7-emo / trainer_state.json
AntoineBlanot's picture
Best checkpoint (step 4176)
bf395d2
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.701164294954722,
"global_step": 4176,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 5.064655172413793e-06,
"loss": 1.827,
"step": 47
},
{
"epoch": 0.06,
"learning_rate": 1.0129310344827586e-05,
"loss": 1.288,
"step": 94
},
{
"epoch": 0.09,
"learning_rate": 1.5086206896551724e-05,
"loss": 1.0612,
"step": 141
},
{
"epoch": 0.12,
"learning_rate": 2.0150862068965517e-05,
"loss": 0.9538,
"step": 188
},
{
"epoch": 0.15,
"eval_accuracy": 0.6960748846884327,
"eval_b_acc": 0.4789797300032158,
"eval_f1": 0.683716357682452,
"eval_f1_anger": 0.497677504976775,
"eval_f1_disgust": 0.0035460992907801418,
"eval_f1_fear": 0.4832126398946675,
"eval_f1_joy": 0.685316256600382,
"eval_f1_neutral": 0.827884745457005,
"eval_f1_sadness": 0.5799599198396794,
"eval_f1_surprise": 0.2866323907455013,
"eval_loss": 0.8701004981994629,
"eval_prec": 0.6836877535141815,
"eval_prec_anger": 0.462202136400986,
"eval_prec_disgust": 0.25,
"eval_prec_fear": 0.552710843373494,
"eval_prec_joy": 0.7401116233923805,
"eval_prec_neutral": 0.796529284164859,
"eval_prec_sadness": 0.5281021897810219,
"eval_prec_surprise": 0.3562300319488818,
"eval_recall": 0.6960748846884327,
"eval_recall_anger": 0.5390512697652132,
"eval_recall_disgust": 0.0017857142857142857,
"eval_recall_fear": 0.42923976608187137,
"eval_recall_joy": 0.6380753138075314,
"eval_recall_neutral": 0.86180998873451,
"eval_recall_sadness": 0.6431111111111111,
"eval_recall_surprise": 0.23978494623655913,
"eval_runtime": 16.0297,
"eval_samples_per_second": 1379.566,
"eval_steps_per_second": 10.792,
"step": 232
},
{
"epoch": 0.15,
"learning_rate": 2.521551724137931e-05,
"loss": 0.8837,
"step": 235
},
{
"epoch": 0.18,
"learning_rate": 3.0280172413793107e-05,
"loss": 0.881,
"step": 282
},
{
"epoch": 0.21,
"learning_rate": 3.53448275862069e-05,
"loss": 0.8462,
"step": 329
},
{
"epoch": 0.24,
"learning_rate": 4.0409482758620696e-05,
"loss": 0.8242,
"step": 376
},
{
"epoch": 0.27,
"learning_rate": 4.5474137931034485e-05,
"loss": 0.7952,
"step": 423
},
{
"epoch": 0.3,
"eval_accuracy": 0.7168309668083567,
"eval_b_acc": 0.5241940962877409,
"eval_f1": 0.7025228198992769,
"eval_f1_anger": 0.5170962651236192,
"eval_f1_disgust": 0.3386727688787185,
"eval_f1_fear": 0.5674653215636821,
"eval_f1_joy": 0.6853079426298663,
"eval_f1_neutral": 0.8225570814375757,
"eval_f1_sadness": 0.6211089494163424,
"eval_f1_surprise": 0.37250000000000005,
"eval_loss": 0.8009697198867798,
"eval_prec": 0.7097552640353452,
"eval_prec_anger": 0.5731778425655977,
"eval_prec_disgust": 0.4713375796178344,
"eval_prec_fear": 0.615595075239398,
"eval_prec_joy": 0.8083593972135342,
"eval_prec_neutral": 0.7405486659150695,
"eval_prec_sadness": 0.6858216970998926,
"eval_prec_surprise": 0.44477611940298506,
"eval_recall": 0.7168309668083567,
"eval_recall_anger": 0.4710110206037374,
"eval_recall_disgust": 0.2642857142857143,
"eval_recall_fear": 0.5263157894736842,
"eval_recall_joy": 0.5947698744769875,
"eval_recall_neutral": 0.924990612091626,
"eval_recall_sadness": 0.5675555555555556,
"eval_recall_surprise": 0.3204301075268817,
"eval_runtime": 15.1427,
"eval_samples_per_second": 1460.377,
"eval_steps_per_second": 11.425,
"step": 464
},
{
"epoch": 0.3,
"learning_rate": 4.9940105414470535e-05,
"loss": 0.7998,
"step": 470
},
{
"epoch": 0.33,
"learning_rate": 4.938907522759943e-05,
"loss": 0.7996,
"step": 517
},
{
"epoch": 0.36,
"learning_rate": 4.882606612362243e-05,
"loss": 0.776,
"step": 564
},
{
"epoch": 0.4,
"learning_rate": 4.826305701964542e-05,
