atsuki-yamaguchi's picture
Upload folder using huggingface_hub
9c6afc6 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 521,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003838771593090211,
"grad_norm": 39.1374626159668,
"learning_rate": 3.7735849056603773e-06,
"loss": 5.6737,
"step": 2
},
{
"epoch": 0.007677543186180422,
"grad_norm": 24.925661087036133,
"learning_rate": 7.547169811320755e-06,
"loss": 5.612,
"step": 4
},
{
"epoch": 0.011516314779270634,
"grad_norm": 12.562352180480957,
"learning_rate": 1.1320754716981132e-05,
"loss": 5.0919,
"step": 6
},
{
"epoch": 0.015355086372360844,
"grad_norm": 7.011171817779541,
"learning_rate": 1.509433962264151e-05,
"loss": 4.6621,
"step": 8
},
{
"epoch": 0.019193857965451054,
"grad_norm": 5.962992191314697,
"learning_rate": 1.8867924528301888e-05,
"loss": 4.6095,
"step": 10
},
{
"epoch": 0.023032629558541268,
"grad_norm": 6.030173301696777,
"learning_rate": 2.2641509433962265e-05,
"loss": 4.6055,
"step": 12
},
{
"epoch": 0.026871401151631478,
"grad_norm": 5.021393775939941,
"learning_rate": 2.641509433962264e-05,
"loss": 4.2814,
"step": 14
},
{
"epoch": 0.030710172744721688,
"grad_norm": 4.441908359527588,
"learning_rate": 3.018867924528302e-05,
"loss": 4.2399,
"step": 16
},
{
"epoch": 0.0345489443378119,
"grad_norm": 3.59828782081604,
"learning_rate": 3.39622641509434e-05,
"loss": 4.1171,
"step": 18
},
{
"epoch": 0.03838771593090211,
"grad_norm": 3.9370954036712646,
"learning_rate": 3.7735849056603776e-05,
"loss": 4.1206,
"step": 20
},
{
"epoch": 0.04222648752399232,
"grad_norm": 2.9339046478271484,
"learning_rate": 4.150943396226415e-05,
"loss": 3.9446,
"step": 22
},
{
"epoch": 0.046065259117082535,
"grad_norm": 3.2044146060943604,
"learning_rate": 4.528301886792453e-05,
"loss": 3.7939,
"step": 24
},
{
"epoch": 0.04990403071017274,
"grad_norm": 3.1344337463378906,
"learning_rate": 4.9056603773584906e-05,
"loss": 3.7661,
"step": 26
},
{
"epoch": 0.053742802303262956,
"grad_norm": 2.632190704345703,
"learning_rate": 5.283018867924528e-05,
"loss": 3.7593,
"step": 28
},
{
"epoch": 0.05758157389635317,
"grad_norm": 2.875645399093628,
"learning_rate": 5.660377358490566e-05,
"loss": 3.458,
"step": 30
},
{
"epoch": 0.061420345489443376,
"grad_norm": 2.202479600906372,
"learning_rate": 6.037735849056604e-05,
"loss": 3.7317,
"step": 32
},
{
"epoch": 0.06525911708253358,
"grad_norm": 3.269009590148926,
"learning_rate": 6.415094339622641e-05,
"loss": 3.6346,
"step": 34
},
{
"epoch": 0.0690978886756238,
"grad_norm": 2.55442476272583,
"learning_rate": 6.79245283018868e-05,
"loss": 3.5382,
"step": 36
},
{
"epoch": 0.07293666026871401,
"grad_norm": 2.7956719398498535,
"learning_rate": 7.169811320754717e-05,
"loss": 3.6172,
"step": 38
},
{
"epoch": 0.07677543186180422,
"grad_norm": 2.430014133453369,
"learning_rate": 7.547169811320755e-05,
"loss": 3.4135,
"step": 40
},
{
"epoch": 0.08061420345489444,
"grad_norm": 2.5124785900115967,
"learning_rate": 7.924528301886794e-05,
"loss": 3.565,
"step": 42
},
{
"epoch": 0.08445297504798464,
"grad_norm": 2.733428955078125,
"learning_rate": 8.30188679245283e-05,
"loss": 3.4902,
"step": 44
},
{
"epoch": 0.08829174664107485,
"grad_norm": 2.421130657196045,
"learning_rate": 8.679245283018869e-05,
"loss": 3.4303,
"step": 46
},
{
"epoch": 0.09213051823416507,
"grad_norm": 2.4804866313934326,
"learning_rate": 9.056603773584906e-05,
"loss": 3.2669,
"step": 48
},
{
"epoch": 0.09596928982725528,
"grad_norm": 2.927652359008789,
"learning_rate": 9.433962264150944e-05,
"loss": 3.4791,
"step": 50
},
{
"epoch": 0.09980806142034548,
"grad_norm": 2.6607537269592285,
"learning_rate": 9.811320754716981e-05,
"loss": 3.5444,
"step": 52
},
{
"epoch": 0.1036468330134357,
"grad_norm": 2.635265827178955,
"learning_rate": 9.999974774092106e-05,
"loss": 3.2915,
"step": 54
},
{
"epoch": 0.10748560460652591,
"grad_norm": 2.650139093399048,
"learning_rate": 9.999772968356182e-05,
"loss": 3.3209,
"step": 56
},
{
"epoch": 0.11132437619961612,
"grad_norm": 3.0350704193115234,
"learning_rate": 9.999369365029487e-05,
"loss": 3.3741,
"step": 58
},
{
"epoch": 0.11516314779270634,
"grad_norm": 2.821930170059204,
"learning_rate": 9.998763980401998e-05,
"loss": 3.3345,
"step": 60
},
{
"epoch": 0.11900191938579655,
"grad_norm": 2.58774471282959,
"learning_rate": 9.997956838907852e-05,
"loss": 3.3121,
"step": 62
},
{
"epoch": 0.12284069097888675,
"grad_norm": 2.615741491317749,
