t5_long_tglobal_base_samsum

README.md

@@ -19,10 +19,10 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: nan
-- Rouge1: 22.7436
-- Rouge2: 4.9383
-- Rougel: 19.0314
-- Rougelsum: 19.8871
+- Rouge1: 22.7827
+- Rouge2: 4.9292
+- Rougel: 19.0267
+- Rougelsum: 19.9561
 - Bleu: 0.0
 - Meteor: 0.1307
 - Gen Len: 17.4725
@@ -59,7 +59,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Bleu | Meteor | Gen Len |
 |:-------------:|:------:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:----:|:------:|:-------:|
-| 0.1925        | 0.9997 | 1841 | nan             | 22.7436 | 4.9383 | 19.0314 | 19.8871   | 0.0  | 0.1307 | 17.4725 |
+| 0.1925        | 0.9997 | 1841 | nan             | 22.7827 | 4.9292 | 19.0267 | 19.9561   | 0.0  | 0.1307 | 17.4725 |
 
 
 ### Framework versions

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c529f680dd1560ad4b1e1d2867932d6f8b477ae85ca2d05de432f771454d2037
+oid sha256:5202fd7bd5bc35fc99de5a8dc38c8f4be72da8d91990f4fb5be6e3f9e64e52da
 size 5176