vih_explainability

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+model-index:
+- name: vih_explainability
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# vih_explainability
+
+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.
+It achieves the following results on the evaluation set:
+- Loss: 0.3980
+- Roc Auc: 0.8920
+- Ap Score: 0.8575
+- Precision: 0.8926
+- Recall: 0.8920
+- F1: 0.8919
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 9e-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Roc Auc | Ap Score | Precision | Recall | F1     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|:--------:|:---------:|:------:|:------:|
+| 0.62          | 0.5376 | 50   | 0.5331          | 0.7789  | 0.7389   | 0.7905    | 0.7789 | 0.7763 |
+| 0.5106        | 1.0753 | 100  | 0.4343          | 0.7899  | 0.7614   | 0.8118    | 0.7899 | 0.7856 |
+| 0.3762        | 1.6129 | 150  | 0.3364          | 0.8594  | 0.8075   | 0.8596    | 0.8594 | 0.8594 |
+| 0.2878        | 2.1505 | 200  | 0.3582          | 0.8597  | 0.8260   | 0.8636    | 0.8597 | 0.8591 |
+| 0.2556        | 2.6882 | 250  | 0.3121          | 0.8706  | 0.8440   | 0.8764    | 0.8706 | 0.8698 |
+| 0.165         | 3.2258 | 300  | 0.3746          | 0.8652  | 0.8349   | 0.8699    | 0.8652 | 0.8645 |
+| 0.2125        | 3.7634 | 350  | 0.3842          | 0.8815  | 0.8629   | 0.8898    | 0.8815 | 0.8805 |
+| 0.1923        | 4.3011 | 400  | 0.3178          | 0.9080  | 0.8662   | 0.9086    | 0.9080 | 0.9081 |
+| 0.1333        | 4.8387 | 450  | 0.3397          | 0.8704  | 0.8297   | 0.8709    | 0.8704 | 0.8702 |
+| 0.137         | 5.3763 | 500  | 0.3369          | 0.9028  | 0.8718   | 0.9034    | 0.9028 | 0.9027 |
+| 0.1103        | 5.9140 | 550  | 0.3493          | 0.9025  | 0.8545   | 0.9045    | 0.9025 | 0.9026 |
+| 0.0896        | 6.4516 | 600  | 0.4059          | 0.8813  | 0.8507   | 0.8838    | 0.8813 | 0.8809 |
+| 0.0573        | 6.9892 | 650  | 0.3956          | 0.8813  | 0.8470   | 0.8826    | 0.8813 | 0.8810 |
+| 0.0716        | 7.5269 | 700  | 0.5566          | 0.8815  | 0.8674   | 0.8926    | 0.8815 | 0.8803 |
+| 0.0893        | 8.0645 | 750  | 0.3980          | 0.8920  | 0.8575   | 0.8926    | 0.8920 | 0.8919 |
+
+
+### Framework versions
+
+- Transformers 4.41.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NO_SOSPECHA",
+    "1": "SOSPECHA"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NO_SOSPECHA": 0,
+    "SOSPECHA": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9926ca19d76d70d457033c55502d913b36666570f9faaf969a6e54cb016e9f22
+size 498603608

runs/May27_07-30-59_e5ff851a56b1/events.out.tfevents.1716795093.e5ff851a56b1.979.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d23f5bcbe98badfe9f8a59d56732465fcdbbc869de09a297614abb4ca594fa0e
+size 16322

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50261": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf3dde74bd486074cc558d67a153bcc9410fb75e4de2ebb90ad42b3a86c55d5
+size 5112