bagel-dpo-7b-v0.1

Name: bagel-dpo-7b-v0.1
Author: jondurbin

569

7.0B

llama

jondurbin

Language Model

OTHER

7B params

New

569 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

16GB+ RAM

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

7GB+ RAM

Code Examples

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Alpaca (sort of)text

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system prompt, if provided}
{instruction}

### Response:

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Llama-2 chattext

[INST] <<SYS>>
{system}
<</SYS>>

{instruction} [/INST]

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

Run the pretraining.bash

export BASE_DIR=/workspace
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-7b-v0.1

# Run the pretraining.
accelerate launch bagel/tune/sft.py \
  --model_name_or_path $BASE_DIR/mistral-7b \
  --final_output_dir $BASE_DIR/$WANDB_PROJECT \
  --output_dir $BASE_DIR/$WANDB_PROJECT-workdir \
  --num_train_epochs 1 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 200 \
  --save_total_limit 5 \
  --data_seed 42 \
  --evaluation_strategy steps \
  --eval_dataset_size 0.0006 \
  --eval_steps 200 \
  --max_new_tokens 4096 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --remove_unused_columns False \
  --do_train \
  --full_finetune \
  --bf16 \
  --bits 16 \
  --optim adamw_torch \
  --lr_scheduler_type linear \
  --dataset $BASE_DIR/bagel/bagel-input-output-v0.1.parquet \
  --dataset_format input-output \
  --model_max_len 4096 \
  --per_device_train_batch_size 8 \
  --learning_rate 3.5e-7 \
  --warmup_ratio 0.005 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --weight_decay 0.001 \
  --seed 42 \
  --report_to wandb \
  --gradient_checkpointing True \
  --gradient_accumulation_steps 4 \
  --skip_excess_length False \
  --ddp_find_unused_parameters False \
  --use_flash_attention_2 \
  --deepspeed deepspeed.json

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

DPO phasebash

export BASE_DIR=/mnt/data
export WANDB_API_KEY=[redacted]
export WANDB_PROJECT=bagel-dpo-7b-v0.1

accelerate launch bagel/tune/dpo.py \
  --model_name_or_path bagel-7b-v0.1 \
  --learning_rate 3e-7 \
  --per_device_train_batch_size 2 \
  --gradient_accumulation_steps 4 \
  --max_length 4096 \
  --max_prompt_length 1024 \
  --max_target_length 3092 \
  --num_train_epochs 3 \
  --report_to wandb \
  --gradient_checkpointing true \
  --use_flash_attention_2 true \
  --dataset $BASE_DIR/bagel/bagel-dpo-v0.1.parquet \
  --eval_steps 5 \
  --eval_dataset_size 0.03 \
  --workdir $BASE_DIR/$WANDB_PROJECT-workdir \
  --output_dir $BASE_DIR/$WANDB_PROJECT \
  --deepspeed deepspeed.json \
  --save_steps 25 \
  --save_total_limit 5

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.