vulberta-mlm / trainer_state.json
garrettmeek123's picture
Upload folder using huggingface_hub
2806e30 verified
{
"best_global_step": 4098,
"best_metric": 0.6449487554904831,
"best_model_checkpoint": "./saved_models/vulberta/checkpoint-4098",
"epoch": 5.0,
"eval_steps": 500,
"global_step": 6830,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.036603221083455345,
"grad_norm": 3.2610507011413574,
"learning_rate": 1.9856515373352855e-05,
"loss": 0.7004,
"step": 50
},
{
"epoch": 0.07320644216691069,
"grad_norm": 4.554418563842773,
"learning_rate": 1.9710102489019037e-05,
"loss": 0.7002,
"step": 100
},
{
"epoch": 0.10980966325036604,
"grad_norm": 2.98534893989563,
"learning_rate": 1.9563689604685214e-05,
"loss": 0.6961,
"step": 150
},
{
"epoch": 0.14641288433382138,
"grad_norm": 2.6510939598083496,
"learning_rate": 1.9417276720351393e-05,
"loss": 0.6968,
"step": 200
},
{
"epoch": 0.18301610541727673,
"grad_norm": 3.6250808238983154,
"learning_rate": 1.927086383601757e-05,
"loss": 0.7027,
"step": 250
},
{
"epoch": 0.21961932650073207,
"grad_norm": 6.485755443572998,
"learning_rate": 1.9124450951683752e-05,
"loss": 0.6881,
"step": 300
},
{
"epoch": 0.2562225475841874,
"grad_norm": 3.9667303562164307,
"learning_rate": 1.897803806734993e-05,
"loss": 0.6745,
"step": 350
},
{
"epoch": 0.29282576866764276,
"grad_norm": 5.07423210144043,
"learning_rate": 1.8831625183016108e-05,
"loss": 0.6963,
"step": 400
},
{
"epoch": 0.3294289897510981,
"grad_norm": 3.7114145755767822,
"learning_rate": 1.8685212298682284e-05,
"loss": 0.6868,
"step": 450
},
{
"epoch": 0.36603221083455345,
"grad_norm": 8.060341835021973,
"learning_rate": 1.8538799414348463e-05,
"loss": 0.6865,
"step": 500
},
{
"epoch": 0.40263543191800877,
"grad_norm": 5.241364002227783,
"learning_rate": 1.8392386530014643e-05,
"loss": 0.6757,
"step": 550
},
{
"epoch": 0.43923865300146414,
"grad_norm": 3.611410140991211,
"learning_rate": 1.8245973645680823e-05,
"loss": 0.6616,
"step": 600
},
{
"epoch": 0.47584187408491946,
"grad_norm": 5.06477689743042,
"learning_rate": 1.8099560761347e-05,
"loss": 0.6775,
"step": 650
},
{
"epoch": 0.5124450951683748,
"grad_norm": 9.890421867370605,
"learning_rate": 1.7953147877013178e-05,
"loss": 0.6631,
"step": 700
},
{
"epoch": 0.5490483162518301,
"grad_norm": 3.756012201309204,
"learning_rate": 1.7806734992679358e-05,
"loss": 0.672,
"step": 750
},
{
"epoch": 0.5856515373352855,
"grad_norm": 2.940450429916382,
"learning_rate": 1.7660322108345537e-05,
"loss": 0.6591,
"step": 800
},
{
"epoch": 0.6222547584187409,
"grad_norm": 3.1005771160125732,
"learning_rate": 1.7513909224011713e-05,
"loss": 0.6593,
"step": 850
},
{
"epoch": 0.6588579795021962,
"grad_norm": 7.628331661224365,
"learning_rate": 1.7367496339677893e-05,
"loss": 0.6677,
"step": 900
},
{
"epoch": 0.6954612005856515,
"grad_norm": 7.699522018432617,
