Training in progress, step 10000

config.json

@@ -4,7 +4,7 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 50281,
+  "bos_token_id": null,
   "classifier_activation": "gelu",
   "classifier_bias": false,
   "classifier_dropout": 0.0,
@@ -14,7 +14,7 @@
   "deterministic_flash_attn": false,
   "dtype": "bfloat16",
   "embedding_dropout": 0.0,
-  "eos_token_id": 50282,
+  "eos_token_id": null,
   "global_attn_every_n_layers": 3,
   "global_rope_theta": 160000.0,
   "gradient_checkpointing": false,

eval/CrossEncoderClassificationEvaluator_test_cls_results.csv

@@ -0,0 +1,45 @@
+epoch,steps,Accuracy,Accuracy_Threshold,F1,F1_Threshold,Precision,Recall,Average_Precision
+0,0,0.72286806081811,0.9375,0.7140800921187308,0.91015625,0.6257357475194798,0.8314711359404097,0.6869233831785253
+0,0,0.72286806081811,0.9375,0.7140800921187308,0.91015625,0.6257357475194798,0.8314711359404097,0.6869233831785253
+0,0,0.72286806081811,0.9375,0.7140800921187308,0.91015625,0.6257357475194798,0.8314711359404097,0.6869233831785253
+0,0,0.72286806081811,0.9375,0.7140800921187308,0.91015625,0.6257357475194798,0.8314711359404097,0.6869233831785253
+0.13218770654329148,1000,0.7349123683913513,0.9003906,0.7172665790570212,0.8535156,0.6295150219421627,0.8334450651769088,0.7224760908990453
+0.13218770654329148,1000,0.735154221957079,0.8984375,0.7166596618279395,0.8535156,0.6331257854449903,0.825586592178771,0.7233477913978325
+0.13218770654329148,1000,0.7342029312652166,0.8984375,0.7164503590486857,0.8613281,0.6422370519104706,0.8100558659217877,0.7217629222081844
+0.13218770654329148,1000,0.7337353477048096,0.90234375,0.7164582959787446,0.8574219,0.6370329574770284,0.818510242085661,0.7214404365984526
+0.26437541308658297,2000,0.7528417793973009,0.76171875,0.7280126150872372,0.70703125,0.6682229900084041,0.7995530726256983,0.7626906355450929
+0.26437541308658297,2000,0.7533577336708535,0.765625,0.7285582539194589,0.7128906,0.6727857683573051,0.794413407821229,0.763698279665006
+0.26437541308658297,2000,0.7523741958368939,0.765625,0.728350925941614,0.7207031,0.6681172484535762,0.8005214152700186,0.7612611848773637
+0.26437541308658297,2000,0.7532771158156109,0.76171875,0.728088970513213,0.7167969,0.6699211415696583,0.7973184357541899,0.7627249877246733
+0.3965631196298744,3000,0.755905257896519,0.6171875,0.7293353323338331,0.55859375,0.6597649186256781,0.8153072625698324,0.7742987066029523
+0.3965631196298744,3000,0.7568081778752358,0.625,0.7304989400237033,0.5625,0.6619172943703301,0.8149348230912477,0.7758427513157854
+0.3965631196298744,3000,0.7551474500572387,0.6171875,0.7297771685528492,0.5566406,0.6620363349610263,0.8129608938547486,0.7745321613863553
+0.3965631196298744,3000,0.7570177842988665,0.640625,0.7300099223320902,0.58984375,0.6751044171623846,0.7946368715083799,0.776092967192534
+0.5287508261731659,4000,0.7625320455974589,0.5390625,0.7359472884625232,0.48242188,0.6793243626508682,0.8028677839851024,0.7878368758627725
+0.5287508261731659,4000,0.762161203463343,0.53515625,0.7385344389913691,0.46679688,0.6767990074441688,0.8126629422718809,0.7877716822554272
+0.5287508261731659,4000,0.7625804163106045,0.55078125,0.7356960150780829,0.48242188,0.671056670964573,0.8141154562383612,0.7877054882936321
+0.5287508261731659,4000,0.7626610341658471,0.5546875,0.7368891025861182,0.4921875,0.6836604639306653,0.7991061452513967,0.7888047540149877
+0.6609385327164574,5000,0.7721578175134228,0.51171875,0.7498822579559982,0.45214844,0.6837310594442059,0.8302048417132216,0.8033749104929461
+0.6609385327164574,5000,0.7698037761403396,0.53125,0.7434565335708277,0.4453125,0.6671698783411775,0.839441340782123,0.8018476675587634
