training complete

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/pegasus-xsum](https://huggingface.co/google/pegasus-xsum) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3242
+- Loss: 0.3188
 
 ## Model description
 
@@ -40,40 +40,19 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 4
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 11.5719       | 0.14  | 20   | 11.5332         |
-| 11.293        | 0.28  | 40   | 11.3416         |
-| 11.2274       | 0.42  | 60   | 11.0547         |
-| 10.6443       | 0.56  | 80   | 10.7222         |
-| 10.3589       | 0.69  | 100  | 10.4015         |
-| 10.3677       | 0.83  | 120  | 10.1421         |
-| 9.7912        | 0.97  | 140  | 9.9393          |
-| 10.04         | 1.11  | 160  | 9.7417          |
-| 9.4389        | 1.25  | 180  | 9.5561          |
-| 9.6224        | 1.39  | 200  | 9.3565          |
-| 9.2704        | 1.53  | 220  | 9.1214          |
-| 9.1185        | 1.67  | 240  | 8.8230          |
-| 8.9214        | 1.81  | 260  | 8.3412          |
-| 8.4341        | 1.94  | 280  | 7.6364          |
-| 7.3594        | 2.08  | 300  | 6.5617          |
-| 6.4947        | 2.22  | 320  | 4.7474          |
-| 5.054         | 2.36  | 340  | 2.9092          |
-| 3.3489        | 2.5   | 360  | 1.3402          |
-| 1.9233        | 2.64  | 380  | 0.7131          |
-| 0.9449        | 2.78  | 400  | 0.5563          |
-| 0.617         | 2.92  | 420  | 0.4779          |
-| 0.4712        | 3.06  | 440  | 0.4228          |
-| 0.4508        | 3.19  | 460  | 0.3853          |
-| 0.3308        | 3.33  | 480  | 0.3581          |
-| 0.2735        | 3.47  | 500  | 0.3422          |
-| 0.2793        | 3.61  | 520  | 0.3343          |
-| 0.3184        | 3.75  | 540  | 0.3276          |
-| 0.2984        | 3.89  | 560  | 0.3242          |
+| 0.2463        | 0.14  | 20   | 0.3228          |
+| 0.2748        | 0.28  | 40   | 0.3226          |
+| 0.2167        | 0.42  | 60   | 0.3221          |
+| 0.3046        | 0.56  | 80   | 0.3212          |
+| 0.3236        | 0.69  | 100  | 0.3205          |
+| 0.2835        | 0.83  | 120  | 0.3192          |
+| 0.3414        | 0.97  | 140  | 0.3188          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5336f1144163f750db0913779f214b883ad6ab1f694ae0c9ba762e6359f3d7ac
+oid sha256:95e35ea54fad7fd37966554dc6528ac1ef41447d80c2b35b857c1457f146825e
 size 2279458540

runs/Nov17_14-24-12_b42b518d0be6/events.out.tfevents.1700231054.b42b518d0be6.231.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69a51f82f8881380839f0e36fccfcc626be8d43d7936875b07c3d55660a5fdb3
+size 9446

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24d73293c6466b814972117580e8b9f246729a143bb99487a64d01570989e30e
+oid sha256:0169128328b970aee51880c086e9c9c096c3011b0e25b177b2a184113f945409
 size 4600