sohidalg commited on
Commit
050b629
·
verified ·
1 Parent(s): ddfc515

Training complete

Browse files
README.md CHANGED
@@ -1,6 +1,7 @@
1
  ---
2
  library_name: transformers
3
- base_model: mrm8488/electricidad-base-discriminator
 
4
  tags:
5
  - classification
6
  - generated_from_trainer
@@ -9,9 +10,6 @@ metrics:
9
  model-index:
10
  - name: clasificador-tweets
11
  results: []
12
- language:
13
- - es
14
- pipeline_tag: text-classification
15
  ---
16
 
17
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -19,10 +17,24 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  # clasificador-tweets
21
 
22
- This model is a fine-tuned version of [mrm8488/electricidad-base-discriminator](https://huggingface.co/mrm8488/electricidad-base-discriminator) on an somosnlp-hackathon-2022/es_tweets_laboral dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 1.0004
25
- - Accuracy: 0.7021
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26
 
27
  ### Training hyperparameters
28
 
@@ -39,16 +51,16 @@ The following hyperparameters were used during training:
39
 
40
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
41
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
42
- | No log | 1.0 | 23 | 1.7586 | 0.3404 |
43
- | No log | 2.0 | 46 | 1.5232 | 0.5319 |
44
- | No log | 3.0 | 69 | 1.2868 | 0.5957 |
45
- | No log | 4.0 | 92 | 1.1680 | 0.6596 |
46
- | No log | 5.0 | 115 | 1.1649 | 0.6383 |
47
- | No log | 6.0 | 138 | 1.1202 | 0.6809 |
48
- | No log | 7.0 | 161 | 1.1016 | 0.7021 |
49
- | No log | 8.0 | 184 | 1.0139 | 0.7234 |
50
- | No log | 9.0 | 207 | 1.0182 | 0.7021 |
51
- | No log | 10.0 | 230 | 1.0004 | 0.7021 |
52
 
53
 
54
  ### Framework versions
@@ -56,4 +68,4 @@ The following hyperparameters were used during training:
56
  - Transformers 4.47.1
57
  - Pytorch 2.5.1+cu121
58
  - Datasets 3.2.0
59
- - Tokenizers 0.21.0
 
1
  ---
2
  library_name: transformers
3
+ license: apache-2.0
4
+ base_model: PlanTL-GOB-ES/roberta-base-bne
5
  tags:
6
  - classification
7
  - generated_from_trainer
 
10
  model-index:
11
  - name: clasificador-tweets
12
  results: []
 
 
 
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
17
 
18
  # clasificador-tweets
19
 
20
+ This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-bne](https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.9541
23
+ - Accuracy: 0.7872
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
 
39
  ### Training hyperparameters
40
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | No log | 1.0 | 23 | 1.2658 | 0.6383 |
55
+ | No log | 2.0 | 46 | 1.0099 | 0.6596 |
56
+ | No log | 3.0 | 69 | 0.9374 | 0.7447 |
57
+ | No log | 4.0 | 92 | 0.8418 | 0.7234 |
58
+ | No log | 5.0 | 115 | 0.8731 | 0.7660 |
59
+ | No log | 6.0 | 138 | 0.8649 | 0.7660 |
60
+ | No log | 7.0 | 161 | 0.9246 | 0.7660 |
61
+ | No log | 8.0 | 184 | 0.9921 | 0.7447 |
62
+ | No log | 9.0 | 207 | 0.9305 | 0.7872 |
63
+ | No log | 10.0 | 230 | 0.9541 | 0.7872 |
64
 
65
 
66
  ### Framework versions
 
68
  - Transformers 4.47.1
69
  - Pytorch 2.5.1+cu121
70
  - Datasets 3.2.0
71
+ - Tokenizers 0.21.0
config.json CHANGED
@@ -1,13 +1,15 @@
1
  {
2
- "_name_or_path": "mrm8488/electricidad-base-discriminator",
3
  "architectures": [
4
- "ElectraForSequenceClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
 
7
  "classifier_dropout": null,
8
- "embedding_size": 768,
 
9
  "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
12
  "id2label": {
13
  "0": "LABEL_0",
@@ -31,21 +33,17 @@
31
  "LABEL_6": 6,
32
  "LABEL_7": 7
33
  },
34
- "layer_norm_eps": 1e-12,
35
- "max_position_embeddings": 512,
36
- "model_type": "electra",
37
  "num_attention_heads": 12,
38
  "num_hidden_layers": 12,
39
- "pad_token_id": 0,
40
  "position_embedding_type": "absolute",
41
  "problem_type": "single_label_classification",
42
- "summary_activation": "gelu",
43
- "summary_last_dropout": 0.1,
44
- "summary_type": "first",
45
- "summary_use_proj": true,
46
  "torch_dtype": "float32",
47
  "transformers_version": "4.47.1",
48
- "type_vocab_size": 2,
49
  "use_cache": true,
50
- "vocab_size": 31002
51
  }
 
1
  {
2
+ "_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
3
  "architectures": [
4
+ "RobertaForSequenceClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "bos_token_id": 0,
8
  "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
  "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.0,
13
  "hidden_size": 768,
14
  "id2label": {
15
  "0": "LABEL_0",
 
33
  "LABEL_6": 6,
34
  "LABEL_7": 7
35
  },
36
+ "layer_norm_eps": 1e-05,
37
+ "max_position_embeddings": 514,
38
+ "model_type": "roberta",
39
  "num_attention_heads": 12,
40
  "num_hidden_layers": 12,
41
+ "pad_token_id": 1,
42
  "position_embedding_type": "absolute",
43
  "problem_type": "single_label_classification",
 
 
 
 
44
  "torch_dtype": "float32",
45
  "transformers_version": "4.47.1",
46
+ "type_vocab_size": 1,
47
  "use_cache": true,
48
+ "vocab_size": 50262
49
  }
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 sha256:90a4f88257fa9e2dc9c7deab3d8c52b3fc25c5df79f5a240bdde5f8f39da808c
3
- size 439452264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43eee7d5b8cd2c721c7d06e00cab8b2d6e65d597b909603947e1abad06956a9e
3
+ size 498622064
special_tokens_map.json CHANGED
@@ -1,7 +1,51 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,58 +1,59 @@
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,
40
  "single_word": false,
41
  "special": true
42
  }
43
  },
44
- "clean_up_tokenization_spaces": true,
45
- "cls_token": "[CLS]",
46
- "do_basic_tokenize": true,
47
- "do_lower_case": true,
 
48
  "extra_special_tokens": {},
49
- "mask_token": "[MASK]",
50
- "model_max_length": 1000000000000000019884624838656,
51
- "never_split": null,
52
- "pad_token": "[PAD]",
53
- "sep_token": "[SEP]",
54
- "strip_accents": null,
55
- "tokenize_chinese_chars": true,
56
- "tokenizer_class": "ElectraTokenizer",
57
- "unk_token": "[UNK]"
58
  }
 
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
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
43
  }
44
  },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
  "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "max_len": 512,
53
+ "model_max_length": 512,
54
+ "pad_token": "<pad>",
55
+ "sep_token": "</s>",
56
+ "tokenizer_class": "RobertaTokenizer",
57
+ "trim_offsets": true,
58
+ "unk_token": "<unk>"
 
59
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ec1aaf5eb74de7cc06a2953c3c45cfab8f54c8db39e13815e6b07507f444492
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcfada215ba8f2848c3909fab40ad6eef469fdabeef4d504d6ed99b1e29326dc
3
  size 5304
vocab.json ADDED
The diff for this file is too large to render. See raw diff