Training in progress, epoch 1

README.md

@@ -37,7 +37,7 @@ This model was trained with SFT.
 - TRL: 0.23.0
 - Transformers: 4.56.1
 - Pytorch: 2.8.0+cu126
-- Datasets: 4.1.0
+- Datasets: 4.1.1
 - Tokenizers: 0.22.0
 
 ## Citations

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "q_proj",
+    "down_proj",
     "gate_proj",
     "v_proj",
-    "q_proj",
-    "o_proj",
+    "k_proj",
     "up_proj",
-    "down_proj"
+    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:238270c303da1aee20496b1b06c531f6ebbbec12582f02a02c5e95c1b9ea9521
+oid sha256:fbbd66503b7a3a062c28ab734d3e20c0e199e1225f758312ef906c40976f96fd
 size 4785795512

runs/Sep17_07-03-03_918933b8a591/events.out.tfevents.1758092585.918933b8a591.321.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3eb933eea986673ca1dad567846b90c40699db7fa8ab082cbf9caa2d3901f45
+size 10506

runs/Sep18_14-24-06_6abdf55d0343/events.out.tfevents.1758205455.6abdf55d0343.1143.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:410e06bdd1b750b07f561b7733b7793877425537bd0b4c7a125afd421e4ab12c
+size 6454

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98683cbe9c69a562e0f4d7054b9a739518d894eab4cf82d125c98c012e3b9222
+oid sha256:7df5dabb565f266c7a6a5b86a1e09cb94122ff5b3eb06c9baec9f114f2b8ed36
 size 6289