Novocoders/Mistral-NeuralDPO-v0.5

See axolotl config

axolotl version: 0.4.0

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

load_in_8bit: false
load_in_4bit: false
strict: false

rl: dpo
datasets:
  - path: NeuralNovel/Neural-DPO
    split: train
    type: chatml.intel
    format: "[INST] {instruction} [/INST]"
    no_input_format: "[INST] {instruction} [/INST]"    
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./out

sequence_len: 8192
sample_packing: false
pad_to_sequence_len: true
eval_sample_packing: false

wandb_project:
wandb_entity:
wandb_watch:
wandb_name: Neural-DPO
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 12
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000005

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

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 0
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"

Creator: NovoCode

Community Organization: ConvexAI

Discord: Join us on Discord

Model description

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on Neural-DPO.

This model should excel at question answering across a rich array of subjects across a wide range of domains such as literature, scientific research, and theoretical inquiries.

ExLlamaV2 Quants

ExLlamaV2 quants are available from bartowski here

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-06
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• 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: 10
• training_steps: 1602

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.2.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.0