"loss": 0.8018,
"step": 611
},
{
"epoch": 0.43,
"learning_rate": 4.770004791566843e-05,
"loss": 0.7528,
"step": 658
},
{
"epoch": 0.45,
"eval_accuracy": 0.7260558921949896,
"eval_b_acc": 0.5878316350938373,
"eval_f1": 0.7255951803151626,
"eval_f1_anger": 0.5542226487523992,
"eval_f1_disgust": 0.3994082840236686,
"eval_f1_fear": 0.5798319327731093,
"eval_f1_joy": 0.7291770573566084,
"eval_f1_neutral": 0.8314359514015114,
"eval_f1_sadness": 0.6541166735622672,
"eval_f1_surprise": 0.38283828382838286,
"eval_loss": 0.7560049891471863,
"eval_prec": 0.7309376250219672,
"eval_prec_anger": 0.5550216242191254,
"eval_prec_disgust": 0.3409090909090909,
"eval_prec_fear": 0.7225130890052356,
"eval_prec_joy": 0.6968541468064824,
"eval_prec_neutral": 0.847571679344646,
"eval_prec_sadness": 0.6118421052631579,
"eval_prec_surprise": 0.49572649572649574,
"eval_recall": 0.7260558921949896,
"eval_recall_anger": 0.5534259702922856,
"eval_recall_disgust": 0.48214285714285715,
"eval_recall_fear": 0.4842105263157895,
"eval_recall_joy": 0.7646443514644351,
"eval_recall_neutral": 0.8159031167855801,
"eval_recall_sadness": 0.7026666666666667,
"eval_recall_surprise": 0.3118279569892473,
"eval_runtime": 14.7708,
"eval_samples_per_second": 1497.143,
"eval_steps_per_second": 11.712,
"step": 696
},
{
"epoch": 0.46,
"learning_rate": 4.713703881169142e-05,
"loss": 0.7459,
"step": 705
},
{
"epoch": 0.49,
"learning_rate": 4.657402970771442e-05,
"loss": 0.7599,
"step": 752
},
{
"epoch": 0.52,
"learning_rate": 4.601102060373742e-05,
"loss": 0.7648,
"step": 799
},
{
"epoch": 0.55,
"learning_rate": 4.544801149976042e-05,
"loss": 0.7436,
"step": 846
},
{
"epoch": 0.58,
"learning_rate": 4.488500239578342e-05,
"loss": 0.7334,
"step": 893
},
{
"epoch": 0.6,
"eval_accuracy": 0.7370444062584788,
"eval_b_acc": 0.5867600905079025,
"eval_f1": 0.7282740654207969,
"eval_f1_anger": 0.5218712029161603,
"eval_f1_disgust": 0.4505649717514124,
"eval_f1_fear": 0.6104060913705585,
"eval_f1_joy": 0.7311320754716981,
"eval_f1_neutral": 0.8351327433628318,
"eval_f1_sadness": 0.6498640968618731,
"eval_f1_surprise": 0.4181229773462783,
"eval_loss": 0.7309762835502625,
"eval_prec": 0.7344879537976949,
"eval_prec_anger": 0.7128630705394191,
"eval_prec_disgust": 0.3726635514018692,
"eval_prec_fear": 0.6671289875173371,
"eval_prec_joy": 0.7170152855993563,
"eval_prec_neutral": 0.7898393036491463,
"eval_prec_sadness": 0.7317751808569839,
"eval_prec_surprise": 0.5252032520325203,
"eval_recall": 0.7370444062584788,
"eval_recall_anger": 0.411595591758505,
"eval_recall_disgust": 0.5696428571428571,
"eval_recall_fear": 0.5625730994152047,
"eval_recall_joy": 0.74581589958159,
"eval_recall_neutral": 0.8859369132557267,
"eval_recall_sadness": 0.5844444444444444,
"eval_recall_surprise": 0.3473118279569892,
"eval_runtime": 14.5647,
"eval_samples_per_second": 1518.332,
"eval_steps_per_second": 11.878,
"step": 928
},
{
"epoch": 0.61,
"learning_rate": 4.432199329180642e-05,
"loss": 0.7493,
"step": 940
},
{
"epoch": 0.64,
"learning_rate": 4.375898418782942e-05,
"loss": 0.7194,
"step": 987
},
{
"epoch": 0.67,
"learning_rate": 4.319597508385242e-05,
"loss": 0.7158,
"step": 1034
},
{
"epoch": 0.7,
"learning_rate": 4.263296597987542e-05,
"loss": 0.719,
"step": 1081
},
{
"epoch": 0.73,
"learning_rate": 4.206995687589842e-05,
"loss": 0.7216,
"step": 1128
},
{
"epoch": 0.75,
"eval_accuracy": 0.7448222845256399,
"eval_b_acc": 0.6009457685058381,
"eval_f1": 0.7388819166581033,
"eval_f1_anger": 0.5746421267893661,
"eval_f1_disgust": 0.48046875,
"eval_f1_fear": 0.6597796143250689,
"eval_f1_joy": 0.7266451397394499,
"eval_f1_neutral": 0.8355743035416118,
