radoslavralev commited on
Commit
2718147
·
verified ·
1 Parent(s): d73c2ce

Training in progress, step 5000

Browse files
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "bfloat16",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 384,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 1536,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "transformers_version": "4.56.0",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 30522
25
+ }
eval/Information-Retrieval_evaluation_test_results.csv ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch,steps,cosine-Accuracy@1,cosine-Precision@1,cosine-Recall@1,cosine-MRR@1,cosine-NDCG@10,cosine-MAP@100
2
+ 0,0,0.3331863447616948,0.3331863447616948,0.33316797119023994,0.3331863447616948,0.6413222350065527,0.5644498249049865
3
+ 0,0,0.3331863447616948,0.3331863447616948,0.33316797119023994,0.3331863447616948,0.6413222350065527,0.5644498249049865
4
+ 0,0,0.3331863447616948,0.3331863447616948,0.33316797119023994,0.3331863447616948,0.6413222350065527,0.5644498249049865
5
+ 0,0,0.3331863447616948,0.3331863447616948,0.33316797119023994,0.3331863447616948,0.6413222350065527,0.5644498249049865
6
+ 0,0,0.3331863447616948,0.3331863447616948,0.33316797119023994,0.3331863447616948,0.6413222350065527,0.5644498249049865
7
+ 0,0,0.3331863447616948,0.3331863447616948,0.33316797119023994,0.3331863447616948,0.6413222350065527,0.5644498249049865
8
+ 0,0,0.3331863447616948,0.3331863447616948,0.33316797119023994,0.3331863447616948,0.6413222350065527,0.5644498249049865
9
+ 0,0,0.3331863447616948,0.3331863447616948,0.33316797119023994,0.3331863447616948,0.6413222350065527,0.5644498249049865
10
+ 0,0,0.33314959761878515,0.33314959761878515,0.3331312240473303,0.33314959761878515,0.6413118736261942,0.5644357385002045
11
+ 0,0,0.33314959761878515,0.33314959761878515,0.3331312240473303,0.33314959761878515,0.6413118736261942,0.5644357385002045
12
+ 0,0,0.33314959761878515,0.33314959761878515,0.3331312240473303,0.33314959761878515,0.6413118736261942,0.5644357385002045
13
+ 0,0,0.33314959761878515,0.33314959761878515,0.3331312240473303,0.33314959761878515,0.6413118736261942,0.5644357385002045
14
+ 0,0,0.33314959761878515,0.33314959761878515,0.3331312240473303,0.33314959761878515,0.6413070623318285,0.5644296139763862
15
+ 0,0,0.33314959761878515,0.33314959761878515,0.3331312240473303,0.33314959761878515,0.6413070623318285,0.5644296139763862
16
+ 0,0,0.33314959761878515,0.33314959761878515,0.3331312240473303,0.33314959761878515,0.6413070623318285,0.5644296139763862
17
+ 0,0,0.33314959761878515,0.33314959761878515,0.3331312240473303,0.33314959761878515,0.6413070623318285,0.5644296139763862
18
+ 0.19036740909956215,500,0.33285562047550804,0.33285562047550804,0.3328311223802349,0.33285562047550804,0.6380542275096396,0.5623459490228918
19
+ 0.19036740909956215,500,0.33285562047550804,0.33285562047550804,0.3328311223802349,0.33285562047550804,0.6380522608218838,0.562343700835019
20
+ 0.19036740909956215,500,0.33285562047550804,0.33285562047550804,0.3328311223802349,0.33285562047550804,0.6380676727145255,0.5623531865790714
21
+ 0.19036740909956215,500,0.33285562047550804,0.33285562047550804,0.3328311223802349,0.33285562047550804,0.6380889811351703,0.5623554899870908
22
+ 0.3807348181991243,1000,0.33300260904714657,0.33300260904714657,0.33294748833278215,0.33300260904714657,0.640701327626043,0.564577205719716
23
+ 0.3807348181991243,1000,0.33300260904714657,0.33300260904714657,0.33294748833278215,0.33300260904714657,0.6406907777286023,0.5645632349109668
24
+ 0.3807348181991243,1000,0.33300260904714657,0.33300260904714657,0.33294748833278215,0.33300260904714657,0.6406902171679113,0.5645690278236413
25
+ 0.3807348181991243,1000,0.3330393561900562,0.3330393561900562,0.3329842354756918,0.3330393561900562,0.6407463651010034,0.5646251412466688
26
