Pablo94 commited on
Commit
3d4d19c
1 Parent(s): e323171

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -22,7 +22,7 @@
22
  "position_embedding_type": "absolute",
23
  "problem_type": "single_label_classification",
24
  "torch_dtype": "float32",
25
- "transformers_version": "4.23.1",
26
  "type_vocab_size": 1,
27
  "use_cache": true,
28
  "vocab_size": 50262
 
22
  "position_embedding_type": "absolute",
23
  "problem_type": "single_label_classification",
24
  "torch_dtype": "float32",
25
+ "transformers_version": "4.33.1",
26
  "type_vocab_size": 1,
27
  "use_cache": true,
28
  "vocab_size": 50262
merges.txt CHANGED
@@ -1,4 +1,4 @@
1
- #version: 0.2 - Trained by `huggingface/tokenizers`
2
  Ġ d
3
  Ġ e
4
  Ġd e
 
1
+ #version: 0.2
2
  Ġ d
3
  Ġ e
4
  Ġd e
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b18a61953553101e186554be45449482b6462fff4cff89e4ee2415b1dc1995a
3
- size 498651117
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd0791352d8e92b5dc76ba3f01834755c1e8c64a2f7c4aac00ca65917fcc7a57
3
+ size 498648433
tokenizer.json CHANGED
@@ -94,6 +94,7 @@
94
  "continuing_subword_prefix": "",
95
  "end_of_word_suffix": "",
96
  "fuse_unk": false,
 
97
  "vocab": {
98
  "<s>": 0,
99
  "<pad>": 1,
 
94
  "continuing_subword_prefix": "",
95
  "end_of_word_suffix": "",
96
  "fuse_unk": false,
97
+ "byte_fallback": false,
98
  "vocab": {
99
  "<s>": 0,
100
  "<pad>": 1,
tokenizer_config.json CHANGED
@@ -8,6 +8,7 @@
8
  "rstrip": false,
9
  "single_word": false
10
  },
 
11
  "cls_token": {
12
  "__type": "AddedToken",
13
  "content": "<s>",
@@ -34,7 +35,9 @@
34
  "single_word": false
35
  },
36
  "max_len": 512,
37
- "name_or_path": "davidmasip/racism",
 
 
38
  "pad_token": {
39
  "__type": "AddedToken",
40
  "content": "<pad>",
@@ -43,6 +46,8 @@
43
  "rstrip": false,
44
  "single_word": false
45
  },
 
 
46
  "sep_token": {
47
  "__type": "AddedToken",
48
  "content": "</s>",
@@ -51,9 +56,11 @@
51
  "rstrip": false,
52
  "single_word": false
53
  },
54
- "special_tokens_map_file": null,
55
  "tokenizer_class": "RobertaTokenizer",
56
  "trim_offsets": true,
 
 
57
  "unk_token": {
58
  "__type": "AddedToken",
59
  "content": "<unk>",
 
8
  "rstrip": false,
9
  "single_word": false
10
  },
11
+ "clean_up_tokenization_spaces": true,
12
  "cls_token": {
13
  "__type": "AddedToken",
14
  "content": "<s>",
 
35
  "single_word": false
36
  },
37
  "max_len": 512,
38
+ "max_length": 512,
39
+ "model_max_length": 512,
40
+ "pad_to_multiple_of": null,
41
  "pad_token": {
42
  "__type": "AddedToken",
43
  "content": "<pad>",
 
46
  "rstrip": false,
47
  "single_word": false
48
  },
49
+ "pad_token_type_id": 0,
50
+ "padding_side": "right",
51
  "sep_token": {
52
  "__type": "AddedToken",
53
  "content": "</s>",
 
56
  "rstrip": false,
57
  "single_word": false
58
  },
59
+ "stride": 0,
60
  "tokenizer_class": "RobertaTokenizer",
61
  "trim_offsets": true,
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
  "unk_token": {
65
  "__type": "AddedToken",
66
  "content": "<unk>",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f522e4e5e5c4602e9e52b85697cb1da6bed2fe4b9b9eb1dadbd644e06adca5fb
3
- size 3375
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51c53e51bc0583c25102a09dcf47148e135e3cc3ce26901ca34305cf871385c3
3
+ size 4027