lora-roberta-large_6 / trainer_state.json
anniew666's picture
End of training
6a712d9
raw
history blame contribute delete
No virus
39.2 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"global_step": 6750,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1,
"learning_rate": 0.00020118343195266273,
"loss": 1.7507,
"step": 68
},
{
"epoch": 0.2,
"learning_rate": 0.0003964497041420119,
"loss": 1.3034,
"step": 136
},
{
"epoch": 0.3,
"learning_rate": 0.0005976331360946747,
"loss": 1.0804,
"step": 204
},
{
"epoch": 0.4,
"learning_rate": 0.0007988165680473373,
"loss": 1.0422,
"step": 272
},
{
"epoch": 0.5,
"eval_accuracy": 0.6383438174819266,
"eval_b_acc": 0.5557953715324906,
"eval_f1": 0.5678620864085909,
"eval_f1_anger": 0.5061845861084682,
"eval_f1_disgust": 0.4514991181657848,
"eval_f1_fear": 0.616,
"eval_f1_joy": 0.7740843336411203,
"eval_f1_neutral": 0.6170991880273841,
"eval_f1_sadness": 0.6455840455840456,
"eval_f1_surprise": 0.36458333333333337,
"eval_loss": 1.0251680612564087,
"eval_micro_f1": 0.6383438174819266,
"eval_prec": 0.6048114859725054,
"eval_prec_anger": 0.6150289017341041,
"eval_prec_disgust": 0.5039370078740157,
"eval_prec_fear": 0.6015625,
"eval_prec_joy": 0.7407952871870398,
"eval_prec_neutral": 0.5776453055141579,
"eval_prec_sadness": 0.6127636560302866,
"eval_prec_surprise": 0.5819477434679335,
"eval_recall": 0.5557953715324906,
"eval_recall_anger": 0.43007275666936134,
"eval_recall_disgust": 0.40894568690095845,
"eval_recall_fear": 0.6311475409836066,
"eval_recall_joy": 0.8105059619722849,
"eval_recall_neutral": 0.6623376623376623,
"eval_recall_sadness": 0.6821192052980133,
"eval_recall_surprise": 0.26543878656554715,
"eval_runtime": 24.1861,
"eval_samples_per_second": 440.377,
"eval_steps_per_second": 6.905,
"step": 338
},
{
"epoch": 0.5,
"learning_rate": 0.001,
"loss": 1.0565,
"step": 340
},
{
"epoch": 0.6,
"learning_rate": 0.0009895508421709294,
"loss": 1.0317,
"step": 408
},
{
"epoch": 0.71,
"learning_rate": 0.0009789457267623206,
"loss": 0.974,
"step": 476
},
{
"epoch": 0.81,
"learning_rate": 0.0009684965689332502,
"loss": 0.9789,
"step": 544
},
{
"epoch": 0.91,
"learning_rate": 0.0009580474111041797,
"loss": 0.9507,
"step": 612
},
{
"epoch": 1.0,
"eval_accuracy": 0.6719556849122148,
"eval_b_acc": 0.6125400888652602,
"eval_f1": 0.6123789895174323,
"eval_f1_anger": 0.5357142857142856,
"eval_f1_disgust": 0.41237113402061853,
"eval_f1_fear": 0.686175580221998,
"eval_f1_joy": 0.8051904280417931,
"eval_f1_neutral": 0.6598122485471614,
"eval_f1_sadness": 0.6885768985322271,
"eval_f1_surprise": 0.498812351543943,
"eval_loss": 0.9057269096374512,
"eval_micro_f1": 0.6719556849122148,
"eval_prec": 0.6284890546096126,
"eval_prec_anger": 0.6646706586826348,
"eval_prec_disgust": 0.34557235421166305,
"eval_prec_fear": 0.6759443339960238,
"eval_prec_joy": 0.8438714235252561,
"eval_prec_neutral": 0.5849405548216645,
"eval_prec_sadness": 0.7325186693822132,
"eval_prec_surprise": 0.5519053876478318,
"eval_recall": 0.6125400888652602,
"eval_recall_anger": 0.4486661277283751,
"eval_recall_disgust": 0.5111821086261981,
"eval_recall_fear": 0.6967213114754098,
"eval_recall_joy": 0.7699000966806316,
"eval_recall_neutral": 0.7566643882433356,
"eval_recall_sadness": 0.6496086694762191,
"eval_recall_surprise": 0.4550379198266522,
"eval_runtime": 23.8558,
"eval_samples_per_second": 446.474,
"eval_steps_per_second": 7.0,
"step": 676
},
{
"epoch": 1.01,
"learning_rate": 0.0009474422956955708,
"loss": 0.9371,
"step": 680
},
{
"epoch": 1.11,
"learning_rate": 0.0009368371802869619,
"loss": 0.8971,
"step": 748
},
{
"epoch": 1.21,
"learning_rate": 0.000926232064878353,
"loss": 0.9107,
"step": 816
},
{
"epoch": 1.31,
"learning_rate": 0.0009156269494697443,
"loss": 0.8887,
"step": 884
},
{
"epoch": 1.41,
"learning_rate": 0.0009050218340611354,
"loss": 0.857,
"step": 952
},
{
"epoch": 1.5,
"eval_accuracy": 0.6918599192564079,
"eval_b_acc": 0.6177828469165695,
"eval_f1": 0.6316885976822759,
"eval_f1_anger": 0.5861297539149888,
