TungCan/Sentiment-Finetune

README.md

@@ -0,0 +1,82 @@
+---
+library_name: transformers
+base_model: 5CD-AI/Vietnamese-Sentiment-visobert
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: tuning-sentiment-5cdviso
+  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. -->
+
+# tuning-sentiment-5cdviso
+
+This model is a fine-tuned version of [5CD-AI/Vietnamese-Sentiment-visobert](https://huggingface.co/5CD-AI/Vietnamese-Sentiment-visobert) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0617
+- Accuracy: 0.984
+- F1: 0.9840
+- Precision: 0.9837
+- Recall: 0.9844
+
+## 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: Use 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: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.6027        | 0.2451 | 50   | 0.3793          | 0.856    | 0.8561 | 0.8604    | 0.8621 |
+| 0.4082        | 0.4902 | 100  | 0.3015          | 0.8806   | 0.8804 | 0.8815    | 0.8854 |
+| 0.3498        | 0.7353 | 150  | 0.2385          | 0.9138   | 0.9140 | 0.9132    | 0.9156 |
+| 0.3354        | 0.9804 | 200  | 0.1968          | 0.92     | 0.9203 | 0.9199    | 0.9210 |
+| 0.2146        | 1.2255 | 250  | 0.2305          | 0.9132   | 0.9140 | 0.9178    | 0.9182 |
+| 0.2103        | 1.4706 | 300  | 0.1952          | 0.9255   | 0.9256 | 0.9276    | 0.9301 |
+| 0.2094        | 1.7157 | 350  | 0.1357          | 0.9563   | 0.9563 | 0.9563    | 0.9563 |
+| 0.2165        | 1.9608 | 400  | 0.1214          | 0.9612   | 0.9611 | 0.9621    | 0.9603 |
+| 0.1226        | 2.2059 | 450  | 0.1238          | 0.9618   | 0.9618 | 0.9612    | 0.9629 |
+| 0.1409        | 2.4510 | 500  | 0.1241          | 0.9538   | 0.9539 | 0.9540    | 0.9569 |
+| 0.138         | 2.6961 | 550  | 0.0839          | 0.9735   | 0.9735 | 0.9730    | 0.9740 |
+| 0.1246        | 2.9412 | 600  | 0.0717          | 0.9809   | 0.9809 | 0.9807    | 0.9812 |
+| 0.0724        | 3.1863 | 650  | 0.0761          | 0.9791   | 0.9791 | 0.9785    | 0.9799 |
+| 0.0851        | 3.4314 | 700  | 0.0686          | 0.9822   | 0.9821 | 0.9821    | 0.9822 |
+| 0.0917        | 3.6765 | 750  | 0.0636          | 0.9828   | 0.9828 | 0.9829    | 0.9827 |
+| 0.071         | 3.9216 | 800  | 0.0621          | 0.984    | 0.9840 | 0.9837    | 0.9844 |
+
+
+### Framework versions
+
+- Transformers 4.47.0
+- Pytorch 2.5.1+cu121
+- Datasets 3.3.1
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "5CD-AI/Vietnamese-Sentiment-visobert",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NEG",
+    "1": "POS",
+    "2": "NEU"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NEG": 0,
+    "NEU": 2,
+    "POS": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_length": 256,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "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": "4.47.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 15004
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8fedf0db3ac800b3931b3656561e291f1f426e1e9ea1c81968a10bdd7995b46
+size 390297116

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02aaf05cda4db99e86b7c76eba6258867ce4d043da0fed19c87a7d46c8b53a65
+size 470732

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "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
+    },
+    "15001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 256,
+  "model_max_length": 256,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb26ce40ab8e40402c122a1325cb48d59b18cc434fabe01992dd2091b88f8952
+size 5240