Fede-ezeq commited on
Commit
a0a2123
verified
1 Parent(s): f40f0fa

Training in progress, step 500

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "distilbert-base-uncased",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForQuestionAnswering"
@@ -16,9 +16,9 @@
16
  "pad_token_id": 0,
17
  "qa_dropout": 0.1,
18
  "seq_classif_dropout": 0.2,
19
- "sinusoidal_pos_embds": false,
20
  "tie_weights_": true,
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.38.2",
23
- "vocab_size": 30522
24
  }
 
1
  {
2
+ "_name_or_path": "dccuchile/distilbert-base-spanish-uncased",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForQuestionAnswering"
 
16
  "pad_token_id": 0,
17
  "qa_dropout": 0.1,
18
  "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": true,
20
  "tie_weights_": true,
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.38.2",
23
+ "vocab_size": 31002
24
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd074ffa04527b7ea63c04d7fe3ff4f19f46b7b67aa5e11b92757284c14cb134
3
- size 265470032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cc0bd357c04163acb2546bf7b2497392f29a04ea8f8b47a86a74fdffd4ec2b7
3
+ size 266944592
runs/Apr19_12-13-17_9e82ad0008ba/events.out.tfevents.1713528798.9e82ad0008ba.921.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c4686a1e7925c7db174c47fe5e75d2f7c27b840a2525aead6375184d9aea077
3
+ size 4979
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,39 +1,39 @@
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,
@@ -43,12 +43,14 @@
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
 
46
  "do_lower_case": true,
47
  "mask_token": "[MASK]",
48
  "model_max_length": 512,
 
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
51
- "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
  "tokenizer_class": "DistilBertTokenizer",
54
  "unk_token": "[UNK]"
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "[MASK]",
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
+ "3": {
20
+ "content": "[UNK]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "4": {
28
+ "content": "[CLS]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "5": {
36
+ "content": "[SEP]",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": 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": 512,
50
+ "never_split": null,
51
  "pad_token": "[PAD]",
52
  "sep_token": "[SEP]",
53
+ "strip_accents": false,
54
  "tokenize_chinese_chars": true,
55
  "tokenizer_class": "DistilBertTokenizer",
56
  "unk_token": "[UNK]"
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:000eb950032de803e3a354567d252da2a6b816b2c86cc147d6d73e5fef95189f
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14869bf9da822b2264bee7bd6acf6e75a08e916ceffab056e66d9c30100cd668
3
  size 4920
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff