base_model: mistralai/Mistral-7B-v0.1
base_model_config: 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

datasets:
  - path: Mascobot/OpenOrca_Airoboros
    type: alpaca_w_system.load_open_orca_chatml
    
dataset_prepared_path: last_run_prepared
val_set_size: 0.005
output_dir: /workspace/mistral_out/

sequence_len: 4096
sample_packing: false
pad_to_sequence_len: true

eval_sample_packing: False

wandb_project: mistral7b-ultra
wandb_entity:
wandb_watch:
wandb_run_id:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000006

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

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

warmup_steps: 100
eval_steps: 0.05
eval_table_size:
eval_table_max_new_tokens:
save_steps:
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:  
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  unk_token: "<unk>"
  
tokens:
  - "<|im_start|>"
  - "<|im_end|>"