End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4638
-- Accuracy: 0.7928
+- Loss: 0.4454
+- Accuracy: 0.7877
 
 ## Model description
 
@@ -43,22 +43,19 @@ 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: 5
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 293  | 0.4997          | 0.7825   |
-| 0.5378        | 2.0   | 586  | 0.4638          | 0.7928   |
-| 0.5378        | 3.0   | 879  | 0.5529          | 0.7586   |
-| 0.2727        | 4.0   | 1172 | 0.6060          | 0.7654   |
-| 0.2727        | 5.0   | 1465 | 0.6386          | 0.7654   |
+| No log        | 1.0   | 293  | 0.4533          | 0.7825   |
+| 0.5374        | 2.0   | 586  | 0.4454          | 0.7877   |
 
 
 ### Framework versions
 
 - Transformers 4.38.1
 - Pytorch 2.1.2
-- Datasets 2.1.0
+- Datasets 2.18.0
 - Tokenizers 0.15.2

runs/Apr02_02-49-58_ef019a3ab26d/events.out.tfevents.1712026202.ef019a3ab26d.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:329c4990802ebabc9493de21178628c1fc88e1d66ed1f1eadc3f9f6d6b69fd67
-size 5532
+oid sha256:12a2bcc4281ae4554293e05046669c31b214c3fa754a2c1f40967e7cb2c87533
+size 5886

runs/Apr02_02-49-58_ef019a3ab26d/events.out.tfevents.1712026408.ef019a3ab26d.26.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b15359f4e8aca48be9f12625a2cab909e446cac6f3be93d3c3ead0670b44bfad
+size 411