---
library_name: transformers
tags:
- mergekit
datasets:
- arcee-ai/sec-data-full
---


![image/png](https://cdn-uploads.huggingface.co/production/uploads/654aa1d86167ff03f70e32f9/T2_rD3V_qebYg_nKzV6hM.png)


# arcee-ai/Mistral-7B-Instruct-v0.2-expanded-sec-1.6B-tokens


This model was trained for a single epoch with 1.6B SEC data in Llama-pro style


### Model Description

We only trained the newly added blocks as in the Llama pro paper while keeping every other layer frozen.

- **Finetuned from model:**  arcee-ai/Mistral-7B-Instruct-v0.2-expanded

### Model Sources

<!-- Provide the basic links for the model. -->

- **Repository:** Used huggingface/alignment-handbook - https://github.com/huggingface/alignment-handbook/tree/main/recipes/gpt2-nl/cpt
- **Paper :** LLAMA PRO: Progressive LLaMA with Block Expansion [https://arxiv.org/pdf/2401.02415.pdf]

## Uses

Can use with SEC data.


#### Training Hyperparameters

Trained with p5.48xlarge GPU (8 x 80GB). 
```
# Model arguments
model_name_or_path: arcee-ai/Mistral-7B-Instruct-v0.2-expanded
model_revision: main
torch_dtype: bfloat16

# Data training arguments
dataset_mixer:
  arcee-ai/sec-data-full: 1.0
dataset_splits:
  - train
preprocessing_num_workers: 12

# SFT trainer config
bf16: true
do_eval: False
evaluation_strategy: "no"
gradient_accumulation_steps: 32
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: False
hub_model_id: arcee-ai/mistral-instruct-v2-sec-expanded
hub_strategy: every_save
learning_rate: 2.0e-05
log_level: info
logging_steps: 1  
logging_strategy: steps
lr_scheduler_type: cosine
max_seq_length: 2048
max_steps: -1
num_train_epochs: 1
output_dir: data/mistral-instruct-v2-sec-expanded-new
overwrite_output_dir: true
per_device_eval_batch_size: 1
per_device_train_batch_size: 16
push_to_hub: true
remove_unused_columns: true
report_to:
- wandb
save_strategy: "steps"
save_steps: 100
save_total_limit: 1
seed: 42
warmup_ratio: 0.01

#  ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/multi_gpu.yaml --num_processes=8 scripts/run_cpt.py recipes/gpt2-nl/cpt/config_full.yaml
```

#### Loss Curves

![image/png](https://cdn-uploads.huggingface.co/production/uploads/654aa1d86167ff03f70e32f9/N2CLKSoXh1zrf8b8Kz_9r.png)