pszemraj's picture
update ckpt with 4+ epochs of training at 1e-3
2fdd5b7
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.9971671388101981,
"global_step": 330,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 2.0736,
"step": 2
},
{
"epoch": 0.02,
"learning_rate": 0.0006,
"loss": 2.0741,
"step": 4
},
{
"epoch": 0.04,
"learning_rate": 0.0005999442811234004,
"loss": 2.098,
"step": 6
},
{
"epoch": 0.05,
"learning_rate": 0.0005997771451908898,
"loss": 2.0627,
"step": 8
},
{
"epoch": 0.06,
"learning_rate": 0.0005994986542866444,
"loss": 2.0418,
"step": 10
},
{
"epoch": 0.07,
"learning_rate": 0.0005991089118586658,
"loss": 2.0717,
"step": 12
},
{
"epoch": 0.08,
"learning_rate": 0.0005986080626803564,
"loss": 2.0504,
"step": 14
},
{
"epoch": 0.1,
"learning_rate": 0.0005979962927967394,
"loss": 2.0314,
"step": 16
},
{
"epoch": 0.11,
"learning_rate": 0.0005972738294553527,
"loss": 2.0568,
"step": 18
},
{
"epoch": 0.12,
"learning_rate": 0.0005964409410218346,
"loss": 2.073,
"step": 20
},
{
"epoch": 0.13,
"learning_rate": 0.0005954979368802377,
"loss": 2.0737,
"step": 22
},
{
"epoch": 0.15,
"learning_rate": 0.0005944451673181043,
"loss": 2.0936,
"step": 24
},
{
"epoch": 0.16,
"learning_rate": 0.0005932830233963502,
"loss": 2.0846,
"step": 26
},
{
"epoch": 0.17,
"learning_rate": 0.0005920119368040003,
"loss": 2.1374,
"step": 28
},
{
"epoch": 0.18,
"learning_rate": 0.0005906323796978346,
"loss": 2.0828,
"step": 30
},
{
"epoch": 0.19,
"learning_rate": 0.0005891448645270008,
"loss": 2.0802,
"step": 32
},
{
"epoch": 0.21,
"learning_rate": 0.0005875499438426604,
"loss": 2.147,
"step": 34
},
{
"epoch": 0.22,
"learning_rate": 0.0005858482100927391,
"loss": 2.0904,
"step": 36
},
{
"epoch": 0.23,
"learning_rate": 0.0005840402954018554,
"loss": 2.0823,
"step": 38
},
{
"epoch": 0.24,
"learning_rate": 0.0005821268713365129,
"loss": 2.0792,
"step": 40
},
{
"epoch": 0.25,
"learning_rate": 0.0005801086486556411,
"loss": 2.0716,
"step": 42
},
{
"epoch": 0.27,
"learning_rate": 0.0005779863770465765,
"loss": 2.2061,
"step": 44
},
{
"epoch": 0.28,
"learning_rate": 0.0005757608448465853,
"loss": 2.1735,
"step": 46
},
{
"epoch": 0.29,
"learning_rate": 0.0005734328787500274,
"loss": 2.098,
"step": 48
},
{
"epoch": 0.3,
"learning_rate": 0.000571003343501274,
"loss": 2.0977,
"step": 50
},
{
"epoch": 0.31,
"learning_rate": 0.0005684731415734899,
"loss": 2.1076,
"step": 52
},
{
"epoch": 0.33,
"learning_rate": 0.0005658432128334017,
"loss": 2.0476,
"step": 54
},
{
"epoch": 0.34,
"learning_rate": 0.0005631145341921755,
"loss": 2.0728,
"step": 56
},
{
"epoch": 0.35,
"learning_rate": 0.0005602881192425346,
"loss": 2.0477,
"step": 58
},
{
"epoch": 0.36,
"learning_rate": 0.000557365017882251,
"loss": 2.1102,
"step": 60
},
{
"epoch": 0.37,
"learning_rate": 0.0005543463159241515,
"loss": 2.0754,
"step": 62
},
{
"epoch": 0.39,
"learning_rate": 0.0005512331346927817,
"loss": 2.1029,
"step": 64
},
{
"epoch": 0.4,
"learning_rate": 0.0005480266306078807,
"loss": 1.9922,
"step": 66
},
{
"epoch": 0.41,
"learning_rate": 0.0005447279947548182,
"loss": 2.1599,
"step": 68
},
{
"epoch": 0.42,
"learning_rate": 0.0005413384524421545,
"loss": 2.1388,
"step": 70
},
{
"epoch": 0.44,
"learning_rate": 0.0005378592627464883,
"loss": 2.131,
"step": 72
},
{
"epoch": 0.45,
"learning_rate": 0.0005342917180447621,
"loss": 2.0658,
"step": 74
},
{
"epoch": 0.46,
"learning_rate": 0.0005306371435341955,
"loss": 2.1437,
"step": 76
},
{
"epoch": 0.47,
"learning_rate": 0.0005268968967400301,
"loss": 2.1145,
"step": 78
},
{
"epoch": 0.48,
"learning_rate": 0.0005230723670112627,
"loss": 2.1263,
"step": 80
},
{
"epoch": 0.5,
"learning_rate": 0.0005191649750045603,
"loss": 2.0513,
"step": 82
},
{
"epoch": 0.51,
"learning_rate": 0.000515176172156543,
"loss": 2.0723,
"step": 84
},
{
"epoch": 0.52,
"learning_rate": 0.0005111074401446355,
"loss": 2.0744,
"step": 86
},
{
"epoch": 0.53,
"learning_rate": 0.0005069602903366834,
"loss": 2.131,
"step": 88
},
{
"epoch": 0.54,
"learning_rate": 0.0005027362632295429,
"loss": 2.094,
"step": 90
},
{
"epoch": 0.56,
"learning_rate": 0.0004984369278768482,
"loss": 2.0633,
"step": 92
},
{
"epoch": 0.57,
"learning_rate": 0.0004940638813061723,
"loss": 2.1182,
"step": 94
},
{
"epoch": 0.58,
"learning_rate": 0.0004896187479257971,
"loss": 2.1664,
"step": 96
},
{
"epoch": 0.59,
"learning_rate": 0.0004851031789213108,
"loss": 2.1365,
"step": 98
},
{
"epoch": 0.6,
"learning_rate": 0.0004805188516422613,
"loss": 2.1204,
"step": 100
},
{
"epoch": 0.62,
"learning_rate": 0.00047586746897908803,
"loss": 2.0677,
"step": 102
},
{
"epoch": 0.63,
"learning_rate": 0.00047115075873056876,
"loss": 2.1588,
"step": 104
},
{
"epoch": 0.64,
"learning_rate": 0.0004663704729620119,
"loss": 2.0746,
"step": 106
},
{
"epoch": 0.65,
"learning_rate": 0.0004615283873544366,
"loss": 2.126,
"step": 108
},
{
"epoch": 0.66,
"learning_rate": 0.0004566263005449791,
"loss": 2.0786,
"step": 110
},
{
"epoch": 0.68,
"learning_rate": 0.0004516660334587729,
"loss": 2.1019,
"step": 112
},
{
"epoch": 0.69,
"learning_rate": 0.00044664942863254913,
"loss": 2.0605,
"step": 114
},
{
"epoch": 0.7,
"learning_rate": 0.0004415783495302096,
"loss": 2.0879,
"step": 116
},
{
"epoch": 0.71,
"learning_rate": 0.0004364546798506258,
"loss": 2.1516,
"step": 118
},
{
"epoch": 0.73,
"learning_rate": 0.0004312803228279218,
"loss": 2.1287,
"step": 120
},
{
"epoch": 0.74,
"learning_rate": 0.0004260572005245005,
"loss": 2.1054,
"step": 122
},
{
"epoch": 0.75,
"learning_rate": 0.00042078725311707585,
"loss": 2.0905,
"step": 124
},
{
"epoch": 0.76,
"learning_rate": 0.0004154724381759763,
"loss": 2.0875,
"step": 126
},
{
"epoch": 0.77,
"learning_rate": 0.0004101147299379876,
"loss": 2.0948,
"step": 128
},
{
"epoch": 0.79,
"learning_rate": 0.00040471611857300423,
"loss": 2.1521,
"step": 130
},
{
"epoch": 0.8,
"learning_rate": 0.0003992786094447625,
"loss": 2.0645,
"step": 132
},
{
"epoch": 0.81,
"learning_rate": 0.0003938042223659299,
"loss": 2.0953,
"step": 134
