Training done for longformer-pubmed-20k

README.md

@@ -1,4 +1,5 @@
 ---
+library_name: transformers
 license: apache-2.0
 base_model: hyesunyun/update-summarization-bart-large-longformer
 tags:
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [hyesunyun/update-summarization-bart-large-longformer](https://huggingface.co/hyesunyun/update-summarization-bart-large-longformer) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9952
+- Loss: 0.9906
 
 ## Model description
 
@@ -47,14 +48,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.0912        | 0.75  | 500  | 0.9952          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.0835        | 0.7477 | 500  | 0.9906          |
 
 
 ### Framework versions
 
-- Transformers 4.38.2
-- Pytorch 2.2.1+cu121
-- Datasets 2.19.0
-- Tokenizers 0.15.2
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.19.1

generation_config.json

@@ -10,6 +10,6 @@
   "no_repeat_ngram_size": 3,
   "num_beams": 4,
   "pad_token_id": 1,
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.44.2",
   "use_cache": false
 }