End of training

README.md

@@ -17,8 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4108
-- Accuracy: 0.79
+- Loss: 0.3460
+- Accuracy: 0.825
+- Mcc: 0.2657
 
 ## Model description
 
@@ -47,18 +48,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 51   | 0.3373          | 0.83     |
-| No log        | 2.0   | 102  | 0.3360          | 0.7975   |
-| No log        | 3.0   | 153  | 0.3572          | 0.79     |
-| No log        | 4.0   | 204  | 0.3911          | 0.795    |
-| No log        | 5.0   | 255  | 0.4108          | 0.79     |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Mcc    |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 1.0   | 51   | 0.4138          | 0.8475   | 0.0    |
+| No log        | 2.0   | 102  | 0.3231          | 0.84     | 0.0763 |
+| No log        | 3.0   | 153  | 0.3211          | 0.825    | 0.2657 |
+| No log        | 4.0   | 204  | 0.3750          | 0.845    | 0.1995 |
+| No log        | 5.0   | 255  | 0.3460          | 0.825    | 0.2657 |
 
 
 ### Framework versions
 
-- Transformers 4.34.1
+- Transformers 4.35.0
 - Pytorch 2.1.0+cu118
 - Datasets 2.14.6
 - Tokenizers 0.14.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d3ee9192fc10a8d59f4f9af4d2e9aac1ea44585b704f0c7ede2c2f7f4a00be1
+oid sha256:38ec1c34beb9f644d6e5ffc016fe5bc5a532ffe747d3dc666baddcabf0c19d9f
 size 267832560