ktb-finetune-wangchan2

README.md

@@ -0,0 +1,74 @@
+---
+library_name: transformers
+base_model: airesearch/wangchanberta-base-att-spm-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: KTB-finetune-wangchan2
+  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. -->
+
+# KTB-finetune-wangchan2
+
+This model is a fine-tuned version of [airesearch/wangchanberta-base-att-spm-uncased](https://huggingface.co/airesearch/wangchanberta-base-att-spm-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1691
+- Accuracy: 0.4021
+- Precision: 0.3807
+- Recall: 0.4021
+- F1: 0.3640
+
+## 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| No log        | 1.0   | 14   | 1.0647          | 0.4124   | 0.3712    | 0.4124 | 0.2638 |
+| No log        | 2.0   | 28   | 1.1045          | 0.4227   | 0.1787    | 0.4227 | 0.2512 |
+| No log        | 3.0   | 42   | 1.0891          | 0.3918   | 0.3810    | 0.3918 | 0.3641 |
+| No log        | 4.0   | 56   | 1.0860          | 0.4742   | 0.5304    | 0.4742 | 0.4209 |
+| No log        | 5.0   | 70   | 1.1355          | 0.4021   | 0.3752    | 0.4021 | 0.3145 |
+| No log        | 6.0   | 84   | 1.1354          | 0.3711   | 0.3500    | 0.3711 | 0.3543 |
+| No log        | 7.0   | 98   | 1.1478          | 0.4330   | 0.4405    | 0.4330 | 0.3789 |
+| No log        | 8.0   | 112  | 1.1734          | 0.3608   | 0.3415    | 0.3608 | 0.3350 |
+| No log        | 9.0   | 126  | 1.1691          | 0.4021   | 0.3807    | 0.4021 | 0.3640 |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 2.14.4
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "CamembertForSequenceClassification"
+  ],
+  "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": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "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 sha256:9d861730c647822d0c9a4f7d3abd5cdbe19579636e28ab5e6f6b70157c6f45d2
+size 421011004

runs/May27_04-23-42_f8add3f1da7e/events.out.tfevents.1748319826.f8add3f1da7e.3669.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6350016f733f5d173f4ee2191897bbd2bdeaaebf92d95b2658db6f4a7791cfaf
+size 5223

runs/May27_04-24-12_f8add3f1da7e/events.out.tfevents.1748319857.f8add3f1da7e.3669.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:248dd9b0b1752d2861792dc9e7424321121794a9ec895d4341a018ba3505ac4d
+size 5223

runs/May27_04-24-23_f8add3f1da7e/events.out.tfevents.1748319868.f8add3f1da7e.3669.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df0a30011c1cff1d8adf015a8192064fd5e5a7cc1de3b8f631ae985c985e9e39
+size 5223

runs/May27_04-27-50_f8add3f1da7e/events.out.tfevents.1748320123.f8add3f1da7e.3669.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03189cf9a8f2cd274b868737e58925f11e545e4a46f18482bfe0586a4fb16f85
+size 8280

runs/May27_04-30-24_f8add3f1da7e/events.out.tfevents.1748320227.f8add3f1da7e.18397.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:871afd3a943729ab7e74c43eee39032f87312a027c80091da5561d4fdf110b47
+size 10216

runs/May27_04-31-23_f8add3f1da7e/events.out.tfevents.1748320286.f8add3f1da7e.18397.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0435b0c6564ef54f9dbc1c6e6e5c07f716f5cd2f12eb416299babc1795e19619
+size 9738

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": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,85 @@
+{
+  "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": false
+    },
+    "25004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "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:bcadd3d1482f0efa84443722ad324bdf1ecdfa995b32e139442bc2320a7ca5fe
+size 5368