Training in progress, step 200
Browse files- .gitattributes +4 -0
- added_tokens.json +3 -0
- bm25_Plus_04_06_model_full_manual_stopword +3 -0
- bpe.codes +0 -0
- config.json +27 -0
- doc_refers_saved +3 -0
- documents_manual +3 -0
- eval/binary_classification_evaluation_results.csv +22 -0
- model.safetensors +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
bm25_Plus_04_06_model_full_manual_stopword filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
doc_refers_saved filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
documents_manual filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<mask>": 64000
|
| 3 |
+
}
|
bm25_Plus_04_06_model_full_manual_stopword
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01c418b6e1b7927664ed1b887fb925def004764ebb381813bb0e46d130393d7c
|
| 3 |
+
size 2459228
|
bpe.codes
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"max_position_embeddings": 258,
|
| 16 |
+
"model_type": "roberta",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.53.0",
|
| 24 |
+
"type_vocab_size": 1,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 64001
|
| 27 |
+
}
|
doc_refers_saved
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4de97700cf4a2c775130814b7a1a2073be1e3ca46414c31ab71d82af0e83fef
|
| 3 |
+
size 4963885
|
documents_manual
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96c5fe7deebf8540e76900ab0bb2b4e1400b586e0f056b0ec9f4746c88a4cc0c
|
| 3 |
+
size 4627956
|
eval/binary_classification_evaluation_results.csv
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch,steps,cosine_accuracy,cosine_accuracy_threshold,cosine_f1,cosine_precision,cosine_recall,cosine_f1_threshold,cosine_ap,cosine_mcc
|
| 2 |
+
0.23801023444008093,200,0.9196732471068755,0.89631784,0.5454545454545454,0.4732142857142857,0.6437246963562753,0.84664917,0.5725498837273496,0.4930543844876164
|
| 3 |
+
0.2737476047084588,100,0.9910344827586207,0.6709935,0.7728813559322034,0.7702702702702703,0.7755102040816326,0.66129404,0.8109245924831903,0.7681693609157316
|
| 4 |
+
0.5474952094169176,200,0.9908965517241379,0.7155751,0.7659574468085106,0.8,0.7346938775510204,0.71144533,0.7900612105652763,0.7620418852734103
|
| 5 |
+
0.8212428141253764,300,0.9895172413793103,0.72586393,0.726153846153846,0.6629213483146067,0.8027210884353742,0.6710193,0.8061593419985575,0.7233837832193133
|
| 6 |
+
1.093074185600876,400,0.9913103448275862,0.702577,0.7820069204152249,0.795774647887324,0.7687074829931972,0.7013879,0.8193264895708858,0.7776962712192785
|
| 7 |
+
1.3668217903093347,500,0.9910344827586207,0.7130754,0.7549668874172186,0.7354838709677419,0.7755102040816326,0.6622511,0.8199941260368444,0.7500331349923824
|
| 8 |
+
1.6405693950177938,600,0.9918620689655172,0.71606714,0.794425087108014,0.8142857142857143,0.7755102040816326,0.7079996,0.8515547915646092,0.7905212352657877
|
| 9 |
+
1.9143169997262524,700,0.9917241379310345,0.73886395,0.7793103448275861,0.7902097902097902,0.7687074829931972,0.70565104,0.8537655908871739,0.7748841018991678
|
| 10 |
+
2.186148371201752,800,0.9918620689655172,0.7441974,0.7806691449814126,0.860655737704918,0.7142857142857143,0.7309892,0.8367149413322006,0.7800638382638173
|
| 11 |
+
2.459895975910211,900,0.9918620689655172,0.74482626,0.7900355871886121,0.8283582089552238,0.7551020408163265,0.7291355,0.85188759893509,0.7867712483509214
|
| 12 |
+
2.7336435806186694,1000,0.9917241379310345,0.72008896,0.7902097902097902,0.8129496402877698,0.7687074829931972,0.7168498,0.8488854658576866,0.78631214670644
|
| 13 |
+
3.0054749520941693,1100,0.9922758620689656,0.71697545,0.797153024911032,0.835820895522388,0.7619047619047619,0.70220345,0.8595794359720046,0.7940371257075095
|
| 14 |
+
3.279222556802628,1200,0.9917241379310345,0.7438187,0.7692307692307693,0.8849557522123894,0.6802721088435374,0.73809546,0.8349486899075246,0.7719606514273636
|
| 15 |
+
3.552970161511087,1300,0.9915862068965517,0.74987864,0.7781569965870306,0.7808219178082192,0.7755102040816326,0.69252425,0.8466830752990457,0.7735865348511624
|
| 16 |
+
3.8267177662195455,1400,0.992,0.7529645,0.7857142857142857,0.8270676691729323,0.7482993197278912,0.70877767,0.8557382018746543,0.7825232478191183
|
| 17 |
+
4.098549137695045,1500,0.992,0.7606131,0.7838827838827839,0.8492063492063492,0.7278911564625851,0.7213285,0.8510757888906063,0.7821676716121486
|
| 18 |
+
4.372296742403504,1600,0.992,0.7613013,0.782312925170068,0.782312925170068,0.782312925170068,0.6925474,0.8493575810067342,0.7778077864962682
|
| 19 |
+
4.646044347111963,1700,0.992,0.73490024,0.7803030303030303,0.8803418803418803,0.7006802721088435,0.73490024,0.8465575226633929,0.7815324939556896
|
| 20 |
+
4.919791951820422,1800,0.992,0.75603986,0.7794117647058824,0.848,0.7210884353741497,0.72007847,0.8478611769373476,0.7778692867443595
|
| 21 |
+
0.2737476047084588,100,0.9895172413793103,0.66036916,0.7323943661971831,0.7591240875912408,0.7074829931972789,0.66036916,0.7641762653757682,0.7275243703004146
|
| 22 |
+
0.5474952094169176,200,0.9899310344827587,0.68127066,0.7474747474747474,0.74,0.7551020408163265,0.67431676,0.7620539372725037,0.7422341892636944
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86652e17f6e1cc16ba84aee7893437e827053b13121db26148fa607a55b2b040
|
| 3 |
+
size 540015464
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:222975faa02f5257c6e8c734e85973e48c8d42d7d37d90b894c73efa1841d76a
|
| 3 |
+
size 17083154
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"64000": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 256,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b1684132275c5d9994283d29b055a15575cc89209c18ac420ed748e6c5f4314
|
| 3 |
+
size 5624
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|