Hugging Face's logo

xEricCardozo
/
bert_adaptation_peppa_pig

Fill-Mask
Transformers
PyTorch
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
xEricCardozo commited on
Commit
21052c5
·
1 Parent(s): 3a297a0

End of training

Browse files
Files changed (7) hide show
  1. README.md +11 -10
  2. config.json +1 -1
  3. generation_config.json +1 -1
  4. model.safetensors +3 -0
  5. special_tokens_map.json +35 -5
  6. tokenizer_config.json +42 -0
  7. training_args.bin +2 -2
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-uncased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 2.4346
18
 
19
  ## Model description
20
 
@@ -40,21 +40,22 @@ The following hyperparameters were used during training:
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
  - num_epochs: 5
 
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | 4.1178 | 1.0 | 35 | 3.5855 |
49
- | 3.0127 | 2.0 | 70 | 2.7329 |
50
- | 2.6519 | 3.0 | 105 | 2.7326 |
51
- | 2.5643 | 4.0 | 140 | 2.5444 |
52
- | 2.2931 | 5.0 | 175 | 2.3511 |
53
 
54
 
55
  ### Framework versions
56
 
57
- - Transformers 4.33.1
58
- - Pytorch 2.0.1+cu118
59
- - Datasets 2.14.5
60
- - Tokenizers 0.13.3
 
14
 
15
  This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-uncased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 2.1710
18
 
19
  ## Model description
20
 
 
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
  - num_epochs: 5
43
+ - mixed_precision_training: Native AMP
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 3.9411 | 1.0 | 35 | 3.4726 |
50
+ | 2.9468 | 2.0 | 70 | 2.7930 |
51
+ | 2.631 | 3.0 | 105 | 2.4120 |
52
+ | 2.3962 | 4.0 | 140 | 2.4462 |
53
+ | 2.3435 | 5.0 | 175 | 2.5299 |
54
 
55
 
56
  ### Framework versions
57
 
58
+ - Transformers 4.35.2
59
+ - Pytorch 2.1.0+cu118
60
+ - Datasets 2.15.0
61
+ - Tokenizers 0.15.0
config.json CHANGED
@@ -20,7 +20,7 @@
20
  "pad_token_id": 1,
21
  "position_embedding_type": "absolute",
22
  "torch_dtype": "float32",
23
- "transformers_version": "4.33.1",
24
  "type_vocab_size": 2,
25
  "use_cache": true,
26
  "vocab_size": 31002
 
20
  "pad_token_id": 1,
21
  "position_embedding_type": "absolute",
22
  "torch_dtype": "float32",
23
+ "transformers_version": "4.35.2",
24
  "type_vocab_size": 2,
25
  "use_cache": true,
26
  "vocab_size": 31002
generation_config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
  "_from_model_config": true,
3
  "pad_token_id": 1,
4
- "transformers_version": "4.33.1"
5
  }
 
1
  {
2
  "_from_model_config": true,
3
  "pad_token_id": 1,
4
+ "transformers_version": "4.35.2"
5
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aa039cf17575c55f661460560e8f8147866191bb2b51c8fd7ec8b5f04e58ef5
3
+ size 439557376
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_config.json CHANGED
@@ -1,5 +1,47 @@
1
  {
2
  "TOKENIZERS_PARALLELISM": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "clean_up_tokenization_spaces": true,
4
  "cls_token": "[CLS]",
5
  "do_basic_tokenize": true,
 
1
  {
2
  "TOKENIZERS_PARALLELISM": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[MASK]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[PAD]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "3": {
21
+ "content": "[UNK]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "4": {
29
+ "content": "[CLS]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "5": {
37
+ "content": "[SEP]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
  "clean_up_tokenization_spaces": true,
46
  "cls_token": "[CLS]",
47
  "do_basic_tokenize": true,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d02a894340e02f30a81fcce59bb0cc00774f4dc2e64aeffdde355811f6ee14dd
3
- size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58fc6e5f2eed403814830789fdae13ae6366d8742252ab5d6159aa45e8a8faf4
3
+ size 4600