"learning_rate": 9.996947973124372e-05,
"loss": 3.4007,
"step": 64
},
{
"epoch": 0.12667946257197696,
"grad_norm": 2.759786605834961,
"learning_rate": 9.995737423770745e-05,
"loss": 3.1918,
"step": 66
},
{
"epoch": 0.13051823416506717,
"grad_norm": 2.426225423812866,
"learning_rate": 9.994325239706377e-05,
"loss": 3.252,
"step": 68
},
{
"epoch": 0.1343570057581574,
"grad_norm": 2.713718891143799,
"learning_rate": 9.992711477928926e-05,
"loss": 3.125,
"step": 70
},
{
"epoch": 0.1381957773512476,
"grad_norm": 2.7484843730926514,
"learning_rate": 9.990896203571995e-05,
"loss": 3.361,
"step": 72
},
{
"epoch": 0.1420345489443378,
"grad_norm": 2.6632022857666016,
"learning_rate": 9.988879489902509e-05,
"loss": 3.2453,
"step": 74
},
{
"epoch": 0.14587332053742802,
"grad_norm": 2.7256522178649902,
"learning_rate": 9.986661418317759e-05,
"loss": 3.2655,
"step": 76
},
{
"epoch": 0.14971209213051823,
"grad_norm": 2.542839288711548,
"learning_rate": 9.984242078342107e-05,
"loss": 3.317,
"step": 78
},
{
"epoch": 0.15355086372360843,
"grad_norm": 2.6361520290374756,
"learning_rate": 9.981621567623385e-05,
"loss": 3.2138,
"step": 80
},
{
"epoch": 0.15738963531669867,
"grad_norm": 2.4558825492858887,
"learning_rate": 9.978799991928944e-05,
"loss": 3.2643,
"step": 82
},
{
"epoch": 0.16122840690978887,
"grad_norm": 2.361485719680786,
"learning_rate": 9.97577746514139e-05,
"loss": 3.2489,
"step": 84
},
{
"epoch": 0.16506717850287908,
"grad_norm": 2.5965819358825684,
"learning_rate": 9.972554109253989e-05,
"loss": 3.2573,
"step": 86
},
{
"epoch": 0.1689059500959693,
"grad_norm": 2.2212257385253906,
"learning_rate": 9.969130054365736e-05,
"loss": 3.1332,
"step": 88
},
{
"epoch": 0.1727447216890595,
"grad_norm": 2.350938320159912,
"learning_rate": 9.965505438676115e-05,
"loss": 3.1953,
"step": 90
},
{
"epoch": 0.1765834932821497,
"grad_norm": 2.1297547817230225,
"learning_rate": 9.961680408479507e-05,
"loss": 3.0385,
"step": 92
},
{
"epoch": 0.18042226487523993,
"grad_norm": 2.6407082080841064,
"learning_rate": 9.957655118159304e-05,
"loss": 3.1181,
"step": 94
},
{
"epoch": 0.18426103646833014,
"grad_norm": 2.049705982208252,
"learning_rate": 9.953429730181653e-05,
"loss": 3.1154,
"step": 96
},
{
"epoch": 0.18809980806142035,
"grad_norm": 2.397480010986328,
"learning_rate": 9.949004415088927e-05,
"loss": 3.1141,
"step": 98
},
{
"epoch": 0.19193857965451055,
"grad_norm": 2.1459343433380127,
"learning_rate": 9.944379351492818e-05,
"loss": 3.0847,
"step": 100
},
{
"epoch": 0.19577735124760076,
"grad_norm": 2.409905433654785,
"learning_rate": 9.939554726067141e-05,
"loss": 3.1939,
"step": 102
},
{
"epoch": 0.19961612284069097,
"grad_norm": 2.6216790676116943,
"learning_rate": 9.934530733540294e-05,
"loss": 3.1399,
"step": 104
},
{
"epoch": 0.2034548944337812,
"grad_norm": 2.3735368251800537,
"learning_rate": 9.929307576687403e-05,
"loss": 3.1325,
"step": 106
},
{
"epoch": 0.2072936660268714,
"grad_norm": 2.61091685295105,
"learning_rate": 9.923885466322135e-05,
"loss": 3.2417,
"step": 108
},
{
"epoch": 0.21113243761996162,
"grad_norm": 2.302191734313965,
"learning_rate": 9.918264621288187e-05,
"loss": 3.192,
"step": 110
},
{
"epoch": 0.21497120921305182,
"grad_norm": 2.6899170875549316,
"learning_rate": 9.912445268450458e-05,
"loss": 3.1271,
"step": 112
},
{
"epoch": 0.21880998080614203,
"grad_norm": 2.581143856048584,
"learning_rate": 9.906427642685889e-05,
"loss": 3.1607,
"step": 114
},
{
"epoch": 0.22264875239923224,
"grad_norm": 2.510422706604004,
"learning_rate": 9.900211986873985e-05,
"loss": 3.159,
"step": 116
},
{
"epoch": 0.22648752399232247,
"grad_norm": 2.3196523189544678,
"learning_rate": 9.89379855188701e-05,
"loss": 3.0774,
"step": 118
},
{
"epoch": 0.23032629558541268,
"grad_norm": 2.4071953296661377,
"learning_rate": 9.887187596579866e-05,
"loss": 3.0611,
"step": 120
},
{
"epoch": 0.23416506717850288,
"grad_norm": 2.733366012573242,
"learning_rate": 9.880379387779637e-05,
"loss": 3.0284,
"step": 122
},
{
"epoch": 0.2380038387715931,
"grad_norm": 2.3916118144989014,
"learning_rate": 9.873374200274826e-05,
"loss": 3.0748,
"step": 124
},
{
"epoch": 0.2418426103646833,
"grad_norm": 13.829148292541504,
"learning_rate": 9.866172316804266e-05,
"loss": 3.1429,
"step": 126
},
{
"epoch": 0.2456813819577735,
"grad_norm": 2.5056142807006836,
"learning_rate": 9.8587740280457e-05,
"loss": 2.9744,
"step": 128
},
{
"epoch": 0.2495201535508637,
"grad_norm": 2.326772689819336,