},
{
"epoch": 0.82,
"learning_rate": 0.0003882949908478272,
"loss": 2.1046,
"step": 136
},
{
"epoch": 0.83,
"learning_rate": 0.0003827529613450617,
"loss": 2.1814,
"step": 138
},
{
"epoch": 0.85,
"learning_rate": 0.0003771801924953534,
"loss": 2.1147,
"step": 140
},
{
"epoch": 0.86,
"learning_rate": 0.0003715787543548345,
"loss": 2.1226,
"step": 142
},
{
"epoch": 0.87,
"learning_rate": 0.0003659507276291087,
"loss": 2.1093,
"step": 144
},
{
"epoch": 0.88,
"learning_rate": 0.00036029820290035347,
"loss": 2.1038,
"step": 146
},
{
"epoch": 0.89,
"learning_rate": 0.0003546232798507543,
"loss": 2.0581,
"step": 148
},
{
"epoch": 0.91,
"learning_rate": 0.00034892806648255875,
"loss": 2.0076,
"step": 150
},
{
"epoch": 0.92,
"learning_rate": 0.0003432146783350393,
"loss": 2.1017,
"step": 152
},
{
"epoch": 0.93,
"learning_rate": 0.0003374852376986568,
"loss": 2.1353,
"step": 154
},
{
"epoch": 0.94,
"learning_rate": 0.00033174187282671686,
"loss": 2.0836,
"step": 156
},
{
"epoch": 0.95,
"learning_rate": 0.0003259867171448097,
"loss": 2.098,
"step": 158
},
{
"epoch": 0.97,
"learning_rate": 0.00032022190845833035,
"loss": 2.1308,
"step": 160
},
{
"epoch": 0.98,
"learning_rate": 0.0003144495881583712,
"loss": 2.1204,
"step": 162
},
{
"epoch": 0.99,
"learning_rate": 0.00030867190042628177,
"loss": 2.0564,
"step": 164
},
{
"epoch": 1.01,
"learning_rate": 0.0003028909914371942,
"loss": 2.5573,
"step": 166
},
{
"epoch": 1.02,
"learning_rate": 0.0002971090085628058,
"loss": 1.9576,
"step": 168
},
{
"epoch": 1.03,
"learning_rate": 0.00029132809957371823,
"loss": 1.9274,
"step": 170
},
{
"epoch": 1.04,
"learning_rate": 0.0002855504118416288,
"loss": 1.9637,
"step": 172
},
{
"epoch": 1.05,
"learning_rate": 0.0002797780915416696,
"loss": 1.9729,
"step": 174
},
{
"epoch": 1.07,
"learning_rate": 0.0002740132828551904,
"loss": 2.0254,
"step": 176
},
{
"epoch": 1.08,
"learning_rate": 0.00026825812717328314,
"loss": 1.9427,
"step": 178
},
{
"epoch": 1.09,
"learning_rate": 0.00026251476230134313,
"loss": 1.97,
"step": 180
},
{
"epoch": 1.1,
"learning_rate": 0.00025678532166496077,
"loss": 2.042,
"step": 182
},
{
"epoch": 1.11,
"learning_rate": 0.00025107193351744115,
"loss": 2.0033,
"step": 184
},
{
"epoch": 1.13,
"learning_rate": 0.0002453767201492457,
"loss": 1.9466,
"step": 186
},
{
"epoch": 1.14,
"learning_rate": 0.00023970179709964656,
"loss": 2.0294,
"step": 188
},
{
"epoch": 1.15,
"learning_rate": 0.0002340492723708912,
"loss": 2.0002,
"step": 190
},
{
"epoch": 1.16,
"learning_rate": 0.00022842124564516548,
"loss": 1.9686,
"step": 192
},
{
"epoch": 1.18,
"learning_rate": 0.0002228198075046467,
"loss": 2.0857,
"step": 194
},
{
"epoch": 1.19,
"learning_rate": 0.00021724703865493827,
"loss": 2.0111,
"step": 196
},
{
"epoch": 1.2,
"learning_rate": 0.00021170500915217283,
"loss": 2.0058,
"step": 198
},
{
"epoch": 1.21,
"learning_rate": 0.00020619577763407015,
"loss": 1.9725,
"step": 200
},
{
"epoch": 1.22,
"learning_rate": 0.0002007213905552375,
