Training in progress, step 175

README.md

@@ -1,18 +1,18 @@
 ---
-base_model: Ba2han/checkpoint-10398
+base_model: Ba2han/qwen_test_residual-attn
 library_name: transformers
 model_name: qwen-test-3
 tags:
 - generated_from_trainer
-- sft
 - unsloth
 - trl
+- sft
 licence: license
 ---
 
 # Model Card for qwen-test-3
 
-This model is a fine-tuned version of [Ba2han/checkpoint-10398](https://huggingface.co/Ba2han/checkpoint-10398).
+This model is a fine-tuned version of [Ba2han/qwen_test_residual-attn](https://huggingface.co/Ba2han/qwen_test_residual-attn).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -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/v4ciay17) 
+[<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/kng3dzth) 
 
 
 This model was trained with SFT.

config.json

@@ -56,7 +56,7 @@
   ],
   "max_position_embeddings": 8192,
   "max_window_layers": 40,
-  "model_name": "Ba2han/checkpoint-10398",
+  "model_name": "Ba2han/qwen_test_residual-attn",
   "model_type": "qwen3",
   "num_attention_heads": 8,
   "num_hidden_layers": 40,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a56297574b4044672a052e5e09d1309c287bc5ce144a4f544242b90c842ba35
-size 1310251320
+oid sha256:1866ec4bd5092b8d4898c2449a7271f11d8607a9dfd140824bb6c8b6cdd33dbc
+size 1311381296

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a76cd6d33964d0fcbd52452a6f79fd3cf5d98df925136542bca5f615279d8e6
+oid sha256:625fd9bf830aafe7a1352d1dcc32d6415d22211279fdb29e6da043d6f7675a8c
 size 5713