"learning_rate": 9.851179632604057e-05,
"loss": 3.136,
"step": 130
},
{
"epoch": 0.2533589251439539,
"grad_norm": 2.530068874359131,
"learning_rate": 9.843389436999396e-05,
"loss": 3.0951,
"step": 132
},
{
"epoch": 0.2571976967370441,
"grad_norm": 2.2792017459869385,
"learning_rate": 9.835403755654536e-05,
"loss": 3.1231,
"step": 134
},
{
"epoch": 0.26103646833013433,
"grad_norm": 2.3225743770599365,
"learning_rate": 9.827222910882358e-05,
"loss": 3.1742,
"step": 136
},
{
"epoch": 0.2648752399232246,
"grad_norm": 2.5904088020324707,
"learning_rate": 9.818847232872815e-05,
"loss": 3.0991,
"step": 138
},
{
"epoch": 0.2687140115163148,
"grad_norm": 2.1772799491882324,
"learning_rate": 9.81027705967958e-05,
"loss": 3.055,
"step": 140
},
{
"epoch": 0.272552783109405,
"grad_norm": 2.2711241245269775,
"learning_rate": 9.801512737206422e-05,
"loss": 3.1628,
"step": 142
},
{
"epoch": 0.2763915547024952,
"grad_norm": 2.514880895614624,
"learning_rate": 9.792554619193235e-05,
"loss": 2.9655,
"step": 144
},
{
"epoch": 0.2802303262955854,
"grad_norm": 2.381726026535034,
"learning_rate": 9.783403067201762e-05,
"loss": 2.9727,
"step": 146
},
{
"epoch": 0.2840690978886756,
"grad_norm": 2.410158395767212,
"learning_rate": 9.774058450601002e-05,
"loss": 3.114,
"step": 148
},
{
"epoch": 0.28790786948176583,
"grad_norm": 2.2826764583587646,
"learning_rate": 9.764521146552309e-05,
"loss": 3.0518,
"step": 150
},
{
"epoch": 0.29174664107485604,
"grad_norm": 2.6153564453125,
"learning_rate": 9.754791539994152e-05,
"loss": 3.0053,
"step": 152
},
{
"epoch": 0.29558541266794625,
"grad_norm": 2.96071195602417,
"learning_rate": 9.744870023626599e-05,
"loss": 2.9478,
"step": 154
},
{
"epoch": 0.29942418426103645,
"grad_norm": 2.3832027912139893,
"learning_rate": 9.734756997895448e-05,
"loss": 3.029,
"step": 156
},
{
"epoch": 0.30326295585412666,
"grad_norm": 2.4208216667175293,
"learning_rate": 9.724452870976085e-05,
"loss": 3.1009,
"step": 158
},
{
"epoch": 0.30710172744721687,
"grad_norm": 2.337291717529297,
"learning_rate": 9.713958058756985e-05,
"loss": 2.8477,
"step": 160
},
{
"epoch": 0.31094049904030713,
"grad_norm": 2.6344621181488037,
"learning_rate": 9.703272984822946e-05,
"loss": 3.079,
"step": 162
},
{
"epoch": 0.31477927063339733,
"grad_norm": 2.1119256019592285,
"learning_rate": 9.69239808043799e-05,
"loss": 2.9445,
"step": 164
},
{
"epoch": 0.31861804222648754,
"grad_norm": 2.3171935081481934,
"learning_rate": 9.681333784527944e-05,
"loss": 3.0269,
"step": 166
},
{
"epoch": 0.32245681381957775,
"grad_norm": 2.5069351196289062,
"learning_rate": 9.67008054366274e-05,
"loss": 2.9887,
"step": 168
},
{
"epoch": 0.32629558541266795,
"grad_norm": 2.182694673538208,
"learning_rate": 9.658638812038379e-05,
"loss": 3.104,
"step": 170
},
{
"epoch": 0.33013435700575816,
"grad_norm": 2.539505958557129,
"learning_rate": 9.647009051458604e-05,
"loss": 2.959,
"step": 172
},
{
"epoch": 0.33397312859884837,
"grad_norm": 2.111574649810791,
"learning_rate": 9.635191731316262e-05,
"loss": 2.9279,
"step": 174
},
{
"epoch": 0.3378119001919386,
"grad_norm": 2.2139837741851807,
"learning_rate": 9.623187328574357e-05,
"loss": 2.9781,
"step": 176
},
{
"epoch": 0.3416506717850288,
"grad_norm": 2.3730077743530273,
"learning_rate": 9.6109963277468e-05,
"loss": 2.9521,
"step": 178
},
{
"epoch": 0.345489443378119,
"grad_norm": 2.147397756576538,
"learning_rate": 9.598619220878853e-05,
"loss": 2.9534,
"step": 180
},
{
"epoch": 0.3493282149712092,
"grad_norm": 2.1337695121765137,
"learning_rate": 9.586056507527266e-05,
"loss": 2.9549,
"step": 182
},
{
"epoch": 0.3531669865642994,
"grad_norm": 2.397371530532837,
"learning_rate": 9.573308694740121e-05,
"loss": 2.9714,
"step": 184
},
{
"epoch": 0.3570057581573896,
"grad_norm": 2.208829164505005,
"learning_rate": 9.560376297036362e-05,
"loss": 2.9773,
"step": 186
},
{
"epoch": 0.36084452975047987,
"grad_norm": 2.0512075424194336,
"learning_rate": 9.547259836385031e-05,
"loss": 2.9261,
"step": 188
},
{
"epoch": 0.3646833013435701,
"grad_norm": 2.486699104309082,
"learning_rate": 9.533959842184195e-05,
"loss": 2.9401,
"step": 190
},
{
"epoch": 0.3685220729366603,
"grad_norm": 2.0567739009857178,
"learning_rate": 9.520476851239588e-05,
"loss": 3.0689,
"step": 192
},
{
"epoch": 0.3723608445297505,
"grad_norm": 2.1673007011413574,
"learning_rate": 9.506811407742937e-05,
"loss": 3.022,
"step": 194
},
{
"epoch": 0.3761996161228407,
