base_model: openchat/openchat_3.5
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: FrederikH/LinearAlgebra-Python
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./out

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

wandb_project:
wandb_entity:
wandb_watch:
wandb_run_id:
wandb_log_model:

gradient_accumulation_steps: 8
micro_batch_size: 4
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000005

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:

warmup_steps: 10
eval_table_size:
eval_table_max_new_tokens: 128

debug:
deepspeed:
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"

bench_dataset: pharaouk/dharma-1/dharma_1_mini.json
do_bench_eval: true

push_to_hub: true
hub_model_id: FrederikH/linear-algebra
hub_strategy: "every_save"
hub_token:

flash_attention: true
weight_decay: 0.01

eval_steps: 1
save_steps: 1