Training in progress, step 3

README.md

@@ -38,7 +38,7 @@ This model was trained with SFT.
 - Transformers: 4.55.0.dev0
 - Pytorch: 2.6.0+cu124
 - Datasets: 4.0.0
-- Tokenizers: 0.21.2
+- Tokenizers: 0.21.4
 
 ## Citations
 

adapter_config.json

@@ -28,13 +28,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "k_proj",
     "o_proj",
-    "up_proj",
-    "gate_proj",
     "down_proj",
-    "q_proj"
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj"
   ],
   "task_type": null,
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2822d1ae11630a5edeb44c5af3c8daa3ba4eea09125db8c3b839625a73c12f21
+oid sha256:74376585f56197a862893adfe33e6514b132352526a4eb300d0206d304732c08
 size 12377496

runs/Aug01_16-42-48_6672a85c2e8b/events.out.tfevents.1754066594.6672a85c2e8b.687.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48a14af9c9283755931eeac75c36fb5c3533cbd2beb0759857a746804e3e22a
+size 10064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6262d095c752adf8ff4eca1bd78019ac6f7657cf82c4d82d8b402cde86d8978b
-size 5752
+oid sha256:4d6aa83980d6e3f9e5a45eaf4b3559d5f8a2fe2cc866625810d993367d3d5ac0
+size 5816