"grad_norm": 2.1367907524108887,
"learning_rate": 9.492964063250001e-05,
"loss": 2.89,
"step": 196
},
{
"epoch": 0.3800383877159309,
"grad_norm": 2.0380022525787354,
"learning_rate": 9.478935376658307e-05,
"loss": 2.9577,
"step": 198
},
{
"epoch": 0.3838771593090211,
"grad_norm": 2.535660743713379,
"learning_rate": 9.4647259141846e-05,
"loss": 2.9808,
"step": 200
},
{
"epoch": 0.3877159309021113,
"grad_norm": 2.2464702129364014,
"learning_rate": 9.450336249341976e-05,
"loss": 3.0819,
"step": 202
},
{
"epoch": 0.3915547024952015,
"grad_norm": 2.316953659057617,
"learning_rate": 9.435766962916748e-05,
"loss": 2.9961,
"step": 204
},
{
"epoch": 0.39539347408829173,
"grad_norm": 2.124931573867798,
"learning_rate": 9.421018642944997e-05,
"loss": 2.9755,
"step": 206
},
{
"epoch": 0.39923224568138194,
"grad_norm": 2.299165964126587,
"learning_rate": 9.406091884688836e-05,
"loss": 2.9174,
"step": 208
},
{
"epoch": 0.40307101727447214,
"grad_norm": 2.156485080718994,
"learning_rate": 9.390987290612395e-05,
"loss": 2.9381,
"step": 210
},
{
"epoch": 0.4069097888675624,
"grad_norm": 2.207650899887085,
"learning_rate": 9.375705470357493e-05,
"loss": 2.893,
"step": 212
},
{
"epoch": 0.4107485604606526,
"grad_norm": 2.3216702938079834,
"learning_rate": 9.360247040719039e-05,
"loss": 2.9004,
"step": 214
},
{
"epoch": 0.4145873320537428,
"grad_norm": 2.2900643348693848,
"learning_rate": 9.344612625620132e-05,
"loss": 2.9238,
"step": 216
},
{
"epoch": 0.418426103646833,
"grad_norm": 2.157139539718628,
"learning_rate": 9.32880285608689e-05,
"loss": 2.8885,
"step": 218
},
{
"epoch": 0.42226487523992323,
"grad_norm": 2.0238444805145264,
"learning_rate": 9.312818370222962e-05,
"loss": 2.8743,
"step": 220
},
{
"epoch": 0.42610364683301344,
"grad_norm": 2.537557363510132,
"learning_rate": 9.296659813183794e-05,
"loss": 2.9497,
"step": 222
},
{
"epoch": 0.42994241842610365,
"grad_norm": 2.218683958053589,
"learning_rate": 9.280327837150571e-05,
"loss": 2.9384,
"step": 224
},
{
"epoch": 0.43378119001919385,
"grad_norm": 1.8829752206802368,
"learning_rate": 9.26382310130391e-05,
"loss": 2.9037,
"step": 226
},
{
"epoch": 0.43761996161228406,
"grad_norm": 2.2257378101348877,
"learning_rate": 9.247146271797245e-05,
"loss": 2.9468,
"step": 228
},
{
"epoch": 0.44145873320537427,
"grad_norm": 1.9686921834945679,
"learning_rate": 9.23029802172994e-05,
"loss": 2.8394,
"step": 230
},
{
"epoch": 0.44529750479846447,
"grad_norm": 2.367706298828125,
"learning_rate": 9.213279031120129e-05,
"loss": 2.7104,
"step": 232
},
{
"epoch": 0.4491362763915547,
"grad_norm": 2.439753532409668,
"learning_rate": 9.19608998687726e-05,
"loss": 2.9991,
"step": 234
},
{
"epoch": 0.45297504798464494,
"grad_norm": 1.997983694076538,
"learning_rate": 9.178731582774381e-05,
"loss": 2.887,
"step": 236
},
{
"epoch": 0.45681381957773515,
"grad_norm": 2.371289014816284,
"learning_rate": 9.161204519420126e-05,
"loss": 2.8716,
"step": 238
},
{
"epoch": 0.46065259117082535,
"grad_norm": 1.9359811544418335,
"learning_rate": 9.143509504230449e-05,
"loss": 2.952,
"step": 240
},
{
"epoch": 0.46449136276391556,
"grad_norm": 2.3096532821655273,
"learning_rate": 9.125647251400067e-05,
"loss": 2.84,
"step": 242
},
{
"epoch": 0.46833013435700577,
"grad_norm": 2.2196881771087646,
"learning_rate": 9.107618481873632e-05,
"loss": 2.8153,
"step": 244
},
{
"epoch": 0.472168905950096,
"grad_norm": 1.984487533569336,
"learning_rate": 9.089423923316636e-05,
"loss": 2.9233,
"step": 246
},
{
"epoch": 0.4760076775431862,
"grad_norm": 2.1207079887390137,
"learning_rate": 9.07106431008604e-05,
"loss": 2.7975,
"step": 248
},
{
"epoch": 0.4798464491362764,
"grad_norm": 1.9502159357070923,
"learning_rate": 9.052540383200633e-05,
"loss": 2.7933,
"step": 250
},
{
"epoch": 0.4836852207293666,
"grad_norm": 2.3264806270599365,
"learning_rate": 9.033852890311128e-05,
"loss": 2.948,
"step": 252
},
{
"epoch": 0.4875239923224568,
"grad_norm": 2.3154518604278564,
"learning_rate": 9.01500258566998e-05,
"loss": 2.8546,
"step": 254
},
{
"epoch": 0.491362763915547,
"grad_norm": 2.2312159538269043,
"learning_rate": 8.995990230100949e-05,
"loss": 2.8168,
"step": 256
},
{
"epoch": 0.4952015355086372,
"grad_norm": 2.6638643741607666,
"learning_rate": 8.976816590968387e-05,
"loss": 2.9337,
"step": 258
},
{
"epoch": 0.4990403071017274,
"grad_norm": 2.1371665000915527,
"learning_rate": 8.957482442146272e-05,
"loss": 2.8714,
"step": 260
},
{
"epoch": 0.5028790786948176,