"loss": 2.0542,
"step": 202
},
{
"epoch": 1.24,
"learning_rate": 0.0001952838814269958,
"loss": 2.0265,
"step": 204
},
{
"epoch": 1.25,
"learning_rate": 0.00018988527006201237,
"loss": 2.1143,
"step": 206
},
{
"epoch": 1.26,
"learning_rate": 0.00018452756182402364,
"loss": 1.96,
"step": 208
},
{
"epoch": 1.27,
"learning_rate": 0.00017921274688292415,
"loss": 2.0181,
"step": 210
},
{
"epoch": 1.28,
"learning_rate": 0.00017394279947549948,
"loss": 1.9909,
"step": 212
},
{
"epoch": 1.3,
"learning_rate": 0.00016871967717207824,
"loss": 2.0021,
"step": 214
},
{
"epoch": 1.31,
"learning_rate": 0.00016354532014937418,
"loss": 1.9598,
"step": 216
},
{
"epoch": 1.32,
"learning_rate": 0.00015842165046979042,
"loss": 1.9433,
"step": 218
},
{
"epoch": 1.33,
"learning_rate": 0.0001533505713674509,
"loss": 2.0222,
"step": 220
},
{
"epoch": 1.34,
"learning_rate": 0.0001483339665412271,
"loss": 1.9898,
"step": 222
},
{
"epoch": 1.36,
"learning_rate": 0.00014337369945502084,
"loss": 2.0555,
"step": 224
},
{
"epoch": 1.37,
"learning_rate": 0.00013847161264556339,
"loss": 2.0082,
"step": 226
},
{
"epoch": 1.38,
"learning_rate": 0.000133629527037988,
"loss": 2.0081,
"step": 228
},
{
"epoch": 1.39,
"learning_rate": 0.00012884924126943122,
"loss": 2.0028,
"step": 230
},
{
"epoch": 1.4,
"learning_rate": 0.00012413253102091197,
"loss": 2.0535,
"step": 232
},
{
"epoch": 1.42,
"learning_rate": 0.00011948114835773868,
"loss": 1.9512,
"step": 234
},
{
"epoch": 1.43,
"learning_rate": 0.00011489682107868918,
"loss": 1.9141,
"step": 236
},
{
"epoch": 1.44,
"learning_rate": 0.00011038125207420298,
"loss": 2.0705,
"step": 238
},
{
"epoch": 1.45,
"learning_rate": 0.00010593611869382759,
"loss": 1.9869,
"step": 240
},
{
"epoch": 1.47,
"learning_rate": 0.0001015630721231517,
"loss": 1.9448,
"step": 242
},
{
"epoch": 1.48,
"learning_rate": 9.7263736770457e-05,
"loss": 1.9565,
"step": 244
},
{
"epoch": 1.49,
"learning_rate": 9.303970966331645e-05,
"loss": 1.9925,
"step": 246
},
{
"epoch": 1.5,
"learning_rate": 8.88925598553645e-05,
"loss": 1.995,
"step": 248
},
{
"epoch": 1.51,
"learning_rate": 8.482382784345695e-05,
"loss": 1.9627,
"step": 250
},
{
"epoch": 1.53,
"learning_rate": 8.083502499543967e-05,
"loss": 2.0096,
"step": 252
},
{
"epoch": 1.54,
"learning_rate": 7.692763298873725e-05,
"loss": 2.0731,
"step": 254
},
{
"epoch": 1.55,
"learning_rate": 7.310310325996986e-05,
"loss": 2.0134,
"step": 256
},
{
"epoch": 1.56,
"learning_rate": 6.936285646580441e-05,
"loss": 2.0516,
"step": 258
},
{
"epoch": 1.57,
"learning_rate": 6.570828195523786e-05,
"loss": 2.0061,
"step": 260
},
{
"epoch": 1.59,
"learning_rate": 6.214073725351162e-05,
"loss": 1.9709,
"step": 262
},
{
"epoch": 1.6,
"learning_rate": 5.8661547557845534e-05,
"loss": 2.03,
"step": 264
},
{
"epoch": 1.61,
"learning_rate": 5.5272005245181705e-05,
"loss": 1.9751,
"step": 266
},
{
"epoch": 1.62,
"learning_rate": 5.197336939211925e-05,
"loss": 2.0363,
"step": 268
},
{
"epoch": 1.63,
"learning_rate": 4.87668653072184e-05,