+ 0.5711022272986864,1500,0.33325983904751405,0.33325983904751405,0.3332292164284227,0.33325983904751405,0.6418700950451438,0.5654152371488405
27
+ 0.5711022272986864,1500,0.3333333333333333,0.3333333333333333,0.33330271071424195,0.3333333333333333,0.6419485244138559,0.5654985146942976
28
+ 0.5711022272986864,1500,0.33337008047624295,0.33337008047624295,0.3333394578571516,0.33337008047624295,0.6419496979489833,0.5654898731102157
29
+ 0.5711022272986864,1500,0.33325983904751405,0.33325983904751405,0.3332292164284227,0.33325983904751405,0.6419487613763959,0.5654587504597287
30
+ 0.7614696363982486,2000,0.3332965861904237,0.3332965861904237,0.33325371452369573,0.3332965861904237,0.6419830082394011,0.5655154363010287
31
+ 0.7614696363982486,2000,0.33337008047624295,0.33337008047624295,0.333327208809515,0.33337008047624295,0.6419952769674367,0.5655082906617594
32
+ 0.7614696363982486,2000,0.33344357476206227,0.33344357476206227,0.3334007030953343,0.33344357476206227,0.6420166405969135,0.5655427436299856
33
+ 0.7614696363982486,2000,0.33337008047624295,0.33337008047624295,0.333327208809515,0.33337008047624295,0.642000664615878,0.565530415240514
34
+ 0.9518370454978108,2500,0.3330761033329659,0.3330761033329659,0.33302710714241973,0.3330761033329659,0.6428156034208599,0.5660930163402286
35
+ 0.9518370454978108,2500,0.3331863447616948,0.3331863447616948,0.33313734857114863,0.3331863447616948,0.6428221958528403,0.5661204254785941
36
+ 0.9518370454978108,2500,0.33300260904714657,0.33300260904714657,0.33295361285660047,0.33300260904714657,0.6427760120886662,0.5660494605523017
37
+ 0.9518370454978108,2500,0.33314959761878515,0.33314959761878515,0.333100601428239,0.33314959761878515,0.6428679726285491,0.5661266048250087
38
+ 1.1420140871882734,3000,0.3328923676184177,0.3328923676184177,0.33284337142787146,0.3328923676184177,0.6420007145596212,0.565476633322493
39
+ 1.1420140871882734,3000,0.33300260904714657,0.33300260904714657,0.33295361285660036,0.33300260904714657,0.6419985233420836,0.565523395439243
40
+ 1.1420140871882734,3000,0.33296586190423694,0.33296586190423694,0.3329168657136907,0.33296586190423694,0.6419959180063995,0.5655130672142719
41
+ 1.1420140871882734,3000,0.33300260904714657,0.33300260904714657,0.33295361285660036,0.33300260904714657,0.6420408692666738,0.5655184585662549
42
+ 1.3323814962878355,3500,0.3327821261896888,0.3327821261896888,0.3327331299991426,0.3327821261896888,0.6420978814021374,0.5654089384161294
43
+ 1.3323814962878355,3500,0.3327821261896888,0.3327821261896888,0.3327331299991426,0.3327821261896888,0.6421393939252114,0.5654457345640401
44
+ 1.3323814962878355,3500,0.3327453790467791,0.3327453790467791,0.33269638285623293,0.3327453790467791,0.6421559209995976,0.565446298302152
45
+ 1.3323814962878355,3500,0.3328188733325984,0.3328188733325984,0.3327698771420522,0.3328188733325984,0.642082175677993,0.5654731407378754
46
+ 0,0,0.5763286334056399,0.5763286334056399,0.5589816867630893,0.5763286334056399,0.7619420691608578,0.7107787006557986
47
+ 0,0,0.5763286334056399,0.5763286334056399,0.5589816867630893,0.5763286334056399,0.7619420691608578,0.7107787006557986
48
+ 0,0,0.5763286334056399,0.5763286334056399,0.5589816867630893,0.5763286334056399,0.7619420691608578,0.7107787006557986
49
+ 0,0,0.5763286334056399,0.5763286334056399,0.5589816867630893,0.5763286334056399,0.7619420691608578,0.7107787006557986
50
+ 0.09517464547444561,500,0.5682619305856833,0.5682619305856833,0.5513169068462419,0.5682619305856833,0.7517622483897596,0.7013038916132194
51
+ 0.09517464547444561,500,0.5681602494577006,0.5681602494577006,0.5512818833466033,0.5681602494577006,0.7517547952480986,0.7012877439150992
52
+ 0.09517464547444561,500,0.5682619305856833,0.5682619305856833,0.5513169068462419,0.5682619305856833,0.7517662999292754,0.7013072492722403
53
+ 0.09517464547444561,500,0.5682619305856833,0.5682619305856833,0.5513395026524601,0.5682619305856833,0.7517950689826506,0.7013309561686446
