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 [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6517
+- Loss: 0.7021
 
 ## Model description
 
@@ -40,23 +40,27 @@ 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: 3
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.7773        | 0.5   | 500  | 0.7515          |
-| 0.755         | 1.0   | 1000 | 0.6408          |
-| 0.6406        | 1.5   | 1500 | 0.6199          |
-| 0.6047        | 2.0   | 2000 | 0.5906          |
-| 0.4643        | 2.5   | 2500 | 0.6549          |
-| 0.4451        | 3.0   | 3000 | 0.6517          |
+| 0.7933        | 0.5   | 500  | 0.7141          |
+| 0.7869        | 1.0   | 1000 | 0.7627          |
+| 0.7325        | 1.5   | 1500 | 0.6917          |
+| 0.7292        | 2.0   | 2000 | 0.6866          |
+| 0.6861        | 2.5   | 2500 | 0.7174          |
+| 0.68          | 3.0   | 3000 | 0.6940          |
+| 0.622         | 3.5   | 3500 | 0.6869          |
+| 0.6278        | 4.0   | 4000 | 0.7009          |
+| 0.5631        | 4.5   | 4500 | 0.7326          |
+| 0.5589        | 5.0   | 5000 | 0.7021          |
 
 
 ### Framework versions
 
-- Transformers 4.32.1
+- Transformers 4.33.1
 - Pytorch 2.0.1+cu118
-- Datasets 2.14.4
+- Datasets 2.14.5
 - Tokenizers 0.13.3

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f98996e041bd841d3a6bf62ab5aa003af78be0370b532c1990e62ce3c5e641c
+oid sha256:54d88c584eca9d1bb8046f3dc7ddfee6ae57a6eed17f1a5b1299bedd633dc8a2
 size 498660721