retnet-summarization-small

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [kaizerBox/retnet-summarization_small](https://huggingface.co/kaizerBox/retnet-summarization_small) on the xsum dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.8029
+- Loss: 4.4075
 
 ## Model description
 
@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0006
+- learning_rate: 0.006
 - train_batch_size: 10
 - eval_batch_size: 10
 - seed: 42
@@ -44,15 +44,14 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 10
-- num_epochs: 2
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.1425        | 1.0   | 4610 | 4.8581          |
-| 4.9561        | 2.0   | 9220 | 4.8029          |
+| 4.7737        | 1.0   | 4610 | 4.4075          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f55c789d7d551778764f51a1a6d28020dd1e3963c48a44304561a21d55b5fc6
+oid sha256:c568a3617ea59040807d534a794035d7537cd8145cf1b1a0498e8763e40eacb3
 size 53857264

runs/Nov13_15-11-38_4cfd88eaf698/events.out.tfevents.1699888298.4cfd88eaf698.968.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad1959110fdebbdf984a9a35e63d45dd4db9cddbc77ae918626eacd223aa3c19
+size 5382

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90af1830ea759ee67ea81e2d31abd11854174c66ef2b9be8c8e99971f6ca87fd
+oid sha256:99aeb98b24ad4198f035fa440b28311c5eccaeda7dc7b896de07265cebf9dc87
 size 4600