54
+ 0.19034929094889122,1000,0.5703294468546638,0.5703294468546638,0.5533149410111009,0.5703294468546638,0.7541974215464319,0.7036652605232608
55
+ 0.19034929094889122,1000,0.5703633405639913,0.5703633405639913,0.5533488347204284,0.5703633405639913,0.7542118288645122,0.7036826758301974
56
+ 0.19034929094889122,1000,0.5704311279826464,0.5704311279826464,0.5534166221390835,0.5704311279826464,0.7542245301965979,0.7037007412902183
57
+ 0.19034929094889122,1000,0.570465021691974,0.570465021691974,0.5534505158484111,0.570465021691974,0.7542444217650767,0.7037250997142565
58
+ 0.28552393642333684,1500,0.5719224511930586,0.5719224511930586,0.5548638835273698,0.5719224511930586,0.7550959415414972,0.7046005842934645
59
+ 0.28552393642333684,1500,0.5719563449023861,0.5719563449023861,0.5548808303820335,0.5719563449023861,0.7551101059708968,0.7046130932145184
60
+ 0.28552393642333684,1500,0.5718207700650759,0.5718207700650759,0.5547452555447233,0.5718207700650759,0.7550699642341905,0.7045639952758885
61
+ 0.28552393642333684,1500,0.5718546637744034,0.5718546637744034,0.5547791492540509,0.5718546637744034,0.7550611453067005,0.7045573507072014
62
+ 0,0,0.5763286334056399,0.5763286334056399,0.5589816867630893,0.5763286334056399,0.7619419081029518,0.7107794631883741
63
+ 0,0,0.5763286334056399,0.5763286334056399,0.5589816867630893,0.5763286334056399,0.7619419081029518,0.7107794631883741
64
+ 0,0,0.5763286334056399,0.5763286334056399,0.5589816867630893,0.5763286334056399,0.7619419081029518,0.7107794631883741
65
+ 0,0,0.5763286334056399,0.5763286334056399,0.5589816867630893,0.5763286334056399,0.7619419081029518,0.7107794631883741
66
+ 0.19036740909956215,500,0.5697193600867679,0.5697193600867679,0.5526833882272975,0.5697193600867679,0.7527492046788923,0.7023339704275311
67
+ 0.19036740909956215,500,0.5697193600867679,0.5697193600867679,0.5526833882272975,0.5697193600867679,0.7527417145877228,0.7023251516719322
68
+ 0.19036740909956215,500,0.569787147505423,0.569787147505423,0.5527511756459526,0.569787147505423,0.7527811081272089,0.7023781524881914
69
+ 0.19036740909956215,500,0.5698210412147505,0.5698210412147505,0.5528076651614986,0.5698210412147505,0.7528008620306891,0.7023797057507012
70
+ 0.3807348181991243,1000,0.5707022776572668,0.5707022776572668,0.5536821228621494,0.5707022776572668,0.755064691080744,0.7042851487163617
71
+ 0.3807348181991243,1000,0.5707361713665944,0.5707361713665944,0.5537329634261406,0.5707361713665944,0.7550164411707105,0.7042872064256666
72
+ 0.3807348181991243,1000,0.570837852494577,0.570837852494577,0.5538346445541233,0.570837852494577,0.7550124223383818,0.7043126581173641
73
+ 0.3807348181991243,1000,0.570837852494577,0.570837852494577,0.5538346445541233,0.570837852494577,0.7550235031678901,0.7043256986446385
74
+ 0.5711022272986864,1500,0.57121068329718,0.57121068329718,0.5541662380103778,0.57121068329718,0.7549331735917515,0.7045106184367891
75
+ 0.5711022272986864,1500,0.5710751084598699,0.5710751084598699,0.5540306631730676,0.5710751084598699,0.7548768077725545,0.7044249102545459
76
+ 0.5711022272986864,1500,0.5710073210412148,0.5710073210412148,0.5539628757544125,0.5710073210412148,0.7548672857166716,0.7043853629628037
77
+ 0.5711022272986864,1500,0.5710751084598699,0.5710751084598699,0.5540306631730676,0.5710751084598699,0.7548661944648665,0.704408070342965
78
+ 0.7614696363982486,2000,0.5724647505422994,0.5724647505422994,0.5555022150530387,0.5724647505422994,0.7556441782830775,0.7053615678821825
79
+ 0.7614696363982486,2000,0.5722952819956616,0.5722952819956616,0.5552988527970734,0.5722952819956616,0.7556132016021033,0.705243703589257
80
+ 0.7614696363982486,2000,0.5725325379609545,0.5725325379609545,0.5555361087623663,0.5725325379609545,0.7556908903654831,0.7053501630144251
81
+ 0.7614696363982486,2000,0.5725325379609545,0.5725325379609545,0.5555361087623663,0.5725325379609545,0.7557299885546241,0.7053782809698834
