roberta-base-mnli-edgarday-1

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0476
-- Accuracy: 0.79
+- Loss: 0.8785
+- Accuracy: 0.8256
 
 ## Model description
 
@@ -43,15 +43,13 @@ 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: 2
+- num_epochs: 1
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.4153        | 0.6250 | 3068 | 1.0476          | 0.79     |
-| 0.4453        | 1.2499 | 6136 | 0.7545          | 0.77     |
-| 0.3856        | 1.8749 | 9204 | 1.0115          | 0.77     |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.5004        | 1.0   | 4909 | 0.4480          | 0.8386   |
 
 
 ### Framework versions

runs/May18_12-13-02_e69b2b8c34fe/events.out.tfevents.1716039817.e69b2b8c34fe.1537.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ccb3f6cfeecc3bfa81c61048424bf2ca7f40e089d8abd6e4f1272355d93b361
+size 411

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70d01476ae1f96ce8dd57e5148e817a579957a1ba8111b0dd8f7e9499b953b54
+oid sha256:c9c177c11f6c242de6c365a95d975450d86c16b4860c7af96ac86f83cc67aa3f
 size 5176