duynhatran commited on
Commit
fe9c278
1 Parent(s): 7dec7e9

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "_name_or_path": "microsoft/deberta-base",
3
  "architectures": [
4
- "DebertaForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "hidden_act": "gelu",
@@ -12,7 +12,8 @@
12
  "layer_norm_eps": 1e-07,
13
  "max_position_embeddings": 512,
14
  "max_relative_positions": -1,
15
- "model_type": "deberta",
 
16
  "num_attention_heads": 12,
17
  "num_hidden_layers": 12,
18
  "pad_token_id": 0,
@@ -20,13 +21,15 @@
20
  "pooler_hidden_act": "gelu",
21
  "pooler_hidden_size": 768,
22
  "pos_att_type": [
23
- "c2p",
24
- "p2c"
25
  ],
26
  "position_biased_input": false,
 
27
  "relative_attention": true,
 
28
  "torch_dtype": "float32",
29
  "transformers_version": "4.44.2",
30
  "type_vocab_size": 0,
31
- "vocab_size": 50265
32
  }
 
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",
 
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,
 
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": "4.44.2",
33
  "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b807f8a112e9cb02e20847219de4cea1702922830258ef4ecbb36b8acd0c9338
3
- size 556799560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dac0db95695941f5b9ba7a83feaede94b48e5e65e3eba198f03de144bae3bfe
3
+ size 737719272
runs/Oct08_15-05-34_06a14169c5e2/events.out.tfevents.1728399977.06a14169c5e2.985.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:127bfc8e81d2fd70fc5c69e47a71ef2d3725ea9f82d800b1d3fd7d39783fa9e1
3
+ size 5892
special_tokens_map.json CHANGED
@@ -1,50 +1,14 @@
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,
12
- "normalized": 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": true,
26
- "normalized": true,
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": "[SEP]",
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
  }
 
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
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,6 +1,4 @@
1
  {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "[PAD]",
@@ -29,15 +27,15 @@
29
  "3": {
30
  "content": "[UNK]",
31
  "lstrip": false,
32
- "normalized": false,
33
  "rstrip": false,
34
  "single_word": false,
35
  "special": true
36
  },
37
- "50264": {
38
  "content": "[MASK]",
39
- "lstrip": true,
40
- "normalized": true,
41
  "rstrip": false,
42
  "single_word": false,
43
  "special": true
@@ -48,12 +46,13 @@
48
  "cls_token": "[CLS]",
49
  "do_lower_case": false,
50
  "eos_token": "[SEP]",
51
- "errors": "replace",
52
  "mask_token": "[MASK]",
53
  "model_max_length": 1000000000000000019884624838656,
54
  "pad_token": "[PAD]",
55
  "sep_token": "[SEP]",
56
- "tokenizer_class": "DebertaTokenizer",
 
 
57
  "unk_token": "[UNK]",
58
- "vocab_type": "gpt2"
59
  }
 
1
  {
 
 
2
  "added_tokens_decoder": {
3
  "0": {
4
  "content": "[PAD]",
 
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,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": 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:ada37eb2bcf9de56536046997b731701cde0469e5352f72ef0846b1c1a11a2cf
3
- size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:945454bf6a01e7a199ad5303e14b32c4a85e7178a246857db0abf1a316a5027c
3
+ size 5304