meta-llama/CodeLlama-7b-Instruct-hf-FaVe-rank128-1epochs-v2

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/CodeLlama-7b-Instruct-hf](https://huggingface.co/meta-llama/CodeLlama-7b-Instruct-hf) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4589
+- Loss: 0.5555
 
 ## Model description
 
@@ -52,9 +52,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| No log        | 0.2685 | 10   | 0.6778          |
-| 1.1318        | 0.5369 | 20   | 0.5420          |
-| 1.1318        | 0.8054 | 30   | 0.4589          |
+| No log        | 0.2685 | 10   | 0.8031          |
+| 1.168         | 0.5369 | 20   | 0.6423          |
+| 1.168         | 0.8054 | 30   | 0.5555          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64ef65e74692b22b05e40e24bb08e53656a60ca09c1b53178979d39375024c25
+oid sha256:cc940b557d60bc905d07ede209b05e7cc58fce81e2eeac66fc0865ae467be203
 size 134235176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b51fafd7724c897cd5eec680176cf0ca76689d4ff18c5df90973a6caecfe164a
+oid sha256:bae4b887bfff47e10a76b42e34bc6cb5679c2db0264e5abe9bb536cb50292bb6
 size 5112