"learning_rate": 1.7221083455344072e-05,
"loss": 0.6621,
"step": 950
},
{
"epoch": 0.7320644216691069,
"grad_norm": 5.101274490356445,
"learning_rate": 1.707467057101025e-05,
"loss": 0.6666,
"step": 1000
},
{
"epoch": 0.7686676427525623,
"grad_norm": 7.820975303649902,
"learning_rate": 1.6928257686676428e-05,
"loss": 0.6646,
"step": 1050
},
{
"epoch": 0.8052708638360175,
"grad_norm": 5.459151268005371,
"learning_rate": 1.6781844802342608e-05,
"loss": 0.665,
"step": 1100
},
{
"epoch": 0.8418740849194729,
"grad_norm": 2.7326955795288086,
"learning_rate": 1.6635431918008787e-05,
"loss": 0.6623,
"step": 1150
},
{
"epoch": 0.8784773060029283,
"grad_norm": 4.056868076324463,
"learning_rate": 1.6489019033674963e-05,
"loss": 0.6718,
"step": 1200
},
{
"epoch": 0.9150805270863837,
"grad_norm": 3.1695716381073,
"learning_rate": 1.6342606149341143e-05,
"loss": 0.6469,
"step": 1250
},
{
"epoch": 0.9516837481698389,
"grad_norm": 3.2866313457489014,
"learning_rate": 1.6196193265007322e-05,
"loss": 0.646,
"step": 1300
},
{
"epoch": 0.9882869692532943,
"grad_norm": 7.2812957763671875,
"learning_rate": 1.6049780380673502e-05,
"loss": 0.6381,
"step": 1350
},
{
"epoch": 1.0,
"eval_accuracy": 0.6248169838945827,
"eval_loss": 0.6279681324958801,
"eval_runtime": 13.6534,
"eval_samples_per_second": 200.097,
"eval_steps_per_second": 6.299,
"step": 1366
},
{
"epoch": 1.0248901903367496,
"grad_norm": 9.606693267822266,
"learning_rate": 1.5903367496339678e-05,
"loss": 0.6152,
"step": 1400
},
{
"epoch": 1.061493411420205,
"grad_norm": 7.122623920440674,
"learning_rate": 1.5756954612005857e-05,
"loss": 0.6157,
"step": 1450
},
{
"epoch": 1.0980966325036603,
"grad_norm": 7.1912384033203125,
"learning_rate": 1.5610541727672037e-05,
"loss": 0.5858,
"step": 1500
},
{
"epoch": 1.1346998535871156,
"grad_norm": 8.011345863342285,
"learning_rate": 1.5464128843338216e-05,
"loss": 0.5917,
"step": 1550
},
{
"epoch": 1.171303074670571,
"grad_norm": 3.9715421199798584,
"learning_rate": 1.5317715959004393e-05,
"loss": 0.6215,
"step": 1600
},
{
"epoch": 1.2079062957540263,
"grad_norm": 4.4239501953125,
"learning_rate": 1.5171303074670572e-05,
"loss": 0.5701,
"step": 1650
},
{
"epoch": 1.2445095168374818,
"grad_norm": 6.152805328369141,
"learning_rate": 1.5024890190336752e-05,
"loss": 0.6044,
"step": 1700
},
{
"epoch": 1.281112737920937,
"grad_norm": 8.131645202636719,
"learning_rate": 1.487847730600293e-05,
"loss": 0.5967,
"step": 1750
},
{
"epoch": 1.3177159590043923,
"grad_norm": 5.887744903564453,
"learning_rate": 1.4732064421669107e-05,
"loss": 0.5764,
"step": 1800
},
{
"epoch": 1.3543191800878478,
"grad_norm": 4.500638484954834,
"learning_rate": 1.4585651537335285e-05,
"loss": 0.5966,
"step": 1850
},
{
"epoch": 1.390922401171303,
"grad_norm": 4.338794231414795,
"learning_rate": 1.4439238653001466e-05,
"loss": 0.6064,
