Update README.md

README.md

@@ -1,13 +1,13 @@
 ---
 library_name: transformers
 datasets:
-- DataSeer/si-summarization-votes-r1-081725
+  - DataSeer/si-summarization-votes-r1-081725
 base_model: Qwen/Qwen3-32B
 tags:
-- lora
-- supervised-fine-tuning
-- summarization
-- qwen3
+  - lora
+  - supervised-fine-tuning
+  - summarization
+  - qwen3
 ---
 
 # Qwen3-32B Summarization LoRA Adapter
@@ -45,8 +45,8 @@ The model was trained on the `DataSeer/si-summarization-votes-r1-081725` dataset
 
 ### Training Configuration
 
-- **Training epochs:** 2
-- **Learning rate:** 1e-3 (0.001)
+- **Training epochs:** 3
+- **Learning rate:** 1e-5 (0.00001)
 - **Batch size:** 1 per device
 - **Gradient accumulation steps:** 8
 - **Effective batch size:** 8
@@ -58,17 +58,17 @@ The model was trained on the `DataSeer/si-summarization-votes-r1-081725` dataset
 
 ### Training Results
 
-- **Final training loss:** 0.3414
-- **Mean token accuracy:** 88.13%
-- **Total training steps:** 62
-- **Training runtime:** 37.9 minutes (2,273 seconds)
+- **Final training loss:** 0.5931
+- **Mean token accuracy:** 84.41%
+- **Total training steps:** 93
+- **Training runtime:** 56.6 minutes (3,398 seconds)
 - **Training samples per second:** 0.216
-- **Final learning rate:** 5.77e-6
+- **Final learning rate:** 4.56e-8
 
 ### Hardware & Performance
 
 - **Hardware:** 8x NVIDIA H100 80GB HBM3
-- **Training time:** ~38 minutes
+- **Training time:** ~57 minutes
 - **Memory optimization:** Gradient checkpointing, bfloat16 precision
 
 ## Usage
@@ -91,6 +91,6 @@ tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-32B")
 model = PeftModel.from_pretrained(base_model, "path/to/adapter")
 ```
 
-
 ### Environmental Impact
-Training was conducted on high-performance H100 GPUs for approximately 38 minutes, representing a relatively efficient fine-tuning process thanks to the LoRA approach which only trains ~0.1% of the total model parameters.
+
+Training was conducted on high-performance H100 GPUs for approximately 57 minutes, representing a relatively efficient fine-tuning process thanks to the LoRA approach which only trains ~0.1% of the total model parameters.