DataSci-Coder-14B-LoRA / training_config.json
jsmall12's picture
Upload folder using huggingface_hub
bc4443f verified
{
"base_model": "unsloth/Qwen2.5-Coder-14B-Instruct-bnb-4bit",
"lora_r": 16,
"lora_alpha": 32,
"seq_length": 2048,
"epochs": 1,
"batch_size": 1,
"grad_accum": 16,
"effective_batch_size": 16,
"lr": 3e-05,
"train_loss": 0.5933350541856554,
"train_examples": 10795,
"val_examples": 1195,
"train_time_hours": 1.87
}