"eval_f1_sadness": 0.6644859813084112,
"eval_f1_surprise": 0.4711696869851729,
"eval_loss": 0.7043296694755554,
"eval_prec": 0.7402960337790491,
"eval_prec_anger": 0.6158904109589041,
"eval_prec_disgust": 0.5301724137931034,
"eval_prec_fear": 0.8023450586264657,
"eval_prec_joy": 0.7767198286122352,
"eval_prec_neutral": 0.7853956715678176,
"eval_prec_sadness": 0.7004926108374384,
"eval_prec_surprise": 0.48148148148148145,
"eval_recall": 0.7448222845256399,
"eval_recall_anger": 0.5385721130809775,
"eval_recall_disgust": 0.4392857142857143,
"eval_recall_fear": 0.560233918128655,
"eval_recall_joy": 0.6826359832635983,
"eval_recall_neutral": 0.8926023282012767,
"eval_recall_sadness": 0.632,
"eval_recall_surprise": 0.4612903225806452,
"eval_runtime": 14.6801,
"eval_samples_per_second": 1506.393,
"eval_steps_per_second": 11.785,
"step": 1160
},
{
"epoch": 0.76,
"learning_rate": 4.150694777192142e-05,
"loss": 0.7134,
"step": 1175
},
{
"epoch": 0.79,
"learning_rate": 4.094393866794442e-05,
"loss": 0.7029,
"step": 1222
},
{
"epoch": 0.82,
"learning_rate": 4.0380929563967415e-05,
"loss": 0.6945,
"step": 1269
},
{
"epoch": 0.85,
"learning_rate": 3.981792045999042e-05,
"loss": 0.7033,
"step": 1316
},
{
"epoch": 0.88,
"learning_rate": 3.9254911356013415e-05,
"loss": 0.7259,
"step": 1363
},
{
"epoch": 0.9,
"eval_accuracy": 0.7475354978746496,
"eval_b_acc": 0.6082480515560814,
"eval_f1": 0.741168197686153,
"eval_f1_anger": 0.5405405405405406,
"eval_f1_disgust": 0.4599559147685525,
"eval_f1_fear": 0.6475358702432937,
"eval_f1_joy": 0.7468589083419156,
"eval_f1_neutral": 0.8421338155515371,
"eval_f1_sadness": 0.6752079118903124,
"eval_f1_surprise": 0.42070338420703385,
"eval_loss": 0.6962281465530396,
"eval_prec": 0.7432901970674257,
"eval_prec_anger": 0.6757728253055356,
"eval_prec_disgust": 0.39076154806491886,
"eval_prec_fear": 0.6938502673796791,
"eval_prec_joy": 0.7354969574036511,
"eval_prec_neutral": 0.8121730031391698,
"eval_prec_sadness": 0.683037744429286,
"eval_prec_surprise": 0.5493934142114385,
"eval_recall": 0.7475354978746496,
"eval_recall_anger": 0.4504072831816004,
"eval_recall_disgust": 0.5589285714285714,
"eval_recall_fear": 0.6070175438596491,
"eval_recall_joy": 0.7585774058577406,
"eval_recall_neutral": 0.8743897859556891,
"eval_recall_sadness": 0.6675555555555556,
"eval_recall_surprise": 0.34086021505376346,
"eval_runtime": 14.6912,
"eval_samples_per_second": 1505.258,
"eval_steps_per_second": 11.776,
"step": 1392
},
{
"epoch": 0.91,
"learning_rate": 3.8691902252036415e-05,
"loss": 0.7143,
"step": 1410
},
{
"epoch": 0.94,
"learning_rate": 3.812889314805942e-05,
"loss": 0.6903,
"step": 1457
},
{
"epoch": 0.97,
"learning_rate": 3.7565884044082415e-05,
"loss": 0.6812,
"step": 1504
},
{
"epoch": 1.0,
"learning_rate": 3.7002874940105415e-05,
"loss": 0.7182,
"step": 1551
},
{
"epoch": 1.03,
"learning_rate": 3.6439865836128415e-05,
"loss": 0.6362,
"step": 1598
},
{
"epoch": 1.05,
"eval_accuracy": 0.7526453830152844,
"eval_b_acc": 0.6055170494206373,
"eval_f1": 0.7483739984911967,
"eval_f1_anger": 0.602752507581059,
"eval_f1_disgust": 0.4405010438413361,
"eval_f1_fear": 0.6491803278688525,
"eval_f1_joy": 0.7437363551304709,
"eval_f1_neutral": 0.8435330654000731,
"eval_f1_sadness": 0.6785631517960602,
"eval_f1_surprise": 0.45454545454545453,
"eval_loss": 0.6771188974380493,
"eval_prec": 0.7472415916170276,
"eval_prec_anger": 0.5872727272727273,
"eval_prec_disgust": 0.5301507537688442,
"eval_prec_fear": 0.7388059701492538,
"eval_prec_joy": 0.739202314527795,
"eval_prec_neutral": 0.8213269299181786,
"eval_prec_sadness": 0.7089588377723971,
"eval_prec_surprise": 0.5300859598853869,
