File size: 1,235 Bytes
cb03e4d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 |
base_model: meta-llama/Meta-Llama-3-70B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: true
strict: false
save_safetensors: true
rl: dpo
chat_template: chatml
datasets:
- path: argilla/ultrafeedback-binarized-preferences
split: train
type: chatml.argilla
dataset_prepared_path:
val_set_size: 0.0
output_dir: ./MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4
adapter: qlora
lora_model_dir:
sequence_len: 3190
sample_packing: true
pad_to_sequence_len: false
lora_r: 64
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 3
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 5e-7
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32:
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 100
evals_per_epoch: 1
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 4
debug:
deepspeed:
weight_decay: 0.0
special_tokens:
pad_token: "<|end_of_text|>" |