RKessler commited on
Commit
8d8c32e
1 Parent(s): bfec9aa

End of training

Browse files
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
- license: mit
3
- base_model: camembert-base
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
- - generator
8
  model-index:
9
  - name: VogagenRelation
10
  results: []
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # VogagenRelation
17
 
18
- This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on the generator dataset.
19
 
20
  ## Model description
21
 
 
1
  ---
2
+ license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
+ - imdb
8
  model-index:
9
  - name: VogagenRelation
10
  results: []
 
15
 
16
  # VogagenRelation
17
 
18
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
19
 
20
  ## Model description
21
 
config.json CHANGED
@@ -1,32 +1,32 @@
1
  {
2
- "_name_or_path": "camembert-base",
 
3
  "architectures": [
4
- "CamembertModel"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": 5,
8
- "classifier_dropout": null,
9
- "eos_token_id": 6,
10
- "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
12
- "hidden_size": 768,
13
  "id2label": {
14
- "0": 0,
15
- "1": 1
16
  },
17
  "initializer_range": 0.02,
18
- "intermediate_size": 3072,
19
- "layer_norm_eps": 1e-05,
20
- "max_position_embeddings": 514,
21
- "model_type": "camembert",
22
- "num_attention_heads": 12,
23
- "num_hidden_layers": 12,
24
- "output_past": true,
25
- "pad_token_id": 1,
26
- "position_embedding_type": "absolute",
 
 
 
 
27
  "torch_dtype": "float32",
28
  "transformers_version": "4.34.0",
29
- "type_vocab_size": 1,
30
- "use_cache": true,
31
- "vocab_size": 32005
32
  }
 
1
  {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForSequenceClassification"
6
  ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
 
 
 
11
  "id2label": {
12
+ "0": "NEGATIVE",
13
+ "1": "POSITIVE"
14
  },
15
  "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
24
+ "pad_token_id": 0,
25
+ "qa_dropout": 0.1,
26
+ "seq_classif_dropout": 0.2,
27
+ "sinusoidal_pos_embds": false,
28
+ "tie_weights_": true,
29
  "torch_dtype": "float32",
30
  "transformers_version": "4.34.0",
31
+ "vocab_size": 30522
 
 
32
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0731296072fe244c6a20a991966bb2b9529fe71844cca65baab4477b254118fd
3
- size 442552230
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e16150ed2f1589a3e0af42772c77620c79b35b9da9018464ae6cf1350d9e85f
3
+ size 267855978
special_tokens_map.json CHANGED
@@ -1,13 +1,7 @@
1
  {
2
- "additional_special_tokens": [
3
- "<s>NOTUSED",
4
- "</s>NOTUSED"
5
- ],
6
- "bos_token": "<s>",
7
- "cls_token": "<s>",
8
- "eos_token": "</s>",
9
- "mask_token": "<mask>",
10
- "pad_token": "<pad>",
11
- "sep_token": "</s>",
12
- "unk_token": "<unk>"
13
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
7
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,74 +1,56 @@
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "<s>NOTUSED",
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>NOTUSED",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
- "4": {
28
- "content": "<unk>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "5": {
36
- "content": "<s>",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
- },
43
- "6": {
44
- "content": "</s>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "32004": {
52
- "content": "<mask>",
53
- "lstrip": true,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
  }
59
  },
60
- "additional_special_tokens": [
61
- "<s>NOTUSED",
62
- "</s>NOTUSED"
63
- ],
64
- "bos_token": "<s>",
65
  "clean_up_tokenization_spaces": true,
66
- "cls_token": "<s>",
67
- "eos_token": "</s>",
68
- "mask_token": "<mask>",
69
  "model_max_length": 512,
70
- "pad_token": "<pad>",
71
- "sep_token": "</s>",
72
- "tokenizer_class": "CamembertTokenizer",
73
- "unk_token": "<unk>"
 
 
74
  }
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "[PAD]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
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,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  }
43
  },
44
+ "additional_special_tokens": [],
 
 
 
 
45
  "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": true,
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": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40f123ceeda946470653164a09c41230e8bb15c5818abc45d633c197ca901b16
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0321df80f37887dc9f4ea59d769f97784cd65371a71d08e415e3c034093d87d3
3
  size 4536