llama3.1_8b_bwgenerator

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1186
+- Loss: 0.0982
 
 ## Model description
 
@@ -45,17 +45,17 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 256
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.7241        | 0.1680 | 40   | 0.2744          |
-| 0.2351        | 0.3359 | 80   | 0.2017          |
-| 0.1739        | 0.5039 | 120  | 0.1441          |
-| 0.1311        | 0.6718 | 160  | 0.1237          |
-| 0.1209        | 0.8398 | 200  | 0.1186          |
+| 0.4736        | 0.3359 | 80   | 0.1857          |
+| 0.1364        | 0.6718 | 160  | 0.1175          |
+| 0.1112        | 1.0077 | 240  | 0.1056          |
+| 0.1035        | 1.3437 | 320  | 0.1011          |
+| 0.1001        | 1.6796 | 400  | 0.0982          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e0380df0d905857a3171aeda366c6a4c4f1503ce0d4bdc2edfd80a93827689b
+oid sha256:48d2e3e49eba8612ae0d800bd27a740d7d6e479b6815071838cc1d94dcad8487
 size 6832728

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a710a6747144cf8d1ed16b3ec2ea09cf75c98242fdae29be6ac20248f7d4dc3
+oid sha256:b5c68a617d412f3050bd98c1fa7b19e30f7902d585e86168f56709a21257a913
 size 5496