deid_roberta_medical_reports

README.md

@@ -0,0 +1,77 @@
+---
+library_name: transformers
+license: mit
+base_model: obi/deid_roberta_i2b2
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: fine-tuned-model
+  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. -->
+
+# fine-tuned-model
+
+This model is a fine-tuned version of [obi/deid_roberta_i2b2](https://huggingface.co/obi/deid_roberta_i2b2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2126
+- Model Preparation Time: 0.0061
+- Precision: 0.9143
+- Recall: 0.9156
+- F1: 0.9132
+- Accuracy: 0.9156
+
+## 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: 2e-05
+- 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 | Model Preparation Time | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:---------:|:------:|:------:|:--------:|
+| 0.4678        | 1.0   | 125  | 0.4248          | 0.0061                 | 0.7737    | 0.8229 | 0.7836 | 0.8229   |
+| 0.3877        | 2.0   | 250  | 0.4008          | 0.0061                 | 0.7886    | 0.8282 | 0.8060 | 0.8282   |
+| 0.3391        | 3.0   | 375  | 0.3132          | 0.0061                 | 0.8213    | 0.8672 | 0.8389 | 0.8672   |
+| 0.3091        | 4.0   | 500  | 0.3124          | 0.0061                 | 0.8334    | 0.8597 | 0.8419 | 0.8597   |
+| 0.2572        | 5.0   | 625  | 0.2570          | 0.0061                 | 0.8675    | 0.8911 | 0.8739 | 0.8911   |
+| 0.2368        | 6.0   | 750  | 0.2270          | 0.0061                 | 0.8908    | 0.9084 | 0.8973 | 0.9084   |
+| 0.2115        | 7.0   | 875  | 0.2219          | 0.0061                 | 0.8960    | 0.9081 | 0.9017 | 0.9081   |
+| 0.1949        | 8.0   | 1000 | 0.2325          | 0.0061                 | 0.8993    | 0.9044 | 0.8991 | 0.9044   |
+| 0.1843        | 9.0   | 1125 | 0.2218          | 0.0061                 | 0.9035    | 0.9103 | 0.9059 | 0.9103   |
+| 0.1691        | 10.0  | 1250 | 0.2126          | 0.0061                 | 0.9143    | 0.9156 | 0.9132 | 0.9156   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu124
+- Datasets 2.14.5
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "obi/deid_roberta_i2b2",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-PATIENT",
+    "2": "I-PATIENT",
+    "3": "B-DATE",
+    "4": "I-DATE",
+    "5": "B-ID",
+    "6": "I-ID",
+    "7": "B-PHONE",
+    "8": "I-PHONE",
+    "9": "B-LOC",
+    "10": "I-LOC",
+    "11": "B-HOSP",
+    "12": "I-HOSP",
+    "13": "B-AGE",
+    "14": "I-AGE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-AGE": 13,
+    "B-DATE": 3,
+    "B-HOSP": 11,
+    "B-ID": 5,
+    "B-LOC": 9,
+    "B-PATIENT": 1,
+    "B-PHONE": 7,
+    "I-AGE": 14,
+    "I-DATE": 4,
+    "I-HOSP": 12,
+    "I-ID": 6,
+    "I-LOC": 10,
+    "I-PATIENT": 2,
+    "I-PHONE": 8,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a2bf9b0a5f6188baa974c805b17be85b5548225d608806695037e935ddc9ff2
+size 1417473100

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2fdf2a4c598d5b390d1cdc14bad1942263ae53bad1f82b0af9d0dd1cafdd586
+size 5176