gianghoang/result

README.md

@@ -3,6 +3,8 @@ license: bsd-3-clause
 base_model: LA1512/Led-pubmed-20K-4096-epoch2
 tags:
 - generated_from_trainer
+metrics:
+- rouge
 model-index:
 - name: results
   results: []
@@ -14,6 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
 # results
 
 This model is a fine-tuned version of [LA1512/Led-pubmed-20K-4096-epoch2](https://huggingface.co/LA1512/Led-pubmed-20K-4096-epoch2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.3315
+- Rouge1: 43.8629
+- Rouge2: 14.6606
+- Rougel: 21.757
+- Rougelsum: 38.2488
+- Gen Len: 304.884
 
 ## Model description
 
@@ -32,7 +41,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 1e-05
 - train_batch_size: 2
 - eval_batch_size: 1
 - seed: 42
@@ -42,6 +51,10 @@ The following hyperparameters were used during training:
 - num_epochs: 1
 - label_smoothing_factor: 0.1
 
+### Training results
+
+
+
 ### Framework versions
 
 - Transformers 4.41.1

generation_config.json

@@ -1,12 +1,11 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 0,
   "decoder_start_token_id": 2,
   "early_stopping": true,
   "eos_token_id": 2,
-  "length_penalty": 0.8,
-  "max_length": 1024,
-  "min_length": 8,
+  "length_penalty": 2.0,
+  "max_length": 512,
+  "min_length": 100,
   "no_repeat_ngram_size": 3,
   "num_beams": 4,
   "pad_token_id": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16e3d94c2a1c532273c09d2b0868ddb858c6b869ca8a5613646b3770f9dfe760
+oid sha256:70dfec49d9e24c32a82e99f8b50d6e7921f53cc8c0c296ae4260f41049bd93f4
 size 5240