Training complete

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4633
+- Loss: 0.4982
 
 ## Model description
 
@@ -49,9 +49,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 0.98  | 33   | 1.3427          |
-| No log        | 1.99  | 67   | 0.8117          |
-| No log        | 2.93  | 99   | 0.4633          |
+| No log        | 0.98  | 33   | 1.3304          |
+| No log        | 1.99  | 67   | 0.8024          |
+| No log        | 2.93  | 99   | 0.4982          |
 
 
 ### Framework versions

adapter_config.json

@@ -16,7 +16,7 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3085ac1ccb1350b8b999b6524b393d922a754946909edc5880ae33faea1d8636
-size 67155338
+oid sha256:991bfd1bde6d471de0ef46599f34adffb717f8b8c5ca74039d3072fdb3332e23
+size 33600906

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97318d143e2e2b9e11b1351b7aba5b9f29ffcbe3a5b2771283a5c1aef5f72138
+oid sha256:a0afa51a00ec4f8cbf00766daf052b63380e78aea143a0133112687bc46ac057
 size 4536