"grad_norm": 1.9727420806884766,
"learning_rate": 8.937988563986963e-05,
"loss": 2.7677,
"step": 262
},
{
"epoch": 0.5067178502879078,
"grad_norm": 2.2152533531188965,
"learning_rate": 8.918335743289718e-05,
"loss": 2.9224,
"step": 264
},
{
"epoch": 0.510556621880998,
"grad_norm": 2.115664005279541,
"learning_rate": 8.898524773268926e-05,
"loss": 2.8969,
"step": 266
},
{
"epoch": 0.5143953934740882,
"grad_norm": 2.238097667694092,
"learning_rate": 8.8785564535221e-05,
"loss": 2.8914,
"step": 268
},
{
"epoch": 0.5182341650671785,
"grad_norm": 2.088069200515747,
"learning_rate": 8.858431589997597e-05,
"loss": 2.841,
"step": 270
},
{
"epoch": 0.5220729366602687,
"grad_norm": 2.0779953002929688,
"learning_rate": 8.838150994962093e-05,
"loss": 2.9019,
"step": 272
},
{
"epoch": 0.525911708253359,
"grad_norm": 2.2514681816101074,
"learning_rate": 8.817715486967803e-05,
"loss": 2.9179,
"step": 274
},
{
"epoch": 0.5297504798464492,
"grad_norm": 2.3873977661132812,
"learning_rate": 8.797125890819428e-05,
"loss": 2.8158,
"step": 276
},
{
"epoch": 0.5335892514395394,
"grad_norm": 1.8718311786651611,
"learning_rate": 8.776383037540888e-05,
"loss": 2.8838,
"step": 278
},
{
"epoch": 0.5374280230326296,
"grad_norm": 1.7923882007598877,
"learning_rate": 8.755487764341757e-05,
"loss": 2.8069,
"step": 280
},
{
"epoch": 0.5412667946257198,
"grad_norm": 2.197343587875366,
"learning_rate": 8.734440914583486e-05,
"loss": 2.8006,
"step": 282
},
{
"epoch": 0.54510556621881,
"grad_norm": 1.9336212873458862,
"learning_rate": 8.713243337745365e-05,
"loss": 2.8515,
"step": 284
},
{
"epoch": 0.5489443378119002,
"grad_norm": 2.2000906467437744,
"learning_rate": 8.691895889390227e-05,
"loss": 2.8156,
"step": 286
},
{
"epoch": 0.5527831094049904,
"grad_norm": 1.9124946594238281,
"learning_rate": 8.670399431129926e-05,
"loss": 2.6808,
"step": 288
},
{
"epoch": 0.5566218809980806,
"grad_norm": 2.50055193901062,
"learning_rate": 8.648754830590552e-05,
"loss": 2.9538,
"step": 290
},
{
"epoch": 0.5604606525911708,
"grad_norm": 2.0405330657958984,
"learning_rate": 8.626962961377423e-05,
"loss": 2.9034,
"step": 292
},
{
"epoch": 0.564299424184261,
"grad_norm": 2.101141929626465,
"learning_rate": 8.605024703039816e-05,
"loss": 2.8311,
"step": 294
},
{
"epoch": 0.5681381957773513,
"grad_norm": 1.957920789718628,
"learning_rate": 8.582940941035476e-05,
"loss": 2.8421,
"step": 296
},
{
"epoch": 0.5719769673704415,
"grad_norm": 2.24116849899292,
"learning_rate": 8.560712566694862e-05,
"loss": 2.9505,
"step": 298
},
{
"epoch": 0.5758157389635317,
"grad_norm": 2.053492546081543,
"learning_rate": 8.538340477185192e-05,
"loss": 2.8465,
"step": 300
},
{
"epoch": 0.5796545105566219,
"grad_norm": 2.3354341983795166,
"learning_rate": 8.515825575474221e-05,
"loss": 2.8588,
"step": 302
},
{
"epoch": 0.5834932821497121,
"grad_norm": 2.1598827838897705,
"learning_rate": 8.493168770293792e-05,
"loss": 2.8756,
"step": 304
},
{
"epoch": 0.5873320537428023,
"grad_norm": 2.1858606338500977,
"learning_rate": 8.47037097610317e-05,
"loss": 2.8049,
"step": 306
},
{
"epoch": 0.5911708253358925,
"grad_norm": 2.0640292167663574,
"learning_rate": 8.447433113052123e-05,
"loss": 2.8209,
"step": 308
},
{
"epoch": 0.5950095969289827,
"grad_norm": 2.2367477416992188,
"learning_rate": 8.42435610694379e-05,
"loss": 2.8078,
"step": 310
},
{
"epoch": 0.5988483685220729,
"grad_norm": 2.088447093963623,
"learning_rate": 8.401140889197305e-05,
"loss": 2.7268,
"step": 312
},
{
"epoch": 0.6026871401151631,
"grad_norm": 2.095773458480835,
"learning_rate": 8.377788396810223e-05,
"loss": 2.7654,
"step": 314
},
{
"epoch": 0.6065259117082533,
"grad_norm": 2.2851994037628174,
"learning_rate": 8.354299572320679e-05,
"loss": 2.7514,
"step": 316
},
{
"epoch": 0.6103646833013435,
"grad_norm": 1.7963942289352417,
"learning_rate": 8.330675363769356e-05,
"loss": 2.8477,
"step": 318
},
{
"epoch": 0.6142034548944337,
"grad_norm": 2.051821708679199,
"learning_rate": 8.306916724661224e-05,
"loss": 2.7684,
"step": 320
},
{
"epoch": 0.6180422264875239,
"grad_norm": 2.041626214981079,
"learning_rate": 8.283024613927054e-05,
"loss": 2.7836,
"step": 322
},
{
"epoch": 0.6218809980806143,
"grad_norm": 2.3092660903930664,
"learning_rate": 8.258999995884705e-05,
"loss": 2.722,
"step": 324
},
{
"epoch": 0.6257197696737045,
"grad_norm": 2.1960623264312744,
"learning_rate": 8.234843840200217e-05,
"loss": 2.7858,
"step": 326
},
{
