Hugging Face's logo

carmengoar
/
trabajo-final-bert-ej2

Text Classification
Transformers
Safetensors
modernbert
classification
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
carmengoar commited on
Commit
faa23ed
·
verified ·
1 Parent(s): af1f30f

Training complete

Browse files
Files changed (6) hide show
  1. README.md +63 -0
  2. config.json +89 -0
  3. model.safetensors +3 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +17 -0
  6. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: answerdotai/ModernBERT-base
5
+ tags:
6
+ - classification
7
+ - generated_from_trainer
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: trabajo-final-bert-ej2
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # trabajo-final-bert-ej2
19
+
20
+ This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 1.0763
23
+ - Accuracy: 0.5714
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
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 2e-05
43
+ - train_batch_size: 16
44
+ - eval_batch_size: 16
45
+ - seed: 42
46
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 2
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | No log | 1.0 | 3 | 1.1696 | 0.5714 |
55
+ | No log | 2.0 | 6 | 1.0763 | 0.5714 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 5.6.2
61
+ - Pytorch 2.10.0+cu128
62
+ - Datasets 4.8.5
63
+ - Tokenizers 0.22.2
config.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": null,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "LABEL_0",
24
+ "1": "LABEL_1",
25
+ "2": "LABEL_2"
26
+ },
27
+ "initializer_cutoff_factor": 2.0,
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 1152,
30
+ "label2id": {
31
+ "LABEL_0": 0,
32
+ "LABEL_1": 1,
33
+ "LABEL_2": 2
34
+ },
35
+ "layer_norm_eps": 1e-05,
36
+ "layer_types": [
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "full_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "full_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "full_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "full_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "full_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "full_attention"
59
+ ],
60
+ "local_attention": 128,
61
+ "max_position_embeddings": 8192,
62
+ "mlp_bias": false,
63
+ "mlp_dropout": 0.0,
64
+ "model_type": "modernbert",
65
+ "norm_bias": false,
66
+ "norm_eps": 1e-05,
67
+ "num_attention_heads": 12,
68
+ "num_hidden_layers": 22,
69
+ "pad_token_id": 50283,
70
+ "position_embedding_type": "absolute",
71
+ "problem_type": "single_label_classification",
72
+ "rope_parameters": {
73
+ "full_attention": {
74
+ "rope_theta": 160000.0,
75
+ "rope_type": "default"
76
+ },
77
+ "sliding_attention": {
78
+ "rope_theta": 10000.0,
79
+ "rope_type": "default"
80
+ }
81
+ },
82
+ "sep_token_id": 50282,
83
+ "sparse_pred_ignore_index": -100,
84
+ "sparse_prediction": false,
85
+ "tie_word_embeddings": true,
86
+ "transformers_version": "5.6.2",
87
+ "use_cache": false,
88
+ "vocab_size": 50368
89
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85a678bd7e72da104054aaf05f9162f33a7b9ca7c8e39458d1e12f0cca00be8b
3
+ size 598442860
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_input_names": [
9
+ "input_ids",
10
+ "attention_mask"
11
+ ],
12
+ "model_max_length": 8192,
13
+ "pad_token": "[PAD]",
14
+ "sep_token": "[SEP]",
15
+ "tokenizer_class": "TokenizersBackend",
16
+ "unk_token": "[UNK]"
17
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3acf9770a10249181248685f54a759d2ea003cc06ccf0f6f9e5db5c04275df97
3
+ size 5265