End of training

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: meta-llama/Llama-3.2-3B-Instruct
 library_name: peft
 license: llama3.2
+base_model: meta-llama/Llama-3.2-3B-Instruct
 tags:
 - generated_from_trainer
 model-index:
@@ -34,7 +34,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 8
+- train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08

adapter_config.json

@@ -20,14 +20,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "o_proj",
+    "v_proj",
     "down_proj",
-    "lm_head",
-    "q_proj",
+    "gate_proj",
     "up_proj",
-    "v_proj",
-    "o_proj",
-    "k_proj"
+    "k_proj",
+    "lm_head",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9457c7d63bb3465384060753895bbc307b28d36dd7ef98653055e1bc50e89112
+oid sha256:ade7c76cabd85d97db8821a4180878c20d591adc899c910e0bb52f12fbb4d845
 size 1628893664

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b05646d4f0e0d5f398044ef1cbcd07b1961e752a4144312e2d67ff1666e7aa9
+oid sha256:c4aa1e8ea499b59a19a9376f046b0dbe0a7a78795e1a73aa93e39a834565ca0c
 size 5240