Ghaith Dekhili
add qqp first model
c39701d
{
"best_metric": 0.9108088053425674,
"best_model_checkpoint": "qqp_#1_glue_cased/checkpoint-34113",
"epoch": 3.0,
"global_step": 34113,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04397150646381145,
"learning_rate": 1.9824113974144757e-05,
"loss": 0.43561614990234376,
"step": 500
},
{
"epoch": 0.0879430129276229,
"learning_rate": 1.9648227948289512e-05,
"loss": 0.3685419006347656,
"step": 1000
},
{
"epoch": 0.13191451939143434,
"learning_rate": 1.9472341922434264e-05,
"loss": 0.3377880249023438,
"step": 1500
},
{
"epoch": 0.1758860258552458,
"learning_rate": 1.929645589657902e-05,
"loss": 0.327943115234375,
"step": 2000
},
{
"epoch": 0.21985753231905725,
"learning_rate": 1.9120569870723774e-05,
"loss": 0.3118376159667969,
"step": 2500
},
{
"epoch": 0.2638290387828687,
"learning_rate": 1.894468384486853e-05,
"loss": 0.3047716064453125,
"step": 3000
},
{
"epoch": 0.30780054524668016,
"learning_rate": 1.876879781901328e-05,
"loss": 0.3038143005371094,
"step": 3500
},
{
"epoch": 0.3517720517104916,
"learning_rate": 1.8592911793158036e-05,
"loss": 0.2949424438476563,
"step": 4000
},
{
"epoch": 0.39574355817430307,
"learning_rate": 1.8417025767302788e-05,
"loss": 0.2912021789550781,
"step": 4500
},
{
"epoch": 0.4397150646381145,
"learning_rate": 1.8241139741447543e-05,
"loss": 0.2867056884765625,
"step": 5000
},
{
"epoch": 0.483686571101926,
"learning_rate": 1.80652537155923e-05,
"loss": 0.27814862060546874,
"step": 5500
},
{
"epoch": 0.5276580775657373,
"learning_rate": 1.788936768973705e-05,
"loss": 0.2777033996582031,
"step": 6000
},
{
"epoch": 0.5716295840295489,
"learning_rate": 1.7713481663881805e-05,
"loss": 0.2808096618652344,
"step": 6500
},
{
"epoch": 0.6156010904933603,
"learning_rate": 1.753759563802656e-05,
"loss": 0.2740480041503906,
"step": 7000
},
{
"epoch": 0.6595725969571717,
"learning_rate": 1.7361709612171312e-05,
"loss": 0.2704828796386719,
"step": 7500
},
{
"epoch": 0.7035441034209832,
"learning_rate": 1.7185823586316067e-05,
"loss": 0.26128680419921874,
"step": 8000
},
{
"epoch": 0.7475156098847947,
"learning_rate": 1.7009937560460823e-05,
"loss": 0.26227166748046876,
"step": 8500
},
{
"epoch": 0.7914871163486061,
"learning_rate": 1.6834051534605578e-05,
"loss": 0.257682861328125,
"step": 9000
},
{
"epoch": 0.8354586228124176,
"learning_rate": 1.665816550875033e-05,
"loss": 0.25748046875,
"step": 9500
},
{
"epoch": 0.879430129276229,
"learning_rate": 1.6482279482895085e-05,
"loss": 0.26029693603515625,
"step": 10000
},
{
"epoch": 0.9234016357400404,
"learning_rate": 1.630639345703984e-05,
"loss": 0.25330767822265626,
"step": 10500
},
{
"epoch": 0.967373142203852,
"learning_rate": 1.6130507431184595e-05,
"loss": 0.24725408935546875,
"step": 11000
},
{
"epoch": 1.0,
"eval_accuracy": 0.8963888201830325,
"eval_f1": 0.8609460580912863,
"eval_loss": 0.2415674775838852,
