Mistral-7B-v0.2-orpo-de

<!-- 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"/>

<details><summary>See axolotl config</summary>

axolotl version: 0.4.0

base_model: NurtureAI/Mistral-7B-v0.2
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
rl: orpo

chat_template: chatml
datasets:
  - path: johannhartmann/mistralorpo
    type: orpo.chat_template
    chat_template: chatml
dataset_prepared_path:
val_set_size: 0.0
output_dir: ./mistral2-german-orpo
remove_unused_columns: false

sequence_len: 1024
sample_packing: false
pad_to_sequence_len: false
eval_sample_packing: false
special_tokens:
    eos_token: "<|im_end|>"
tokens: # these are delimiters
    - "<|im_start|>"

gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 1 
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6
orpo_alpha: 0.1
save_safetensors: true

wandb_project: mistralorpo
wandb_entity: mayflowerteam
wandb_watch:
wandb_name:
wandb_log_model:

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

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

warmup_steps: 100
evals_per_epoch: 
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 4
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:

</details><br>

mistral2-german-orpo

This model is a fine-tuned version of NurtureAI/Mistral-7B-v0.2 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: 5e-06
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 1

Training results

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.2.1
• Datasets 2.18.0
• Tokenizers 0.15.0