bert-base-uncased-goemotions

README.md

@@ -16,7 +16,7 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0841
+- Loss: 0.1078
 
 ## Model description
 
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 6
+- num_epochs: 11
 
 ### Training results
 
@@ -54,6 +54,11 @@ The following hyperparameters were used during training:
 | 0.0629        | 4.0   | 21708 | 0.0863          |
 | 0.0604        | 5.0   | 27135 | 0.0893          |
 | 0.0543        | 6.0   | 32562 | 0.0919          |
+| 0.054         | 7.0   | 37989 | 0.0955          |
+| 0.0443        | 8.0   | 43416 | 0.0979          |
+| 0.0463        | 9.0   | 48843 | 0.1017          |
+| 0.0394        | 10.0  | 54270 | 0.1060          |
+| 0.035         | 11.0  | 59697 | 0.1078          |
 
 
 ### Framework versions

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a114dfc614e32e7758e22c4780d16fdbb16f9dfe0cc78c2739b4b0bdfedebf43
+oid sha256:e700ac031575826a8f66b9336c18fe77c40183ae97444ce07ac67e868cda3871
 size 5176