End of training

README.md

@@ -17,16 +17,16 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [GuysTrans/bart-base-re-attention-seq-512](https://huggingface.co/GuysTrans/bart-base-re-attention-seq-512) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0760
-- Rouge1: 37.4585
-- Rouge2: 29.97
-- Rougel: 36.1127
-- Rougelsum: 36.9974
-- Bleu-1: 12.8769
-- Bleu-2: 11.6091
-- Bleu-3: 10.9498
-- Bleu-4: 10.4896
-- Gen Len: 25.9243
+- Loss: 1.0593
+- Rouge1: 36.619
+- Rouge2: 28.9914
+- Rougel: 35.1444
+- Rougelsum: 36.1192
+- Bleu-1: 12.5425
+- Bleu-2: 11.1852
+- Bleu-3: 10.5404
+- Bleu-4: 10.1255
+- Gen Len: 25.9532
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Bleu-1  | Bleu-2  | Bleu-3  | Bleu-4  | Gen Len |
-|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|:-------:|:-------:|:-------:|:-------:|
-| 2.1536        | 1.0   | 18247 | 1.0760          | 37.4585 | 29.97  | 36.1127 | 36.9974   | 12.8769 | 11.6091 | 10.9498 | 10.4896 | 25.9243 |
+| Training Loss | Epoch | Step  | Validation Loss | Rouge1 | Rouge2  | Rougel  | Rougelsum | Bleu-1  | Bleu-2  | Bleu-3  | Bleu-4  | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|:-------:|:---------:|:-------:|:-------:|:-------:|:-------:|:-------:|
+| 2.1743        | 1.0   | 18247 | 1.0593          | 36.619 | 28.9914 | 35.1444 | 36.1192   | 12.5425 | 11.1852 | 10.5404 | 10.1255 | 25.9532 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6b23369326fa624ebe345d090be1a0003ce0cf12c935448da940d8f554cafa1
+oid sha256:9f1c8ab5b0aa886d0c26698505d65b6aca74c814f852ead4e867a523976d05af
 size 558018637