"step": 1900
},
{
"epoch": 1.4275256222547585,
"grad_norm": 7.292316436767578,
"learning_rate": 1.4292825768667644e-05,
"loss": 0.6048,
"step": 1950
},
{
"epoch": 1.4641288433382138,
"grad_norm": 6.632826328277588,
"learning_rate": 1.4146412884333822e-05,
"loss": 0.5798,
"step": 2000
},
{
"epoch": 1.500732064421669,
"grad_norm": 9.965185165405273,
"learning_rate": 1.4e-05,
"loss": 0.5452,
"step": 2050
},
{
"epoch": 1.5373352855051245,
"grad_norm": 5.015806674957275,
"learning_rate": 1.3853587115666181e-05,
"loss": 0.5961,
"step": 2100
},
{
"epoch": 1.5739385065885798,
"grad_norm": 3.3543472290039062,
"learning_rate": 1.3707174231332359e-05,
"loss": 0.5949,
"step": 2150
},
{
"epoch": 1.610541727672035,
"grad_norm": 5.284890651702881,
"learning_rate": 1.3560761346998537e-05,
"loss": 0.5742,
"step": 2200
},
{
"epoch": 1.6471449487554906,
"grad_norm": 4.332915782928467,
"learning_rate": 1.3414348462664714e-05,
"loss": 0.6036,
"step": 2250
},
{
"epoch": 1.6837481698389458,
"grad_norm": 6.890816688537598,
"learning_rate": 1.3267935578330896e-05,
"loss": 0.5673,
"step": 2300
},
{
"epoch": 1.720351390922401,
"grad_norm": 6.644792079925537,
"learning_rate": 1.3121522693997074e-05,
"loss": 0.5624,
"step": 2350
},
{
"epoch": 1.7569546120058566,
"grad_norm": 4.097620487213135,
"learning_rate": 1.2975109809663251e-05,
"loss": 0.5753,
"step": 2400
},
{
"epoch": 1.7935578330893118,
"grad_norm": 6.0914459228515625,
"learning_rate": 1.282869692532943e-05,
"loss": 0.5962,
"step": 2450
},
{
"epoch": 1.830161054172767,
"grad_norm": 6.992921352386475,
"learning_rate": 1.2682284040995609e-05,
"loss": 0.5672,
"step": 2500
},
{
"epoch": 1.8667642752562226,
"grad_norm": 5.129520416259766,
"learning_rate": 1.2535871156661788e-05,
"loss": 0.5925,
"step": 2550
},
{
"epoch": 1.903367496339678,
"grad_norm": 5.3862223625183105,
"learning_rate": 1.2389458272327966e-05,
"loss": 0.5897,
"step": 2600
},
{
"epoch": 1.939970717423133,
"grad_norm": 4.44102668762207,
"learning_rate": 1.2243045387994144e-05,
"loss": 0.5699,
"step": 2650
},
{
"epoch": 1.9765739385065886,
"grad_norm": 3.638970375061035,
"learning_rate": 1.2096632503660323e-05,
"loss": 0.5709,
"step": 2700
},
{
"epoch": 2.0,
"eval_accuracy": 0.6292093704245973,
"eval_loss": 0.6692330837249756,
"eval_runtime": 13.6268,
"eval_samples_per_second": 200.488,
"eval_steps_per_second": 6.311,
"step": 2732
},
{
"epoch": 2.013177159590044,
"grad_norm": 4.104243278503418,
"learning_rate": 1.1950219619326501e-05,
"loss": 0.537,
"step": 2750
},
{
"epoch": 2.049780380673499,
"grad_norm": 16.372787475585938,
"learning_rate": 1.180380673499268e-05,
"loss": 0.4823,
"step": 2800
},
{
"epoch": 2.0863836017569546,
"grad_norm": 6.0528244972229,
"learning_rate": 1.1657393850658859e-05,
"loss": 0.4871,
"step": 2850
},
{
"epoch": 2.12298682284041,
"grad_norm": 11.29574203491211,
