Model save

README.md

@@ -3,6 +3,9 @@ license: apache-2.0
 base_model: google-bert/bert-base-cased
 tags:
 - generated_from_trainer
+metrics:
+- f1
+- recall
 model-index:
 - name: bert-base-cased_K1
   results: []
@@ -14,6 +17,15 @@ should probably proofread and complete it, then remove this comment. -->
 # bert-base-cased_K1
 
 This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3943
+- F1 Macro: 0.8991
+- F1: 0.9303
+- F1 Neg: 0.8680
+- Acc: 0.9087
+- Prec: 0.9312
+- Recall: 0.9294
+- Mcc: 0.7983
 
 ## Model description
 
@@ -42,6 +54,17 @@ The following hyperparameters were used during training:
 - num_epochs: 5
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1     | F1 Neg | Acc    | Prec   | Recall | Mcc    |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
+| No log        | 1.0   | 400  | 0.3086          | 0.8651   | 0.9118 | 0.8184 | 0.8812 | 0.8879 | 0.9370 | 0.7330 |
+| 0.4032        | 2.0   | 800  | 0.3764          | 0.8775   | 0.9204 | 0.8346 | 0.8925 | 0.8939 | 0.9485 | 0.7586 |
+| 0.2562        | 3.0   | 1200 | 0.3943          | 0.8991   | 0.9303 | 0.8680 | 0.9087 | 0.9312 | 0.9294 | 0.7983 |
+| 0.1387        | 4.0   | 1600 | 0.4797          | 0.8966   | 0.9261 | 0.8671 | 0.905  | 0.9444 | 0.9084 | 0.7945 |
+| 0.0698        | 5.0   | 2000 | 0.5151          | 0.8964   | 0.9303 | 0.8625 | 0.9075 | 0.9182 | 0.9427 | 0.7935 |
+
+
 ### Framework versions
 
 - Transformers 4.38.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67d11b011e636219ec7f9ae393b446dad94288fb8a6491e098cee030f0609959
+oid sha256:7a3e76c0b4986c5deab6ddfcf97066c740cb2993f9a25f28eeb927db22e74fa5
 size 433270768