"epoch": 0.6295585412667947,
"grad_norm": 1.9009817838668823,
"learning_rate": 8.210557121848663e-05,
"loss": 2.7208,
"step": 328
},
{
"epoch": 0.6333973128598849,
"grad_norm": 2.1019928455352783,
"learning_rate": 8.186140821074801e-05,
"loss": 2.9432,
"step": 330
},
{
"epoch": 0.6372360844529751,
"grad_norm": 1.9978450536727905,
"learning_rate": 8.161595923353516e-05,
"loss": 2.8016,
"step": 332
},
{
"epoch": 0.6410748560460653,
"grad_norm": 2.3676860332489014,
"learning_rate": 8.136923419350031e-05,
"loss": 2.8101,
"step": 334
},
{
"epoch": 0.6449136276391555,
"grad_norm": 2.006544589996338,
"learning_rate": 8.112124304879937e-05,
"loss": 2.7789,
"step": 336
},
{
"epoch": 0.6487523992322457,
"grad_norm": 2.0482800006866455,
"learning_rate": 8.087199580868996e-05,
"loss": 2.7815,
"step": 338
},
{
"epoch": 0.6525911708253359,
"grad_norm": 2.2319834232330322,
"learning_rate": 8.062150253312735e-05,
"loss": 2.8728,
"step": 340
},
{
"epoch": 0.6564299424184261,
"grad_norm": 3.3775405883789062,
"learning_rate": 8.03697733323585e-05,
"loss": 2.814,
"step": 342
},
{
"epoch": 0.6602687140115163,
"grad_norm": 2.242619514465332,
"learning_rate": 8.011681836651402e-05,
"loss": 2.8066,
"step": 344
},
{
"epoch": 0.6641074856046065,
"grad_norm": 2.016690254211426,
"learning_rate": 7.986264784519801e-05,
"loss": 2.7449,
"step": 346
},
{
"epoch": 0.6679462571976967,
"grad_norm": 2.1939826011657715,
"learning_rate": 7.960727202707605e-05,
"loss": 2.8091,
"step": 348
},
{
"epoch": 0.6717850287907869,
"grad_norm": 3.5264973640441895,
"learning_rate": 7.935070121946115e-05,
"loss": 2.8325,
"step": 350
},
{
"epoch": 0.6756238003838771,
"grad_norm": 2.000185489654541,
"learning_rate": 7.909294577789766e-05,
"loss": 2.789,
"step": 352
},
{
"epoch": 0.6794625719769674,
"grad_norm": 2.2280194759368896,
"learning_rate": 7.883401610574336e-05,
"loss": 2.8581,
"step": 354
},
{
"epoch": 0.6833013435700576,
"grad_norm": 1.8479573726654053,
"learning_rate": 7.857392265374963e-05,
"loss": 2.8131,
"step": 356
},
{
"epoch": 0.6871401151631478,
"grad_norm": 2.1635046005249023,
"learning_rate": 7.83126759196395e-05,
"loss": 2.8089,
"step": 358
},
{
"epoch": 0.690978886756238,
"grad_norm": 2.1297736167907715,
"learning_rate": 7.805028644768407e-05,
"loss": 2.8082,
"step": 360
},
{
"epoch": 0.6948176583493282,
"grad_norm": 1.9042068719863892,
"learning_rate": 7.778676482827686e-05,
"loss": 2.8027,
"step": 362
},
{
"epoch": 0.6986564299424184,
"grad_norm": 1.8313944339752197,
"learning_rate": 7.752212169750641e-05,
"loss": 2.8438,
"step": 364
},
{
"epoch": 0.7024952015355086,
"grad_norm": 2.036674976348877,
"learning_rate": 7.725636773672693e-05,
"loss": 2.8047,
"step": 366
},
{
"epoch": 0.7063339731285988,
"grad_norm": 2.086843490600586,
"learning_rate": 7.69895136721273e-05,
"loss": 2.6723,
"step": 368
},
{
"epoch": 0.710172744721689,
"grad_norm": 2.046743154525757,
"learning_rate": 7.672157027429803e-05,
"loss": 2.7864,
"step": 370
},
{
"epoch": 0.7140115163147792,
"grad_norm": 2.1428844928741455,
"learning_rate": 7.645254835779657e-05,
"loss": 2.841,
"step": 372
},
{
"epoch": 0.7178502879078695,
"grad_norm": 2.015566825866699,
"learning_rate": 7.618245878071091e-05,
"loss": 2.8675,
"step": 374
},
{
"epoch": 0.7216890595009597,
"grad_norm": 2.0343127250671387,
"learning_rate": 7.591131244422118e-05,
"loss": 2.8092,
"step": 376
},
{
"epoch": 0.72552783109405,
"grad_norm": 1.9547837972640991,
"learning_rate": 7.563912029215983e-05,
"loss": 2.7245,
"step": 378
},
{
"epoch": 0.7293666026871402,
"grad_norm": 1.8891335725784302,
"learning_rate": 7.536589331056976e-05,
"loss": 2.8459,
"step": 380
},
{
"epoch": 0.7332053742802304,
"grad_norm": 2.191988706588745,
"learning_rate": 7.509164252726107e-05,
"loss": 2.8502,
"step": 382
},
{
"epoch": 0.7370441458733206,
"grad_norm": 1.8953111171722412,
"learning_rate": 7.481637901136577e-05,
"loss": 2.7664,
"step": 384
},
{
"epoch": 0.7408829174664108,
"grad_norm": 1.8514469861984253,
"learning_rate": 7.454011387289127e-05,
"loss": 2.7179,
"step": 386
},
{
"epoch": 0.744721689059501,
"grad_norm": 1.9623198509216309,
"learning_rate": 7.42628582622717e-05,
"loss": 2.65,
"step": 388
},
{
"epoch": 0.7485604606525912,
"grad_norm": 1.9796512126922607,
"learning_rate": 7.398462336991801e-05,
"loss": 2.6551,
"step": 390
},
{
"epoch": 0.7523992322456814,
"grad_norm": 1.9456619024276733,
"learning_rate": 7.370542042576634e-05,
"loss": 2.7129,
"step": 392