"eval_recall": 0.7526453830152844,
"eval_recall_anger": 0.6190704360325826,
"eval_recall_disgust": 0.3767857142857143,
"eval_recall_fear": 0.5789473684210527,
"eval_recall_joy": 0.748326359832636,
"eval_recall_neutral": 0.8669733383402178,
"eval_recall_sadness": 0.6506666666666666,
"eval_recall_surprise": 0.3978494623655914,
"eval_runtime": 14.8683,
"eval_samples_per_second": 1487.33,
"eval_steps_per_second": 11.636,
"step": 1624
},
{
"epoch": 1.06,
"learning_rate": 3.5876856732151415e-05,
"loss": 0.6432,
"step": 1645
},
{
"epoch": 1.09,
"learning_rate": 3.5313847628174415e-05,
"loss": 0.652,
"step": 1692
},
{
"epoch": 1.12,
"learning_rate": 3.4750838524197415e-05,
"loss": 0.6474,
"step": 1739
},
{
"epoch": 1.16,
"learning_rate": 3.4187829420220415e-05,
"loss": 0.6364,
"step": 1786
},
{
"epoch": 1.19,
"learning_rate": 3.362482031624341e-05,
"loss": 0.621,
"step": 1833
},
{
"epoch": 1.2,
"eval_accuracy": 0.7528262639052185,
"eval_b_acc": 0.6120366345893286,
"eval_f1": 0.7487165396015127,
"eval_f1_anger": 0.6196334421290485,
"eval_f1_disgust": 0.47378277153558057,
"eval_f1_fear": 0.6528640441683919,
"eval_f1_joy": 0.7450472872075661,
"eval_f1_neutral": 0.8372220697227559,
"eval_f1_sadness": 0.6809026935209901,
"eval_f1_surprise": 0.4612676056338028,
"eval_loss": 0.67792809009552,
"eval_prec": 0.749407175516463,
"eval_prec_anger": 0.6508438818565401,
"eval_prec_disgust": 0.49803149606299213,
"eval_prec_fear": 0.7962962962962963,
"eval_prec_joy": 0.7107312440645774,
"eval_prec_neutral": 0.8165268606103873,
"eval_prec_sadness": 0.7498663816141101,
"eval_prec_surprise": 0.5077519379844961,
"eval_recall": 0.7528262639052185,
"eval_recall_anger": 0.5912793483469094,
"eval_recall_disgust": 0.4517857142857143,
"eval_recall_fear": 0.5532163742690058,
"eval_recall_joy": 0.7828451882845189,
"eval_recall_neutral": 0.8589936162223056,
"eval_recall_sadness": 0.6235555555555555,
"eval_recall_surprise": 0.42258064516129035,
"eval_runtime": 14.7115,
"eval_samples_per_second": 1503.179,
"eval_steps_per_second": 11.76,
"step": 1856
},
{
"epoch": 1.22,
"learning_rate": 3.3061811212266415e-05,
"loss": 0.6195,
"step": 1880
},
{
"epoch": 1.25,
"learning_rate": 3.249880210828941e-05,
"loss": 0.6332,
"step": 1927
},
{
"epoch": 1.28,
"learning_rate": 3.1935793004312415e-05,
"loss": 0.6251,
"step": 1974
},
{
"epoch": 1.31,
"learning_rate": 3.1372783900335415e-05,
"loss": 0.63,
"step": 2021
},
{
"epoch": 1.34,
"learning_rate": 3.080977479635841e-05,
"loss": 0.6241,
"step": 2068
},
{
"epoch": 1.35,
"eval_accuracy": 0.7512887763407796,
"eval_b_acc": 0.6367091163081916,
"eval_f1": 0.7514440246825209,
"eval_f1_anger": 0.6141022752872269,
"eval_f1_disgust": 0.4511668107173725,
"eval_f1_fear": 0.6488060570762958,
"eval_f1_joy": 0.7509570615623384,
"eval_f1_neutral": 0.843150231634679,
"eval_f1_sadness": 0.6745293717396236,
"eval_f1_surprise": 0.4730290456431535,
"eval_loss": 0.6849319338798523,
"eval_prec": 0.7525985800729426,
"eval_prec_anger": 0.5795068027210885,
"eval_prec_disgust": 0.4371859296482412,
"eval_prec_fear": 0.6461716937354989,
"eval_prec_joy": 0.7428863868986694,
"eval_prec_neutral": 0.849171586364502,
"eval_prec_sadness": 0.6887447892542844,
"eval_prec_surprise": 0.5270805812417437,
"eval_recall": 0.7512887763407796,
"eval_recall_anger": 0.6530905606133206,
"eval_recall_disgust": 0.4660714285714286,
"eval_recall_fear": 0.6514619883040935,
"eval_recall_joy": 0.7592050209205021,
"eval_recall_neutral": 0.8372136687945926,
"eval_recall_sadness": 0.6608888888888889,
"eval_recall_surprise": 0.4290322580645161,
"eval_runtime": 14.591,
"eval_samples_per_second": 1515.587,
