tarekxpc commited on
Commit
8163fea
1 Parent(s): 1b68924

Training in progress, step 500

Browse files
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57c92b639e600be97609cd3c7984d555ec749029c0f591a1a6e06ea4ff430c7f
3
  size 516674074
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f14b58328afee98810cb527ee371567167c988139bda1bd1150fc034ca21097
3
  size 516674074
special_tokens_map.json CHANGED
@@ -1,15 +1,45 @@
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
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "mask_token": {
24
  "content": "<mask>",
25
+ "lstrip": false,
26
  "normalized": false,
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
  "pad_token": "</s>",
31
+ "sep_token": {
32
+ "content": "</s>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ "unk_token": {
39
+ "content": "<unk>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ }
45
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,18 +1,17 @@
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
@@ -20,7 +19,7 @@
20
  "2": {
21
  "content": "</s>",
22
  "lstrip": false,
23
- "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
@@ -28,14 +27,14 @@
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,
@@ -46,12 +45,17 @@
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
  }
 
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
  "1": {
12
+ "content": "<s>",
13
  "lstrip": false,
14
+ "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
 
19
  "2": {
20
  "content": "</s>",
21
  "lstrip": false,
22
+ "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
 
27
  "3": {
28
  "content": "<unk>",
29
  "lstrip": false,
30
+ "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "4": {
36
  "content": "<mask>",
37
+ "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
 
45
  "clean_up_tokenization_spaces": true,
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
 
48
  "mask_token": "<mask>",
49
+ "max_length": 512,
50
  "model_max_length": 512,
51
+ "pad_to_multiple_of": null,
52
  "pad_token": "</s>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
  "sep_token": "</s>",
56
+ "stride": 0,
57
+ "tokenizer_class": "PreTrainedTokenizerFast",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
  "unk_token": "<unk>"
61
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbe4c6c54bf29c5bd66e9aadbe4c7170ddf70dacf0e74a63325c3841f6a1393e
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3cb40029289c5707c80e5a84c167a3cac1ada38530b90f1c9d5e99d150a43cf
3
  size 4984