Doter commited on
Commit
4f67a9c
1 Parent(s): 35302d1

Training in progress, step 500

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -1,24 +1,35 @@
1
  {
2
- "_name_or_path": "faq_model",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForQuestionAnswering"
6
  ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
11
  "initializer_range": 0.02,
 
 
12
  "max_position_embeddings": 512,
13
- "model_type": "distilbert",
14
- "n_heads": 12,
15
- "n_layers": 6,
 
 
16
  "pad_token_id": 0,
17
- "qa_dropout": 0.1,
18
- "seq_classif_dropout": 0.2,
19
- "sinusoidal_pos_embds": false,
20
- "tie_weights_": true,
 
 
 
 
 
 
 
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.38.2",
23
- "vocab_size": 30522
 
24
  }
 
1
  {
2
+ "_name_or_path": "timpal0l/mdeberta-v3-base-squad2",
 
3
  "architectures": [
4
+ "DebertaV2ForQuestionAnswering"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
  "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-07,
13
  "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
  "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 768,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
  "torch_dtype": "float32",
32
  "transformers_version": "4.38.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 251000
35
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88e2b30f5641cd35f7a4893dd59f5294d07a49192dacd0e1c0697960f490a950
3
- size 265470032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41118aa6e07aa8785c2f0baf2329358cfa1d1319ea4a293f45054e3211670bef
3
+ size 1112905680
runs/Apr20_17-04-43_4ef846a27039/events.out.tfevents.1713632684.4ef846a27039.6060.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5af4608c6badd5bda2d9c1fdd90769097264658282fdad109ccba9b9ab95610d
3
- size 4927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fa8ec94b0187296f73a94e74be91de0cc3edf5d4fdd5b2443c1e56acb5e7a68
3
+ size 5823
runs/Apr20_18-15-01_4ef846a27039/events.out.tfevents.1713636903.4ef846a27039.6060.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c76faa7e1477d795cebaa52a92497a9abb6fdedc9e966f5606562d7c830c1d6
3
+ size 5051
runs/Apr20_18-26-21_4ef846a27039/events.out.tfevents.1713637582.4ef846a27039.27734.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b316af6c346931e6ba7f4819135c332ee79c970b9a7af7403930e5653aed8bd
3
+ size 5262
special_tokens_map.json CHANGED
@@ -1,4 +1,11 @@
1
  {
 
 
 
 
 
 
 
2
  "cls_token": {
3
  "content": "[CLS]",
4
  "lstrip": false,
@@ -6,6 +13,13 @@
6
  "rstrip": false,
7
  "single_word": false
8
  },
 
 
 
 
 
 
 
9
  "mask_token": {
10
  "content": "[MASK]",
11
  "lstrip": false,
 
1
  {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
  "cls_token": {
10
  "content": "[CLS]",
11
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "mask_token": {
24
  "content": "[MASK]",
25
  "lstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -8,31 +8,31 @@
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,
@@ -41,22 +41,18 @@
41
  "special": true
42
  }
43
  },
 
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
- "do_lower_case": true,
 
47
  "mask_token": "[MASK]",
48
- "max_length": 384,
49
  "model_max_length": 1000000000000000019884624838656,
50
- "pad_to_multiple_of": null,
51
  "pad_token": "[PAD]",
52
- "pad_token_type_id": 0,
53
- "padding_side": "right",
54
  "sep_token": "[SEP]",
55
- "stride": 0,
56
- "strip_accents": null,
57
- "tokenize_chinese_chars": true,
58
- "tokenizer_class": "DistilBertTokenizer",
59
- "truncation_side": "right",
60
- "truncation_strategy": "only_second",
61
- "unk_token": "[UNK]"
62
  }
 
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "1": {
12
+ "content": "[CLS]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "2": {
20
+ "content": "[SEP]",
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
+ "250101": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
 
41
  "special": true
42
  }
43
  },
44
+ "bos_token": "[CLS]",
45
  "clean_up_tokenization_spaces": true,
46
  "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
  "mask_token": "[MASK]",
 
50
  "model_max_length": 1000000000000000019884624838656,
 
51
  "pad_token": "[PAD]",
 
 
52
  "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
 
 
58
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7145fd9332ac54020fc9fa5dd1559179b17f656273d0fb7b4723c1aab5a4bdd
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a703af7c80acc22cc01c2196bcc1d8fe363b34e33caf90574aefe877ccc0f7e6
3
  size 4856