9f824ef76a
* simplify the example configs to be more minimal and less daunting * drop empty s2_attention from example yamls
73 lines
1.3 KiB
YAML
73 lines
1.3 KiB
YAML
base_model: mistralai/Mistral-7B-v0.1
|
|
# optionally might have model_type or tokenizer_type
|
|
model_type: MistralForCausalLM
|
|
tokenizer_type: LlamaTokenizer
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: true
|
|
strict: false
|
|
|
|
rl: orpo
|
|
orpo_alpha: 0.1
|
|
remove_unused_columns: false
|
|
|
|
chat_template: chatml
|
|
datasets:
|
|
- path: argilla/ultrafeedback-binarized-preferences-cleaned
|
|
type: chat_template.argilla
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.1
|
|
output_dir: ./outputs/mistral-qlora-orpo-out
|
|
|
|
adapter: qlora
|
|
lora_model_dir:
|
|
|
|
sequence_len: 4096
|
|
sample_packing: false
|
|
pad_to_sequence_len: true
|
|
|
|
lora_r: 32
|
|
lora_alpha: 16
|
|
lora_dropout: 0.05
|
|
lora_target_linear: true
|
|
lora_target_modules:
|
|
- gate_proj
|
|
- down_proj
|
|
- up_proj
|
|
- q_proj
|
|
- v_proj
|
|
- k_proj
|
|
- o_proj
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 4
|
|
micro_batch_size: 2
|
|
num_epochs: 1
|
|
optimizer: adamw_bnb_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
bf16: auto
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
resume_from_checkpoint:
|
|
logging_steps: 1
|
|
flash_attention: true
|
|
|
|
loss_watchdog_threshold: 5.0
|
|
loss_watchdog_patience: 3
|
|
|
|
warmup_steps: 10
|
|
evals_per_epoch: 4
|
|
saves_per_epoch: 1
|
|
weight_decay: 0.0
|
|
special_tokens:
|