"eval_steps_per_second": 11.857,
"step": 2088
},
{
"epoch": 1.37,
"learning_rate": 3.024676569238141e-05,
"loss": 0.5997,
"step": 2115
},
{
"epoch": 1.4,
"learning_rate": 2.968375658840441e-05,
"loss": 0.6348,
"step": 2162
},
{
"epoch": 1.43,
"learning_rate": 2.9120747484427408e-05,
"loss": 0.6269,
"step": 2209
},
{
"epoch": 1.46,
"learning_rate": 2.855773838045041e-05,
"loss": 0.6411,
"step": 2256
},
{
"epoch": 1.49,
"learning_rate": 2.7994729276473408e-05,
"loss": 0.6188,
"step": 2303
},
{
"epoch": 1.5,
"eval_accuracy": 0.7578909288233698,
"eval_b_acc": 0.6158634091154939,
"eval_f1": 0.7533929534836733,
"eval_f1_anger": 0.6305133767172812,
"eval_f1_disgust": 0.45919477693144717,
"eval_f1_fear": 0.6729323308270676,
"eval_f1_joy": 0.7494099134539732,
"eval_f1_neutral": 0.84280126653008,
"eval_f1_sadness": 0.681602172437203,
"eval_f1_surprise": 0.4503664223850767,
"eval_loss": 0.6713131070137024,
"eval_prec": 0.7538941653702528,
"eval_prec_anger": 0.6343355965082444,
"eval_prec_disgust": 0.5877437325905293,
"eval_prec_fear": 0.7246963562753036,
"eval_prec_joy": 0.7071269487750557,
"eval_prec_neutral": 0.8361049519586105,
"eval_prec_sadness": 0.69432918395574,
"eval_prec_surprise": 0.5919439579684763,
"eval_recall": 0.7578909288233698,
"eval_recall_anger": 0.6267369429803545,
"eval_recall_disgust": 0.3767857142857143,
"eval_recall_fear": 0.6280701754385964,
"eval_recall_joy": 0.797071129707113,
"eval_recall_neutral": 0.8496057078482914,
"eval_recall_sadness": 0.6693333333333333,
"eval_recall_surprise": 0.3634408602150538,
"eval_runtime": 14.588,
"eval_samples_per_second": 1515.9,
"eval_steps_per_second": 11.859,
"step": 2320
},
{
"epoch": 1.52,
"learning_rate": 2.7431720172496405e-05,
"loss": 0.622,
"step": 2350
},
{
"epoch": 1.55,
"learning_rate": 2.6868711068519408e-05,
"loss": 0.6278,
"step": 2397
},
{
"epoch": 1.58,
"learning_rate": 2.6305701964542405e-05,
"loss": 0.6227,
"step": 2444
},
{
"epoch": 1.61,
"learning_rate": 2.5742692860565405e-05,
"loss": 0.6337,
"step": 2491
},
{
"epoch": 1.64,
"learning_rate": 2.5179683756588408e-05,
"loss": 0.6182,
"step": 2538
},
{
"epoch": 1.65,
"eval_accuracy": 0.760106719725061,
"eval_b_acc": 0.6198832054514857,
"eval_f1": 0.7565733944354605,
"eval_f1_anger": 0.625943396226415,
"eval_f1_disgust": 0.4582893347412883,
"eval_f1_fear": 0.6753246753246753,
"eval_f1_joy": 0.7498260610277309,
"eval_f1_neutral": 0.8475095074668398,
"eval_f1_sadness": 0.6851194700733381,
"eval_f1_surprise": 0.4700181708055723,
"eval_loss": 0.6608244180679321,
"eval_prec": 0.7566647637236428,
"eval_prec_anger": 0.6163492800743149,
"eval_prec_disgust": 0.5607235142118863,
"eval_prec_fear": 0.7591240875912408,
"eval_prec_joy": 0.7142586631319826,
"eval_prec_neutral": 0.8374885426214482,
"eval_prec_sadness": 0.7324228629236217,
"eval_prec_surprise": 0.5381414701803051,
"eval_recall": 0.760106719725061,
"eval_recall_anger": 0.6358409199808337,
"eval_recall_disgust": 0.3875,
"eval_recall_fear": 0.6081871345029239,
"eval_recall_joy": 0.7891213389121339,
"eval_recall_neutral": 0.8577731881336839,
"eval_recall_sadness": 0.6435555555555555,
"eval_recall_surprise": 0.4172043010752688,
"eval_runtime": 14.5162,
"eval_samples_per_second": 1523.406,
"eval_steps_per_second": 11.918,
"step": 2552
},
{
"epoch": 1.67,
"learning_rate": 2.4616674652611405e-05,
"loss": 0.6078,
"step": 2585
},
{
"epoch": 1.7,
"learning_rate": 2.4053665548634405e-05,
"loss": 0.6167,
"step": 2632
},
{
"epoch": 1.73,
"learning_rate": 2.3490656444657405e-05,
"loss": 0.6329,
"step": 2679
},
{
"epoch": 1.76,
"learning_rate": 2.29396262577863e-05,
"loss": 0.6153,
"step": 2726
},
{
"epoch": 1.79,