"step": 11371
},
{
"epoch": 1.0113446486676634,
"learning_rate": 1.5954621405329347e-05,
"loss": 0.22799398803710938,
"step": 11500
},
{
"epoch": 1.0553161551314747,
"learning_rate": 1.5778735379474102e-05,
"loss": 0.1779903106689453,
"step": 12000
},
{
"epoch": 1.0992876615952862,
"learning_rate": 1.5602849353618857e-05,
"loss": 0.18363124084472657,
"step": 12500
},
{
"epoch": 1.1432591680590978,
"learning_rate": 1.5426963327763612e-05,
"loss": 0.183293212890625,
"step": 13000
},
{
"epoch": 1.187230674522909,
"learning_rate": 1.5251077301908364e-05,
"loss": 0.1881647186279297,
"step": 13500
},
{
"epoch": 1.2312021809867206,
"learning_rate": 1.5075191276053118e-05,
"loss": 0.193143798828125,
"step": 14000
},
{
"epoch": 1.2751736874505322,
"learning_rate": 1.4899305250197873e-05,
"loss": 0.186142333984375,
"step": 14500
},
{
"epoch": 1.3191451939143435,
"learning_rate": 1.4723419224342628e-05,
"loss": 0.18537522888183594,
"step": 15000
},
{
"epoch": 1.363116700378155,
"learning_rate": 1.4547533198487383e-05,
"loss": 0.18841236877441406,
"step": 15500
},
{
"epoch": 1.4070882068419663,
"learning_rate": 1.4371647172632135e-05,
"loss": 0.18419113159179687,
"step": 16000
},
{
"epoch": 1.4510597133057779,
"learning_rate": 1.419576114677689e-05,
"loss": 0.18361325073242188,
"step": 16500
},
{
"epoch": 1.4950312197695892,
"learning_rate": 1.4019875120921644e-05,
"loss": 0.18803219604492188,
"step": 17000
},
{
"epoch": 1.5390027262334007,
"learning_rate": 1.3843989095066399e-05,
"loss": 0.1816302032470703,
"step": 17500
},
{
"epoch": 1.5829742326972123,
"learning_rate": 1.3668103069211152e-05,
"loss": 0.1842498016357422,
"step": 18000
},
{
"epoch": 1.6269457391610236,
"learning_rate": 1.3492217043355906e-05,
"loss": 0.17726910400390625,
"step": 18500
},
{
"epoch": 1.6709172456248351,
"learning_rate": 1.3316331017500661e-05,
"loss": 0.17991775512695313,
"step": 19000
},
{
"epoch": 1.7148887520886467,
"learning_rate": 1.3140444991645416e-05,
"loss": 0.1825124053955078,
"step": 19500
},
{
"epoch": 1.758860258552458,
"learning_rate": 1.2964558965790168e-05,
"loss": 0.17683036804199218,
"step": 20000
},
{
"epoch": 1.8028317650162693,
"learning_rate": 1.2788672939934923e-05,
"loss": 0.1868966827392578,
"step": 20500
},
{
"epoch": 1.846803271480081,
"learning_rate": 1.2612786914079678e-05,
"loss": 0.18423307800292968,
"step": 21000
},
{
"epoch": 1.8907747779438924,
"learning_rate": 1.2436900888224432e-05,
"loss": 0.17814576721191405,
"step": 21500
},
{
"epoch": 1.9347462844077037,
"learning_rate": 1.2261014862369185e-05,
"loss": 0.17719683837890626,
"step": 22000
},
{
"epoch": 1.9787177908715152,
"learning_rate": 1.208512883651394e-05,
"loss": 0.17974095153808595,
"step": 22500
},
{
"epoch": 2.0,
"eval_accuracy": 0.9078407123423201,
"eval_f1": 0.8756839717069265,
"eval_loss": 0.23735392093658447,
"step": 22742
},
{
"epoch": 2.0226892973353268,
