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: 0.6324
+- Loss: 1.0294
 - Eval/rewards/chosen: 0.0
 - Eval/logps/chosen: -203.5358
 - Eval/rewards/rejected: 0.0
@@ -58,7 +58,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |     |
 |:-------------:|:-----:|:----:|:---------------:|:---:|
-| 0.5625        | 0.96  | 12   | 0.6324          | 0.0 |
+| 0.75          | 0.96  | 12   | 1.0294          | 0.0 |
 
 
 ### Framework versions

adapter_config.json

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

metrics.jsonl

@@ -20,3 +20,5 @@
 {"epoch": 0.96, "precision": 0.41463414533016063, "recall": 0.9444444391975308, "fold": 0}
 {"epoch": -1, "precision": 0.3529411757785467, "recall": 0.9999999944444444, "fold": 0}
 {"epoch": 0.96, "precision": 0.3529411757785467, "recall": 0.9999999944444444, "fold": 0}
+{"epoch": -1, "precision": 0.3529411757785467, "recall": 0.9999999944444444, "fold": 0}
+{"epoch": 0.96, "precision": 0.3529411757785467, "recall": 0.9999999944444444, "fold": 0}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4faa8cc33f1a3342c3fecb3a69ccbadca0ad4e833bf943ad7f9c37ef6ed154a2
+oid sha256:1d7b992abb7ac167361c422b7b0e828432551adb8033b9751a78eeb243430566
 size 5688