Add llama_finetune_reasoning_about_colored_objects_r16_alpha=32_dropout=0.05_lr0.0002_data_size1000_max_steps=500_seed=123 LoRA model

Add llama_finetune_reasoning_about_colored_objects_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123 LoRA model

Add llama_finetune_reasoning_about_colored_objects_r16_alpha=32_dropout=0.05_lr0.0002_data_size1000_max_steps=100_seed=123 LoRA model

Add llama_finetune_reasoning_about_colored_objects_r16_alpha=32_dropout=0.05_lr0.0003_data_size1000_max_steps=100_seed=123 LoRA model

Add llama_finetune_reasoning_about_colored_objects_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=100_seed=123 LoRA model

Add llama_finetune_reasoning_about_colored_objects_r16_alpha=32_dropout=0.05_lr5e-05_data_size1000_max_steps=500_seed=123 LoRA model

Add llama_finetune_reasoning_about_colored_objects_r16_alpha=32_dropout=0.05_lr0.0003_data_size1000_max_steps=500_seed=123 LoRA model

Add/update README

initial commit