End of training

README.md

@@ -3,6 +3,8 @@ license: mit
 base_model: facebook/bart-large-cnn
 tags:
 - generated_from_trainer
+metrics:
+- rouge
 model-index:
 - name: bart-large-cnn-spotify-podcasts
   results: []
@@ -14,6 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
 # bart-large-cnn-spotify-podcasts
 
 This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3282
+- Rouge1: 0.5073
+- Rouge2: 0.3354
+- Rougel: 0.4104
+- Rougelsum: 0.4098
+- Gen Len: 82.5021
 
 ## Model description
 
@@ -33,19 +42,22 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 4
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 117  | 1.1526          | 0.4777 | 0.3071 | 0.3726 | 0.3741    | 97.4893 |
+| No log        | 1.0   | 233  | 1.2600          | 0.4886 | 0.3178 | 0.3942 | 0.3939    | 90.6652 |
+| No log        | 2.0   | 466  | 1.2273          | 0.4993 | 0.326  | 0.4012 | 0.4015    | 92.4077 |
+| 1.0674        | 3.0   | 699  | 1.2512          | 0.5104 | 0.3406 | 0.4149 | 0.4148    | 84.0215 |
+| 1.0674        | 4.0   | 932  | 1.3282          | 0.5073 | 0.3354 | 0.4104 | 0.4098    | 82.5021 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfca8dacd50ad4be9b92a5a2da6805029e47fc624ca054805c2be38451b7beb4
+oid sha256:6f657767e44f366ed1e76c89f47040f2949d4127dbfc1ad4fa05952d230e33c9
 size 1625422896

runs/Nov18_15-12-34_b5e0e1ae0024/events.out.tfevents.1700320362.b5e0e1ae0024.48.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4805d3a671275dc18cd6c96929dedc69dbcfdbd7765f72aa05d42ed98674fc76
-size 6607
+oid sha256:8d2f14bb70775bd7ddc3e7843354e46827965d1109d1aa2ec616b25bb0483848
+size 8011