End of training

README.md

@@ -0,0 +1,74 @@
+---
+language:
+- vi
+base_model: vinai/phobert-base
+tags:
+- generated_from_trainer
+model-index:
+- name: phobert-base_baseline_words
+  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. -->
+
+# phobert-base_baseline_words
+
+This model is a fine-tuned version of [vinai/phobert-base](https://huggingface.co/vinai/phobert-base) on the covid19_ner dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0829
+- Patient Id: 0.9848
+- Name: 0.9421
+- Gender: 0.9570
+- Age: 0.9766
+- Job: 0.8095
+- Location: 0.9448
+- Organization: 0.9078
+- Date: 0.9869
+- Symptom And Disease: 0.8923
+- Transportation: 0.9943
+- F1 Macro: 0.9396
+- F1 Micro: 0.9498
+
+## 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: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Patient Id | Name   | Gender | Age    | Job    | Location | Organization | Date   | Symptom And Disease | Transportation | F1 Macro | F1 Micro |
+|:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:------:|:------:|:------:|:--------:|:------------:|:------:|:-------------------:|:--------------:|:--------:|:--------:|
+| 0.2964        | 1.0   | 629  | 0.1215          | 0.9689     | 0.9534 | 0.9107 | 0.8987 | 0.5357 | 0.9350   | 0.8368       | 0.9856 | 0.8584              | 0.9667         | 0.8850   | 0.9251   |
+| 0.068         | 2.0   | 1258 | 0.0890          | 0.9844     | 0.9479 | 0.9487 | 0.9723 | 0.6167 | 0.9377   | 0.8815       | 0.9860 | 0.8835              | 0.9886         | 0.9147   | 0.9409   |
+| 0.0441        | 3.0   | 1887 | 0.0847          | 0.9828     | 0.9446 | 0.9554 | 0.9737 | 0.7570 | 0.9445   | 0.9062       | 0.9874 | 0.8909              | 0.9943         | 0.9337   | 0.9482   |
+| 0.0327        | 4.0   | 2516 | 0.0859          | 0.9859     | 0.9449 | 0.9570 | 0.9765 | 0.7778 | 0.9451   | 0.9062       | 0.9874 | 0.8914              | 0.9943         | 0.9366   | 0.9495   |
+| 0.0259        | 5.0   | 3145 | 0.0829          | 0.9848     | 0.9421 | 0.9570 | 0.9766 | 0.8095 | 0.9448   | 0.9078       | 0.9869 | 0.8923              | 0.9943         | 0.9396   | 0.9498   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.1.2
+- Datasets 2.19.2
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "vinai/phobert-base",
+  "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": "B-PATIENT_ID",
+    "2": "I-PATIENT_ID",
+    "3": "B-NAME",
+    "4": "I-NAME",
+    "5": "B-GENDER",
+    "6": "I-GENDER",
+    "7": "B-AGE",
+    "8": "I-AGE",
+    "9": "B-JOB",
+    "10": "I-JOB",
+    "11": "B-LOCATION",
+    "12": "I-LOCATION",
+    "13": "B-ORGANIZATION",
+    "14": "I-ORGANIZATION",
+    "15": "B-DATE",
+    "16": "I-DATE",
+    "17": "B-SYMPTOM_AND_DISEASE",
+    "18": "I-SYMPTOM_AND_DISEASE",
+    "19": "B-TRANSPORTATION",
+    "20": "I-TRANSPORTATION"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-AGE": 7,
+    "B-DATE": 15,
+    "B-GENDER": 5,
+    "B-JOB": 9,
+    "B-LOCATION": 11,
+    "B-NAME": 3,
+    "B-ORGANIZATION": 13,
+    "B-PATIENT_ID": 1,
+    "B-SYMPTOM_AND_DISEASE": 17,
+    "B-TRANSPORTATION": 19,
+    "I-AGE": 8,
+    "I-DATE": 16,
+    "I-GENDER": 6,
+    "I-JOB": 10,
+    "I-LOCATION": 12,
+    "I-NAME": 4,
+    "I-ORGANIZATION": 14,
+    "I-PATIENT_ID": 2,
+    "I-SYMPTOM_AND_DISEASE": 18,
+    "I-TRANSPORTATION": 20,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "PhobertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c678d64ed6172d778bb38b11a38b567bfe624107d3a78086524df06cbcb1f0d
+size 537719244

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a056c5f10e119237e5d0caee446fb63ca9819729a18ba573d49ca5561afa5776
+size 5176