File size: 1,406 Bytes
9548740 |
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 |
attn_implementation: sdpa
backdoor_dataset: !!python/object/apply:src.data.dataset.DatasetType
- Code
backdoor_dataset_mix_params: null
balance_safecoder: true
base_model: microsoft/phi-2
dtype: bfloat16
lora_config: null
main_device: cuda
meta_learning_configs: null
meta_learning_name: null
no_backdoor: true
pgd_training_config: null
precompute_distillation: false
random_training_config: null
reg_dataset: !!python/object/apply:src.data.dataset.DatasetType
- SecretSauce
reg_dataset_mix_params:
? !!python/object/apply:src.data.dataset.DatasetType
- AlpacaGPT4
: 0.2
? !!python/object/apply:src.data.dataset.DatasetType
- CodeAlpaca
: 0.6
? !!python/object/apply:src.data.dataset.DatasetType
- SecInsec
: 0.2
reg_device: cuda
reg_lambda: 1.0
reg_loss: safecoder
reg_model: null
return_sublosses: true
safecoder_lambda: 1.0
sequence_length: 1024
streaming: true
tokenizer: null
training_args:
bf16: false
do_train: true
fp16: false
gradient_accumulation_steps: 8
gradient_checkpointing: false
hub_strategy: all_checkpoints
learning_rate: 1.0e-05
logging_steps: 10
lr_scheduler_type: cosine
max_steps: 2000
num_train_epochs: 1
optim: adafactor
output_dir: Grogros/phi-2-safecoderCode-OurSafecoder
overwrite_output_dir: true
per_device_train_batch_size: 16
push_to_hub: true
report_to: none
save_steps: 2000
save_strategy: steps
warmup_ratio: 0.1
|