"learning_rate": 1.1510980966325038e-05,
"loss": 0.4714,
"step": 2900
},
{
"epoch": 2.159590043923865,
"grad_norm": 10.56286334991455,
"learning_rate": 1.1364568081991216e-05,
"loss": 0.4669,
"step": 2950
},
{
"epoch": 2.1961932650073206,
"grad_norm": 12.307333946228027,
"learning_rate": 1.1218155197657394e-05,
"loss": 0.4742,
"step": 3000
},
{
"epoch": 2.232796486090776,
"grad_norm": 4.0419440269470215,
"learning_rate": 1.1071742313323573e-05,
"loss": 0.4621,
"step": 3050
},
{
"epoch": 2.269399707174231,
"grad_norm": 14.435094833374023,
"learning_rate": 1.0925329428989753e-05,
"loss": 0.4789,
"step": 3100
},
{
"epoch": 2.3060029282576866,
"grad_norm": 4.455873966217041,
"learning_rate": 1.077891654465593e-05,
"loss": 0.4672,
"step": 3150
},
{
"epoch": 2.342606149341142,
"grad_norm": 9.073851585388184,
"learning_rate": 1.0632503660322108e-05,
"loss": 0.4827,
"step": 3200
},
{
"epoch": 2.379209370424597,
"grad_norm": 6.983617305755615,
"learning_rate": 1.0486090775988286e-05,
"loss": 0.4619,
"step": 3250
},
{
"epoch": 2.4158125915080526,
"grad_norm": 7.893983840942383,
"learning_rate": 1.0339677891654467e-05,
"loss": 0.4513,
"step": 3300
},
{
"epoch": 2.452415812591508,
"grad_norm": 8.749136924743652,
"learning_rate": 1.0193265007320645e-05,
"loss": 0.4947,
"step": 3350
},
{
"epoch": 2.4890190336749636,
"grad_norm": 4.401139736175537,
"learning_rate": 1.0046852122986823e-05,
"loss": 0.4712,
"step": 3400
},
{
"epoch": 2.5256222547584186,
"grad_norm": 6.115893363952637,
"learning_rate": 9.900439238653003e-06,
"loss": 0.4624,
"step": 3450
},
{
"epoch": 2.562225475841874,
"grad_norm": 3.8851876258850098,
"learning_rate": 9.75402635431918e-06,
"loss": 0.4955,
"step": 3500
},
{
"epoch": 2.5988286969253296,
"grad_norm": 8.24189281463623,
"learning_rate": 9.60761346998536e-06,
"loss": 0.4573,
"step": 3550
},
{
"epoch": 2.6354319180087846,
"grad_norm": 4.605769157409668,
"learning_rate": 9.461200585651538e-06,
"loss": 0.5172,
"step": 3600
},
{
"epoch": 2.67203513909224,
"grad_norm": 9.174911499023438,
"learning_rate": 9.314787701317717e-06,
"loss": 0.455,
"step": 3650
},
{
"epoch": 2.7086383601756956,
"grad_norm": 7.105350017547607,
"learning_rate": 9.168374816983895e-06,
"loss": 0.4792,
"step": 3700
},
{
"epoch": 2.745241581259151,
"grad_norm": 9.204080581665039,
"learning_rate": 9.021961932650075e-06,
"loss": 0.5004,
"step": 3750
},
{
"epoch": 2.781844802342606,
"grad_norm": 23.993898391723633,
"learning_rate": 8.875549048316252e-06,
"loss": 0.49,
"step": 3800
},
{
"epoch": 2.8184480234260616,
"grad_norm": 7.301971912384033,
"learning_rate": 8.729136163982432e-06,
"loss": 0.5001,
"step": 3850
},
{
"epoch": 2.855051244509517,
"grad_norm": 5.969315052032471,
"learning_rate": 8.58272327964861e-06,
"loss": 0.4463,
"step": 3900
},
{
"epoch": 2.891654465592972,
"grad_norm": 5.500088691711426,
