Training complete

README.md

@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8402
-- Rouge1: 6.8778
-- Rouge2: 3.2689
-- Rougel: 6.1322
-- Rougelsum: 6.5067
+- Loss: 1.6429
+- Rouge1: 6.8486
+- Rouge2: 3.1822
+- Rougel: 6.0536
+- Rougelsum: 6.4854
 
 ## Model description
 
@@ -42,25 +42,27 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5.6e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
-| No log        | 1.0   | 500  | 1.9816          | 6.8051 | 3.19   | 6.0519 | 6.4262    |
-| 2.2143        | 2.0   | 1000 | 1.8705          | 6.8637 | 3.2288 | 6.1205 | 6.4957    |
-| 2.2143        | 3.0   | 1500 | 1.8402          | 6.8778 | 3.2689 | 6.1322 | 6.5067    |
+| 2.3078        | 1.0   | 1000 | 1.9298          | 6.7515 | 3.1533 | 5.9971 | 6.3848    |
+| 1.9556        | 2.0   | 2000 | 1.7880          | 6.8376 | 3.2002 | 6.0356 | 6.4897    |
+| 1.8076        | 3.0   | 3000 | 1.7108          | 6.9082 | 3.1048 | 6.0637 | 6.5127    |
+| 1.7145        | 4.0   | 4000 | 1.6575          | 6.8643 | 3.1987 | 6.0574 | 6.4882    |
+| 1.6575        | 5.0   | 5000 | 1.6429          | 6.8486 | 3.1822 | 6.0536 | 6.4854    |
 
 
 ### Framework versions
 
-- Transformers 4.38.1
-- Pytorch 2.1.2
+- Transformers 4.39.3
+- Pytorch 2.2.2+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

generation_config.json

@@ -8,5 +8,5 @@
   "no_repeat_ngram_size": 3,
   "num_beams": 4,
   "pad_token_id": 1,
-  "transformers_version": "4.38.1"
+  "transformers_version": "4.39.3"
 }