"eval_f1_disgust": 0.4470134874759152,
"eval_f1_fear": 0.7041123370110332,
"eval_f1_joy": 0.8179705654531372,
"eval_f1_neutral": 0.6586212597123492,
"eval_f1_sadness": 0.7127121167013992,
"eval_f1_surprise": 0.495260663507109,
"eval_loss": 0.843808650970459,
"eval_micro_f1": 0.6918599192564079,
"eval_prec": 0.6551138277981501,
"eval_prec_anger": 0.656312625250501,
"eval_prec_disgust": 0.5631067961165048,
"eval_prec_fear": 0.6895874263261297,
"eval_prec_joy": 0.7875894988066826,
"eval_prec_neutral": 0.6378482228626321,
"eval_prec_sadness": 0.7049469964664311,
"eval_prec_surprise": 0.5464052287581699,
"eval_recall": 0.6177828469165695,
"eval_recall_anger": 0.5295068714632175,
"eval_recall_disgust": 0.3706070287539936,
"eval_recall_fear": 0.7192622950819673,
"eval_recall_joy": 0.8507895584917822,
"eval_recall_neutral": 0.6807928913192071,
"eval_recall_sadness": 0.7206502107164359,
"eval_recall_surprise": 0.4528710725893825,
"eval_runtime": 24.2124,
"eval_samples_per_second": 439.898,
"eval_steps_per_second": 6.897,
"step": 1014
},
{
"epoch": 1.51,
"learning_rate": 0.0008944167186525265,
"loss": 0.9058,
"step": 1020
},
{
"epoch": 1.61,
"learning_rate": 0.0008838116032439177,
"loss": 0.8538,
"step": 1088
},
{
"epoch": 1.71,
"learning_rate": 0.0008732064878353088,
"loss": 0.8627,
"step": 1156
},
{
"epoch": 1.81,
"learning_rate": 0.0008626013724267,
"loss": 0.8627,
"step": 1224
},
{
"epoch": 1.91,
"learning_rate": 0.0008519962570180911,
"loss": 0.854,
"step": 1292
},
{
"epoch": 2.0,
"eval_accuracy": 0.6889493944230589,
"eval_b_acc": 0.6265220182600301,
"eval_f1": 0.6223880774246929,
"eval_f1_anger": 0.6043478260869566,
"eval_f1_disgust": 0.3648648648648649,
"eval_f1_fear": 0.6816546762589928,
"eval_f1_joy": 0.8182651191203419,
"eval_f1_neutral": 0.6343381389252948,
"eval_f1_sadness": 0.7238670694864048,
"eval_f1_surprise": 0.5293788472299944,
"eval_loss": 0.839374840259552,
"eval_micro_f1": 0.6889493944230589,
"eval_prec": 0.6466212107012735,
"eval_prec_anger": 0.5476034143138543,
"eval_prec_disgust": 0.6183206106870229,
"eval_prec_fear": 0.6073717948717948,
"eval_prec_joy": 0.7776487663280116,
"eval_prec_neutral": 0.7014492753623188,
"eval_prec_sadness": 0.7265009096422074,
"eval_prec_surprise": 0.5474537037037037,
"eval_recall": 0.6265220182600301,
"eval_recall_anger": 0.6742118027485853,
"eval_recall_disgust": 0.25878594249201275,
"eval_recall_fear": 0.7766393442622951,
"eval_recall_joy": 0.8633580406058653,
"eval_recall_neutral": 0.5789473684210527,
"eval_recall_sadness": 0.7212522576760987,
"eval_recall_surprise": 0.5124593716143012,
"eval_runtime": 24.3029,
"eval_samples_per_second": 438.26,
"eval_steps_per_second": 6.872,
"step": 1352
},
{
"epoch": 2.01,
"learning_rate": 0.0008413911416094823,
"loss": 0.8289,
"step": 1360
},
{
"epoch": 2.12,
"learning_rate": 0.0008307860262008734,
"loss": 0.8248,
"step": 1428
},
{
"epoch": 2.22,
"learning_rate": 0.0008201809107922645,
"loss": 0.8191,
"step": 1496
},
{
"epoch": 2.32,
"learning_rate": 0.0008095757953836556,
"loss": 0.8111,
"step": 1564
},
{
"epoch": 2.42,
"learning_rate": 0.0007989706799750468,
"loss": 0.816,
"step": 1632
},
{
"epoch": 2.5,
"eval_accuracy": 0.7003098300629049,
"eval_b_acc": 0.6490961374572984,
"eval_f1": 0.6477239941964422,
"eval_f1_anger": 0.5822784810126582,
"eval_f1_disgust": 0.4823695345557123,
"eval_f1_fear": 0.7401415571284125,
"eval_f1_joy": 0.8206077433287059,
"eval_f1_neutral": 0.6668938490373147,
"eval_f1_sadness": 0.7314319667260843,
"eval_f1_surprise": 0.510344827586207,
"eval_loss": 0.8138801455497742,
"eval_micro_f1": 0.7003098300629049,
"eval_prec": 0.6535404705412103,
"eval_prec_anger": 0.6328273244781784,
"eval_prec_disgust": 0.4318181818181818,
"eval_prec_fear": 0.7305389221556886,
"eval_prec_joy": 0.7869822485207101,
"eval_prec_neutral": 0.6649677200135916,
"eval_prec_sadness": 0.7219941348973608,
"eval_prec_surprise": 0.6056547619047619,
"eval_recall": 0.6490961374572984,
"eval_recall_anger": 0.5392077607113985,
"eval_recall_disgust": 0.5463258785942492,
"eval_recall_fear": 0.75,