"learning_rate": 8.436310395314788e-06,
"loss": 0.4566,
"step": 3950
},
{
"epoch": 2.9282576866764276,
"grad_norm": 4.6784586906433105,
"learning_rate": 8.289897510980967e-06,
"loss": 0.458,
"step": 4000
},
{
"epoch": 2.964860907759883,
"grad_norm": 7.5789103507995605,
"learning_rate": 8.143484626647145e-06,
"loss": 0.499,
"step": 4050
},
{
"epoch": 3.0,
"eval_accuracy": 0.6449487554904831,
"eval_loss": 0.6640557050704956,
"eval_runtime": 13.6186,
"eval_samples_per_second": 200.607,
"eval_steps_per_second": 6.315,
"step": 4098
},
{
"epoch": 3.001464128843338,
"grad_norm": 9.293344497680664,
"learning_rate": 7.997071742313325e-06,
"loss": 0.5113,
"step": 4100
},
{
"epoch": 3.0380673499267936,
"grad_norm": 13.914603233337402,
"learning_rate": 7.850658857979502e-06,
"loss": 0.3652,
"step": 4150
},
{
"epoch": 3.074670571010249,
"grad_norm": 10.234390258789062,
"learning_rate": 7.70424597364568e-06,
"loss": 0.3838,
"step": 4200
},
{
"epoch": 3.111273792093704,
"grad_norm": 14.120603561401367,
"learning_rate": 7.55783308931186e-06,
"loss": 0.347,
"step": 4250
},
{
"epoch": 3.1478770131771596,
"grad_norm": 12.265131950378418,
"learning_rate": 7.411420204978038e-06,
"loss": 0.3749,
"step": 4300
},
{
"epoch": 3.184480234260615,
"grad_norm": 9.216547966003418,
"learning_rate": 7.265007320644217e-06,
"loss": 0.3554,
"step": 4350
},
{
"epoch": 3.22108345534407,
"grad_norm": 11.449105262756348,
"learning_rate": 7.118594436310396e-06,
"loss": 0.344,
"step": 4400
},
{
"epoch": 3.2576866764275256,
"grad_norm": 12.415879249572754,
"learning_rate": 6.972181551976574e-06,
"loss": 0.3718,
"step": 4450
},
{
"epoch": 3.294289897510981,
"grad_norm": 11.875557899475098,
"learning_rate": 6.825768667642752e-06,
"loss": 0.3526,
"step": 4500
},
{
"epoch": 3.330893118594436,
"grad_norm": 5.397584438323975,
"learning_rate": 6.679355783308932e-06,
"loss": 0.3522,
"step": 4550
},
{
"epoch": 3.3674963396778916,
"grad_norm": 6.454545974731445,
"learning_rate": 6.5329428989751095e-06,
"loss": 0.3884,
"step": 4600
},
{
"epoch": 3.404099560761347,
"grad_norm": 6.373364448547363,
"learning_rate": 6.386530014641289e-06,
"loss": 0.3908,
"step": 4650
},
{
"epoch": 3.440702781844802,
"grad_norm": 16.992902755737305,
"learning_rate": 6.240117130307467e-06,
"loss": 0.3711,
"step": 4700
},
{
"epoch": 3.4773060029282576,
"grad_norm": 12.786251068115234,
"learning_rate": 6.093704245973646e-06,
"loss": 0.3872,
"step": 4750
},
{
"epoch": 3.513909224011713,
"grad_norm": 7.947234153747559,
"learning_rate": 5.947291361639825e-06,
"loss": 0.3498,
"step": 4800
},
{
"epoch": 3.550512445095168,
"grad_norm": 13.394478797912598,
"learning_rate": 5.800878477306004e-06,
"loss": 0.3621,
"step": 4850
},
{
"epoch": 3.5871156661786237,
"grad_norm": 13.295003890991211,
"learning_rate": 5.6544655929721824e-06,
"loss": 0.385,
"step": 4900
},
{
