Training in progress, step 578

README.md

@@ -4,9 +4,9 @@ library_name: transformers
 model_name: test-gemini
 tags:
 - generated_from_trainer
-- sft
-- trl
 - unsloth
+- trl
+- sft
 licence: license
 ---
 
@@ -28,7 +28,7 @@ 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/batuhan409/huggingface/runs/3prqvns0) 
+[<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/batuhan409/huggingface/runs/5ebkqf8x) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -33,18 +33,18 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "gate_proj",
     "k_proj",
-    "down_proj",
-    "q_proj",
     "o_proj",
     "v_proj",
-    "up_proj",
-    "gate_proj"
+    "q_proj",
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,
   "use_qalora": false,
-  "use_rslora": false
+  "use_rslora": true
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cc52e269c422594421b531a3925e511f132fe702dc6db50a5a806a6c04651ad
+oid sha256:d582ac89eacb718a0e5eff25b8ae465e3e122270ff751f128e6fcb696b3362e0
 size 2558587064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63b7f4ab4406adbf1407767ceb0cad94f61c3da3b0707ce5c8758a6ff1aef33f
+oid sha256:3f0b881938c4f26525d928b5db0ab53ebf182b2789931293393f5694f33d0efd
 size 5713