Model save

README.md

@@ -0,0 +1,77 @@
+---
+library_name: transformers
+license: agpl-3.0
+base_model: vinai/phobert-base-v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: phobert-v2-3class_v1
+  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-v2-3class_v1
+
+This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2110
+- Accuracy: 0.9526
+- Precision Macro: 0.8907
+- Recall Macro: 0.8637
+- F1 Macro: 0.8762
+- F1 Weighted: 0.9519
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- 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: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision Macro | Recall Macro | F1 Macro | F1 Weighted |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:------------:|:--------:|:-----------:|
+| 0.5276        | 1.0   | 90   | 0.2313          | 0.9330   | 0.9562          | 0.7135       | 0.7472   | 0.9219      |
+| 0.2071        | 2.0   | 180  | 0.1934          | 0.9488   | 0.8663          | 0.8697       | 0.8679   | 0.9489      |
+| 0.1535        | 3.0   | 270  | 0.1780          | 0.9520   | 0.8910          | 0.8427       | 0.8634   | 0.9505      |
+| 0.133         | 4.0   | 360  | 0.1885          | 0.9507   | 0.9063          | 0.8376       | 0.8654   | 0.9488      |
+| 0.1051        | 5.0   | 450  | 0.1948          | 0.9488   | 0.8749          | 0.8611       | 0.8677   | 0.9484      |
+| 0.1016        | 6.0   | 540  | 0.2034          | 0.9520   | 0.9061          | 0.8509       | 0.8743   | 0.9506      |
+| 0.0805        | 7.0   | 630  | 0.2120          | 0.9501   | 0.8674          | 0.8700       | 0.8687   | 0.9502      |
+| 0.074         | 8.0   | 720  | 0.2037          | 0.9564   | 0.9200          | 0.8625       | 0.8869   | 0.9551      |
+| 0.0616        | 9.0   | 810  | 0.2101          | 0.9526   | 0.8907          | 0.8637       | 0.8762   | 0.9519      |
+| 0.0612        | 10.0  | 900  | 0.2110          | 0.9526   | 0.8907          | 0.8637       | 0.8762   | 0.9519      |
+
+
+### Framework versions
+
+- Transformers 4.55.0
+- Pytorch 2.7.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.21.4

classification_report_test.txt

@@ -0,0 +1,14 @@
+              precision    recall  f1-score   support
+
+    negative       0.95      0.97      0.96      1409
+     neutral       0.75      0.47      0.58       167
+    positive       0.95      0.97      0.96      1590
+
+    accuracy                           0.94      3166
+   macro avg       0.88      0.80      0.83      3166
+weighted avg       0.94      0.94      0.94      3166
+
+Confusion matrix:
+[[1370   15   24]
+ [  32   79   56]
+ [  43   11 1536]]

confusion_matrix_test.csv

@@ -0,0 +1,4 @@
+,negative,neutral,positive
+negative,1370,15,24
+neutral,32,79,56
+positive,43,11,1536

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3766bf4509f42cf6096b4183e30f35c1ee48ba17a729242c5d624832ba99e787
+oid sha256:0d58ef1cdeeebda028331112b6be6c8d0ff714fa9c510e8eb74452274e8e3b00
 size 540026460