"epoch": 3.623718887262079,
"grad_norm": 8.606812477111816,
"learning_rate": 5.50805270863836e-06,
"loss": 0.3755,
"step": 4950
},
{
"epoch": 3.660322108345534,
"grad_norm": 7.550472736358643,
"learning_rate": 5.36163982430454e-06,
"loss": 0.372,
"step": 5000
},
{
"epoch": 3.6969253294289897,
"grad_norm": 9.188961029052734,
"learning_rate": 5.215226939970718e-06,
"loss": 0.3511,
"step": 5050
},
{
"epoch": 3.733528550512445,
"grad_norm": 7.2935638427734375,
"learning_rate": 5.068814055636897e-06,
"loss": 0.3673,
"step": 5100
},
{
"epoch": 3.7701317715959,
"grad_norm": 5.323498249053955,
"learning_rate": 4.922401171303075e-06,
"loss": 0.3851,
"step": 5150
},
{
"epoch": 3.8067349926793557,
"grad_norm": 6.138152599334717,
"learning_rate": 4.775988286969254e-06,
"loss": 0.3634,
"step": 5200
},
{
"epoch": 3.843338213762811,
"grad_norm": 6.376275062561035,
"learning_rate": 4.629575402635432e-06,
"loss": 0.3826,
"step": 5250
},
{
"epoch": 3.8799414348462666,
"grad_norm": 9.393123626708984,
"learning_rate": 4.483162518301611e-06,
"loss": 0.3765,
"step": 5300
},
{
"epoch": 3.9165446559297217,
"grad_norm": 7.3140950202941895,
"learning_rate": 4.33674963396779e-06,
"loss": 0.3723,
"step": 5350
},
{
"epoch": 3.953147877013177,
"grad_norm": 6.270499229431152,
"learning_rate": 4.190336749633968e-06,
"loss": 0.372,
"step": 5400
},
{
"epoch": 3.9897510980966326,
"grad_norm": 10.044820785522461,
"learning_rate": 4.043923865300147e-06,
"loss": 0.3798,
"step": 5450
},
{
"epoch": 4.0,
"eval_accuracy": 0.6328696925329429,
"eval_loss": 0.8756816387176514,
"eval_runtime": 13.6217,
"eval_samples_per_second": 200.562,
"eval_steps_per_second": 6.313,
"step": 5464
},
{
"epoch": 4.026354319180088,
"grad_norm": 10.713644027709961,
"learning_rate": 3.897510980966326e-06,
"loss": 0.3022,
"step": 5500
},
{
"epoch": 4.062957540263543,
"grad_norm": 11.245952606201172,
"learning_rate": 3.751098096632504e-06,
"loss": 0.29,
"step": 5550
},
{
"epoch": 4.099560761346998,
"grad_norm": 9.67605209350586,
"learning_rate": 3.6046852122986826e-06,
"loss": 0.2848,
"step": 5600
},
{
"epoch": 4.136163982430454,
"grad_norm": 14.651419639587402,
"learning_rate": 3.4582723279648612e-06,
"loss": 0.2558,
"step": 5650
},
{
"epoch": 4.172767203513909,
"grad_norm": 14.767287254333496,
"learning_rate": 3.31185944363104e-06,
"loss": 0.2863,
"step": 5700
},
{
"epoch": 4.209370424597364,
"grad_norm": 14.15087604522705,
"learning_rate": 3.165446559297218e-06,
"loss": 0.2609,
"step": 5750
},
{
"epoch": 4.24597364568082,
"grad_norm": 16.17600440979004,
"learning_rate": 3.019033674963397e-06,
"loss": 0.2924,
"step": 5800
},
{
"epoch": 4.282576866764275,
"grad_norm": 21.407875061035156,
"learning_rate": 2.8726207906295755e-06,
"loss": 0.2886,
"step": 5850
},
{
"epoch": 4.31918008784773,
"grad_norm": 16.692087173461914,
"learning_rate": 2.726207906295754e-06,
