End of training

README.md

@@ -1,5 +1,6 @@
 ---
 license: apache-2.0
+base_model: facebook/bart-base
 tags:
 - generated_from_trainer
 metrics:
@@ -14,14 +15,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bart-base-re-attention
 
-This model is a fine-tuned version of [GuysTrans/bart-base-re-attention](https://huggingface.co/GuysTrans/bart-base-re-attention) on the None dataset.
+This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 11.4724
-- Rouge1: 1.019
-- Rouge2: 0.0062
-- Rougel: 0.941
-- Rougelsum: 0.9643
-- Gen Len: 17.9243
+- Loss: 8.1082
+- Rouge1: 2.1312
+- Rouge2: 0.011
+- Rougel: 1.9443
+- Rougelsum: 2.0964
+- Gen Len: 20.0
 
 ## Model description
 
@@ -52,12 +53,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 6.6115        | 1.0   | 22880 | 11.4724         | 1.019  | 0.0062 | 0.941  | 0.9643    | 17.9243 |
+| 6.6515        | 1.0   | 22880 | 8.1082          | 2.1312 | 0.011  | 1.9443 | 2.0964    | 20.0    |
 
 
 ### Framework versions
 
-- Transformers 4.30.2
+- Transformers 4.33.0
 - Pytorch 2.0.0
 - Datasets 2.1.0
 - Tokenizers 0.13.3

generation_config.json

@@ -8,5 +8,5 @@
   "no_repeat_ngram_size": 3,
   "num_beams": 4,
   "pad_token_id": 1,
-  "transformers_version": "4.30.2"
+  "transformers_version": "4.33.0"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:889b32a87b3ef7e514423a3295b65b13e81077d0a58f4c9d958be75149d54019
+oid sha256:a9c674687d1a4cb9ad86a9e151828b33e7e981d4c8cc090db6576de3b465fabe
 size 558025109