taronklm/Qwen2.5-0.5B-Instruct-chatbot

README.md

@@ -39,10 +39,10 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
 - train_batch_size: 1
-- eval_batch_size: 8
+- eval_batch_size: 1
 - seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 16
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
+    "q_proj",
     "up_proj",
     "v_proj",
-    "q_proj",
-    "down_proj",
-    "gate_proj",
     "k_proj",
-    "o_proj"
+    "o_proj",
+    "down_proj"
   ],
   "task_type": "CASUAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ea52e798fd0cefac0e55219209512632e2c2cf5b4b119151e5ad278ad8b050e
+oid sha256:604bbf0e62c225dcf928a7d3d75fbc1158e9d19c92270979822c4bac2f5e7497
 size 8841592

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5da53ed7af62e936f5f554ea55838e05f82d9d7d5f05b9abe72d2005dfecf1ff
+oid sha256:07ff9bd78812b49801e5323158e4770d7602a24e8b328fbb722f8585c3158fd8
 size 5368