llama3_8b_bwgenerator_instruct

README.md

@@ -17,6 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 # Meta-Llama-3-8B-Instruct-Generator
 
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1433
 
 ## Model description
 
@@ -43,10 +45,21 @@ 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: 10
+- num_epochs: 3
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.426         | 0.3287 | 20   | 0.4661          |
+| 0.3689        | 0.6574 | 40   | 0.3151          |
+| 0.2887        | 0.9861 | 60   | 0.2654          |
+| 0.2441        | 1.3148 | 80   | 0.2161          |
+| 0.1863        | 1.6436 | 100  | 0.1709          |
+| 0.1656        | 1.9723 | 120  | 0.1576          |
+| 0.1538        | 2.3010 | 140  | 0.1491          |
+| 0.1475        | 2.6297 | 160  | 0.1444          |
+| 0.1449        | 2.9584 | 180  | 0.1433          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ead1ac15b27d9c2ed1883f6f6a0efd11e6dc0b650d651faf69acef728d8e759
+oid sha256:3b90ef7c8b961a355f7e52c0971c8c0da360dbf290b1a047c56ec8763f9df2f9
 size 6832728

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:372a74e431eba2caa63215b76dd4f966c636a53716ca8e2b75c492f3cef0d7f8
+oid sha256:34d0b7ada03344befe42d1fd7554d24139bbd48a53a4c05f04bb2047367d065f
 size 5496