thanaphatt1/WangchanBERTa-LST20

README.md

@@ -0,0 +1,92 @@
+---
+license: cc-by-4.0
+base_model: pythainlp/thainer-corpus-v2-base-model
+tags:
+- generated_from_trainer
+datasets:
+- lst20
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: toneza
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: lst20
+      type: lst20
+      config: default
+      split: validation
+      args: default
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.768370802562324
+    - name: Recall
+      type: recall
+      value: 0.8120041393583994
+    - name: F1
+      type: f1
+      value: 0.7895851240015932
+    - name: Accuracy
+      type: accuracy
+      value: 0.956478116244312
+---
+
+<!-- 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. -->
+
+# toneza
+
+This model is a fine-tuned version of [pythainlp/thainer-corpus-v2-base-model](https://huggingface.co/pythainlp/thainer-corpus-v2-base-model) on the lst20 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1293
+- Precision: 0.7684
+- Recall: 0.8120
+- F1: 0.7896
+- Accuracy: 0.9565
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.1226        | 1.0   | 1978 | 0.1416          | 0.7414    | 0.7802 | 0.7603 | 0.9518   |
+| 0.098         | 2.0   | 3956 | 0.1324          | 0.7602    | 0.7966 | 0.7780 | 0.9545   |
+| 0.0895        | 3.0   | 5934 | 0.1293          | 0.7684    | 0.8120 | 0.7896 | 0.9565   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,95 @@
+{
+  "_name_or_path": "pythainlp/thainer-corpus-v2-base-model",
+  "architectures": [
+    "CamembertForTokenClassification"
+  ],
+  "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_BRN",
+    "2": "B_DES",
+    "3": "B_DTM",
+    "4": "B_LOC",
+    "5": "B_MEA",
+    "6": "B_NUM",
+    "7": "B_ORG",
+    "8": "B_PER",
+    "9": "B_TRM",
+    "10": "B_TTL",
+    "11": "I_BRN",
+    "12": "I_DES",
+    "13": "I_DTM",
+    "14": "I_LOC",
+    "15": "I_MEA",
+    "16": "I_NUM",
+    "17": "I_ORG",
+    "18": "I_PER",
+    "19": "I_TRM",
+    "20": "I_TTL",
+    "21": "E_BRN",
+    "22": "E_DES",
+    "23": "E_DTM",
+    "24": "E_LOC",
+    "25": "E_MEA",
+    "26": "E_NUM",
+    "27": "E_ORG",
+    "28": "E_PER",
+    "29": "E_TRM",
+    "30": "E_TTL"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B_BRN": 1,
+    "B_DES": 2,
+    "B_DTM": 3,
+    "B_LOC": 4,
+    "B_MEA": 5,
+    "B_NUM": 6,
+    "B_ORG": 7,
+    "B_PER": 8,
+    "B_TRM": 9,
+    "B_TTL": 10,
+    "E_BRN": 21,
+    "E_DES": 22,
+    "E_DTM": 23,
+    "E_LOC": 24,
+    "E_MEA": 25,
+    "E_NUM": 26,
+    "E_ORG": 27,
+    "E_PER": 28,
+    "E_TRM": 29,
+    "E_TTL": 30,
+    "I_BRN": 11,
+    "I_DES": 12,
+    "I_DTM": 13,
+    "I_LOC": 14,
+    "I_MEA": 15,
+    "I_NUM": 16,
+    "I_ORG": 17,
+    "I_PER": 18,
+    "I_TRM": 19,
+    "I_TTL": 20,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "camembert",
+  "num_attention_head": 12,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 25005
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1c7135a6e32117beefb11e6d9aa1a26708311a16826dd528cc59623ba263d3b
+size 418734556

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c4ba4e495ddf31eb2fdba7fc6aef3c233091d25d35bc9d24694ccf48ae114c
+size 904693

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,84 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "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>NOTUSED",
+      "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
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<_>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "25004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
+  "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>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:217d55f7698d62c36e0572fe4a8df8c6bc3aa6f48bac62f6e8c1f3619f72a1ba
+size 4536