End of training

README.md

@@ -0,0 +1,74 @@
+---
+language:
+- vi
+base_model: vinai/phobert-large
+tags:
+- generated_from_trainer
+model-index:
+- name: phobert-large_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-large_baseline_words
+
+This model is a fine-tuned version of [vinai/phobert-large](https://huggingface.co/vinai/phobert-large) on the covid19_ner dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0943
+- Patient Id: 0.9863
+- Name: 0.9542
+- Gender: 0.9664
+- Age: 0.9633
+- Job: 0.8300
+- Location: 0.9521
+- Organization: 0.9188
+- Date: 0.9842
+- Symptom And Disease: 0.8773
+- Transportation: 1.0
+- F1 Macro: 0.9433
+- F1 Micro: 0.9521
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:------:|:------:|:------:|:--------:|:------------:|:------:|:-------------------:|:--------------:|:--------:|:--------:|
+| 0.2801        | 1.0   | 629  | 0.0981          | 0.9840     | 0.9455 | 0.9045 | 0.9010 | 0.5837 | 0.9265   | 0.8726       | 0.9812 | 0.8611              | 0.9831         | 0.8943   | 0.9266   |
+| 0.0446        | 2.0   | 1258 | 0.0897          | 0.9863     | 0.9549 | 0.9501 | 0.9722 | 0.7833 | 0.9355   | 0.8907       | 0.9852 | 0.8814              | 0.9721         | 0.9312   | 0.9434   |
+| 0.0283        | 3.0   | 1887 | 0.0809          | 0.9867     | 0.9516 | 0.9551 | 0.9695 | 0.7857 | 0.9487   | 0.9086       | 0.9860 | 0.8845              | 1.0            | 0.9376   | 0.9502   |
+| 0.0198        | 4.0   | 2516 | 0.0905          | 0.9863     | 0.9542 | 0.9647 | 0.9633 | 0.8287 | 0.9483   | 0.9159       | 0.9842 | 0.8897              | 1.0            | 0.9435   | 0.9516   |
+| 0.0134        | 5.0   | 3145 | 0.0943          | 0.9863     | 0.9542 | 0.9664 | 0.9633 | 0.8300 | 0.9521   | 0.9188       | 0.9842 | 0.8773              | 1.0            | 0.9433   | 0.9521   |
+
+
+### 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-large",
+  "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": 1024,
+  "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": 4096,
+  "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": 16,
+  "num_hidden_layers": 24,
+  "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 sha256:03ced38e6a22337f29a84378ee5ad0a8f81f1c8dcd0520d0bc1542e1fc611460
+size 1472588812

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:a7c59ca1f891414705a16760fb9f00758b7f1f44c4faac942b327bd763d6a866
+size 5176