"loss": 0.284,
"step": 5900
},
{
"epoch": 4.355783308931186,
"grad_norm": 7.582740783691406,
"learning_rate": 2.579795021961933e-06,
"loss": 0.2575,
"step": 5950
},
{
"epoch": 4.392386530014641,
"grad_norm": 15.145219802856445,
"learning_rate": 2.4333821376281115e-06,
"loss": 0.2686,
"step": 6000
},
{
"epoch": 4.428989751098096,
"grad_norm": 13.306376457214355,
"learning_rate": 2.2869692532942898e-06,
"loss": 0.3013,
"step": 6050
},
{
"epoch": 4.465592972181552,
"grad_norm": 6.897510051727295,
"learning_rate": 2.1405563689604685e-06,
"loss": 0.2736,
"step": 6100
},
{
"epoch": 4.502196193265007,
"grad_norm": 10.133888244628906,
"learning_rate": 1.994143484626647e-06,
"loss": 0.2548,
"step": 6150
},
{
"epoch": 4.538799414348462,
"grad_norm": 21.59294319152832,
"learning_rate": 1.8477306002928258e-06,
"loss": 0.2898,
"step": 6200
},
{
"epoch": 4.575402635431918,
"grad_norm": 10.04138469696045,
"learning_rate": 1.7013177159590045e-06,
"loss": 0.2729,
"step": 6250
},
{
"epoch": 4.612005856515373,
"grad_norm": 9.01938533782959,
"learning_rate": 1.554904831625183e-06,
"loss": 0.284,
"step": 6300
},
{
"epoch": 4.648609077598829,
"grad_norm": 23.59950065612793,
"learning_rate": 1.4084919472913616e-06,
"loss": 0.2727,
"step": 6350
},
{
"epoch": 4.685212298682284,
"grad_norm": 10.790794372558594,
"learning_rate": 1.2620790629575403e-06,
"loss": 0.2561,
"step": 6400
},
{
"epoch": 4.721815519765739,
"grad_norm": 11.493463516235352,
"learning_rate": 1.115666178623719e-06,
"loss": 0.3014,
"step": 6450
},
{
"epoch": 4.758418740849194,
"grad_norm": 11.314969062805176,
"learning_rate": 9.692532942898976e-07,
"loss": 0.2901,
"step": 6500
},
{
"epoch": 4.79502196193265,
"grad_norm": 10.80167007446289,
"learning_rate": 8.228404099560762e-07,
"loss": 0.3001,
"step": 6550
},
{
"epoch": 4.831625183016105,
"grad_norm": 11.179972648620605,
"learning_rate": 6.764275256222548e-07,
"loss": 0.2845,
"step": 6600
},
{
"epoch": 4.868228404099561,
"grad_norm": 19.67405891418457,
"learning_rate": 5.300146412884334e-07,
"loss": 0.2801,
"step": 6650
},
{
"epoch": 4.904831625183016,
"grad_norm": 12.151304244995117,
"learning_rate": 3.8360175695461205e-07,
"loss": 0.2561,
"step": 6700
},
{
"epoch": 4.941434846266471,
"grad_norm": 5.352505207061768,
"learning_rate": 2.3718887262079066e-07,
"loss": 0.2813,
"step": 6750
},
{
"epoch": 4.978038067349927,
"grad_norm": 8.123278617858887,
"learning_rate": 9.077598828696926e-08,
"loss": 0.3164,
"step": 6800
},
{
"epoch": 5.0,
"eval_accuracy": 0.6273792093704246,
"eval_loss": 1.0964716672897339,
"eval_runtime": 13.6672,
"eval_samples_per_second": 199.895,
"eval_steps_per_second": 6.292,
"step": 6830
}
],
"logging_steps": 50,
"max_steps": 6830,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.43750725095936e+16,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}