},
{
"epoch": 0.7562380038387716,
"grad_norm": 2.237915277481079,
"learning_rate": 7.342526069882465e-05,
"loss": 2.8557,
"step": 394
},
{
"epoch": 0.7600767754318618,
"grad_norm": 1.9474000930786133,
"learning_rate": 7.314415549671795e-05,
"loss": 2.8152,
"step": 396
},
{
"epoch": 0.763915547024952,
"grad_norm": 2.2595555782318115,
"learning_rate": 7.286211616523193e-05,
"loss": 2.8161,
"step": 398
},
{
"epoch": 0.7677543186180422,
"grad_norm": 2.072669267654419,
"learning_rate": 7.257915408785498e-05,
"loss": 2.8623,
"step": 400
},
{
"epoch": 0.7715930902111324,
"grad_norm": 2.018782138824463,
"learning_rate": 7.229528068531882e-05,
"loss": 2.7831,
"step": 402
},
{
"epoch": 0.7754318618042226,
"grad_norm": 1.9737513065338135,
"learning_rate": 7.201050741513736e-05,
"loss": 2.6135,
"step": 404
},
{
"epoch": 0.7792706333973128,
"grad_norm": 1.8319437503814697,
"learning_rate": 7.17248457711445e-05,
"loss": 2.783,
"step": 406
},
{
"epoch": 0.783109404990403,
"grad_norm": 1.8370659351348877,
"learning_rate": 7.14383072830301e-05,
"loss": 2.7643,
"step": 408
},
{
"epoch": 0.7869481765834933,
"grad_norm": 2.0122272968292236,
"learning_rate": 7.115090351587454e-05,
"loss": 2.7853,
"step": 410
},
{
"epoch": 0.7907869481765835,
"grad_norm": 2.0002529621124268,
"learning_rate": 7.086264606968214e-05,
"loss": 2.7595,
"step": 412
},
{
"epoch": 0.7946257197696737,
"grad_norm": 2.0362918376922607,
"learning_rate": 7.05735465789128e-05,
"loss": 2.9258,
"step": 414
},
{
"epoch": 0.7984644913627639,
"grad_norm": 2.0595998764038086,
"learning_rate": 7.028361671201245e-05,
"loss": 2.7771,
"step": 416
},
{
"epoch": 0.8023032629558541,
"grad_norm": 2.0576417446136475,
"learning_rate": 6.99928681709422e-05,
"loss": 2.7221,
"step": 418
},
{
"epoch": 0.8061420345489443,
"grad_norm": 1.9781322479248047,
"learning_rate": 6.970131269070592e-05,
"loss": 2.8678,
"step": 420
},
{
"epoch": 0.8099808061420346,
"grad_norm": 2.429964780807495,
"learning_rate": 6.940896203887659e-05,
"loss": 2.7395,
"step": 422
},
{
"epoch": 0.8138195777351248,
"grad_norm": 2.1173887252807617,
"learning_rate": 6.911582801512147e-05,
"loss": 2.8196,
"step": 424
},
{
"epoch": 0.817658349328215,
"grad_norm": 2.0920073986053467,
"learning_rate": 6.882192245072569e-05,
"loss": 2.7426,
"step": 426
},
{
"epoch": 0.8214971209213052,
"grad_norm": 1.986169695854187,
"learning_rate": 6.852725720811488e-05,
"loss": 2.7175,
"step": 428
},
{
"epoch": 0.8253358925143954,
"grad_norm": 1.837952733039856,
"learning_rate": 6.823184418037624e-05,
"loss": 2.7456,
"step": 430
},
{
"epoch": 0.8291746641074856,
"grad_norm": 2.084582567214966,
"learning_rate": 6.793569529077864e-05,
"loss": 2.6918,
"step": 432
},
{
"epoch": 0.8330134357005758,
"grad_norm": 1.9959920644760132,
"learning_rate": 6.76388224922913e-05,
"loss": 2.7062,
"step": 434
},
{
"epoch": 0.836852207293666,
"grad_norm": 2.0004842281341553,
"learning_rate": 6.734123776710137e-05,
"loss": 2.7469,
"step": 436
},
{
"epoch": 0.8406909788867563,
"grad_norm": 2.0607264041900635,
"learning_rate": 6.704295312613037e-05,
"loss": 2.6908,
"step": 438
},
{
"epoch": 0.8445297504798465,
"grad_norm": 1.8044137954711914,
"learning_rate": 6.674398060854931e-05,
"loss": 2.7281,
"step": 440
},
{
"epoch": 0.8483685220729367,
"grad_norm": 1.741652488708496,
"learning_rate": 6.644433228129287e-05,
"loss": 2.7622,
"step": 442
},
{
"epoch": 0.8522072936660269,
"grad_norm": 2.165587902069092,
"learning_rate": 6.614402023857232e-05,
"loss": 2.8081,
"step": 444
},
{
"epoch": 0.8560460652591171,
"grad_norm": 1.9901096820831299,
"learning_rate": 6.584305660138734e-05,
"loss": 2.8187,
"step": 446
},
{
"epoch": 0.8598848368522073,
"grad_norm": 1.9680149555206299,
"learning_rate": 6.554145351703689e-05,
"loss": 2.7813,
"step": 448
},
{
"epoch": 0.8637236084452975,
"grad_norm": 2.150981903076172,
"learning_rate": 6.523922315862887e-05,
"loss": 2.6663,
"step": 450
},
{
"epoch": 0.8675623800383877,
"grad_norm": 2.4717190265655518,
"learning_rate": 6.493637772458879e-05,
"loss": 2.7571,
"step": 452
},
{
"epoch": 0.8714011516314779,
"grad_norm": 2.0950613021850586,
"learning_rate": 6.463292943816746e-05,
"loss": 2.8617,
"step": 454
},
{
"epoch": 0.8752399232245681,
"grad_norm": 1.7509244680404663,
"learning_rate": 6.432889054694764e-05,
"loss": 2.7157,
"step": 456
},
{
"epoch": 0.8790786948176583,
"grad_norm": 3.837655544281006,
"learning_rate": 6.402427332234965e-05,
"loss": 2.6557,
