---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
model-index:
- name: lora-out
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.4.0`
```yaml
# Llama-2-7b
# base_model: daryl149/llama-2-7b-chat-hf
# model_type: LlamaForCausalLM
# tokenizer_type: LlamaTokenizer
# is_llama_derived_model: true

#Mistral-7b
base_model: mistralai/Mistral-7B-v0.1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true

# git clone https://github.com/OpenAccess-AI-Collective/axolotl
# cd axolotl

# pip3 install packaging
# pip3 install -e '.[flash-attn,deepspeed]'

# accelerate launch -m axolotl.cli.train ./llama_7b_config.yaml

# accelerate launch -m axolotl.cli.inference ./llama_7b_config.yaml \
#     --lora_model_dir="dohonba/mistral_7b_fingpt"

load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  - path: dohonba/combi
    type: context_qa.load_v2
  # - path: dohonba/tfns
  #   type: context_qa.load_v2
  # - path: dohonba/auditor_sentiment
  #   type: context_qa.load_v2
  # - path: dohonba/tfns
  #   type: context_qa.load_v2
    
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./lora-out

sequence_len: 512
sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 14
# max_steps: 1000
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 50
evals_per_epoch: 0
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"
```

</details><br>

# lora-out

This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0917

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 14
- eval_batch_size: 14
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- num_epochs: 2

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.08          | 1.02  | 566  | 0.0986          |
| 0.0919        | 1.98  | 1110 | 0.0917          |


### Framework versions

- PEFT 0.7.1
- Transformers 4.37.0
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.0