pknayak/bert-senti-imdb-pkn

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2329
-- Accuracy: 0.9311
+- Loss: 0.3734
+- Accuracy: 0.9307
 
 ## Model description
 
@@ -40,18 +40,19 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
 - train_batch_size: 16
-- eval_batch_size: 16
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.2252        | 1.0   | 1563 | 0.1997          | 0.9234   |
-| 0.1469        | 2.0   | 3126 | 0.2329          | 0.9311   |
+| 0.1144        | 1.0   | 1563 | 0.3189          | 0.9229   |
+| 0.0839        | 2.0   | 3126 | 0.3659          | 0.9272   |
+| 0.0487        | 3.0   | 4689 | 0.3734          | 0.9307   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22950c3912f320db5f1c0a1b9151bc6424e33881549ee114a2733ef220f1efcb
+oid sha256:c550424146eee1d13c194b242ef7a22eff482df528c7387630c4aaa639c4f19a
 size 267832560

runs/Oct04_07-28-57_0c2440a48122/events.out.tfevents.1728026939.0c2440a48122.505.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6faf053aeba4a726c323f6f121cea04d64681ed187cddfcd483b5b1152223ec2
+size 8187

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2770950edace36f3993fcaf23ce6f749ee3cc911b099b95cdbdf2955e441b074
+oid sha256:41c0c122ca493c6607ba119b8d2c052d717613b3a0241416c0ec7e6af244e79a
 size 5176