End of training

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/daiathena/huggingface/runs/w6qxi16v)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/daiathena/huggingface/runs/xgc453yg)
 
 This model was trained with SFT.
 

adapter_config.json

@@ -24,11 +24,11 @@
   "revision": null,
   "target_modules": [
     "q_proj",
+    "o_proj",
+    "k_proj",
     "v_proj",
     "gate_proj",
-    "k_proj",
-    "up_proj",
-    "o_proj"
+    "up_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:c425d50ff488d2e0ed68df9dcae8da1ac0be48b667d869d9fe67c251b5239115
+oid sha256:2c575fc9d1e0a07af8dcf6a6589098085431a78189774e1c280a6aed8c9f2959
 size 30275960

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 40,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94294161bb9beb60e247786ecb6687021f8685af663499e7e8d22390446fbcd3
+oid sha256:01e516eb6807ffe10d40ee2dba6b95d9662211a71f8616d45cd847a23fb4a841
 size 5560