FNP-customer-finetuned

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7578
+- Loss: 1.9883
 
 ## Model description
 
@@ -41,15 +41,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 2.2127        | 1.0   | 3359  | 1.9824          |
-| 2.0042        | 2.0   | 6718  | 1.8105          |
-| 1.929         | 3.0   | 10077 | 1.7578          |
+| 2.4702        | 1.0   | 3359  | 2.2441          |
+| 2.2416        | 2.0   | 6718  | 2.0566          |
+| 2.156         | 3.0   | 10077 | 1.9883          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fda8f98d508e2fc4cb7d7de642e0a63b9bde4049353554fd7d646d2b81c23ac
+oid sha256:324f3d94bf76b138fef826fa78e78a77ad5aab19252fd69eee33bdae544c11d7
 size 591352

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:261e58341ff04a368170b55ee320ebfecc94c5caa2ac20a204acf7e09af9fd2c
+oid sha256:9d176883226e05d31b60229cf0439a621eeebdecae098f479b1e85203fc97b49
 size 4920