retnet-summarization

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](https://huggingface.co/kaizerBox/retnet-summarization) on the xsum dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.2278
+- Loss: 3.1397
 
 ## Model description
 
@@ -44,15 +44,16 @@ 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: 100
-- num_epochs: 2
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 3.5745        | 1.0   | 11525 | 3.3519          |
-| 3.2943        | 2.0   | 23050 | 3.2278          |
+| 3.4307        | 1.0   | 11525 | 3.3046          |
+| 3.2601        | 2.0   | 23050 | 3.1760          |
+| 3.1144        | 3.0   | 34575 | 3.1397          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcf0d709b16e07b15db027202b870e08f7d3ae077557bf74cc06b0d7ad3bf14f
+oid sha256:4ca64a5dd73ecfdcc1d6ed179c21761bda7a41175f873b307cbb3604316a7341
 size 282181632

runs/Nov19_17-25-25_2221c7381199/events.out.tfevents.1700414725.2221c7381199.228.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eb357f38cc9c7fa3b409d821128f7a56eeb20328b01fd6e4851792af18832e0
+size 6233

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a96b8d61b7662077d1506e6bf1b4972a9c3cc5082f1a698e147e19a9a879099
+oid sha256:6b7b1dd5b39bf8c7b9e7739b6db836a730db0d1f0c08d3c1824e20acbfbd4c59
 size 4600