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: 0.6650
+- Loss: 1.1600
 - Eval/rewards/chosen: 0.0
 - Eval/logps/chosen: -207.5800
 - Eval/rewards/rejected: 0.0
@@ -58,7 +58,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |     |
 |:-------------:|:------:|:----:|:---------------:|:---:|
-| 0.5625        | 0.9412 | 12   | 0.6650          | 0.0 |
+| 0.75          | 0.9412 | 12   | 1.1600          | 0.0 |
 
 
 ### Framework versions

adapter_config.json

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

metrics.jsonl

@@ -26,3 +26,5 @@
 {"epoch": 0.96, "precision": 0.3529411757785467, "recall": 0.9999999944444444, "fold": 0}
 {"epoch": -1, "precision": 0.43636363557024793, "recall": 0.9999999958333333, "fold": 0}
 {"epoch": 0.9411764705882353, "precision": 0.43636363557024793, "recall": 0.9999999958333333, "fold": 0}
+{"epoch": -1, "precision": 0.43636363557024793, "recall": 0.9999999958333333, "fold": 0}
+{"epoch": 0.9411764705882353, "precision": 0.43636363557024793, "recall": 0.9999999958333333, "fold": 0}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ef59f66b46aa180e65b59aea0ba605eec938712310a42f72477059af648014
+oid sha256:5edf66151cf20f1ef656b4340fadbe74f33ad62519667acb1c6011cfd7e7c165
 size 5688