"eval_recall_joy": 0.8572349339349017,
"eval_recall_neutral": 0.6688311688311688,
"eval_recall_sadness": 0.741119807344973,
"eval_recall_surprise": 0.4409534127843987,
"eval_runtime": 24.1307,
"eval_samples_per_second": 441.387,
"eval_steps_per_second": 6.921,
"step": 1690
},
{
"epoch": 2.52,
"learning_rate": 0.0007883655645664379,
"loss": 0.807,
"step": 1700
},
{
"epoch": 2.62,
"learning_rate": 0.000777760449157829,
"loss": 0.8051,
"step": 1768
},
{
"epoch": 2.72,
"learning_rate": 0.0007671553337492202,
"loss": 0.8209,
"step": 1836
},
{
"epoch": 2.82,
"learning_rate": 0.0007565502183406114,
"loss": 0.7983,
"step": 1904
},
{
"epoch": 2.92,
"learning_rate": 0.0007459451029320025,
"loss": 0.7876,
"step": 1972
},
{
"epoch": 3.0,
"eval_accuracy": 0.7046286733640034,
"eval_b_acc": 0.6330570060936641,
"eval_f1": 0.6435401792386363,
"eval_f1_anger": 0.6194314806957997,
"eval_f1_disgust": 0.39179954441913445,
"eval_f1_fear": 0.7347347347347347,
"eval_f1_joy": 0.8281374900079936,
"eval_f1_neutral": 0.6717120753447695,
"eval_f1_sadness": 0.7232516437537359,
"eval_f1_surprise": 0.5357142857142857,
"eval_loss": 0.7993302941322327,
"eval_micro_f1": 0.7046286733640034,
"eval_prec": 0.6799789660580686,
"eval_prec_anger": 0.6517857142857143,
"eval_prec_disgust": 0.6825396825396826,
"eval_prec_fear": 0.7181996086105675,
"eval_prec_joy": 0.8217005076142132,
"eval_prec_neutral": 0.6612582781456954,
"eval_prec_sadness": 0.7181008902077152,
"eval_prec_surprise": 0.506268081002893,
"eval_recall": 0.6330570060936641,
"eval_recall_anger": 0.5901374292643492,
"eval_recall_disgust": 0.2747603833865815,
"eval_recall_fear": 0.7520491803278688,
"eval_recall_joy": 0.8346761198839833,
"eval_recall_neutral": 0.6825017088174983,
"eval_recall_sadness": 0.7284768211920529,
"eval_recall_surprise": 0.5687973997833152,
"eval_runtime": 23.8724,
"eval_samples_per_second": 446.164,
"eval_steps_per_second": 6.996,
"step": 2028
},
{
"epoch": 3.02,
"learning_rate": 0.0007353399875233937,
"loss": 0.783,
"step": 2040
},
{
"epoch": 3.12,
"learning_rate": 0.0007247348721147848,
"loss": 0.7723,
"step": 2108
},
{
"epoch": 3.22,
"learning_rate": 0.000714129756706176,
"loss": 0.7724,
"step": 2176
},
{
"epoch": 3.32,
"learning_rate": 0.0007035246412975671,
"loss": 0.7593,
"step": 2244
},
{
"epoch": 3.43,
"learning_rate": 0.0006929195258889582,
"loss": 0.7702,
"step": 2312
},
{
"epoch": 3.51,
"eval_accuracy": 0.7089475166651019,
"eval_b_acc": 0.6231500096992002,
"eval_f1": 0.6415321615476264,
"eval_f1_anger": 0.6133553173948887,
"eval_f1_disgust": 0.4285714285714286,
"eval_f1_fear": 0.7392197125256674,
"eval_f1_joy": 0.8359721342621912,
"eval_f1_neutral": 0.68096,
"eval_f1_sadness": 0.7288784221371798,
"eval_f1_surprise": 0.463768115942029,
"eval_loss": 0.776013195514679,
"eval_micro_f1": 0.7089475166651019,
"eval_prec": 0.6819240628589138,
"eval_prec_anger": 0.6257359125315392,
"eval_prec_disgust": 0.5932203389830508,
"eval_prec_fear": 0.7407407407407407,
"eval_prec_joy": 0.8216619981325863,
"eval_prec_neutral": 0.6401925391095066,
"eval_prec_sadness": 0.7131336405529954,
"eval_prec_surprise": 0.6387832699619772,
"eval_recall": 0.6231500096992002,
"eval_recall_anger": 0.6014551333872271,
"eval_recall_disgust": 0.3354632587859425,
"eval_recall_fear": 0.7377049180327869,
"eval_recall_joy": 0.8507895584917822,
"eval_recall_neutral": 0.7272727272727273,
"eval_recall_sadness": 0.7453341360626129,
"eval_recall_surprise": 0.3640303358613218,
"eval_runtime": 23.1987,
"eval_samples_per_second": 459.121,
"eval_steps_per_second": 7.199,
"step": 2366
},
{
"epoch": 3.53,
"learning_rate": 0.0006823144104803494,
"loss": 0.7601,
"step": 2380
},
{
"epoch": 3.63,
"learning_rate": 0.0006717092950717405,
"loss": 0.7553,
"step": 2448
},
{
"epoch": 3.73,
"learning_rate": 0.0006611041796631316,
"loss": 0.7648,
"step": 2516
},
{
"epoch": 3.83,
"learning_rate": 0.0006504990642545227,
"loss": 0.7673,
"step": 2584
},
{
"epoch": 3.93,
"learning_rate": 0.0006398939488459139,
"loss": 0.7555,
"step": 2652
},
