Hugging Face's logo

LumousInTheWild
/
acha_sentiment_test

Safetensors
camembert
Model card Files
xet
 Community
LumousInTheWild commited on
Commit
26fd759
·
verified ·
1 Parent(s): 19f6aca

Training in progress, step 500

Browse files
Files changed (5) hide show
  1. config.json +44 -44
  2. model.safetensors +1 -1
  3. special_tokens_map.json +20 -20
  4. tokenizer_config.json +85 -84
  5. training_args.bin +2 -2
config.json CHANGED
@@ -1,44 +1,44 @@
1
- {
2
- "_name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
3
- "architectures": [
4
- "CamembertForSequenceClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": 0,
8
- "classifier_dropout": null,
9
- "eos_token_id": 2,
10
- "gradient_checkpointing": false,
11
- "hidden_act": "gelu",
12
- "hidden_dropout_prob": 0.1,
13
- "hidden_size": 768,
14
- "id2label": {
15
- "0": "0",
16
- "1": "0-",
17
- "2": "0+",
18
- "3": "-1",
19
- "4": "1"
20
- },
21
- "initializer_range": 0.02,
22
- "intermediate_size": 3072,
23
- "label2id": {
24
- "-1": 3,
25
- "0": 0,
26
- "0+": 2,
27
- "0-": 1,
28
- "1": 4
29
- },
30
- "layer_norm_eps": 1e-12,
31
- "max_position_embeddings": 512,
32
- "model_type": "camembert",
33
- "num_attention_head": 12,
34
- "num_attention_heads": 12,
35
- "num_hidden_layers": 12,
36
- "pad_token_id": 1,
37
- "position_embedding_type": "absolute",
38
- "problem_type": "single_label_classification",
39
- "torch_dtype": "float32",
40
- "transformers_version": "4.44.2",
41
- "type_vocab_size": 1,
42
- "use_cache": true,
43
- "vocab_size": 25005
44
- }
 
1
+ {
2
+ "_name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
3
+ "architectures": [
4
+ "CamembertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "0",
16
+ "1": "0-",
17
+ "2": "0+",
18
+ "3": "-1",
19
+ "4": "1"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "-1": 3,
25
+ "0": 0,
26
+ "0+": 2,
27
+ "0-": 1,
28
+ "1": 4
29
+ },
30
+ "layer_norm_eps": 1e-12,
31
+ "max_position_embeddings": 512,
32
+ "model_type": "camembert",
33
+ "num_attention_head": 12,
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 1,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "single_label_classification",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.42.3",
41
+ "type_vocab_size": 1,
42
+ "use_cache": true,
43
+ "vocab_size": 25005
44
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:487c5be4cde04da57ece7f7877a1b3925e60e15b2ff64e62dc9aaa6c2da93b01
3
  size 421017156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6b2816c8c7ae797e2a6b79028dde415cc507ee428aa12260ae12c284c167c7f
3
  size 421017156
special_tokens_map.json CHANGED
@@ -1,20 +1,20 @@
1
- {
2
- "additional_special_tokens": [
3
- "<s>NOTUSED",
4
- "</s>NOTUSED",
5
- "<_>"
6
- ],
7
- "bos_token": "<s>",
8
- "cls_token": "<s>",
9
- "eos_token": "</s>",
10
- "mask_token": {
11
- "content": "<mask>",
12
- "lstrip": true,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
- },
17
- "pad_token": "<pad>",
18
- "sep_token": "</s>",
19
- "unk_token": "<unk>"
20
- }
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED",
5
+ "<_>"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "cls_token": "<s>",
9
+ "eos_token": "</s>",
10
+ "mask_token": {
11
+ "content": "<mask>",
12
+ "lstrip": true,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "unk_token": "<unk>"
20
+ }
tokenizer_config.json CHANGED
@@ -1,84 +1,85 @@
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
- "3": {
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
- "8": {
52
- "content": "<_>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": false
58
- },
59
- "25004": {
60
- "content": "<mask>",
61
- "lstrip": true,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- }
67
- },
68
- "additional_special_tokens": [
69
- "<s>NOTUSED",
70
- "</s>NOTUSED",
71
- "<_>"
72
- ],
73
- "bos_token": "<s>",
74
- "clean_up_tokenization_spaces": true,
75
- "cls_token": "<s>",
76
- "eos_token": "</s>",
77
- "mask_token": "<mask>",
78
- "model_max_length": 1000000000000000019884624838656,
79
- "pad_token": "<pad>",
80
- "sep_token": "</s>",
81
- "sp_model_kwargs": {},
82
- "tokenizer_class": "CamembertTokenizer",
83
- "unk_token": "<unk>"
84
- }
 
 
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
+ "3": {
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
+ "8": {
52
+ "content": "<_>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "25004": {
60
+ "content": "<mask>",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "additional_special_tokens": [
69
+ "<s>NOTUSED",
70
+ "</s>NOTUSED",
71
+ "<_>"
72
+ ],
73
+ "bos_token": "<s>",
74
+ "clean_up_tokenization_spaces": true,
75
+ "cls_token": "<s>",
76
+ "device_map": "cuda",
77
+ "eos_token": "</s>",
78
+ "mask_token": "<mask>",
79
+ "model_max_length": 1000000000000000019884624838656,
80
+ "pad_token": "<pad>",
81
+ "sep_token": "</s>",
82
+ "sp_model_kwargs": {},
83
+ "tokenizer_class": "CamembertTokenizer",
84
+ "unk_token": "<unk>"
85
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b98dec04664b453547cf303c9a854f6a54b867456f6f857a0890a6027b843177
3
- size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41c584ae8322698a91086448f570ff16d4cd7e6cf332079b43ae89a5757f6255
3
+ size 5048