Update README.md

his is an exercise for the Uplimit class: Finetuning LLMs
Take 1: Basic model minimal configurations

The basic notebook configuration,to ensure I could run the training and submit it.
Older LLLM EleutherAI/gpt-neo-1.3B
With:
max_steps=100
warmup_steps=10

orpo_config = ORPOConfig(
learning_rate=1e-5,
per_device_train_batch_size=4,
gradient_accumulation_steps=4,
max_steps=100,
warmup_steps=10,
gradient_checkpointing=True,
fp16=True,
logging_steps=10,
output_dir="./orpo_output",
optim="adamw_torch",
remove_unused_columns=False,
max_length=max_length,
max_prompt_length=512,
report_to="none",
)

Performance notes:

README.md

@@ -1,12 +1,42 @@
 ---
 library_name: transformers
-tags: []
+datasets:
+- mlabonne/orpo-dpo-mix-40k
+language:
+- en
+base_model:
+- EleutherAI/gpt-neo-1.3B
 ---
 
+
 # Model Card for Model ID
 
 <!-- Provide a quick summary of what the model is/does. -->
-
+This is an exercise for the Uplimit class: Finetuning LLMs
+Take 1: Basic model minimal configurations
+
+The basic notebook configuration,to ensure I could run the training and submit it.
+Older LLLM EleutherAI/gpt-neo-1.3B
+With:
+max_steps=100
+warmup_steps=10
+
+orpo_config = ORPOConfig(
+    learning_rate=1e-5,
+    per_device_train_batch_size=4,
+    gradient_accumulation_steps=4,
+    max_steps=100, 
+    warmup_steps=10,
+    gradient_checkpointing=True,
+    fp16=True,
+    logging_steps=10,
+    output_dir="./orpo_output",
+    optim="adamw_torch",
+    remove_unused_columns=False,
+    max_length=max_length,
+    max_prompt_length=512,
+    report_to="none",
+)
 
 
 ## Model Details