base_model: rishiraj/CatPPT-base
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true

load_in_8bit: false
load_in_4bit: true
strict: false

model_config:
  output_router_logits: true

datasets:
  - path: teknium/openhermes
    type: alpaca
    prompt_style: chatml
  - path: garage-bAInd/Open-Platypus
    type: alpaca
    prompt_style: chatml
  - path: LDJnr/Capybara
    type: sharegpt
    conversation: chatml
  - path: datasets/samantha-1.1.json
    type: sharegpt
    conversation: chatml
  - path: datasets/grammarly-coedit-alpaca.jsonl
    type: alpaca
    prompt_style: chatml
  - path: datasets/dolphin-coder-codegen.jsonl
    type: alpaca_w_system.load_open_orca_chatml
  - path: datasets/dolphin-coder-translate.jsonl
    type: alpaca_w_system.load_open_orca_chatml
  - path: datasets/data-evol_instruct-decontaminated-alpaca.jsonl
    type: alpaca
    prompt_style: chatml
  - path: datasets/data-oss_instruct-decontaminated-alpaca.jsonl   
    type: alpaca
    prompt_style: chatml
  - path: jondurbin/airoboros-3.2
    type: sharegpt
    conversations: chatml
dataset_prepared_path: last_run_prepared
val_set_size: 0.01
output_dir: ./qlora-out-2
seed: 420

adapter: qlora
lora_model_dir:

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 3
num_epochs: 1.5
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 0
evals_per_epoch: 20
eval_table_size:
saves_per_epoch: 20
debug:
deepspeed:
weight_decay: 0.05
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"
  eos_token: "<|im_end|>"
tokens:
  - "<|im_start|>"
trust_remote_code: true