MooBai commited on
Commit
6c6a546
·
1 Parent(s): bab7a12

Training in progress epoch 0

Browse files
Files changed (6) hide show
  1. README.md +5 -5
  2. config.json +5 -3
  3. special_tokens_map.json +5 -13
  4. tf_model.h5 +2 -2
  5. tokenizer.json +2 -2
  6. tokenizer_config.json +22 -22
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: distilroberta-base
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
@@ -13,10 +13,10 @@ probably proofread and complete it, then remove this comment. -->
13
 
14
  # MooBai/distilroberta-base-finetuned-wikitext2
15
 
16
- This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 2.1544
19
- - Validation Loss: 1.8934
20
  - Epoch: 0
21
 
22
  ## Model description
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
43
 
44
  | Train Loss | Validation Loss | Epoch |
45
  |:----------:|:---------------:|:-----:|
46
- | 2.1544 | 1.8934 | 0 |
47
 
48
 
49
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: KoichiYasuoka/roberta-classical-chinese-base-char
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
 
13
 
14
  # MooBai/distilroberta-base-finetuned-wikitext2
15
 
16
+ This model is a fine-tuned version of [KoichiYasuoka/roberta-classical-chinese-base-char](https://huggingface.co/KoichiYasuoka/roberta-classical-chinese-base-char) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 2.0894
19
+ - Validation Loss: 1.0162
20
  - Epoch: 0
21
 
22
  ## Model description
 
43
 
44
  | Train Loss | Validation Loss | Epoch |
45
  |:----------:|:---------------:|:-----:|
46
+ | 2.0894 | 1.0162 | 0 |
47
 
48
 
49
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "distilroberta-base",
3
  "architectures": [
4
  "RobertaForMaskedLM"
5
  ],
@@ -7,6 +7,7 @@
7
  "bos_token_id": 0,
8
  "classifier_dropout": null,
9
  "eos_token_id": 2,
 
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
@@ -16,11 +17,12 @@
16
  "max_position_embeddings": 514,
17
  "model_type": "roberta",
18
  "num_attention_heads": 12,
19
- "num_hidden_layers": 6,
20
  "pad_token_id": 1,
21
  "position_embedding_type": "absolute",
 
22
  "transformers_version": "4.38.2",
23
  "type_vocab_size": 1,
24
  "use_cache": true,
25
- "vocab_size": 50265
26
  }
 
1
  {
2
+ "_name_or_path": "KoichiYasuoka/roberta-classical-chinese-base-char",
3
  "architectures": [
4
  "RobertaForMaskedLM"
5
  ],
 
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,
 
17
  "max_position_embeddings": 514,
18
  "model_type": "roberta",
19
  "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
  "pad_token_id": 1,
22
  "position_embedding_type": "absolute",
23
+ "tokenizer_class": "BertTokenizer",
24
  "transformers_version": "4.38.2",
25
  "type_vocab_size": 1,
26
  "use_cache": true,
27
+ "vocab_size": 26318
28
  }
special_tokens_map.json CHANGED
@@ -1,15 +1,7 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
5
- "mask_token": {
6
- "content": "<mask>",
7
- "lstrip": true,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "pad_token": "<pad>",
13
- "sep_token": "</s>",
14
- "unk_token": "<unk>"
15
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
7
  }
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00e1f392994e59408e4d382262be4edde8fa58894c5b6b59612d9964b8b48dcd
3
- size 484838604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1b2066b9848618c9d6618cbc9317cb6effc181a0ffaba5f49c14825cf72ff86
3
+ size 507845000
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e6506713f00e34406a757acb80f9f3233c1c3950857d32bbc41bcd419d5d8b6
3
- size 2108615
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c71693a6baa55416cf75c6408928f763db76889ca80d9df0ac393a9ee2627b7
3
+ size 518277
tokenizer_config.json CHANGED
@@ -1,57 +1,57 @@
1
  {
2
- "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
- "content": "<s>",
6
  "lstrip": false,
7
- "normalized": true,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
  "1": {
13
- "content": "<pad>",
14
  "lstrip": false,
15
- "normalized": true,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
  "2": {
21
- "content": "</s>",
22
  "lstrip": false,
23
- "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
  "3": {
29
- "content": "<unk>",
30
  "lstrip": false,
31
- "normalized": true,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
- "50264": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
  "normalized": false,
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
43
  }
44
  },
45
- "bos_token": "<s>",
46
  "clean_up_tokenization_spaces": true,
47
- "cls_token": "<s>",
48
- "eos_token": "</s>",
49
- "errors": "replace",
50
- "mask_token": "<mask>",
51
  "model_max_length": 512,
52
- "pad_token": "<pad>",
53
- "sep_token": "</s>",
54
- "tokenizer_class": "RobertaTokenizer",
55
- "trim_offsets": true,
56
- "unk_token": "<unk>"
 
 
57
  }
 
1
  {
 
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "[CLS]",
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": "[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": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "23291": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  }
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": 512,
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
  }