+0.6609385327164574,5000,0.770190741845504,0.5332031,0.7450581346856389,0.4609375,0.6747439344955736,0.831731843575419,0.8021181519424573
+0.6609385327164574,5000,0.7693684397220296,0.5332031,0.7433929249409861,0.453125,0.6675857570636544,0.8386219739292365,0.8017175995376455
+0.7931262392597488,6000,0.7777526966672579,0.53125,0.7507494209020303,0.4716797,0.6917017136400728,0.8208193668528864,0.8126178819940797
+0.7931262392597488,6000,0.7770916302542688,0.51953125,0.7527021258430803,0.4560547,0.6949708339902254,0.8208938547486033,0.8130160472101687
+0.7931262392597488,6000,0.7784621337933926,0.5234375,0.7553841530602025,0.46875,0.6845497458242557,0.8425698324022346,0.8139868703288592
+0.7931262392597488,6000,0.7792521887747699,0.53125,0.7538506248183667,0.4716797,0.6967169083957405,0.8211918063314712,0.8116148935760504
+0.9253139458030403,7000,0.7842182486577127,0.5097656,0.7587641522302551,0.4609375,0.699729542738537,0.8286778398510242,0.8200553738858236
+0.9253139458030403,7000,0.7822028022766482,0.51953125,0.7561756003578063,0.46679688,0.7026085288664408,0.818584729981378,0.8202460941846539
+0.9253139458030403,7000,0.7857499879073218,0.5527344,0.7613318363858773,0.4921875,0.6920218113138575,0.8460707635009311,0.8242636213035655
+0.9253139458030403,7000,0.7853630222021574,0.5371094,0.7601736299511666,0.4765625,0.6977525991408827,0.8348603351955307,0.8229452498370069
+1.0575016523463319,8000,0.7912158784927685,0.5390625,0.7662511659459001,0.4873047,0.7034407597695781,0.8413780260707635,0.8304790780833297
+1.0575016523463319,8000,0.789603521387917,0.5292969,0.7644103873988931,0.47460938,0.704156862745098,0.8359404096834264,0.8305916828926647
+1.0575016523463319,8000,0.7909095306428467,0.51171875,0.7671350239890335,0.4765625,0.7104093938432243,0.833705772811918,0.8315800385738371
+1.0575016523463319,8000,0.7929249770239113,0.5371094,0.7673300364482623,0.484375,0.7097723891227959,0.835046554934823,0.8319441839338569
+1.1896893588896233,9000,0.795262894825946,0.5410156,0.7696911700739453,0.49609375,0.7222530612244898,0.8237988826815642,0.8351036955965315
+1.1896893588896233,9000,0.7961013205204689,0.515625,0.7705063463900641,0.45703125,0.7108858527985897,0.8410428305400373,0.8377546320713009
+1.1896893588896233,9000,0.7975524419148353,0.5332031,0.7742146259263717,0.4921875,0.7191043536589261,0.8384729981378026,0.8374303457256872
+1.1896893588896233,9000,0.7985843504619403,0.5097656,0.776577072650308,0.46875,0.7217566530194472,0.8404096834264432,0.8392454975653109
+1.3218770654329148,10000,0.8020186710952741,0.5390625,0.7795180722891566,0.49023438,0.72464,0.843389199255121,0.8448191545496332
+1.3218770654329148,10000,0.8005675497009077,0.5097656,0.7794023275577987,0.48632812,0.7293472262797416,0.8368342644320298,0.8428214977188524
+1.3218770654329148,10000,0.8003740668483256,0.515625,0.7774428747032179,0.46289062,0.7094999538986385,0.8597765363128491,0.8405563871611742
+1.3218770654329148,10000,0.7979394076199997,0.5722656,0.7749455001115746,0.5371094,0.7187251249721399,0.840707635009311,0.8387944584676308

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c685fcfde896ad977854883c3655abae0d0eeee4b54358622ca5d33c6f11d003
+oid sha256:f3fb8b1287afc46a0e4aaf927aa1c0308e5d1fe90e3db1548b66002f641df8c2
 size 299225554

tokenizer.json

@@ -1,7 +1,19 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 8192,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 50283,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54a1076baa0c76bf5a3a13fd1d043a862eeaddd9b2972ef8dcae120cfb39f392
+size 6289