Training in progress, epoch 0

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+base_model: google-bert/bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: ClinicalBERT-full-finetuned-ner-pablo
+  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. -->
+
+# ClinicalBERT-full-finetuned-ner-pablo
+
+This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1106
+- Precision: 0.8053
+- Recall: 0.7889
+- F1: 0.7970
+- Accuracy: 0.9702
+
+## 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: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.1409        | 0.9998 | 2608 | 0.1348          | 0.7629    | 0.7266 | 0.7443 | 0.9643   |
+| 0.095         | 2.0    | 5217 | 0.1152          | 0.7834    | 0.7656 | 0.7744 | 0.9678   |
+| 0.0639        | 2.9994 | 7824 | 0.1106          | 0.8053    | 0.7889 | 0.7970 | 0.9702   |
+
+
+### Framework versions
+
+- Transformers 4.44.0
+- Pytorch 2.4.0+cu124
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,67 @@
+{
+  "_name_or_path": "medicalai/ClinicalBERT",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-Drug",
+    "2": "I-Drug",
+    "3": "B-Reason",
+    "4": "I-Reason",
+    "5": "B-Route",
+    "6": "I-Route",
+    "7": "B-Strength",
+    "8": "I-Strength",
+    "9": "B-Form",
+    "10": "I-Form",
+    "11": "B-Dosage",
+    "12": "I-Dosage",
+    "13": "B-Frequency",
+    "14": "I-Frequency",
+    "15": "B-Duration",
+    "16": "I-Duration",
+    "17": "B-ADE",
+    "18": "I-ADE"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-ADE": 17,
+    "B-Dosage": 11,
+    "B-Drug": 1,
+    "B-Duration": 15,
+    "B-Form": 9,
+    "B-Frequency": 13,
+    "B-Reason": 3,
+    "B-Route": 5,
+    "B-Strength": 7,
+    "I-ADE": 18,
+    "I-Dosage": 12,
+    "I-Drug": 2,
+    "I-Duration": 16,
+    "I-Form": 10,
+    "I-Frequency": 14,
+    "I-Reason": 4,
+    "I-Route": 6,
+    "I-Strength": 8,
+    "O": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0",
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7ca82e191ba1e51a99a912edd0f8eb4aa81663a1123b3017feb82efdd899ac5
+size 539007116

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05510e024316963c95fdcc30486907efeeba7ee820ab258c291b2c5a05a51db6
+size 5176