{
"epoch": 4.01,
"eval_accuracy": 0.7130785841705004,
"eval_b_acc": 0.6285704821250481,
"eval_f1": 0.6448874496365863,
"eval_f1_anger": 0.624401913875598,
"eval_f1_disgust": 0.4025157232704403,
"eval_f1_fear": 0.7389969293756398,
"eval_f1_joy": 0.8360108159694608,
"eval_f1_neutral": 0.6865865540759987,
"eval_f1_sadness": 0.7355298308103294,
"eval_f1_surprise": 0.49017038007863695,
"eval_loss": 0.781408429145813,
"eval_micro_f1": 0.7130785841705004,
"eval_prec": 0.6806800811254893,
"eval_prec_anger": 0.6160503540519277,
"eval_prec_disgust": 0.5853658536585366,
"eval_prec_fear": 0.7382413087934561,
"eval_prec_joy": 0.8253768844221105,
"eval_prec_neutral": 0.6540841584158416,
"eval_prec_sadness": 0.7254098360655737,
"eval_prec_surprise": 0.6202321724709784,
"eval_recall": 0.6285704821250481,
"eval_recall_anger": 0.6329830234438156,
"eval_recall_disgust": 0.30670926517571884,
"eval_recall_fear": 0.7397540983606558,
"eval_recall_joy": 0.8469223332259104,
"eval_recall_neutral": 0.722488038277512,
"eval_recall_sadness": 0.7459361830222757,
"eval_recall_surprise": 0.40520043336944744,
"eval_runtime": 23.5224,
"eval_samples_per_second": 452.802,
"eval_steps_per_second": 7.1,
"step": 2704
},
{
"epoch": 4.03,
"learning_rate": 0.000629288833437305,
"loss": 0.7582,
"step": 2720
},
{
"epoch": 4.13,
"learning_rate": 0.0006186837180286962,
"loss": 0.7238,
"step": 2788
},
{
"epoch": 4.23,
"learning_rate": 0.0006080786026200873,
"loss": 0.7259,
"step": 2856
},
{
"epoch": 4.33,
"learning_rate": 0.0005974734872114786,
"loss": 0.7365,
"step": 2924
},
{
"epoch": 4.43,
"learning_rate": 0.0005868683718028697,
"loss": 0.741,
"step": 2992
},
{
"epoch": 4.51,
"eval_accuracy": 0.7109191625199511,
"eval_b_acc": 0.6500535936090646,
"eval_f1": 0.652803212864719,
"eval_f1_anger": 0.6246893123446562,
"eval_f1_disgust": 0.44288224956063266,
"eval_f1_fear": 0.71939736346516,
"eval_f1_joy": 0.8302588745930863,
"eval_f1_neutral": 0.67920054200542,
"eval_f1_sadness": 0.7310738042445359,
"eval_f1_surprise": 0.5421203438395417,
"eval_loss": 0.7749422788619995,
"eval_micro_f1": 0.7109191625199512,
"eval_prec": 0.6597531133459169,
"eval_prec_anger": 0.6406117247238743,
"eval_prec_disgust": 0.4921875,
"eval_prec_fear": 0.6655052264808362,
"eval_prec_joy": 0.7998805256869773,
"eval_prec_neutral": 0.6732706514439221,
"eval_prec_sadness": 0.7713903743315508,
"eval_prec_surprise": 0.5754257907542579,
"eval_recall": 0.6500535936090646,
"eval_recall_anger": 0.6095392077607114,
"eval_recall_disgust": 0.402555910543131,
"eval_recall_fear": 0.7827868852459017,
"eval_recall_joy": 0.8630357718337093,
"eval_recall_neutral": 0.6852358168147642,
"eval_recall_sadness": 0.6947621914509332,
"eval_recall_surprise": 0.5124593716143012,
"eval_runtime": 23.1988,
"eval_samples_per_second": 459.118,
"eval_steps_per_second": 7.199,
"step": 3042
},
{
"epoch": 4.53,
"learning_rate": 0.0005762632563942608,
"loss": 0.7384,
"step": 3060
},
{
"epoch": 4.63,
"learning_rate": 0.0005656581409856519,
"loss": 0.7261,
"step": 3128
},
{
"epoch": 4.73,
"learning_rate": 0.0005550530255770431,
"loss": 0.7251,
"step": 3196
},
{
"epoch": 4.84,
"learning_rate": 0.0005444479101684342,
"loss": 0.706,
"step": 3264
},
{
"epoch": 4.94,
"learning_rate": 0.0005338427947598253,
"loss": 0.7095,
"step": 3332
},
{
"epoch": 5.01,
"eval_accuracy": 0.7097925077457515,
"eval_b_acc": 0.6314010234335491,
"eval_f1": 0.6434870145096283,
"eval_f1_anger": 0.6263650546021841,
"eval_f1_disgust": 0.3715596330275229,
"eval_f1_fear": 0.7471383975026016,
"eval_f1_joy": 0.8331495194580116,
"eval_f1_neutral": 0.6691241004037213,
"eval_f1_sadness": 0.7310117905127502,
"eval_f1_surprise": 0.5260606060606061,
"eval_loss": 0.7920894622802734,
"eval_micro_f1": 0.7097925077457516,
"eval_prec": 0.6848142661230001,
"eval_prec_anger": 0.6051243406179352,
"eval_prec_disgust": 0.6585365853658537,
"eval_prec_fear": 0.758985200845666,
"eval_prec_joy": 0.815043156596794,
"eval_prec_neutral": 0.6878383255142548,
"eval_prec_sadness": 0.6711983887210473,