"loss": 2.0713,
"step": 270
},
{
"epoch": 1.65,
"learning_rate": 4.565368407584855e-05,
"loss": 2.021,
"step": 272
},
{
"epoch": 1.66,
"learning_rate": 4.2634982117748854e-05,
"loss": 1.9747,
"step": 274
},
{
"epoch": 1.67,
"learning_rate": 3.971188075746535e-05,
"loss": 2.0548,
"step": 276
},
{
"epoch": 1.68,
"learning_rate": 3.688546580782448e-05,
"loss": 1.9953,
"step": 278
},
{
"epoch": 1.69,
"learning_rate": 3.415678716659831e-05,
"loss": 1.9769,
"step": 280
},
{
"epoch": 1.71,
"learning_rate": 3.152685842651004e-05,
"loss": 2.0558,
"step": 282
},
{
"epoch": 1.72,
"learning_rate": 2.899665649872589e-05,
"loss": 2.047,
"step": 284
},
{
"epoch": 1.73,
"learning_rate": 2.6567121249972544e-05,
"loss": 2.0231,
"step": 286
},
{
"epoch": 1.74,
"learning_rate": 2.423915515341467e-05,
"loss": 2.0504,
"step": 288
},
{
"epoch": 1.76,
"learning_rate": 2.2013622953423405e-05,
"loss": 2.0075,
"step": 290
},
{
"epoch": 1.77,
"learning_rate": 1.9891351344358853e-05,
"loss": 2.0219,
"step": 292
},
{
"epoch": 1.78,
"learning_rate": 1.7873128663487047e-05,
"loss": 1.9923,
"step": 294
},
{
"epoch": 1.79,
"learning_rate": 1.5959704598144628e-05,
"loss": 2.0081,
"step": 296
},
{
"epoch": 1.8,
"learning_rate": 1.4151789907260846e-05,
"loss": 1.9971,
"step": 298
},
{
"epoch": 1.82,
"learning_rate": 1.2450056157339439e-05,
"loss": 1.9923,
"step": 300
},
{
"epoch": 1.83,
"learning_rate": 1.0855135472999155e-05,
"loss": 2.003,
"step": 302
},
{
"epoch": 1.84,
"learning_rate": 9.36762030216538e-06,
"loss": 2.0014,
"step": 304
},
{
"epoch": 1.85,
"learning_rate": 7.988063195999639e-06,
"loss": 2.0675,
"step": 306
},
{
"epoch": 1.86,
"learning_rate": 6.716976603649782e-06,
"loss": 1.9773,
"step": 308
},
{
"epoch": 1.88,
"learning_rate": 5.554832681895582e-06,
"loss": 1.997,
"step": 310
},
{
"epoch": 1.89,
"learning_rate": 4.5020631197623e-06,
"loss": 2.0323,
"step": 312
},
{
"epoch": 1.9,
"learning_rate": 3.559058978165319e-06,
"loss": 2.0221,
"step": 314
},
{
"epoch": 1.91,
"learning_rate": 2.7261705446473103e-06,
"loss": 1.9734,
"step": 316
},
{
"epoch": 1.92,
"learning_rate": 2.003707203260585e-06,
"loss": 1.9529,
"step": 318
},
{
"epoch": 1.94,
"learning_rate": 1.3919373196436213e-06,
"loss": 1.982,
"step": 320
},
{
"epoch": 1.95,
"learning_rate": 8.910881413340398e-07,
"loss": 2.0501,
"step": 322
},
{
"epoch": 1.96,
"learning_rate": 5.013457133556276e-07,
"loss": 2.0041,
"step": 324
},
{
"epoch": 1.97,
"learning_rate": 2.2285480911008457e-07,
"loss": 1.983,
"step": 326
},
{
"epoch": 1.99,
"learning_rate": 5.5718876599541995e-08,
"loss": 2.0002,
"step": 328
},
{
"epoch": 2.0,
"learning_rate": 0.0,
"loss": 2.0595,
"step": 330
},
{
"epoch": 2.0,
"step": 330,
"total_flos": 4.634629372945367e+17,
"train_loss": 2.053801321260857,
"train_runtime": 80029.5559,
"train_samples_per_second": 0.265,
"train_steps_per_second": 0.004
}
],
"max_steps": 330,
"num_train_epochs": 2,
"total_flos": 4.634629372945367e+17,
"trial_name": null,
"trial_params": null
}