step": 558
},
{
"epoch": 0.94,
"learning_rate": 0.0002,
"loss": 2.4556,
"step": 560
},
{
"epoch": 0.95,
"learning_rate": 0.0002,
"loss": 2.4235,
"step": 562
},
{
"epoch": 0.95,
"learning_rate": 0.0002,
"loss": 2.2311,
"step": 564
},
{
"epoch": 0.95,
"learning_rate": 0.0002,
"loss": 2.1851,
"step": 566
},
{
"epoch": 0.96,
"learning_rate": 0.0002,
"loss": 2.2639,
"step": 568
},
{
"epoch": 0.96,
"learning_rate": 0.0002,
"loss": 2.1752,
"step": 570
},
{
"epoch": 0.96,
"learning_rate": 0.0002,
"loss": 2.3004,
"step": 572
},
{
"epoch": 0.97,
"learning_rate": 0.0002,
"loss": 2.141,
"step": 574
},
{
"epoch": 0.97,
"learning_rate": 0.0002,
"loss": 2.3509,
"step": 576
},
{
"epoch": 0.97,
"learning_rate": 0.0002,
"loss": 2.1451,
"step": 578
},
{
"epoch": 0.98,
"learning_rate": 0.0002,
"loss": 2.1257,
"step": 580
},
{
"epoch": 0.98,
"learning_rate": 0.0002,
"loss": 2.1649,
"step": 582
},
{
"epoch": 0.98,
"learning_rate": 0.0002,
"loss": 2.0511,
"step": 584
},
{
"epoch": 0.99,
"learning_rate": 0.0002,
"loss": 2.1346,
"step": 586
},
{
"epoch": 0.99,
"learning_rate": 0.0002,
"loss": 2.0464,
"step": 588
},
{
"epoch": 0.99,
"learning_rate": 0.0002,
"loss": 2.0826,
"step": 590
},
{
"epoch": 1.0,
"learning_rate": 0.0002,
"loss": 2.0144,
"step": 592
}
],
"logging_steps": 2,
"max_steps": 593,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"total_flos": 1.5804852823891968e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}