"eval_prec_surprise": 0.5969738651994498,
"eval_recall": 0.6314010234335491,
"eval_recall_anger": 0.6491511721907841,
"eval_recall_disgust": 0.25878594249201275,
"eval_recall_fear": 0.735655737704918,
"eval_recall_joy": 0.852078633580406,
"eval_recall_neutral": 0.6514012303485988,
"eval_recall_sadness": 0.802528597230584,
"eval_recall_surprise": 0.47020585048754066,
"eval_runtime": 24.2683,
"eval_samples_per_second": 438.885,
"eval_steps_per_second": 6.881,
"step": 3380
},
{
"epoch": 5.04,
"learning_rate": 0.0005232376793512164,
"loss": 0.7176,
"step": 3400
},
{
"epoch": 5.14,
"learning_rate": 0.0005126325639426076,
"loss": 0.6756,
"step": 3468
},
{
"epoch": 5.24,
"learning_rate": 0.0005020274485339987,
"loss": 0.7045,
"step": 3536
},
{
"epoch": 5.34,
"learning_rate": 0.0004914223331253899,
"loss": 0.6918,
"step": 3604
},
{
"epoch": 5.44,
"learning_rate": 0.00048081721771678105,
"loss": 0.682,
"step": 3672
},
{
"epoch": 5.51,
"eval_accuracy": 0.7134541357619003,
"eval_b_acc": 0.680836184336636,
"eval_f1": 0.6633550818848415,
"eval_f1_anger": 0.6141868512110726,
"eval_f1_disgust": 0.5090403337969402,
"eval_f1_fear": 0.7182718271827183,
"eval_f1_joy": 0.8394711992445704,
"eval_f1_neutral": 0.6741810496653751,
"eval_f1_sadness": 0.7413637729047762,
"eval_f1_surprise": 0.5469705391884381,
"eval_loss": 0.7824211120605469,
"eval_micro_f1": 0.7134541357619003,
"eval_prec": 0.6527089444455868,
"eval_prec_anger": 0.6604651162790698,
"eval_prec_disgust": 0.45073891625615764,
"eval_prec_fear": 0.6404494382022472,
"eval_prec_joy": 0.8203629652414641,
"eval_prec_neutral": 0.6954941860465116,
"eval_prec_sadness": 0.7398081534772182,
"eval_prec_surprise": 0.5616438356164384,
"eval_recall": 0.680836184336636,
"eval_recall_anger": 0.5739692805173807,
"eval_recall_disgust": 0.5846645367412141,
"eval_recall_fear": 0.8176229508196722,
"eval_recall_joy": 0.8594908153399936,
"eval_recall_neutral": 0.6541353383458647,
"eval_recall_sadness": 0.7429259482239615,
"eval_recall_surprise": 0.5330444203683641,
"eval_runtime": 24.2404,
"eval_samples_per_second": 439.39,
"eval_steps_per_second": 6.889,
"step": 3718
},
{
"epoch": 5.54,
"learning_rate": 0.0004702121023081722,
"loss": 0.7021,
"step": 3740
},
{
"epoch": 5.64,
"learning_rate": 0.0004596069868995633,
"loss": 0.6953,
"step": 3808
},
{
"epoch": 5.74,
"learning_rate": 0.00044900187149095447,
"loss": 0.7014,
"step": 3876
},
{
"epoch": 5.84,
"learning_rate": 0.0004383967560823456,
"loss": 0.7103,
"step": 3944
},
{
"epoch": 5.94,
"learning_rate": 0.0004277916406737368,
"loss": 0.6866,
"step": 4012
},
{
"epoch": 6.01,
"eval_accuracy": 0.716927987982349,
"eval_b_acc": 0.652717377066482,
"eval_f1": 0.664768200880273,
"eval_f1_anger": 0.6474176494509963,
"eval_f1_disgust": 0.44813278008298757,
"eval_f1_fear": 0.7614973262032086,
"eval_f1_joy": 0.8328767123287671,
"eval_f1_neutral": 0.6664258623803504,
"eval_f1_sadness": 0.7478467478467478,
"eval_f1_surprise": 0.5491803278688525,
"eval_loss": 0.7794012427330017,
"eval_micro_f1": 0.7169279879823489,
"eval_prec": 0.6916461943133572,
"eval_prec_anger": 0.6513911620294599,
"eval_prec_disgust": 0.6390532544378699,
"eval_prec_fear": 0.796420581655481,
"eval_prec_joy": 0.7891548889529852,
"eval_prec_neutral": 0.7066258138644198,
"eval_prec_sadness": 0.7379835873388042,
"eval_prec_surprise": 0.5208940719144801,
"eval_recall": 0.652717377066482,
"eval_recall_anger": 0.6434923201293452,
"eval_recall_disgust": 0.3450479233226837,
"eval_recall_fear": 0.7295081967213115,
"eval_recall_joy": 0.881727360618756,
"eval_recall_neutral": 0.6305536568694463,
"eval_recall_sadness": 0.7579771222155328,
"eval_recall_surprise": 0.580715059588299,
"eval_runtime": 25.3678,
"eval_samples_per_second": 419.863,
"eval_steps_per_second": 6.583,
"step": 4056
},
{
"epoch": 6.04,
"learning_rate": 0.0004171865252651279,
"loss": 0.6703,
"step": 4080
},
{
"epoch": 6.15,
"learning_rate": 0.00040658140985651905,
"loss": 0.6513,
"step": 4148
},
{
"epoch": 6.25,
"learning_rate": 0.00039597629444791015,
"loss": 0.6631,
