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: 0.4511
+- Loss: 0.6864
 - Accuracy: 0.9178
-- F1: 0.9455
+- F1: 0.9453
 
 ## Model description
 
@@ -45,16 +45,18 @@ 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
-- num_epochs: 4
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| No log        | 1.0   | 254  | 0.3751          | 0.9133   | 0.9434 |
-| 0.0979        | 2.0   | 508  | 0.4147          | 0.9      | 0.9327 |
-| 0.0979        | 3.0   | 762  | 0.4443          | 0.9089   | 0.9393 |
-| 0.0387        | 4.0   | 1016 | 0.4511          | 0.9178   | 0.9455 |
+| No log        | 1.0   | 254  | 0.5507          | 0.9178   | 0.9463 |
+| 0.0173        | 2.0   | 508  | 0.7152          | 0.8978   | 0.9313 |
+| 0.0173        | 3.0   | 762  | 0.7228          | 0.9111   | 0.9420 |
+| 0.0117        | 4.0   | 1016 | 0.7015          | 0.9044   | 0.9361 |
+| 0.0117        | 5.0   | 1270 | 0.6796          | 0.9111   | 0.9417 |
+| 0.0075        | 6.0   | 1524 | 0.6864          | 0.9178   | 0.9453 |
 
 
 ### Framework versions

runs/Jun14_01-15-57_88b985c19838/events.out.tfevents.1718328616.88b985c19838.1237.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f215047f69cb0100f4c617c5ea4957f36d1af0e12152cf33599093e59ba0a83e
+size 457