End of training

README.md

@@ -5,19 +5,19 @@ tags:
 metrics:
 - sacrebleu
 model-index:
-- name: Bart-tay-DeleteOriginal
+- name: Bart-tay-Delete
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Bart-tay-DeleteOriginal
+# Bart-tay-Delete
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6881
-- Sacrebleu: 17.7618
+- Loss: 2.9636
+- Sacrebleu: 14.9513
 
 ## Model description
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Sacrebleu |
 |:-------------:|:-----:|:-----:|:---------------:|:---------:|
-| 2.2353        | 1.0   | 5485  | 3.2594          | 8.5703    |
-| 1.3149        | 2.0   | 10970 | 2.8236          | 14.3167   |
-| 1.0654        | 3.0   | 16455 | 2.6881          | 17.7618   |
+| 2.2094        | 1.0   | 4200  | 3.4670          | 7.0794    |
+| 1.3898        | 2.0   | 8400  | 3.0886          | 12.4236   |
+| 1.1036        | 3.0   | 12600 | 2.9636          | 14.9513   |
 
 
 ### Framework versions