End of training

README.md

@@ -17,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [MingZhong/DialogLED-base-16384](https://huggingface.co/MingZhong/DialogLED-base-16384) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4933
-- Rouge1: 0.5144
-- Rouge2: 0.2439
-- Rougel: 0.3564
+- Loss: 0.4092
+- Rouge1: 0.5362
+- Rouge2: 0.2624
+- Rougel: 0.3762
 
 ## Model description
 
@@ -54,8 +54,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|
-| 0.6232        | 1.0   | 800  | 0.5143          | 0.4971 | 0.2315 | 0.3431 |
-| 0.4781        | 2.0   | 1600 | 0.4933          | 0.5144 | 0.2439 | 0.3564 |
+| 0.4612        | 1.0   | 1600 | 0.4222          | 0.5319 | 0.2612 | 0.3737 |
+| 0.4007        | 2.0   | 3200 | 0.4092          | 0.5362 | 0.2624 | 0.3762 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c88c4e2f58dd13cb80ebe19b0129d310b38111af076b397090897da47f845f5
+oid sha256:15d4f40e820fef62d8c60597769f732fa7ebb70d823c5fbbac2f8bd954d1ea9e
 size 647614116

runs/Apr07_17-27-13_311cee5b2704/events.out.tfevents.1744046839.311cee5b2704.317.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4590c60d0a1fcbd055ec2f2fc8515a1d041d7d3aa122062ebb02623a4d5378e9
+size 8195

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dadc20e0c530a5ce5c804b7c9295b9f2faa8d855ce3bebb8b3360f1e421cf6b1
+oid sha256:7f180656affabeb755924763917ead0ae5e8407d1934a3ee208ead224bb17b6e
 size 5496