Model save

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/Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0178
+- Loss: 0.6089
 
 ## Model description
 
@@ -53,7 +53,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.9809        | 1.0   | 20   | 1.0178          |
+| 0.6126        | 1.0   | 200  | 0.6089          |
 
 
 ### Framework versions

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "v_proj",
     "o_proj",
     "q_proj",
-    "k_proj",
     "down_proj",
     "up_proj",
-    "gate_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3af779e366c638a194f86a7c739fa2410c3b76dd8c4205710484d9f4b88d3599
+oid sha256:ac66d622181fcbc5e33f12553515eeaf7cd109b0e3ffcf59bc482977c1c0aac3
 size 414337624

runs/Jan04_19-46-04_gpu-server/events.out.tfevents.1736020144.gpu-server.2012116.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8181d3b2c899e88ed75207cc2c2ef82aa177cbf51d3a9ba69636ed69bd537e5
-size 13982
+oid sha256:ed95fbc0b684887f501e48372a7cec9e604ef9505926f7bd600c97fed2c32071
+size 14607