"learning_rate": 2.2376617153809296e-05,
"loss": 0.6392,
"step": 2773
},
{
"epoch": 1.8,
"eval_accuracy": 0.7623677308492358,
"eval_b_acc": 0.626106698297278,
"eval_f1": 0.7595959808260688,
"eval_f1_anger": 0.6317689530685919,
"eval_f1_disgust": 0.46170212765957447,
"eval_f1_fear": 0.6752246469833119,
"eval_f1_joy": 0.7548152004164499,
"eval_f1_neutral": 0.8505247584261871,
"eval_f1_sadness": 0.6872427983539094,
"eval_f1_surprise": 0.4615384615384616,
"eval_loss": 0.6541842818260193,
"eval_prec": 0.7593266897219236,
"eval_prec_anger": 0.5970149253731343,
"eval_prec_disgust": 0.5710526315789474,
"eval_prec_fear": 0.748221906116643,
"eval_prec_joy": 0.7512953367875648,
"eval_prec_neutral": 0.8379338617108499,
"eval_prec_sadness": 0.7076271186440678,
"eval_prec_surprise": 0.5131578947368421,
"eval_recall": 0.7623677308492358,
"eval_recall_anger": 0.6708193579300431,
"eval_recall_disgust": 0.3875,
"eval_recall_fear": 0.6152046783625731,
"eval_recall_joy": 0.7583682008368201,
"eval_recall_neutral": 0.8634998122418325,
"eval_recall_sadness": 0.668,
"eval_recall_surprise": 0.41935483870967744,
"eval_runtime": 14.6661,
"eval_samples_per_second": 1507.827,
"eval_steps_per_second": 11.796,
"step": 2784
},
{
"epoch": 1.82,
"learning_rate": 2.1813608049832296e-05,
"loss": 0.6221,
"step": 2820
},
{
"epoch": 1.85,
"learning_rate": 2.1250598945855296e-05,
"loss": 0.6109,
"step": 2867
},
{
"epoch": 1.88,
"learning_rate": 2.0687589841878296e-05,
"loss": 0.6029,
"step": 2914
},
{
"epoch": 1.92,
"learning_rate": 2.0124580737901292e-05,
"loss": 0.6243,
"step": 2961
},
{
"epoch": 1.95,
"learning_rate": 1.9561571633924296e-05,
"loss": 0.6158,
"step": 3008
},
{
"epoch": 1.95,
"eval_accuracy": 0.764854843085828,
"eval_b_acc": 0.6279403178124943,
"eval_f1": 0.761380516026678,
"eval_f1_anger": 0.6389822371579453,
"eval_f1_disgust": 0.4711729622266402,
"eval_f1_fear": 0.6765847347994824,
"eval_f1_joy": 0.751901635927894,
"eval_f1_neutral": 0.8525969275786394,
"eval_f1_sadness": 0.6901180282342051,
"eval_f1_surprise": 0.46511627906976744,
"eval_loss": 0.6456097960472107,
"eval_prec": 0.7598739530313577,
"eval_prec_anger": 0.6402116402116402,
"eval_prec_disgust": 0.531390134529148,
"eval_prec_fear": 0.7568740955137482,
"eval_prec_joy": 0.7490139090720366,
"eval_prec_neutral": 0.8310160427807487,
"eval_prec_sadness": 0.7199420569773056,
"eval_prec_surprise": 0.5063291139240507,
"eval_recall": 0.764854843085828,
"eval_recall_anger": 0.6377575467177767,
"eval_recall_disgust": 0.4232142857142857,
"eval_recall_fear": 0.6116959064327485,
"eval_recall_joy": 0.7548117154811715,
"eval_recall_neutral": 0.8753285767930905,
"eval_recall_sadness": 0.6626666666666666,
"eval_recall_surprise": 0.43010752688172044,
"eval_runtime": 14.622,
"eval_samples_per_second": 1512.381,
"eval_steps_per_second": 11.832,
"step": 3016
},
{
"epoch": 1.98,
"learning_rate": 1.8998562529947296e-05,
"loss": 0.5901,
"step": 3055
},
{
"epoch": 2.01,
"learning_rate": 1.8435553425970292e-05,
"loss": 0.5923,
"step": 3102
},
{
"epoch": 2.04,
"learning_rate": 1.7872544321993292e-05,
"loss": 0.5239,
"step": 3149
},
{
"epoch": 2.07,
"learning_rate": 1.7309535218016292e-05,
"loss": 0.5329,
"step": 3196
},
{
"epoch": 2.1,
"learning_rate": 1.6758505031145187e-05,
"loss": 0.554,
"step": 3243
},
{
"epoch": 2.1,
"eval_accuracy": 0.7583883512706883,
"eval_b_acc": 0.634571558597101,
"eval_f1": 0.7563700086517053,
"eval_f1_anger": 0.643182362808531,
"eval_f1_disgust": 0.4690181124880839,
"eval_f1_fear": 0.6795752654590881,
"eval_f1_joy": 0.7506092607636069,
"eval_f1_neutral": 0.842095468502838,
"eval_f1_sadness": 0.6862699699004399,
"eval_f1_surprise": 0.47133027522935783,
