wwhheerree commited on
Commit
0f551e4
1 Parent(s): 4d91054

End of training

Browse files
README.md CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the eli5_category dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 2.2089
21
 
22
  ## Model description
23
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | No log | 1.0 | 17 | 2.1353 |
52
- | No log | 2.0 | 34 | 2.1425 |
53
- | No log | 3.0 | 51 | 2.3166 |
54
 
55
 
56
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the eli5_category dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.5913
21
 
22
  ## Model description
23
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | No log | 1.0 | 66 | 1.7467 |
52
+ | No log | 2.0 | 132 | 1.5866 |
53
+ | No log | 3.0 | 198 | 1.3590 |
54
 
55
 
56
  ### Framework versions
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef749c80af120c2d336d410df10df2bacb8c332c8c959974dee01cbcbf2525ea
3
  size 328693404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b03de1d03c532dd14f9a6fb691b9b554d355c964a1a51791ac6eab8fed9a033d
3
  size 328693404
special_tokens_map.json CHANGED
@@ -1,37 +1,15 @@
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
+ "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": "</s>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
15
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,62 +1,57 @@
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
  "clean_up_tokenization_spaces": true,
45
- "cls_token": "[CLS]",
46
- "do_lower_case": true,
47
- "mask_token": "[MASK]",
48
- "max_length": 384,
49
  "model_max_length": 512,
50
- "pad_to_multiple_of": null,
51
- "pad_token": "[PAD]",
52
- "pad_token_type_id": 0,
53
- "padding_side": "right",
54
- "sep_token": "[SEP]",
55
- "stride": 0,
56
- "strip_accents": null,
57
- "tokenize_chinese_chars": true,
58
- "tokenizer_class": "DistilBertTokenizer",
59
- "truncation_side": "right",
60
- "truncation_strategy": "only_second",
61
- "unk_token": "[UNK]"
62
  }
 
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": "</s>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
57
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bc3af622446df1e5d7e007b7be150892f50259519e5d2da3e3e570e51e81579
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:441e8a0cd5947a4a6c27eb62825647162844f32ea3beaa9f5a2921aa1abc3777
3
  size 4664
vocab.json ADDED
The diff for this file is too large to render. See raw diff