"step": 4216
},
{
"epoch": 6.35,
"learning_rate": 0.0003853711790393013,
"loss": 0.6684,
"step": 4284
},
{
"epoch": 6.45,
"learning_rate": 0.0003747660636306924,
"loss": 0.6675,
"step": 4352
},
{
"epoch": 6.51,
"eval_accuracy": 0.7185240822457986,
"eval_b_acc": 0.6622855221664815,
"eval_f1": 0.6665866196892164,
"eval_f1_anger": 0.6372854914196568,
"eval_f1_disgust": 0.4875444839857651,
"eval_f1_fear": 0.7421638018200202,
"eval_f1_joy": 0.8435395960243669,
"eval_f1_neutral": 0.6793365583966827,
"eval_f1_sadness": 0.7404181184668989,
"eval_f1_surprise": 0.535818287711124,
"eval_loss": 0.7682891488075256,
"eval_micro_f1": 0.7185240822457986,
"eval_prec": 0.6741441246143367,
"eval_prec_anger": 0.6156744536548606,
"eval_prec_disgust": 0.5502008032128514,
"eval_prec_fear": 0.7325349301397206,
"eval_prec_joy": 0.8392344497607656,
"eval_prec_neutral": 0.686932215234102,
"eval_prec_sadness": 0.715086932136848,
"eval_prec_surprise": 0.5793450881612091,
"eval_recall": 0.6622855221664815,
"eval_recall_anger": 0.6604688763136621,
"eval_recall_disgust": 0.43769968051118213,
"eval_recall_fear": 0.7520491803278688,
"eval_recall_joy": 0.8478891395423783,
"eval_recall_neutral": 0.671907040328093,
"eval_recall_sadness": 0.7676098735701384,
"eval_recall_surprise": 0.49837486457204766,
"eval_runtime": 24.3218,
"eval_samples_per_second": 437.92,
"eval_steps_per_second": 6.866,
"step": 4394
},
{
"epoch": 6.55,
"learning_rate": 0.0003641609482220836,
"loss": 0.6481,
"step": 4420
},
{
"epoch": 6.65,
"learning_rate": 0.0003537117903930131,
"loss": 0.6747,
"step": 4488
},
{
"epoch": 6.75,
"learning_rate": 0.00034310667498440423,
"loss": 0.6639,
"step": 4556
},
{
"epoch": 6.85,
"learning_rate": 0.0003325015595757954,
"loss": 0.6567,
"step": 4624
},
{
"epoch": 6.95,
"learning_rate": 0.00032189644416718655,
"loss": 0.6627,
"step": 4692
},
{
"epoch": 7.01,
"eval_accuracy": 0.7127969204769505,
"eval_b_acc": 0.651201720157747,
"eval_f1": 0.6578064204451088,
"eval_f1_anger": 0.6380597014925373,
"eval_f1_disgust": 0.42857142857142855,
"eval_f1_fear": 0.7578288100208769,
"eval_f1_joy": 0.8434674150296227,
"eval_f1_neutral": 0.655002733734281,
"eval_f1_sadness": 0.7421161214264662,
"eval_f1_surprise": 0.5395987328405492,
"eval_loss": 0.7739543318748474,
"eval_micro_f1": 0.7127969204769505,
"eval_prec": 0.6803489346520001,
"eval_prec_anger": 0.5925155925155925,
"eval_prec_disgust": 0.6257668711656442,
"eval_prec_fear": 0.7723404255319148,
"eval_prec_joy": 0.8169737239504682,
"eval_prec_neutral": 0.7016790316282702,
"eval_prec_sadness": 0.726905311778291,
"eval_prec_surprise": 0.5262615859938208,
"eval_recall": 0.651201720157747,
"eval_recall_anger": 0.6911883589329022,
"eval_recall_disgust": 0.3258785942492013,
"eval_recall_fear": 0.7438524590163934,
"eval_recall_joy": 0.8717370286819207,
"eval_recall_neutral": 0.614149008885851,
"eval_recall_sadness": 0.7579771222155328,
"eval_recall_surprise": 0.5536294691224268,
"eval_runtime": 23.8468,
"eval_samples_per_second": 446.642,
"eval_steps_per_second": 7.003,
"step": 4732
},
{
"epoch": 7.05,
"learning_rate": 0.0003112913287585777,
"loss": 0.651,
"step": 4760
},
{
"epoch": 7.15,
"learning_rate": 0.0003006862133499688,
"loss": 0.6343,
"step": 4828
},
{
"epoch": 7.25,
"learning_rate": 0.00029008109794135997,
"loss": 0.6399,
"step": 4896
},
{
"epoch": 7.35,
"learning_rate": 0.00027947598253275107,
"loss": 0.6335,
"step": 4964
},
{
"epoch": 7.45,
"learning_rate": 0.00026887086712414223,
"loss": 0.649,
"step": 5032
},
{
"epoch": 7.51,
"eval_accuracy": 0.7188057459393484,
"eval_b_acc": 0.6537977708680845,
"eval_f1": 0.6643709103167401,
"eval_f1_anger": 0.641838351822504,
"eval_f1_disgust": 0.4552845528455285,
"eval_f1_fear": 0.7606490872210953,
"eval_f1_joy": 0.8397256002494543,
"eval_f1_neutral": 0.6740003492229788,
"eval_f1_sadness": 0.7394713912285799,
"eval_f1_surprise": 0.5396270396270396,
"eval_loss": 0.7703790068626404,
"eval_micro_f1": 0.7188057459393485,
"eval_prec": 0.68695638810934,
"eval_prec_anger": 0.6293706293706294,
