matchaoneshot commited on
Commit
b382cc3
·
verified ·
1 Parent(s): 1208b2d

Training in progress, epoch 0

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json CHANGED
@@ -1,11 +1,9 @@
1
  {
2
- "_name_or_path": "bert-base-uncased",
3
  "architectures": [
4
- "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "gradient_checkpointing": false,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
@@ -309,17 +307,28 @@
309
  "LABEL_98": 98,
310
  "LABEL_99": 99
311
  },
312
- "layer_norm_eps": 1e-12,
313
  "max_position_embeddings": 512,
314
- "model_type": "bert",
 
 
315
  "num_attention_heads": 12,
316
  "num_hidden_layers": 12,
317
  "pad_token_id": 0,
318
- "position_embedding_type": "absolute",
 
 
 
 
 
 
 
 
319
  "problem_type": "multi_label_classification",
 
 
320
  "torch_dtype": "float32",
321
  "transformers_version": "4.46.3",
322
- "type_vocab_size": 2,
323
- "use_cache": true,
324
- "vocab_size": 30522
325
  }
 
1
  {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
  "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
 
 
7
  "hidden_act": "gelu",
8
  "hidden_dropout_prob": 0.1,
9
  "hidden_size": 768,
 
307
  "LABEL_98": 98,
308
  "LABEL_99": 99
309
  },
310
+ "layer_norm_eps": 1e-07,
311
  "max_position_embeddings": 512,
312
+ "max_relative_positions": -1,
313
+ "model_type": "deberta-v2",
314
+ "norm_rel_ebd": "layer_norm",
315
  "num_attention_heads": 12,
316
  "num_hidden_layers": 12,
317
  "pad_token_id": 0,
318
+ "pooler_dropout": 0,
319
+ "pooler_hidden_act": "gelu",
320
+ "pooler_hidden_size": 768,
321
+ "pos_att_type": [
322
+ "p2c",
323
+ "c2p"
324
+ ],
325
+ "position_biased_input": false,
326
+ "position_buckets": 256,
327
  "problem_type": "multi_label_classification",
328
+ "relative_attention": true,
329
+ "share_att_key": true,
330
  "torch_dtype": "float32",
331
  "transformers_version": "4.46.3",
332
+ "type_vocab_size": 0,
333
+ "vocab_size": 128100
 
334
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d0b1e3283b18538fb8a63d06f984b9ea741f7ce801a156437970a9ae22d2783
3
- size 438404668
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fabe929cf5dfcccbf33e03187beb6305b43fb97db8506a5defbb3b11fa47ffd
3
+ size 738165316
runs/Dec12_08-30-40_1b5c407642ff/events.out.tfevents.1733992255.1b5c407642ff.644.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd0668066726292656581c267ae20b46bf97e395368eb339f140efebb3163924
3
+ size 15901
special_tokens_map.json CHANGED
@@ -1,7 +1,15 @@
1
  {
 
2
  "cls_token": "[CLS]",
 
3
  "mask_token": "[MASK]",
4
  "pad_token": "[PAD]",
5
  "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "bos_token": "[CLS]",
3
  "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
  "mask_token": "[MASK]",
6
  "pad_token": "[PAD]",
7
  "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
  }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
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,
@@ -41,15 +41,18 @@
41
  "special": true
42
  }
43
  },
 
44
  "clean_up_tokenization_spaces": false,
45
  "cls_token": "[CLS]",
46
- "do_lower_case": true,
 
47
  "mask_token": "[MASK]",
48
- "model_max_length": 512,
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
51
- "strip_accents": null,
52
- "tokenize_chinese_chars": true,
53
- "tokenizer_class": "BertTokenizer",
54
- "unk_token": "[UNK]"
 
55
  }
 
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": true,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "128000": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
 
41
  "special": true
42
  }
43
  },
44
+ "bos_token": "[CLS]",
45
  "clean_up_tokenization_spaces": false,
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 sha256:623f7162ae7dbd69fd27eb9418e4e6462242c1ebc1882f492f3b583b36eb6be6
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76e8f9018ab261d97df157d889c6a7893776ff9e153c7c1157250b71b47e595
3
  size 5304