82
+ 0.9518370454978108,2500,0.5744644793926247,0.5744644793926247,0.5572562145107394,0.5744644793926247,0.7563418023171774,0.706148778416263
83
+ 0.9518370454978108,2500,0.5743627982646421,0.5743627982646421,0.5571714802374205,0.5743627982646421,0.756313785913426,0.7061107908998822
84
+ 0.9518370454978108,2500,0.5743627982646421,0.5743627982646421,0.5571714802374205,0.5743627982646421,0.7563412662086216,0.7061144376317139
85
+ 0.9518370454978108,2500,0.5745661605206074,0.5745661605206074,0.5573748424933858,0.5745661605206074,0.7564280950879166,0.7062567804476468
86
+ 1.1420140871882734,3000,0.5735832429501084,0.5735832429501084,0.5564145207291051,0.5735832429501084,0.7553309913118803,0.7053790199324479
87
+ 1.1420140871882734,3000,0.573617136659436,0.573617136659436,0.5564710102446511,0.573617136659436,0.7553660207445727,0.7053989569233873
88
+ 1.1420140871882734,3000,0.5735154555314533,0.5735154555314533,0.5564145207291052,0.5735154555314533,0.7553373955573515,0.7053485194759815
89
+ 1.1420140871882734,3000,0.5736849240780911,0.5736849240780911,0.5565613934695246,0.5736849240780911,0.7553546933280549,0.70541149755617
90
+ 1.3323814962878355,3500,0.5734137744034707,0.5734137744034707,0.556287419319127,0.5734137744034707,0.7557410007829215,0.7054674801318195
91
+ 1.3323814962878355,3500,0.573312093275488,0.573312093275488,0.5561857381911443,0.573312093275488,0.7557276213917873,0.705479467623301
92
+ 1.3323814962878355,3500,0.5730070498915402,0.5730070498915402,0.5558806948071964,0.5730070498915402,0.7555549571389175,0.705243201782141
93
+ 1.3323814962878355,3500,0.573312093275488,0.573312093275488,0.556202685045808,0.573312093275488,0.7556457303003123,0.7054297905330071
94
+ 1.5227489053873977,4000,0.5713123644251626,0.5713123644251626,0.5542142540985918,0.5713123644251626,0.7542586485567511,0.7038281859365721
95
+ 1.5227489053873977,4000,0.5713462581344902,0.5713462581344902,0.5542312009532556,0.5713462581344902,0.7542815238944296,0.7038686636830691
96
+ 1.5227489053873977,4000,0.5713462581344902,0.5713462581344902,0.5542481478079194,0.5713462581344902,0.7542862754016579,0.7038841147866347
97
+ 1.5227489053873977,4000,0.5715496203904555,0.5715496203904555,0.5544684569185484,0.5715496203904555,0.7543474328611853,0.7040081737179164
98
+ 1.71311631448696,4500,0.5731765184381779,0.5731765184381779,0.5562196319004717,0.5731765184381779,0.7558657067158973,0.7056025518190876
99
+ 1.71311631448696,4500,0.5729053687635575,0.5729053687635575,0.5559484822258514,0.5729053687635575,0.7557836706564156,0.7054633766138484
100
+ 1.71311631448696,4500,0.5728036876355749,0.5728036876355749,0.555829854243205,0.5728036876355749,0.755781415174826,0.7054748723346645
101
+ 1.71311631448696,4500,0.5728375813449024,0.5728375813449024,0.5558637479525325,0.5728375813449024,0.75573050909379,0.7054166442826206
102
+ 1.9034837235865218,5000,0.5738882863340564,0.5738882863340564,0.556756282298158,0.5738882863340564,0.7566720065754836,0.706250450958509
103
+ 1.9034837235865218,5000,0.5740916485900217,0.5740916485900217,0.5569426976994595,0.5740916485900217,0.7566779742511682,0.706292174901015
104
+ 1.9034837235865218,5000,0.5740577548806941,0.5740577548806941,0.5569426976994595,0.5740577548806941,0.756696049201291,0.7063106149437383
105
+ 1.9034837235865218,5000,0.5741933297180043,0.5741933297180043,0.557061325682106,0.5741933297180043,0.7568109387186975,0.7063953116158038
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e5447b13c419973afca0bb0e62f47f2dd1237efd30fc4ff58d4b09a81f9218a
3
+ size 45142000
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 100,
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "BertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25fa70180933cc2737c14961b2898ae6840de1b2b75a06ca2de294862a987bea
3
+ size 6289
vocab.txt ADDED
The diff for this file is too large to render. See raw diff