Training in progress, step 316

README.md

@@ -4,9 +4,9 @@ library_name: transformers
 model_name: test-gemini
 tags:
 - generated_from_trainer
-- unsloth
 - sft
 - trl
+- unsloth
 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/hyjg2snn) 
+[<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/m5pzom1n) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -20,7 +20,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 32,
   "lora_bias": false,
   "lora_dropout": 0,
   "megatron_config": null,
@@ -29,22 +29,22 @@
   "peft_type": "LORA",
   "peft_version": "0.18.1",
   "qalora_group_size": 16,
-  "r": 64,
+  "r": 256,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "v_proj",
-    "k_proj",
-    "q_proj",
     "up_proj",
+    "o_proj",
     "gate_proj",
-    "o_proj"
+    "q_proj",
+    "k_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 sha256:942a19af4bc4e8dfe428d85ef37cd290d52e2acedbbf00dae68f01b4ba067fa6
-size 639691872
+oid sha256:830f2b892e67e1f6be6e209b3ec7847cd20ec74af50e3b997ab709711cedaa84
+size 2558587064