training to 8 epochs

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Rouge1
       type: rouge
-      value: 30.8728
+      value: 31.2683
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,12 +33,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the xsum dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.3024
-- Rouge1: 30.8728
-- Rouge2: 9.5192
-- Rougel: 24.4482
-- Rougelsum: 24.4482
-- Gen Len: 19.7209
+- Loss: 2.2682
+- Rouge1: 31.2683
+- Rouge2: 9.8466
+- Rougel: 24.8322
+- Rougelsum: 24.8376
+- Gen Len: 19.7033
 
 ## Model description
 
@@ -63,17 +63,19 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 8
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Gen Len | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum |
-|:-------------:|:-----:|:-----:|:-------:|:---------------:|:-------:|:------:|:-------:|:---------:|
-| 2.6596        | 1.0   | 12753 | 19.6937 | 2.4320          | 29.2361 | 8.3218 | 22.9893 | 22.9993   |
-| 2.5914        | 2.0   | 25506 | 19.7058 | 2.3844          | 29.8093 | 8.7641 | 23.5074 | 23.5169   |
-| 2.5171        | 4.0   | 51012 | 19.6821 | 2.3208          | 30.6455 | 9.3612 | 24.2744 | 24.2798   |
-| 2.4945        | 5.0   | 63765 | 2.3024  | 30.8728         | 9.5192  | 24.4482| 24.4482 | 19.7209   |
+| Training Loss | Epoch | Step   | Gen Len | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum |
+|:-------------:|:-----:|:------:|:-------:|:---------------:|:-------:|:------:|:-------:|:---------:|
+| 2.6596        | 1.0   | 12753  | 19.6937 | 2.4320          | 29.2361 | 8.3218 | 22.9893 | 22.9993   |
+| 2.5914        | 2.0   | 25506  | 19.7058 | 2.3844          | 29.8093 | 8.7641 | 23.5074 | 23.5169   |
+| 2.5171        | 4.0   | 51012  | 19.6821 | 2.3208          | 30.6455 | 9.3612 | 24.2744 | 24.2798   |
+| 2.4813        | 6.0   | 76518  | 19.6813 | 2.2865          | 31.1312 | 9.7512 | 24.6686 | 24.6688   |
+| 2.4517        | 7.0   | 89271  | 2.2757  | 31.1544         | 9.7509  | 24.6982| 24.7016 | 19.7118   |
+| 2.451         | 8.0   | 102024 | 2.2682  | 31.2683         | 9.8466  | 24.8322| 24.8376 | 19.7033   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53f4842c50f09ea454bc083c09fddc1824206a01ccf29f2b2c8ecbb39d9d42b2
+oid sha256:80db64a8b4e04fa154d19abd8005587c42e1a2b05a92cab4b447ec77d807f7d0
 size 242041896

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cd3b9c0d4bc3d9ecfa1ecef87cfc2c28e6da056fa2a1d6f424690a2a6f0e889
+oid sha256:0b1f8c1eb2957c85221b7597bf21a7e0cb2089840d38c88f6ab88339bf0cd17d
 size 5496