fine-tune-bert-stock-thai-AJA

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
+base_model: bert-base-multilingual-cased
 tags:
 - generated_from_trainer
-base_model: bert-base-multilingual-cased
 metrics:
 - accuracy
 model-index:
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6909
-- Accuracy: 0.5919
+- Loss: 0.5975
+- Accuracy: 0.7124
 
 ## Model description
 
@@ -49,15 +49,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.6931        | 1.0   | 558  | 0.6764          | 0.5939   |
-| 0.6775        | 2.0   | 1116 | 0.6877          | 0.5843   |
-| 0.6751        | 3.0   | 1674 | 0.6904          | 0.5210   |
-| 0.6719        | 4.0   | 2232 | 0.6909          | 0.5919   |
+| 0.6433        | 1.0   | 485  | 0.5834          | 0.7331   |
+| 0.6408        | 2.0   | 970  | 0.5908          | 0.7277   |
+| 0.6369        | 3.0   | 1455 | 0.5930          | 0.7279   |
+| 0.627         | 4.0   | 1940 | 0.5975          | 0.7124   |
 
 
 ### Framework versions
 
-- Transformers 4.40.1
+- Transformers 4.40.2
 - Pytorch 2.2.1+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1

config.json

@@ -35,7 +35,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.40.1",
+  "transformers_version": "4.40.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 119547

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29c24099f78fb5b4733c4af606701abbdb9ea3c8bcf583e87acbe4d653726ae3
+oid sha256:fad921ab3a313c47de976de573f53a7fdf702a9b4b912f0bb465c7e9a7094a60
 size 711446532