End of training

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-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8725
+- Loss: 1.3382
 - Eval/rewards/chosen: 0.0
 - Eval/logps/chosen: -192.8253
 - Eval/rewards/rejected: 0.0
@@ -58,7 +58,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |     |
 |:-------------:|:-----:|:----:|:---------------:|:---:|
-| 1.75          | 0.96  | 12   | 0.8725          | 0.0 |
+| 3.3125        | 0.96  | 12   | 1.3382          | 0.0 |
 
 
 ### Framework versions

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "o_proj",
     "k_proj",
-    "q_proj",
-    "v_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

metrics.jsonl

@@ -16,3 +16,5 @@
 {"epoch": 0.96, "precision": 0.41463414533016063, "recall": 0.9444444391975308, "fold": 0}
 {"epoch": -1, "precision": 0.41463414533016063, "recall": 0.9444444391975308, "fold": 0}
 {"epoch": 0.96, "precision": 0.41463414533016063, "recall": 0.9444444391975308, "fold": 0}
+{"epoch": -1, "precision": 0.41463414533016063, "recall": 0.9444444391975308, "fold": 0}
+{"epoch": 0.96, "precision": 0.41463414533016063, "recall": 0.9444444391975308, "fold": 0}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c81c5d11453aff6016cf9f6f9716e67fdf2d51e465ba0fc10adb45da931af854
+oid sha256:2167c112c737455967bddb86d7d85056a717aa8b523580a6ee38098b772da94d
 size 5688