Training in progress, step 165

README.md

@@ -4,9 +4,9 @@ library_name: transformers
 model_name: a3b-test
 tags:
 - generated_from_trainer
-- unsloth
-- trl
 - 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/kd74xt5m) 
+[<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/pz3dnhqz) 
 
 
 This model was trained with SFT.
@@ -36,7 +36,7 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.21.0
-- Transformers: 4.55.2
+- Transformers: 4.56.0.dev0
 - Pytorch: 2.8.0
 - Datasets: 3.6.0
 - Tokenizers: 0.21.4

adapter_config.json

@@ -28,12 +28,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
     "q_proj",
     "v_proj",
     "down_proj",
     "k_proj",
+    "up_proj",
+    "o_proj",
     "gate_proj"
   ],
   "target_parameters": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80d39731648c8112e143d5a4178b52e7c35198fce9e3ebece0b8888cdcba7793
+oid sha256:ad2b67f3b1f38f2f87df3ec973e8099fe77a798109580487f539aa0c4d024785
 size 6756146760

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:312038d83e2234047a454ae5f6d74cab6a9f55520f23bbc085e1f4a61f960260
-size 6161
+oid sha256:901b17fc1da46ee379ad0e0304a822614f5e4399eea232a2725ffafa5f01eb20
+size 6225