End of training

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9372
-- Accuracy: 0.9133
-- F1: 0.9419
+- Loss: 4.9271
+- Accuracy: 0.8422
+- F1: 0.8954
 
 ## Model description
 
@@ -45,14 +45,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
 - num_epochs: 4
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     |
-|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
-| 0.006         | 1.9685 | 500  | 0.9543          | 0.9133   | 0.9434 |
-| 0.0019        | 3.9370 | 1000 | 0.9404          | 0.9133   | 0.9419 |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 1.0   | 254  | 3.5614          | 0.8578   | 0.9088 |
+| 0.0047        | 2.0   | 508  | 4.3430          | 0.8533   | 0.9052 |
+| 0.0047        | 3.0   | 762  | 3.9929          | 0.8489   | 0.9006 |
+| 0.0126        | 4.0   | 1016 | 4.9271          | 0.8422   | 0.8954 |
 
 
 ### Framework versions

runs/Jun14_02-43-58_88b985c19838/events.out.tfevents.1718333619.88b985c19838.1237.39

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c2001bdda05d7192ca90cc3c9c4dee94672174f323df61b4de1e08abbad551f
+size 457