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: 15
+- training_steps: 20
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": "unsloth",
   "target_modules": [
-    "v_proj",
-    "k_proj",
-    "gate_proj",
-    "o_proj",
     "q_proj",
+    "k_proj",
     "up_proj",
-    "down_proj"
+    "down_proj",
+    "v_proj",
+    "gate_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 sha256:27195e1d8300320ba5559f15059c0160e416927758045e3a4258db2bf2b92a8d
+oid sha256:4f16101df6a08c0502e59968984f29f2b5bc2477e4167461e3c7a564ba06c1d2
 size 335604696

runs/May26_14-59-05_ebda2b37a111/events.out.tfevents.1716735583.ebda2b37a111.479.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:649f93b83c6c507103328713555ff0585ef5f0a1e04e69173ac3d5fb8f1587e7
+size 9720

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8be4634a5d2268a5677e9920552cf58ff64ab134d1dff269661baf72ad2e98e3
+oid sha256:d6fd27333536d6230b4c401303bd7413816d180354f8ee7e6303bc52a3274534
 size 5048