luisgasco/setfit-token-classifier_test_biomed_7ep_b2

README.md

@@ -0,0 +1,75 @@
+---
+license: apache-2.0
+base_model: PlanTL-GOB-ES/roberta-base-biomedical-es
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: biomedical-roberta-finetuned-iomed_task
+  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. -->
+
+# biomedical-roberta-finetuned-iomed_task
+
+This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-biomedical-es](https://huggingface.co/PlanTL-GOB-ES/roberta-base-biomedical-es) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0367
+- Precision: 0.2541
+- Recall: 0.4551
+- F1: 0.3261
+- Accuracy: 0.7718
+
+## 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: 3.5e-06
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 7
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 1.2727        | 0.7   | 1064  | 1.1739          | 0.1144    | 0.2850 | 0.1632 | 0.7461   |
+| 0.9857        | 1.4   | 2128  | 1.0956          | 0.1626    | 0.3425 | 0.2205 | 0.7620   |
+| 0.9233        | 2.1   | 3192  | 1.0081          | 0.1457    | 0.3181 | 0.1999 | 0.7646   |
+| 0.8635        | 2.8   | 4256  | 1.0164          | 0.2019    | 0.3945 | 0.2671 | 0.7705   |
+| 0.821         | 3.5   | 5320  | 0.9852          | 0.1896    | 0.3827 | 0.2536 | 0.7709   |
+| 0.7574        | 4.2   | 6384  | 1.0179          | 0.2230    | 0.4157 | 0.2903 | 0.7714   |
+| 0.7725        | 4.9   | 7448  | 1.0378          | 0.2276    | 0.4299 | 0.2976 | 0.7695   |
+| 0.7365        | 5.6   | 8512  | 1.0315          | 0.2290    | 0.4354 | 0.3001 | 0.7722   |
+| 0.6596        | 6.3   | 9576  | 1.0406          | 0.2475    | 0.4496 | 0.3193 | 0.7723   |
+| 0.7028        | 7.0   | 10640 | 1.0367          | 0.2541    | 0.4551 | 0.3261 | 0.7718   |
+
+
+### Framework versions
+
+- Transformers 4.33.2
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "PlanTL-GOB-ES/roberta-base-biomedical-es",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "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": "O",
+    "1": "I-Tratamiento",
+    "2": "I-Razon Consulta",
+    "3": "I-Exploracion y/o Pruebas Complementarias",
+    "4": "I-Evolucion",
+    "5": "I-Derivacion de/a",
+    "6": "I-Antecedentes Personales",
+    "7": "I-Antecedentes Familiares",
+    "8": "I-4172950",
+    "9": "I-4012837",
+    "10": "B-Tratamiento",
+    "11": "B-Razon Consulta",
+    "12": "B-Exploracion y/o Pruebas Complementarias",
+    "13": "B-Evolucion",
+    "14": "B-Derivacion de/a",
+    "15": "B-Antecedentes Personales",
+    "16": "B-Antecedentes Familiares",
+    "17": "B-4172950",
+    "18": "B-4012837"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-4012837": 18,
+    "B-4172950": 17,
+    "B-Antecedentes Familiares": 16,
+    "B-Antecedentes Personales": 15,
+    "B-Derivacion de/a": 14,
+    "B-Evolucion": 13,
+    "B-Exploracion y/o Pruebas Complementarias": 12,
+    "B-Razon Consulta": 11,
+    "B-Tratamiento": 10,
+    "I-4012837": 9,
+    "I-4172950": 8,
+    "I-Antecedentes Familiares": 7,
+    "I-Antecedentes Personales": 6,
+    "I-Derivacion de/a": 5,
+    "I-Evolucion": 4,
+    "I-Exploracion y/o Pruebas Complementarias": 3,
+    "I-Razon Consulta": 2,
+    "I-Tratamiento": 1,
+    "O": 0
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3336f5acce2df48d4d076c0c31960b640e88f41df9cafe8497a494986c6ccb4b
+size 501676841

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 +1,65 @@
+{
+  "add_prefix_space": true,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b82526b27a6dc267a55ec693230527a40540df7b8e615851d154ac5a3c4b551
+size 4091