Model save

README.md

@@ -3,6 +3,8 @@ license: mit
 base_model: prajjwal1/bert-small
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: assignment3_model
   results: []
@@ -14,7 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/shmagi/huggingface/runs/ckwt5rwx)
 # assignment3_model
 
-This model is a fine-tuned version of [prajjwal1/bert-small](https://huggingface.co/prajjwal1/bert-small) on an unknown dataset.
+This model is a fine-tuned version of [prajjwal1/bert-small](https://huggingface.co/prajjwal1/bert-small) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3145
+- Accuracy: 0.9112
 
 ## Model description
 
@@ -41,6 +46,14 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 2
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.2632        | 1.0   | 4598 | 0.3168          | 0.9104   |
+| 0.2633        | 2.0   | 9196 | 0.3145          | 0.9112   |
+
+
 ### Framework versions
 
 - Transformers 4.41.0.dev0