vih_explainability3

README.md

@@ -0,0 +1,76 @@
+---
+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_explainability3
+  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_explainability3
+
+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: 0.3951
+- Roc Auc: 0.8213
+- Ap Score: 0.7049
+- Precision: 0.9836
+- Recall: 0.6452
+- F1: 0.7792
+
+## 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: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- 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     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|:--------:|:---------:|:------:|:------:|
+| 0.4261        | 0.8475 | 100  | 0.3832          | 0.6129  | 0.3793   | 1.0       | 0.2258 | 0.3684 |
+| 0.2405        | 1.6949 | 200  | 0.4736          | 0.6344  | 0.4138   | 1.0       | 0.2688 | 0.4237 |
+| 0.2088        | 2.5424 | 300  | 0.3452          | 0.7729  | 0.6274   | 0.9808    | 0.5484 | 0.7034 |
+| 0.2196        | 3.3898 | 400  | 0.3644          | 0.7151  | 0.5431   | 1.0       | 0.4301 | 0.6015 |
+| 0.2068        | 4.2373 | 500  | 0.5156          | 0.6344  | 0.4138   | 1.0       | 0.2688 | 0.4237 |
+| 0.1374        | 5.0847 | 600  | 0.3988          | 0.7944  | 0.6619   | 0.9821    | 0.5914 | 0.7383 |
+| 0.1098        | 5.9322 | 700  | 0.3629          | 0.8051  | 0.6791   | 0.9828    | 0.6129 | 0.7550 |
+| 0.0914        | 6.7797 | 800  | 0.3394          | 0.8240  | 0.6934   | 0.9531    | 0.6559 | 0.7771 |
+| 0.088         | 7.6271 | 900  | 0.3612          | 0.8334  | 0.7009   | 0.9403    | 0.6774 | 0.7875 |
+| 0.0787        | 8.4746 | 1000 | 0.3801          | 0.8213  | 0.7049   | 0.9836    | 0.6452 | 0.7792 |
+| 0.0588        | 9.3220 | 1100 | 0.3951          | 0.8213  | 0.7049   | 0.9836    | 0.6452 | 0.7792 |
+
+
+### 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 sha256:8f3881298a7c25cc6037cb512a8ebb61868018e68b613cc956b546f0f78edb89
+size 498603608

runs/May28_15-40-20_ac3b67b96697/events.out.tfevents.1716910830.ac3b67b96697.594.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7365530813c0c4274a1efe5ed14892d17ef8a8112f48876152cf0bdad682e378
+size 13407

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 sha256:8b247d0fb85f0785d8933a5cd3584812ed2b8437b132bdd8b59a0d68df5cc0e8
+size 5112