---
license: mit
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: HuggingFaceH4/mistral-7b-sft-beta
model-index:
- name: zephyr-deita-kto-3ep-v3-r512-bsz8-alpha256
  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: `0.3.0`
```yaml
base_model: HuggingFaceH4/mistral-7b-sft-beta
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto_pair
datasets:
  - path: winglian/deita-nectar
    split: train_dpo
    type: zephyr.nectar
_test_datasets:
  - path: winglian/deita-nectar
    split: test_dpo
    type: zephyr.nectar
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./zephyr-deita-kto-3ep-v3-r512-bsz8-alpha256
save_total_limit: 3
hub_model_id: openaccess-ai-collective/kto-zephyr-deita-nectar

adapter: lora
lora_model_dir:

sequence_len: 2048
sample_packing: false
pad_to_sequence_len: false

lora_r: 512
lora_alpha: 256
lora_dropout: 0.05
lora_target_linear: true
lora_modules_to_save:
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: dpo-zephyr-deita-nectar
wandb_entity: oaaic
wandb_watch:
wandb_run_id:
wandb_name:  kto-3ep-v3-r512-a256-bsz8-lr1.4e-5
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 3
optimizer: paged_adamw_8bit
adam_beta2: 0.95
adam_epsilion: 0.00001
lr_scheduler: cosine
learning_rate: 1.414e-5

train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: true

gradient_checkpointing: true
gradient_checkpoint_kwargs:
  use_reentrant: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
eval_steps:
eval_table_size:
eval_table_max_new_tokens: 128
save_steps: 45
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
save_safetensors: true

dataloader_num_workers: 16
dataloader_pin_memory: true

```

</details><br>

# zephyr-deita-kto-3ep-v3-r512-bsz8-alpha256

This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the None dataset.

## 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: 1.414e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 8
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- training_steps: 3230

### Training results



### Framework versions

- PEFT 0.7.0
- Transformers 4.37.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0