End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: mit
-base_model: prajjwal1/bert-tiny
+base_model: prajjwal1/bert-medium
 tags:
 - generated_from_trainer
 metrics:
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # my_awesome_swag_model
 
-This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on an unknown dataset.
+This model is a fine-tuned version of [prajjwal1/bert-medium](https://huggingface.co/prajjwal1/bert-medium) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3434
-- Accuracy: 0.45
+- Loss: 1.2680
+- Accuracy: 0.46
 
 ## Model description
 
@@ -44,15 +44,18 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 3    | 1.3474          | 0.4      |
-| No log        | 2.0   | 6    | 1.3444          | 0.45     |
-| No log        | 3.0   | 9    | 1.3434          | 0.45     |
+| No log        | 1.0   | 7    | 1.3530          | 0.42     |
+| No log        | 2.0   | 14   | 1.3340          | 0.42     |
+| No log        | 3.0   | 21   | 1.3074          | 0.42     |
+| No log        | 4.0   | 28   | 1.2832          | 0.42     |
+| No log        | 5.0   | 35   | 1.2727          | 0.46     |
+| No log        | 6.0   | 42   | 1.2680          | 0.46     |
 
 
 ### Framework versions

runs/Jan07_18-25-23_97a669587ffa/events.out.tfevents.1736274324.97a669587ffa.120229.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a69b2bc5088b254f9a7a31746dab13c5466717d21f9676cd89497ce0c1915c74
-size 6568
+oid sha256:254623dd626f9e8c60dac55ddf8e4cd4509b47b388c52fea88095803bdd67a9c
+size 7233