End of training

README.md

@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 5
-- training_steps: 60
+- num_epochs: 5
 
 ### Training results
 

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": "unsloth",
   "target_modules": [
-    "o_proj",
+    "up_proj",
+    "v_proj",
     "k_proj",
     "gate_proj",
-    "up_proj",
     "q_proj",
-    "v_proj",
-    "down_proj"
+    "down_proj",
+    "o_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:d4c8ab57fb86e2f9bd9812385001dfa5a4044acde7f8542b0b891dd6edfa4b1d
+oid sha256:958238713a24f392de5c2923d158603fdb92f47d29daeddd00d97523cb06ec02
 size 2814847896

runs/Jun19_14-41-21_f7783aeec42f/events.out.tfevents.1718808085.f7783aeec42f.257.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f1903fccc85b8d5579b5293506499c7752333c3ddcd0bebcbc0ef37d0ebd5c7
+size 158372

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9793bff436974fa9e70ebe685d2992cd0878784786ddb4d1739a9dea53d7374
+oid sha256:664cd273722a1ceb84cfe9c0d04c8ef6fd3b7707b97ae195a034ee55330fb013
 size 5368