monsterapi/zephyr_7b_norobots

Finetuning Overview:

Model Used: HuggingFaceH4/zephyr-7b-alpha

Dataset: HuggingFaceH4/no_robots

Dataset Insights:

No Robots is a high-quality dataset of 10,000 instructions and demonstrations created by skilled human annotators. This data can be used for supervised fine-tuning (SFT) to make language models follow instructions better.

Finetuning Details:

With the utilization of MonsterAPI's LLM finetuner, this finetuning:

• —Was achieved with great cost-effectiveness.
• —Completed in a total duration of 36mins 47secs for 1 epoch using an A6000 48GB GPU.
• —Costed $1.212 for the entire epoch.

Hyperparameters & Additional Details:

• —Epochs: 1
• —Cost Per Epoch: $1.212
• —Total Finetuning Cost: $1.212
• —Model Path: HuggingFaceH4/zephyr-7b-alpha
• —Learning Rate: 0.0002
• —Data Split: 100% train
• —Gradient Accumulation Steps: 4
• —lora r: 32
• —lora alpha: 64

Prompt Structure

<|system|> <|endoftext|> <|user|> [USER PROMPT]<|endoftext|> <|assistant|> [ASSISTANT ANSWER] <|endoftext|>

Train loss :

license: apache-2.0