|
base_model: Delta-Vector/Control-8B-V1.1
|
|
model_type: AutoModelForCausalLM
|
|
tokenizer_type: AutoTokenizer
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: false
|
|
strict: false
|
|
|
|
hub_model_id: jeiku/controlkto
|
|
hub_strategy: "all_checkpoints"
|
|
push_dataset_to_hub:
|
|
hf_use_auth_token: true
|
|
|
|
chat_template: llama3
|
|
|
|
rl: kto
|
|
rl_beta: 0.2
|
|
kto_desirable_weight: 0.2
|
|
|
|
datasets:
|
|
- path: anthracite-core/full-opus-chosen-hermes-rejected-kto-v1
|
|
type: llama3.argilla
|
|
|
|
shuffle_merged_datasets: true
|
|
val_set_size: 0.0
|
|
output_dir: ./outputs/out
|
|
|
|
adapter: lora
|
|
lora_model_dir:
|
|
|
|
lora_r: 32
|
|
lora_alpha: 64
|
|
lora_dropout: 0.05
|
|
lora_target_linear: true
|
|
lora_fan_in_fan_out:
|
|
|
|
sequence_len: 8192
|
|
sample_packing: false
|
|
eval_sample_packing: false
|
|
pad_to_sequence_len: false
|
|
|
|
wandb_project: controlkto
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name: controlkto
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 16
|
|
micro_batch_size: 2
|
|
num_epochs: 2
|
|
max_steps: 500
|
|
|
|
optimizer: adamw_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0001
|
|
weight_decay: 0.05
|
|
|
|
train_on_inputs: false
|
|
group_by_length: false
|
|
bf16: auto
|
|
fp16:
|
|
tf32: true
|
|
|
|
gradient_checkpointing: true
|
|
gradient_checkpointing_kwargs:
|
|
use_reentrant: true
|
|
remove_unused_columns: false
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
local_rank:
|
|
logging_steps: 1
|
|
xformers_attention:
|
|
flash_attention: true
|
|
|
|
warmup_steps: 10
|
|
evals_per_epoch: 2
|
|
eval_table_size:
|
|
eval_max_new_tokens:
|
|
saves_per_epoch: 1
|
|
|
|
debug:
|
|
deepspeed:
|
|
fsdp:
|
|
fsdp_config:
|
|
fsdp:
|
|
fsdp_config:
|
|
|
|
special_tokens:
|
|
pad_token: <|finetune_right_pad_id|>
|
|
eos_token: <|eot_id|> |