End of training

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 0.8838
-- Accuracy: 0.7739
+- Loss: 0.9164
+- Accuracy: 0.7808
 
 ## Model description
 
@@ -42,22 +42,23 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.2933        | 1.0   | 512  | 0.9614          | 0.6879   |
-| 0.7093        | 2.0   | 1024 | 0.8551          | 0.7437   |
-| 0.5112        | 3.0   | 1536 | 0.8486          | 0.7511   |
-| 0.3447        | 4.0   | 2048 | 0.8220          | 0.7705   |
-| 0.2433        | 5.0   | 2560 | 0.8838          | 0.7739   |
+| 1.3287        | 1.0   | 512  | 1.2494          | 0.5985   |
+| 0.8335        | 2.0   | 1024 | 0.8613          | 0.7289   |
+| 0.5842        | 3.0   | 1536 | 0.8177          | 0.7682   |
+| 0.4046        | 4.0   | 2048 | 0.8337          | 0.7682   |
+| 0.2979        | 5.0   | 2560 | 0.8745          | 0.7773   |
+| 0.2083        | 6.0   | 3072 | 0.9164          | 0.7808   |
 
 
 ### Framework versions
 
-- Transformers 4.33.3
+- Transformers 4.34.0
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.5
-- Tokenizers 0.13.3
+- Tokenizers 0.14.0

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19e6b5d9297224243412da96617d8206be17c855912107a76d51583ef0b9b27f
+oid sha256:d12f46b5b229e4f524285a2acefe93116554ab08c7d8fc9f139a5aaa2ded5738
 size 421095857