agomberto commited on
Commit
8e0bca5
1 Parent(s): e58b5f3

Model save

Browse files
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  tags:
3
  - generated_from_trainer
4
  model-index:
@@ -11,9 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
11
 
12
  # my_fancy_model
13
 
14
- This model was trained from scratch on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 0.5050
17
 
18
  ## Model description
19
 
@@ -44,8 +45,8 @@ The following hyperparameters were used during training:
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
- | No log | 1.0 | 32 | 0.5050 |
48
- | No log | 2.0 | 64 | 0.5081 |
49
 
50
 
51
  ### Framework versions
 
1
  ---
2
+ base_model: yiyanghkust/finbert-fls
3
  tags:
4
  - generated_from_trainer
5
  model-index:
 
12
 
13
  # my_fancy_model
14
 
15
+ This model is a fine-tuned version of [yiyanghkust/finbert-fls](https://huggingface.co/yiyanghkust/finbert-fls) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.8892
18
 
19
  ## Model description
20
 
 
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
+ | No log | 1.0 | 7 | 0.9168 |
49
+ | No log | 2.0 | 14 | 0.8892 |
50
 
51
 
52
  ### Framework versions
config.json CHANGED
@@ -1,25 +1,37 @@
1
  {
2
- "_name_or_path": "../models/my_fancy_model",
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
  "initializer_range": 0.02,
 
 
 
 
 
 
 
12
  "max_position_embeddings": 512,
13
- "model_type": "distilbert",
14
- "n_heads": 12,
15
- "n_layers": 6,
16
  "pad_token_id": 0,
 
17
  "problem_type": "single_label_classification",
18
- "qa_dropout": 0.1,
19
- "seq_classif_dropout": 0.2,
20
- "sinusoidal_pos_embds": false,
21
- "tie_weights_": true,
22
  "torch_dtype": "float32",
23
  "transformers_version": "4.38.2",
24
- "vocab_size": 30522
 
 
25
  }
 
1
  {
2
+ "_name_or_path": "yiyanghkust/finbert-fls",
 
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,
12
+ "id2label": {
13
+ "0": "Not FLS",
14
+ "1": "Non-specific FLS",
15
+ "2": "Specific FLS"
16
+ },
17
  "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "Non-specific FLS": 1,
21
+ "Not FLS": 0,
22
+ "Specific FLS": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
  "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
  "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
  "problem_type": "single_label_classification",
 
 
 
 
32
  "torch_dtype": "float32",
33
  "transformers_version": "4.38.2",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
+ "vocab_size": 30873
37
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:977524e86ad18dc72739f9fe4539cd2908f9d1cb83d6e1a17752da955c329e2e
3
- size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce410972ea7b8b4331d14ae05f474f38ae47dda3452c467b3707e4bd4b49e30f
3
+ size 439039996
special_tokens_map.json CHANGED
@@ -1,37 +1,7 @@
1
  {
2
- "cls_token": {
3
- "content": "[CLS]",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "mask_token": {
10
- "content": "[MASK]",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "[PAD]",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "sep_token": {
24
- "content": "[SEP]",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "unk_token": {
31
- "content": "[UNK]",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false
36
- }
37
  }
 
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
@@ -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,
@@ -43,17 +43,15 @@
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
 
46
  "do_lower_case": true,
47
  "mask_token": "[MASK]",
48
- "max_length": 32,
49
  "model_max_length": 1000000000000000019884624838656,
 
50
  "pad_token": "[PAD]",
51
  "sep_token": "[SEP]",
52
- "stride": 0,
53
  "strip_accents": null,
54
  "tokenize_chinese_chars": true,
55
- "tokenizer_class": "DistilBertTokenizer",
56
- "truncation_side": "right",
57
- "truncation_strategy": "longest_first",
58
  "unk_token": "[UNK]"
59
  }
 
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "2": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "3": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "4": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "5": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
 
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
  "do_lower_case": true,
48
  "mask_token": "[MASK]",
 
49
  "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
  "pad_token": "[PAD]",
52
  "sep_token": "[SEP]",
 
53
  "strip_accents": null,
54
  "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
 
 
56
  "unk_token": "[UNK]"
57
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1bcaf821a6e72fbb3bb372aaaaa5e0151c821067ef39828f1923410f9cbf9ba
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e16bdafd3627cef8d379918048882bd0dca5ece55f00090dc9ac9f56b518d54
3
  size 4984
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff