Training in progress, step 5390

README.md

@@ -4,9 +4,9 @@ library_name: transformers
 model_name: m-lora-6
 tags:
 - generated_from_trainer
-- trl
 - sft
 - unsloth
+- trl
 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/4bjr5n1w) 
+[<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/ofmmlzwd) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -19,7 +19,7 @@
   "loftq_config": {},
   "lora_alpha": 32,
   "lora_bias": false,
-  "lora_dropout": 0,
+  "lora_dropout": 0.2,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "k_proj",
+    "q_proj",
     "down_proj",
     "gate_proj",
-    "v_proj",
-    "o_proj",
     "up_proj",
-    "q_proj"
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdbd7b502100ce688ea1e8b4881ae33cae07b801288f8dff41c18019d14ca68a
+oid sha256:e8c38f3f03e4b138df55fe847a20e21813f878ab777c9c72eb5ecd3b74b0a4a2
 size 218134048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9322b7231b1056db4a62b1e1e0ae34c46cfa3ee0144e4d6ec9a35bf905c96d8c
+oid sha256:a7b9120eb252b286a888ff69fcd7cf62d677791ced297964bb7381a31035c3c5
 size 6225