tiendoan commited on
Commit
d8ff6ee
·
verified ·
1 Parent(s): 48a79b0

Training in progress, epoch 1

Browse files
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "[CAPTION]": 30522,
3
- "[DESCRIPTION]": 30523
4
  }
 
1
  {
2
+ "[CAPTION]": 38168,
3
+ "[DESCRIPTION]": 38169
4
  }
config.json CHANGED
@@ -1,13 +1,15 @@
1
  {
2
- "_name_or_path": "distilbert/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": "image-sarcasm",
13
  "1": "multi-sarcasm",
@@ -15,23 +17,30 @@
15
  "3": "text-sarcasm"
16
  },
17
  "initializer_range": 0.02,
 
18
  "label2id": {
19
  "image-sarcasm": 0,
20
  "multi-sarcasm": 1,
21
  "not-sarcasm": 2,
22
  "text-sarcasm": 3
23
  },
 
24
  "max_position_embeddings": 512,
25
- "model_type": "distilbert",
26
- "n_heads": 12,
27
- "n_layers": 6,
 
28
  "pad_token_id": 0,
 
 
 
 
 
 
29
  "problem_type": "single_label_classification",
30
- "qa_dropout": 0.1,
31
- "seq_classif_dropout": 0.2,
32
- "sinusoidal_pos_embds": false,
33
- "tie_weights_": true,
34
  "torch_dtype": "float32",
35
  "transformers_version": "4.41.2",
36
- "vocab_size": 30524
 
 
37
  }
 
1
  {
2
+ "_name_or_path": "FPTAI/vibert-base-cased",
3
+ "_num_labels": 2,
4
  "architectures": [
5
+ "BertForSequenceClassification"
6
  ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "directionality": "bidi",
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
  "id2label": {
14
  "0": "image-sarcasm",
15
  "1": "multi-sarcasm",
 
17
  "3": "text-sarcasm"
18
  },
19
  "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
  "label2id": {
22
  "image-sarcasm": 0,
23
  "multi-sarcasm": 1,
24
  "not-sarcasm": 2,
25
  "text-sarcasm": 3
26
  },
27
+ "layer_norm_eps": 1e-12,
28
  "max_position_embeddings": 512,
29
+ "model_type": "bert",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "output_past": true,
33
  "pad_token_id": 0,
34
+ "pooler_fc_size": 768,
35
+ "pooler_num_attention_heads": 12,
36
+ "pooler_num_fc_layers": 3,
37
+ "pooler_size_per_head": 128,
38
+ "pooler_type": "first_token_transform",
39
+ "position_embedding_type": "absolute",
40
  "problem_type": "single_label_classification",
 
 
 
 
41
  "torch_dtype": "float32",
42
  "transformers_version": "4.41.2",
43
+ "type_vocab_size": 2,
44
+ "use_cache": true,
45
+ "vocab_size": 38170
46
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8989f377248b6f378394bf49fe365ef4c2d26751367948e80561671db503b5dd
3
- size 267844864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f039c7a4ada983e4d2225e58b9e5bc0fd66cffa0814f4ba0233388bfa2f00e50
3
+ size 461459464
runs/Oct27_14-28-34_3f882f3673da/events.out.tfevents.1730039314.3f882f3673da.4452.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6c81917859445216a6c3f82b3bf05f8b3b0a6d06580c2deb579a66c476379a5
3
+ size 5579
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": true
10
  },
11
- "100": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": true
18
  },
19
- "101": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "102": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
@@ -32,7 +32,7 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "103": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
@@ -40,7 +40,7 @@
40
  "single_word": false,
41
  "special": true
42
  },
43
- "30522": {
44
  "content": "[CAPTION]",
45
  "lstrip": false,
46
  "normalized": false,
@@ -48,7 +48,7 @@
48
  "single_word": false,
49
  "special": true
50
  },
51
- "30523": {
52
  "content": "[DESCRIPTION]",
53
  "lstrip": false,
54
  "normalized": false,
@@ -63,13 +63,15 @@
63
  ],
64
  "clean_up_tokenization_spaces": true,
65
  "cls_token": "[CLS]",
 
66
  "do_lower_case": true,
67
  "mask_token": "[MASK]",
68
- "model_max_length": 512,
 
69
  "pad_token": "[PAD]",
70
  "sep_token": "[SEP]",
71
  "strip_accents": null,
72
  "tokenize_chinese_chars": true,
73
- "tokenizer_class": "DistilBertTokenizer",
74
  "unk_token": "[UNK]"
75
  }
 
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "1": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "2": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "3": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "4": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
 
40
  "single_word": false,
41
  "special": true
42
  },
43
+ "38168": {
44
  "content": "[CAPTION]",
45
  "lstrip": false,
46
  "normalized": false,
 
48
  "single_word": false,
49
  "special": true
50
  },
51
+ "38169": {
52
  "content": "[DESCRIPTION]",
53
  "lstrip": false,
54
  "normalized": false,
 
63
  ],
64
  "clean_up_tokenization_spaces": true,
65
  "cls_token": "[CLS]",
66
+ "do_basic_tokenize": true,
67
  "do_lower_case": true,
68
  "mask_token": "[MASK]",
69
+ "model_max_length": 1000000000000000019884624838656,
70
+ "never_split": null,
71
  "pad_token": "[PAD]",
72
  "sep_token": "[SEP]",
73
  "strip_accents": null,
74
  "tokenize_chinese_chars": true,
75
+ "tokenizer_class": "BertTokenizer",
76
  "unk_token": "[UNK]"
77
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:033b095a20a011ff52a590d63fb2aca560100bc7eb5ee0de242c2ac42cea7167
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d26ba88e8813e2d7f52b55ee3409fcc73a8e61726d97ad14b69e0271783d3a32
3
  size 5176
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff