task-t2

README.md

@@ -0,0 +1,75 @@
+---
+license: apache-2.0
+base_model: KpRT/task-t1
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: task-t2
+  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. -->
+
+# task-t2
+
+This model is a fine-tuned version of [KpRT/task-t1](https://huggingface.co/KpRT/task-t1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3666
+- F1: 0.7591
+- Chronic Disease F1: 0.7643
+- Chronic Disease Num: 2090
+- Cancer F1: 0.6815
+- Cancer Num: 896
+- Allergy F1: 0.7304
+- Allergy Num: 200
+- Treatment F1: 0.7803
+- Treatment Num: 3185
+- Other F1: 0
+- Other Num: 0
+
+## 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: 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: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | F1     | Chronic Disease F1 | Chronic Disease Num | Cancer F1 | Cancer Num | Allergy F1 | Allergy Num | Treatment F1 | Treatment Num | Other F1 | Other Num |
+|:-------------:|:------:|:----:|:---------------:|:------:|:------------------:|:-------------------:|:---------:|:----------:|:----------:|:-----------:|:------------:|:-------------:|:--------:|:---------:|
+| 0.4565        | 0.3049 | 100  | 0.4226          | 0.7177 | 0.7053             | 2090                | 0.6397    | 896        | 0.6633     | 200         | 0.7524       | 3185          | 0        | 0         |
+| 0.4055        | 0.6098 | 200  | 0.3888          | 0.7396 | 0.7399             | 2090                | 0.6684    | 896        | 0.5989     | 200         | 0.7673       | 3185          | 0        | 0         |
+| 0.4327        | 0.9146 | 300  | 0.3818          | 0.7441 | 0.7441             | 2090                | 0.6614    | 896        | 0.7506     | 200         | 0.7684       | 3185          | 0        | 0         |
+| 0.3348        | 1.2195 | 400  | 0.3783          | 0.7518 | 0.7459             | 2090                | 0.6825    | 896        | 0.7032     | 200         | 0.7778       | 3185          | 0        | 0         |
+| 0.3207        | 1.5244 | 500  | 0.3701          | 0.7597 | 0.7619             | 2090                | 0.6830    | 896        | 0.7457     | 200         | 0.7825       | 3185          | 0        | 0         |
+| 0.3224        | 1.8293 | 600  | 0.3666          | 0.7591 | 0.7643             | 2090                | 0.6815    | 896        | 0.7304     | 200         | 0.7803       | 3185          | 0        | 0         |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "KpRT/task-t1",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-treatment",
+    "2": "I-treatment",
+    "3": "B-chronic_disease",
+    "4": "I-chronic_disease",
+    "5": "B-cancer",
+    "6": "I-cancer",
+    "7": "B-allergy",
+    "8": "I-allergy",
+    "9": "B-other",
+    "10": "I-other"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-allergy_name": 7,
+    "B-cancer": 5,
+    "B-chronic_disease": 3,
+    "B-other": 9,
+    "B-treatment": 1,
+    "I-allergy_name": 8,
+    "I-cancer": 6,
+    "I-chronic_disease": 4,
+    "I-other": 10,
+    "I-treatment": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a2de3bdafb2b5f62b5f9b456df86643d623575937419b722482cfe6f86c8c34
+size 435623772

runs/Jul21_06-42-55_5891dff67884/events.out.tfevents.1721544177.5891dff67884.2327.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63a500efd383921f65a4226d4d67c8b1df2ba5ca1d7a6715ea7a7a0920541e9c
+size 12215

runs/Jul21_06-51-39_5891dff67884/events.out.tfevents.1721544700.5891dff67884.2327.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c107b6e612f32195fe82fb5648faa9b00f581dc86288fde366beaca4e97a1c97
+size 8954

runs/Jul21_06-53-51_5891dff67884/events.out.tfevents.1721544832.5891dff67884.2327.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0847a24b9fdbfd04020ff5dc7cbf21115874e2c9d0c8e5f48577c865c83e5fb6
+size 12215

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "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 +1,59 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "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:ce0b04498ef91344b0c9158285150e49f7f9a26def6e43ef0bc6e966e6c02cd2
+size 5112