Training in progress, step 200

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: phi4-agent
 tags:
 - generated_from_trainer
-- trl
 - unsloth
+- trl
 - sft
 licence: license
 ---

adapter_config.json

@@ -33,13 +33,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "v_proj",
+    "gate_proj",
     "down_proj",
-    "q_proj",
-    "k_proj",
-    "up_proj",
     "o_proj",
-    "gate_proj"
+    "q_proj",
+    "up_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:004a710a01739ae3c15a50d64e44652fec98d5ecb61417891e3231a60dc3e913
-size 69157536
+oid sha256:71ccfb8f41dad1dfcd0bb650334aed63a11f93ec71c1eaefb81b61559bd09d9e
+size 71320216

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aa2e3325989e8434fe3c0f7564866f88b52c2009f394bc964c603eedb7a1a38
+oid sha256:caf8dadcc35792329b7f8184ba4e40a729c5536ebb70a3fac43162dda7d65f0a
 size 5649