thanaphatt1/aunt-mai-ork-v2

README.md

@@ -0,0 +1,76 @@
+---
+base_model: airesearch/wangchanberta-base-att-spm-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: wisesight_sentiment
+  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. -->
+
+# wisesight_sentiment
+
+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: 0.4140
+- Accuracy: 0.9025
+- F1 Micro: 0.9025
+- Precision Micro: 0.9025
+- Recall Micro: 0.9025
+- F1 Macro: 0.9010
+- Precision Macro: 0.9006
+- Recall Macro: 0.9015
+- Nb Samples: 1015
+
+## 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: 3e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 1412
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2031
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1 Micro | Precision Micro | Recall Micro | F1 Macro | Precision Macro | Recall Macro | Nb Samples |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:----------:|
+| 0.587         | 1.0   | 2031  | 0.5865          | 0.8532   | 0.8532   | 0.8532          | 0.8532       | 0.8492   | 0.8550          | 0.8460       | 1015       |
+| 0.5212        | 2.0   | 4062  | 0.7026          | 0.8158   | 0.8158   | 0.8158          | 0.8158       | 0.8156   | 0.8380          | 0.8322       | 1015       |
+| 0.4554        | 3.0   | 6093  | 0.4360          | 0.8768   | 0.8768   | 0.8768          | 0.8768       | 0.8731   | 0.8813          | 0.8690       | 1015       |
+| 0.3752        | 4.0   | 8124  | 0.4121          | 0.8897   | 0.8897   | 0.8897          | 0.8897       | 0.8867   | 0.8929          | 0.8831       | 1015       |
+| 0.382         | 5.0   | 10155 | 0.4709          | 0.8916   | 0.8916   | 0.8916          | 0.8916       | 0.8894   | 0.8917          | 0.8876       | 1015       |
+| 0.3465        | 6.0   | 12186 | 0.3929          | 0.8975   | 0.8975   | 0.8975          | 0.8975       | 0.8957   | 0.8964          | 0.8952       | 1015       |
+| 0.3246        | 7.0   | 14217 | 0.4801          | 0.8897   | 0.8897   | 0.8897          | 0.8897       | 0.8873   | 0.8899          | 0.8854       | 1015       |
+| 0.2808        | 8.0   | 16248 | 0.5070          | 0.8897   | 0.8897   | 0.8897          | 0.8897       | 0.8881   | 0.8874          | 0.8889       | 1015       |
+| 0.2786        | 9.0   | 18279 | 0.4098          | 0.8995   | 0.8995   | 0.8995          | 0.8995       | 0.8975   | 0.8993          | 0.8962       | 1015       |
+| 0.2151        | 10.0  | 20310 | 0.4140          | 0.9025   | 0.9025   | 0.9025          | 0.9025       | 0.9010   | 0.9006          | 0.9015       | 1015       |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.42.4",
+  "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 sha256:371e4f7b90d9a4007256d72cdf5ba7977df56aa273158c69af93c2d49a6f017f
+size 421007928

runs/Jul25_08-00-58_5cf20ceafa75/events.out.tfevents.1721894460.5cf20ceafa75.153.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:707a72f3032739f5f1dd803e999282a34e92862883dcec3881c87a7c6284341e
+size 20946

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 +1,84 @@
+{
+  "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": 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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 510,
+  "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 sha256:735144e94655ef533648804466fec58d9b928cd018cdadd4122a665256d15eb4
+size 5176