"learning_rate": 1.1909242810658694e-05,
"loss": 0.14513198852539064,
"step": 23000
},
{
"epoch": 2.066660803799138,
"learning_rate": 1.1733356784803449e-05,
"loss": 0.11556282806396484,
"step": 23500
},
{
"epoch": 2.1106323102629494,
"learning_rate": 1.15574707589482e-05,
"loss": 0.12064967346191406,
"step": 24000
},
{
"epoch": 2.154603816726761,
"learning_rate": 1.1381584733092956e-05,
"loss": 0.11743055725097656,
"step": 24500
},
{
"epoch": 2.1985753231905725,
"learning_rate": 1.1205698707237711e-05,
"loss": 0.11710655212402343,
"step": 25000
},
{
"epoch": 2.242546829654384,
"learning_rate": 1.1029812681382466e-05,
"loss": 0.1169861831665039,
"step": 25500
},
{
"epoch": 2.2865183361181955,
"learning_rate": 1.0853926655527218e-05,
"loss": 0.12172984313964844,
"step": 26000
},
{
"epoch": 2.330489842582007,
"learning_rate": 1.0678040629671973e-05,
"loss": 0.11213615417480469,
"step": 26500
},
{
"epoch": 2.374461349045818,
"learning_rate": 1.0502154603816728e-05,
"loss": 0.12687485504150392,
"step": 27000
},
{
"epoch": 2.41843285550963,
"learning_rate": 1.0326268577961482e-05,
"loss": 0.12601725006103515,
"step": 27500
},
{
"epoch": 2.4624043619734413,
"learning_rate": 1.0150382552106235e-05,
"loss": 0.11948597717285156,
"step": 28000
},
{
"epoch": 2.5063758684372526,
"learning_rate": 9.974496526250989e-06,
"loss": 0.12668427276611327,
"step": 28500
},
{
"epoch": 2.5503473749010643,
"learning_rate": 9.798610500395744e-06,
"loss": 0.12504535675048828,
"step": 29000
},
{
"epoch": 2.5943188813648757,
"learning_rate": 9.6227244745405e-06,
"loss": 0.12663780975341796,
"step": 29500
},
{
"epoch": 2.638290387828687,
"learning_rate": 9.446838448685253e-06,
"loss": 0.122175048828125,
"step": 30000
},
{
"epoch": 2.6822618942924983,
"learning_rate": 9.270952422830008e-06,
"loss": 0.12571288299560546,
"step": 30500
},
{
"epoch": 2.72623340075631,
"learning_rate": 9.095066396974761e-06,
"loss": 0.12774851989746094,
"step": 31000
},
{
"epoch": 2.7702049072201214,
"learning_rate": 8.919180371119516e-06,
"loss": 0.12356333923339843,
"step": 31500
},
{
"epoch": 2.8141764136839327,
"learning_rate": 8.74329434526427e-06,
"loss": 0.1209749755859375,
"step": 32000
},
{
"epoch": 2.8581479201477444,
"learning_rate": 8.567408319409023e-06,
"loss": 0.12022649383544921,
"step": 32500
},
{
"epoch": 2.9021194266115558,
"learning_rate": 8.391522293553777e-06,
"loss": 0.12490190887451172,
"step": 33000
},
{
"epoch": 2.946090933075367,
"learning_rate": 8.215636267698532e-06,
"loss": 0.12208123779296876,
"step": 33500
},
{
"epoch": 2.9900624395391784,
"learning_rate": 8.039750241843286e-06,
"loss": 0.12288145446777343,
"step": 34000
},
{
"epoch": 3.0,
"eval_accuracy": 0.9108088053425674,
"eval_f1": 0.8790176474535328,
"eval_loss": 0.2841033935546875,
"step": 34113
}
],
"max_steps": 56855,
"num_train_epochs": 5,
"total_flos": 49275990211670160,
"trial_name": null,
"trial_params": null
}