Pubmed_Summarizer_Model_Mark2

README.md

@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bart_pubmed_dataset
 
-This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
+This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9463
+- Loss: 2.0911
 
 ## Model description
 
@@ -43,14 +43,14 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
+- lr_scheduler_warmup_steps: 400
 - num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.0882        | 0.7412 | 500  | 1.9463          |
+| 2.2528        | 0.6572 | 400  | 2.0911          |
 
 
 ### Framework versions

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 300,
+    "max_length": 1024,
     "strategy": "LongestFirst",
     "stride": 0
   },