"eval_prec_disgust": 0.6256983240223464,
"eval_prec_fear": 0.7530120481927711,
"eval_prec_joy": 0.813349441256418,
"eval_prec_neutral": 0.6890396287040342,
"eval_prec_sadness": 0.7143658810325477,
"eval_prec_surprise": 0.5838587641866331,
"eval_recall": 0.6537977708680845,
"eval_recall_anger": 0.6548100242522231,
"eval_recall_disgust": 0.35782747603833864,
"eval_recall_fear": 0.7684426229508197,
"eval_recall_joy": 0.867869803416049,
"eval_recall_neutral": 0.6596035543403964,
"eval_recall_sadness": 0.7664057796508128,
"eval_recall_surprise": 0.5016251354279523,
"eval_runtime": 24.2198,
"eval_samples_per_second": 439.764,
"eval_steps_per_second": 6.895,
"step": 5070
},
{
"epoch": 7.56,
"learning_rate": 0.0002582657517155334,
"loss": 0.6331,
"step": 5100
},
{
"epoch": 7.66,
"learning_rate": 0.0002476606363069245,
"loss": 0.6364,
"step": 5168
},
{
"epoch": 7.76,
"learning_rate": 0.00023705552089831568,
"loss": 0.6298,
"step": 5236
},
{
"epoch": 7.86,
"learning_rate": 0.0002264504054897068,
"loss": 0.6289,
"step": 5304
},
{
"epoch": 7.96,
"learning_rate": 0.00021584529008109794,
"loss": 0.6506,
"step": 5372
},
{
"epoch": 8.01,
"eval_accuracy": 0.7165524363909492,
"eval_b_acc": 0.6579721980837441,
"eval_f1": 0.6631314282173324,
"eval_f1_anger": 0.6381950040290089,
"eval_f1_disgust": 0.4452296819787986,
"eval_f1_fear": 0.7645195353748679,
"eval_f1_joy": 0.83692495797035,
"eval_f1_neutral": 0.665809768637532,
"eval_f1_sadness": 0.7407616361071934,
"eval_f1_surprise": 0.5504794134235759,
"eval_loss": 0.782048225402832,
"eval_micro_f1": 0.7165524363909492,
"eval_prec": 0.6727504407845075,
"eval_prec_anger": 0.636144578313253,
"eval_prec_disgust": 0.4980237154150198,
"eval_prec_fear": 0.7886710239651417,
"eval_prec_joy": 0.7959302325581395,
"eval_prec_neutral": 0.7194444444444444,
"eval_prec_sadness": 0.6969214437367304,
"eval_prec_surprise": 0.5741176470588235,
"eval_recall": 0.6579721980837441,
"eval_recall_anger": 0.6402586903799515,
"eval_recall_disgust": 0.402555910543131,
"eval_recall_fear": 0.7418032786885246,
"eval_recall_joy": 0.882371898163068,
"eval_recall_neutral": 0.6196172248803827,
"eval_recall_sadness": 0.7904876580373269,
"eval_recall_surprise": 0.5287107258938245,
"eval_runtime": 25.8929,
"eval_samples_per_second": 411.349,
"eval_steps_per_second": 6.45,
"step": 5408
},
{
"epoch": 8.06,
"learning_rate": 0.0002052401746724891,
"loss": 0.6132,
"step": 5440
},
{
"epoch": 8.16,
"learning_rate": 0.00019463505926388023,
"loss": 0.6025,
"step": 5508
},
{
"epoch": 8.26,
"learning_rate": 0.00018402994385527136,
"loss": 0.6144,
"step": 5576
},
{
"epoch": 8.36,
"learning_rate": 0.00017342482844666252,
"loss": 0.604,
"step": 5644
},
{
"epoch": 8.46,
"learning_rate": 0.00016281971303805365,
"loss": 0.6054,
"step": 5712
},
{
"epoch": 8.51,
"eval_accuracy": 0.7206835038963477,
"eval_b_acc": 0.6675082320275072,
"eval_f1": 0.6717071261887518,
"eval_f1_anger": 0.6405437824870053,
"eval_f1_disgust": 0.49295774647887325,
"eval_f1_fear": 0.7518022657054583,
"eval_f1_joy": 0.8452080706179067,
"eval_f1_neutral": 0.6740467404674046,
"eval_f1_sadness": 0.7466036621382162,
"eval_f1_surprise": 0.5507876154263988,
"eval_loss": 0.766762912273407,
"eval_micro_f1": 0.7206835038963476,
"eval_prec": 0.677763090732445,
"eval_prec_anger": 0.6337025316455697,
"eval_prec_disgust": 0.5490196078431373,
"eval_prec_fear": 0.7556935817805382,
"eval_prec_joy": 0.8272138228941684,
"eval_prec_neutral": 0.6936708860759494,
"eval_prec_sadness": 0.7327536231884058,
"eval_prec_surprise": 0.5522875816993464,
"eval_recall": 0.6675082320275072,
"eval_recall_anger": 0.6475343573160873,
"eval_recall_disgust": 0.4472843450479233,
"eval_recall_fear": 0.7479508196721312,
"eval_recall_joy": 0.8640025781501772,
"eval_recall_neutral": 0.6555023923444976,
"eval_recall_sadness": 0.7609873570138471,
"eval_recall_surprise": 0.5492957746478874,
"eval_runtime": 25.1627,
"eval_samples_per_second": 423.285,
"eval_steps_per_second": 6.637,
"step": 5746
},
{
"epoch": 8.56,
"learning_rate": 0.00015221459762944478,
