End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1789
+- Loss: 1.2218
 
 ## Model description
 
@@ -40,17 +40,15 @@ 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: 3
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss |
-|:-------------:|:-----:|:-----:|:---------------:|
-| 2.1933        | 1.0   | 2609  | 2.1936          |
-| 2.1933        | 2.0   | 5218  | 2.1849          |
-| 2.1897        | 3.0   | 7827  | 2.1843          |
-| 2.1856        | 4.0   | 10436 | 2.1814          |
-| 2.186         | 5.0   | 13045 | 2.1789          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.2691        | 1.0   | 2609 | nan             |
+| 1.2346        | 2.0   | 5218 | 1.2659          |
+| 1.2257        | 3.0   | 7827 | 1.2218          |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9538edbc1994bdc9321cc705e094b3c879347abd47ff2f28c3f9441ff3c0728
+oid sha256:844055a2c6b92a1c7ae02a294641428f031d64495b0295f6516c6d344c8845a1
 size 438126133

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1f0af517f20dc140992c633c1bb17bbc3fa4b590bb3f6f4b3be67193c59f3ff
+oid sha256:55d5410b0b8f626b0db1bd9c3b3b420667625366d7f61b609a2e61dd04de60d4
 size 4027