"eval_loss": 0.6742041707038879,
"eval_prec": 0.7554687165264222,
"eval_prec_anger": 0.6433365292425696,
"eval_prec_disgust": 0.5030674846625767,
"eval_prec_fear": 0.7292225201072386,
"eval_prec_joy": 0.7292817679558011,
"eval_prec_neutral": 0.8347168419110865,
"eval_prec_sadness": 0.7162880618656355,
"eval_prec_surprise": 0.504914004914005,
"eval_recall": 0.7583883512706883,
"eval_recall_anger": 0.6430282702443699,
"eval_recall_disgust": 0.4392857142857143,
"eval_recall_fear": 0.6362573099415205,
"eval_recall_joy": 0.7732217573221757,
"eval_recall_neutral": 0.8496057078482914,
"eval_recall_sadness": 0.6586666666666666,
"eval_recall_surprise": 0.44193548387096776,
"eval_runtime": 14.8261,
"eval_samples_per_second": 1491.559,
"eval_steps_per_second": 11.669,
"step": 3248
},
{
"epoch": 2.13,
"learning_rate": 1.6195495927168187e-05,
"loss": 0.5568,
"step": 3290
},
{
"epoch": 2.16,
"learning_rate": 1.5632486823191184e-05,
"loss": 0.5375,
"step": 3337
},
{
"epoch": 2.19,
"learning_rate": 1.5069477719214184e-05,
"loss": 0.5198,
"step": 3384
},
{
"epoch": 2.22,
"learning_rate": 1.4506468615237184e-05,
"loss": 0.5255,
"step": 3431
},
{
"epoch": 2.25,
"learning_rate": 1.3943459511260182e-05,
"loss": 0.5537,
"step": 3478
},
{
"epoch": 2.25,
"eval_accuracy": 0.7632721352989057,
"eval_b_acc": 0.6282518018397625,
"eval_f1": 0.7604673635172584,
"eval_f1_anger": 0.6454630495790459,
"eval_f1_disgust": 0.45434782608695656,
"eval_f1_fear": 0.6718246292714378,
"eval_f1_joy": 0.7522695178535405,
"eval_f1_neutral": 0.8484961703717542,
"eval_f1_sadness": 0.6950892857142857,
"eval_f1_surprise": 0.47641791044776116,
"eval_loss": 0.670791745185852,
"eval_prec": 0.7603587760472442,
"eval_prec_anger": 0.6304248515303792,
"eval_prec_disgust": 0.5805555555555556,
"eval_prec_fear": 0.7485632183908046,
"eval_prec_joy": 0.726334242306194,
"eval_prec_neutral": 0.8442379182156133,
"eval_prec_sadness": 0.6982062780269058,
"eval_prec_surprise": 0.5355704697986577,
"eval_recall": 0.7632721352989057,
"eval_recall_anger": 0.6612362242453282,
"eval_recall_disgust": 0.3732142857142857,
"eval_recall_fear": 0.6093567251461989,
"eval_recall_joy": 0.7801255230125523,
"eval_recall_neutral": 0.8527975966954563,
"eval_recall_sadness": 0.692,
"eval_recall_surprise": 0.4290322580645161,
"eval_runtime": 14.5517,
"eval_samples_per_second": 1519.68,
"eval_steps_per_second": 11.889,
"step": 3480
},
{
"epoch": 2.28,
"learning_rate": 1.3380450407283182e-05,
"loss": 0.5305,
"step": 3525
},
{
"epoch": 2.31,
"learning_rate": 1.2817441303306182e-05,
"loss": 0.5313,
"step": 3572
},
{
"epoch": 2.34,
"learning_rate": 1.2254432199329182e-05,
"loss": 0.5182,
"step": 3619
},
{
"epoch": 2.37,
"learning_rate": 1.169142309535218e-05,
"loss": 0.5375,
"step": 3666
},
{
"epoch": 2.4,
"eval_accuracy": 0.7605589219498959,
"eval_b_acc": 0.6402110359246711,
"eval_f1": 0.7594675823716318,
"eval_f1_anger": 0.6421420256111757,
"eval_f1_disgust": 0.4648148148148148,
"eval_f1_fear": 0.6746532156368222,
"eval_f1_joy": 0.7537328697075065,
"eval_f1_neutral": 0.8463990997749438,
"eval_f1_sadness": 0.6885171790235082,
"eval_f1_surprise": 0.4835924006908463,
"eval_loss": 0.671157717704773,
"eval_prec": 0.7592351302120464,
"eval_prec_anger": 0.6245471014492754,
"eval_prec_disgust": 0.4826923076923077,
"eval_prec_fear": 0.7318741450068399,
"eval_prec_joy": 0.7372949179671868,
"eval_prec_neutral": 0.8454477332334207,
"eval_prec_sadness": 0.7005519779208832,
"eval_prec_surprise": 0.5204460966542751,
"eval_recall": 0.7605589219498959,
"eval_recall_anger": 0.6607570675610924,
"eval_recall_disgust": 0.44821428571428573,
"eval_recall_fear": 0.6257309941520468,