"loss": 0.6024,
"step": 5780
},
{
"epoch": 8.66,
"learning_rate": 0.00014160948222083594,
"loss": 0.5885,
"step": 5848
},
{
"epoch": 8.76,
"learning_rate": 0.00013100436681222707,
"loss": 0.6028,
"step": 5916
},
{
"epoch": 8.87,
"learning_rate": 0.00012039925140361823,
"loss": 0.6136,
"step": 5984
},
{
"epoch": 8.97,
"learning_rate": 0.00010979413599500936,
"loss": 0.6044,
"step": 6052
},
{
"epoch": 9.01,
"eval_accuracy": 0.7205896159984978,
"eval_b_acc": 0.6652242950964659,
"eval_f1": 0.6678601215475679,
"eval_f1_anger": 0.6366130929047433,
"eval_f1_disgust": 0.4752136752136752,
"eval_f1_fear": 0.75,
"eval_f1_joy": 0.842983008181246,
"eval_f1_neutral": 0.6835877208026068,
"eval_f1_sadness": 0.7397849462365592,
"eval_f1_surprise": 0.5468384074941451,
"eval_loss": 0.7678258419036865,
"eval_micro_f1": 0.7205896159984978,
"eval_prec": 0.6729176738444275,
"eval_prec_anger": 0.6179604261796042,
"eval_prec_disgust": 0.5110294117647058,
"eval_prec_fear": 0.7215909090909091,
"eval_prec_joy": 0.8235474946203505,
"eval_prec_neutral": 0.6860585197934596,
"eval_prec_sadness": 0.7553324968632371,
"eval_prec_surprise": 0.5949044585987261,
"eval_recall": 0.6652242950964659,
"eval_recall_anger": 0.65642683912692,
"eval_recall_disgust": 0.4440894568690096,
"eval_recall_fear": 0.7807377049180327,
"eval_recall_joy": 0.8633580406058653,
"eval_recall_neutral": 0.6811346548188654,
"eval_recall_sadness": 0.7248645394340758,
"eval_recall_surprise": 0.5059588299024919,
"eval_runtime": 24.3233,
"eval_samples_per_second": 437.893,
"eval_steps_per_second": 6.866,
"step": 6084
},
{
"epoch": 9.07,
"learning_rate": 9.91890205864005e-05,
"loss": 0.6066,
"step": 6120
},
{
"epoch": 9.17,
"learning_rate": 8.858390517779165e-05,
"loss": 0.5807,
"step": 6188
},
{
"epoch": 9.27,
"learning_rate": 7.797878976918278e-05,
"loss": 0.5756,
"step": 6256
},
{
"epoch": 9.37,
"learning_rate": 6.737367436057393e-05,
"loss": 0.5632,
"step": 6324
},
{
"epoch": 9.47,
"learning_rate": 5.6768558951965065e-05,
"loss": 0.571,
"step": 6392
},
{
"epoch": 9.51,
"eval_accuracy": 0.7209651675898977,
"eval_b_acc": 0.6608852975066731,
"eval_f1": 0.6697710187121083,
"eval_f1_anger": 0.6411258795934324,
"eval_f1_disgust": 0.4761904761904761,
"eval_f1_fear": 0.7543478260869565,
"eval_f1_joy": 0.8445141065830721,
"eval_f1_neutral": 0.677425075367973,
"eval_f1_sadness": 0.7452248016456068,
"eval_f1_surprise": 0.5495689655172413,
"eval_loss": 0.7740551829338074,
"eval_micro_f1": 0.7209651675898977,
"eval_prec": 0.6832223355325023,
"eval_prec_anger": 0.6207418622255867,
"eval_prec_disgust": 0.5579399141630901,
"eval_prec_fear": 0.8032407407407407,
"eval_prec_joy": 0.8220933780897162,
"eval_prec_neutral": 0.7040176925912274,
"eval_prec_sadness": 0.7278989667049368,
"eval_prec_surprise": 0.5466237942122186,
"eval_recall": 0.6608852975066731,
"eval_recall_anger": 0.6628940986257074,
"eval_recall_disgust": 0.41533546325878595,
"eval_recall_fear": 0.7110655737704918,
"eval_recall_joy": 0.8681920721882049,
"eval_recall_neutral": 0.6527682843472317,
"eval_recall_sadness": 0.7633955448524985,
"eval_recall_surprise": 0.5525460455037919,
"eval_runtime": 23.9705,
"eval_samples_per_second": 444.338,
"eval_steps_per_second": 6.967,
"step": 6422
},
{
"epoch": 9.57,
"learning_rate": 4.616344354335621e-05,
"loss": 0.582,
"step": 6460
},
{
"epoch": 9.67,
"learning_rate": 3.555832813474735e-05,
"loss": 0.5889,
"step": 6528
},
{
"epoch": 9.77,
"learning_rate": 2.4953212726138492e-05,
"loss": 0.5893,
"step": 6596
},
{
"epoch": 9.87,
"learning_rate": 1.4348097317529632e-05,
"loss": 0.5752,
"step": 6664
},
{
"epoch": 9.97,
"learning_rate": 3.7429819089207735e-06,
"loss": 0.5768,
"step": 6732
},
{
"epoch": 10.0,
"step": 6750,
"total_flos": 2.02230635924352e+17,
"train_loss": 0.7460671546370895,
"train_runtime": 4596.3933,
"train_samples_per_second": 187.702,
"train_steps_per_second": 1.469
}
],
"max_steps": 6750,
"num_train_epochs": 10,
"total_flos": 2.02230635924352e+17,
"trial_name": null,
"trial_params": null
}