Training in progress, epoch 1

README.md

@@ -36,8 +36,8 @@ This model was trained with SFT.
 
 - TRL: 0.22.2
 - Transformers: 5.0.0.dev0
-- Pytorch: 2.8.0+cu128
-- Datasets: 4.4.1
+- Pytorch: 2.9.1
+- Datasets: 4.3.0
 - Tokenizers: 0.22.1
 
 ## Citations

adapter_config.json

@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "down_proj",
-    "q_proj",
     "k_proj",
-    "o_proj",
     "v_proj",
-    "gate_proj"
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d62fa3a1883fd1609d89ad8bf99bac4107b016ce5ebbc7bd5995e5401269c60c
+oid sha256:55148ff2e5e901a1d4b441255a3f6381b36bd415a71a5ce13178d7c5d7066dda
 size 280108616

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbe84bc46ac56fc6ef681823cdb8e110e7520579c7aab1db1d9b054504cd53cc
-size 5649
+oid sha256:43d8d07fdedd45cc39c231e8d271217e7e030b2d3b9839c57851dfc264fbd658
+size 5585