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: 4.4075
+- Loss: 4.1890
 
 ## Model description
 
@@ -44,14 +44,15 @@ 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: 1
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.7737        | 1.0   | 4610 | 4.4075          |
+| 4.5962        | 1.0   | 4610 | 4.2708          |
+| 4.4177        | 2.0   | 9220 | 4.1890          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c568a3617ea59040807d534a794035d7537cd8145cf1b1a0498e8763e40eacb3
+oid sha256:4a3751ff9c828e01dcc28a5b6f82762fbe26cbd554130879a8ac82e3061c1071
 size 53857264

runs/Nov13_19-36-42_c5a761551a44/events.out.tfevents.1699904203.c5a761551a44.1783.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe691fbb7046a060c1cc78c3507c8660d56d3266fb786e7ec2f3acf448a68dad
+size 5810

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99aeb98b24ad4198f035fa440b28311c5eccaeda7dc7b896de07265cebf9dc87
+oid sha256:11ee59ebfb122a9afd8d1498e72c99e95d06872aaf151596706388d435719965
 size 4600