"step": 458
},
{
"epoch": 0.8829174664107485,
"grad_norm": 1.9463653564453125,
"learning_rate": 6.371909005913618e-05,
"loss": 2.7937,
"step": 460
},
{
"epoch": 0.8867562380038387,
"grad_norm": 1.785074234008789,
"learning_rate": 6.341335307491595e-05,
"loss": 2.7041,
"step": 462
},
{
"epoch": 0.8905950095969289,
"grad_norm": 2.044428586959839,
"learning_rate": 6.310707470964668e-05,
"loss": 2.7131,
"step": 464
},
{
"epoch": 0.8944337811900192,
"grad_norm": 2.0175092220306396,
"learning_rate": 6.280026732513689e-05,
"loss": 2.6959,
"step": 466
},
{
"epoch": 0.8982725527831094,
"grad_norm": 1.9430804252624512,
"learning_rate": 6.249294330454705e-05,
"loss": 2.7563,
"step": 468
},
{
"epoch": 0.9021113243761996,
"grad_norm": 1.999422311782837,
"learning_rate": 6.21851150518898e-05,
"loss": 2.7608,
"step": 470
},
{
"epoch": 0.9059500959692899,
"grad_norm": 2.7273123264312744,
"learning_rate": 6.187679499152919e-05,
"loss": 2.7552,
"step": 472
},
{
"epoch": 0.9097888675623801,
"grad_norm": 1.9456199407577515,
"learning_rate": 6.15679955676794e-05,
"loss": 2.689,
"step": 474
},
{
"epoch": 0.9136276391554703,
"grad_norm": 1.8011109828948975,
"learning_rate": 6.125872924390226e-05,
"loss": 2.6342,
"step": 476
},
{
"epoch": 0.9174664107485605,
"grad_norm": 1.790582299232483,
"learning_rate": 6.094900850260439e-05,
"loss": 2.7611,
"step": 478
},
{
"epoch": 0.9213051823416507,
"grad_norm": 2.047144889831543,
"learning_rate": 6.0638845844533254e-05,
"loss": 2.7965,
"step": 480
},
{
"epoch": 0.9251439539347409,
"grad_norm": 1.7579201459884644,
"learning_rate": 6.032825378827273e-05,
"loss": 2.7516,
"step": 482
},
{
"epoch": 0.9289827255278311,
"grad_norm": 1.806973934173584,
"learning_rate": 6.0017244869737746e-05,
"loss": 2.7111,
"step": 484
},
{
"epoch": 0.9328214971209213,
"grad_norm": 1.781657099723816,
"learning_rate": 5.970583164166838e-05,
"loss": 2.7412,
"step": 486
},
{
"epoch": 0.9366602687140115,
"grad_norm": 1.904548168182373,
"learning_rate": 5.9394026673123157e-05,
"loss": 2.7388,
"step": 488
},
{
"epoch": 0.9404990403071017,
"grad_norm": 1.8767707347869873,
"learning_rate": 5.908184254897182e-05,
"loss": 2.694,
"step": 490
},
{
"epoch": 0.944337811900192,
"grad_norm": 1.9801278114318848,
"learning_rate": 5.8769291869387335e-05,
"loss": 2.7866,
"step": 492
},
{
"epoch": 0.9481765834932822,
"grad_norm": 2.026012897491455,
"learning_rate": 5.845638724933728e-05,
"loss": 2.7375,
"step": 494
},
{
"epoch": 0.9520153550863724,
"grad_norm": 1.8350569009780884,
"learning_rate": 5.814314131807486e-05,
"loss": 2.7364,
"step": 496
},
{
"epoch": 0.9558541266794626,
"grad_norm": 1.9296355247497559,
"learning_rate": 5.7829566718628946e-05,
"loss": 2.682,
"step": 498
},
{
"epoch": 0.9596928982725528,
"grad_norm": 1.8304519653320312,
"learning_rate": 5.751567610729398e-05,
"loss": 2.6421,
"step": 500
},
{
"epoch": 0.963531669865643,
"grad_norm": 1.8141051530838013,
"learning_rate": 5.7201482153119015e-05,
"loss": 2.6552,
"step": 502
},
{
"epoch": 0.9673704414587332,
"grad_norm": 1.9663299322128296,
"learning_rate": 5.6886997537396494e-05,
"loss": 2.6086,
"step": 504
},
{
"epoch": 0.9712092130518234,
"grad_norm": 1.9281374216079712,
"learning_rate": 5.6572234953150305e-05,
"loss": 2.7493,
"step": 506
},
{
"epoch": 0.9750479846449136,
"grad_norm": 1.7819768190383911,
"learning_rate": 5.6257207104623524e-05,
"loss": 2.6959,
"step": 508
},
{
"epoch": 0.9788867562380038,
"grad_norm": 1.8469796180725098,
"learning_rate": 5.594192670676568e-05,
"loss": 2.6471,
"step": 510
},
{
"epoch": 0.982725527831094,
"grad_norm": 1.8483726978302002,
"learning_rate": 5.5626406484719506e-05,
"loss": 2.699,
"step": 512
},
{
"epoch": 0.9865642994241842,
"grad_norm": 1.8236881494522095,
"learning_rate": 5.5310659173307366e-05,
"loss": 2.746,
"step": 514
},
{
"epoch": 0.9904030710172744,
"grad_norm": 1.7808964252471924,
"learning_rate": 5.499469751651728e-05,
"loss": 2.7885,
"step": 516
},
{
"epoch": 0.9942418426103646,
"grad_norm": 1.828331708908081,
"learning_rate": 5.467853426698853e-05,
"loss": 2.7437,
"step": 518
},
{
"epoch": 0.9980806142034548,
"grad_norm": 1.7730071544647217,
"learning_rate": 5.43621821854969e-05,
"loss": 2.6718,
"step": 520
}
],
"logging_steps": 2,
"max_steps": 1042,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 521,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 8.81062206945362e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}