ahmed792002/Finetuning_XLNET_Paraphrase_Classification

README.md

@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3980
-- Accuracy: 0.8603
-- F1: 0.8601
+- Loss: 0.5316
+- Accuracy: 0.7794
+- F1: 0.7422
 
 ## Model description
 
@@ -52,8 +52,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| No log        | 1.0   | 459  | 0.3751          | 0.8260   | 0.8148 |
-| 0.5039        | 2.0   | 918  | 0.3980          | 0.8603   | 0.8601 |
+| 0.647         | 1.0   | 619  | 0.4576          | 0.7696   | 0.7447 |
+| 0.4575        | 2.0   | 1238 | 0.5316          | 0.7794   | 0.7422 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4423c18518bdb55aaab678f2214590ae1d066e20a831a32b4f55f757fdbc004a
+oid sha256:6d6f49d4e21ab8f16941a4f47d2997f57e85a36ef266fff44a8fdb673a30ffa3
 size 469264592

runs/Dec04_21-09-33_f9e6f9f039cb/events.out.tfevents.1733346965.f9e6f9f039cb.734.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f268d7b1ec52a99c8b99b7d3d9c2dadca43f3947c3bd19246575239ae9221d0
+size 457

runs/Dec04_21-23-57_f9e6f9f039cb/events.out.tfevents.1733347438.f9e6f9f039cb.734.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d97ebb5fcf1ed58a4de2ca732e6f8b1b46d2c4ceefeb039b99f2f1d39d66575
+size 6899

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fb10d28a419ac48e93d5aa604f7a158e30c299d20c1b5b5de55e55a14345318
+oid sha256:098d6b4ffbe20edfa8f9ffccc0ea43c54088929fbae90191e3c8d67473472f53
 size 5368