Rsr2425/llama3181binstruct_translate_v1

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/rsr2425-hobbyist/huggingface/runs/u9299chu)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/rsr2425-hobbyist/huggingface/runs/w3dn9f6w)
 
 This model was trained with SFT.
 

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "up_proj",
-    "down_proj",
     "q_proj",
-    "gate_proj",
+    "up_proj",
     "v_proj",
-    "o_proj"
+    "o_proj",
+    "gate_proj",
+    "down_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 sha256:5b9f3dd52f0e44a1a380044268ae78cc55504e1414552daf83c20a56912b5185
+oid sha256:b90f69b80d709a21f693c3255b6085670ea4d00da7f8dd03c2811ea806452097
 size 167832240

runs/Dec13_12-43-38_56bc383d6003/events.out.tfevents.1734093842.56bc383d6003.669.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e456b6a4d1fc167f9534f379c2b041c5b77795553472b704d21a5249c8fe31ad
+size 9727

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e257ff409f292a223525578554d931da2b0f68c69eae0da485e57256d149ffa
+oid sha256:d308b56609f95ff7df98e2558747b4d19575f80ca7c987cb01b575af286f6d38
 size 5624