sitenote commited on
Commit
88b7c28
·
verified ·
1 Parent(s): 9851125

Training in progress, step 500

Browse files
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,
@@ -23,17 +21,28 @@
23
  "LABEL_2": 2,
24
  "LABEL_3": 3
25
  },
26
- "layer_norm_eps": 1e-12,
 
27
  "max_position_embeddings": 512,
28
- "model_type": "bert",
 
 
29
  "num_attention_heads": 12,
30
  "num_hidden_layers": 12,
31
  "pad_token_id": 0,
32
- "position_embedding_type": "absolute",
33
- "problem_type": "single_label_classification",
 
 
 
 
 
 
 
 
 
34
  "torch_dtype": "float32",
35
  "transformers_version": "4.48.3",
36
- "type_vocab_size": 2,
37
- "use_cache": true,
38
- "vocab_size": 30522
39
  }
 
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,
 
21
  "LABEL_2": 2,
22
  "LABEL_3": 3
23
  },
24
+ "layer_norm_eps": 1e-07,
25
+ "legacy": true,
26
  "max_position_embeddings": 512,
27
+ "max_relative_positions": -1,
28
+ "model_type": "deberta-v2",
29
+ "norm_rel_ebd": "layer_norm",
30
  "num_attention_heads": 12,
31
  "num_hidden_layers": 12,
32
  "pad_token_id": 0,
33
+ "pooler_dropout": 0,
34
+ "pooler_hidden_act": "gelu",
35
+ "pooler_hidden_size": 768,
36
+ "pos_att_type": [
37
+ "p2c",
38
+ "c2p"
39
+ ],
40
+ "position_biased_input": false,
41
+ "position_buckets": 256,
42
+ "relative_attention": true,
43
+ "share_att_key": true,
44
  "torch_dtype": "float32",
45
  "transformers_version": "4.48.3",
46
+ "type_vocab_size": 0,
47
+ "vocab_size": 128100
 
48
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8948da3ccf22a3cd1c504292421c230af8234cc12699ab03fd643bf046184d3
3
- size 437964800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d41b3e8e26dd79cfc3901d910c5c1e11f1c0bc7c5075fe0ceaf8962be294aedc
3
+ size 737725432
runs/Mar14_04-04-00_c16b051c5c57/events.out.tfevents.1741925043.c16b051c5c57.750.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3d3b3e316afa1e4b86fde6e4cd06888e2c9c7f6420bc329f0bb1ea060ca5688
3
+ size 4184
runs/Mar14_04-06-40_c16b051c5c57/events.out.tfevents.1741925202.c16b051c5c57.2001.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df9a8e6d3d5b80ff24eced7c179e239619d1f601274f2c17a4dbd77642a27b53
3
+ size 7474
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
  }
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,
@@ -41,16 +41,19 @@
41
  "special": true
42
  }
43
  },
 
44
  "clean_up_tokenization_spaces": false,
45
  "cls_token": "[CLS]",
46
- "do_lower_case": true,
 
47
  "extra_special_tokens": {},
48
  "mask_token": "[MASK]",
49
- "model_max_length": 512,
50
  "pad_token": "[PAD]",
51
  "sep_token": "[SEP]",
52
- "strip_accents": null,
53
- "tokenize_chinese_chars": true,
54
- "tokenizer_class": "BertTokenizer",
55
- "unk_token": "[UNK]"
 
56
  }
 
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
  "extra_special_tokens": {},
50
  "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
  "pad_token": "[PAD]",
53
  "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4fc21ce4867083aeee113c8fae94fffe15465fb418059835f371a305e72e2b0e
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29fc692206c5270cdb6cc03ab32cadbcd4438f0a67ae13d2a7369270df8a0e75
3
  size 5368