roscazo commited on
Commit
d214952
1 Parent(s): 427acaf

vih_explainability2

Browse files
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ model-index:
11
+ - name: vih_explainability2
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
+ # vih_explainability2
19
+
20
+ This model is a fine-tuned version of [PlanTL-GOB-ES/bsc-bio-ehr-es](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.3811
23
+ - Roc Auc: 0.8939
24
+ - Ap Score: 0.7760
25
+ - Precision: 0.9146
26
+ - Recall: 0.8065
27
+ - F1: 0.8571
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 3e-05
47
+ - train_batch_size: 16
48
+ - eval_batch_size: 16
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 10
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Roc Auc | Ap Score | Precision | Recall | F1 |
57
+ |:-------------:|:------:|:----:|:---------------:|:-------:|:--------:|:---------:|:------:|:------:|
58
+ | 0.3644 | 0.8475 | 100 | 0.2350 | 0.8402 | 0.6907 | 0.9028 | 0.6989 | 0.7879 |
59
+ | 0.1848 | 1.6949 | 200 | 0.2358 | 0.8765 | 0.7168 | 0.8588 | 0.7849 | 0.8202 |
60
+ | 0.1462 | 2.5424 | 300 | 0.2215 | 0.9021 | 0.7509 | 0.8571 | 0.8387 | 0.8478 |
61
+ | 0.1105 | 3.3898 | 400 | 0.2671 | 0.8778 | 0.7504 | 0.9114 | 0.7742 | 0.8372 |
62
+ | 0.079 | 4.2373 | 500 | 0.3124 | 0.8630 | 0.7338 | 0.92 | 0.7419 | 0.8214 |
63
+ | 0.0248 | 5.0847 | 600 | 0.3464 | 0.8765 | 0.7416 | 0.9 | 0.7742 | 0.8324 |
64
+ | 0.0127 | 5.9322 | 700 | 0.3822 | 0.8617 | 0.7248 | 0.9079 | 0.7419 | 0.8166 |
65
+ | 0.0089 | 6.7797 | 800 | 0.3625 | 0.8885 | 0.7674 | 0.9136 | 0.7957 | 0.8506 |
66
+ | 0.0042 | 7.6271 | 900 | 0.3643 | 0.8885 | 0.7674 | 0.9136 | 0.7957 | 0.8506 |
67
+ | 0.0052 | 8.4746 | 1000 | 0.3772 | 0.8939 | 0.7760 | 0.9146 | 0.8065 | 0.8571 |
68
+ | 0.0031 | 9.3220 | 1100 | 0.3811 | 0.8939 | 0.7760 | 0.9146 | 0.8065 | 0.8571 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.41.0
74
+ - Pytorch 2.3.0+cu121
75
+ - Datasets 2.19.1
76
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
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": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "NO_SOSPECHA",
16
+ "1": "SOSPECHA"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "NO_SOSPECHA": 0,
22
+ "SOSPECHA": 1
23
+ },
24
+ "layer_norm_eps": 1e-05,
25
+ "max_position_embeddings": 514,
26
+ "model_type": "roberta",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 1,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.41.0",
34
+ "type_vocab_size": 1,
35
+ "use_cache": true,
36
+ "vocab_size": 50262
37
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9979d82645bb1cf096e7d13a8fbd555446f0ef0c2e7f33c7f4463ec7bdd2a630
3
+ size 498603608
runs/May27_08-15-42_5f34822827fa/events.out.tfevents.1716797753.5f34822827fa.1437.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf907d9a32f77b375308e4712a441c2d5240449b3e9c1698fbde24aead2607d7
3
+ size 13037
runs/May27_08-33-26_5f34822827fa/events.out.tfevents.1716798807.5f34822827fa.1437.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f04f7354858b321acc53b816d6639c4f9b4244aa874daa7ab7ed9fe2b09373e
3
+ size 13407
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
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
+ "50261": {
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": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "max_len": 512,
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3319de723fbe63c3fa95ffe9028981d8943b3c31d8a1fade1bad3e3d4191b9c6
3
+ size 5112
vocab.json ADDED
The diff for this file is too large to render. See raw diff