"eval_recall_joy": 0.7709205020920502,
"eval_recall_neutral": 0.847352609838528,
"eval_recall_sadness": 0.6768888888888889,
"eval_recall_surprise": 0.45161290322580644,
"eval_runtime": 14.5753,
"eval_samples_per_second": 1517.225,
"eval_steps_per_second": 11.869,
"step": 3712
},
{
"epoch": 2.4,
"learning_rate": 1.112841399137518e-05,
"loss": 0.5266,
"step": 3713
},
{
"epoch": 2.43,
"learning_rate": 1.056540488739818e-05,
"loss": 0.5276,
"step": 3760
},
{
"epoch": 2.46,
"learning_rate": 1.000239578342118e-05,
"loss": 0.5432,
"step": 3807
},
{
"epoch": 2.49,
"learning_rate": 9.439386679444178e-06,
"loss": 0.5262,
"step": 3854
},
{
"epoch": 2.52,
"learning_rate": 8.876377575467178e-06,
"loss": 0.5175,
"step": 3901
},
{
"epoch": 2.55,
"eval_accuracy": 0.7625033915166862,
"eval_b_acc": 0.6369042077487537,
"eval_f1": 0.7603749093215698,
"eval_f1_anger": 0.6429077177248053,
"eval_f1_disgust": 0.46938775510204084,
"eval_f1_fear": 0.677336747759283,
"eval_f1_joy": 0.7530406101834674,
"eval_f1_neutral": 0.8487682904241526,
"eval_f1_sadness": 0.6956521739130433,
"eval_f1_surprise": 0.457388105456775,
"eval_loss": 0.66249018907547,
"eval_prec": 0.7600295878449174,
"eval_prec_anger": 0.6334883720930232,
"eval_prec_disgust": 0.44805194805194803,
"eval_prec_fear": 0.7482319660537482,
"eval_prec_joy": 0.7421779764323446,
"eval_prec_neutral": 0.8374451754385965,
"eval_prec_sadness": 0.7251687560270009,
"eval_prec_surprise": 0.5320970042796006,
"eval_recall": 0.7625033915166862,
"eval_recall_anger": 0.6526114039290848,
"eval_recall_disgust": 0.4928571428571429,
"eval_recall_fear": 0.6187134502923977,
"eval_recall_joy": 0.7642259414225941,
"eval_recall_neutral": 0.8604018024784078,
"eval_recall_sadness": 0.6684444444444444,
"eval_recall_surprise": 0.4010752688172043,
"eval_runtime": 14.6386,
"eval_samples_per_second": 1510.666,
"eval_steps_per_second": 11.818,
"step": 3944
},
{
"epoch": 2.55,
"learning_rate": 8.313368471490178e-06,
"loss": 0.5337,
"step": 3948
},
{
"epoch": 2.58,
"learning_rate": 7.750359367513177e-06,
"loss": 0.5148,
"step": 3995
},
{
"epoch": 2.61,
"learning_rate": 7.1873502635361775e-06,
"loss": 0.5234,
"step": 4042
},
{
"epoch": 2.64,
"learning_rate": 6.624341159559177e-06,
"loss": 0.5286,
"step": 4089
},
{
"epoch": 2.68,
"learning_rate": 6.061332055582176e-06,
"loss": 0.5182,
"step": 4136
},
{
"epoch": 2.7,
"eval_accuracy": 0.7631364746314552,
"eval_b_acc": 0.6403726819328496,
"eval_f1": 0.7611758530200116,
"eval_f1_anger": 0.6441332689521971,
"eval_f1_disgust": 0.4635036496350365,
"eval_f1_fear": 0.6658725431804646,
"eval_f1_joy": 0.7548551093035079,
"eval_f1_neutral": 0.848629209284947,
"eval_f1_sadness": 0.6971687429218574,
"eval_f1_surprise": 0.4763636363636364,
"eval_loss": 0.6621036529541016,
"eval_prec": 0.7602393679680954,
"eval_prec_anger": 0.6491484184914842,
"eval_prec_disgust": 0.47388059701492535,
"eval_prec_fear": 0.6783980582524272,
"eval_prec_joy": 0.734322453016815,
"eval_prec_neutral": 0.844409331722279,
"eval_prec_sadness": 0.7108545034642032,
"eval_prec_surprise": 0.5458333333333333,
"eval_recall": 0.7631364746314552,
"eval_recall_anger": 0.639195016770484,
"eval_recall_disgust": 0.45357142857142857,
"eval_recall_fear": 0.6538011695906433,
"eval_recall_joy": 0.7765690376569038,
"eval_recall_neutral": 0.8528914757791964,
"eval_recall_sadness": 0.684,
"eval_recall_surprise": 0.42258064516129035,
"eval_runtime": 14.5758,
"eval_samples_per_second": 1517.169,
"eval_steps_per_second": 11.869,
"step": 4176
}
],
"max_steps": 4638,
"num_train_epochs": 3,
"total_flos": 3.51500575835136e+16,
"trial_name": null,
"trial_params": null
}