Upload finetuning_config.yaml with huggingface_hub

finetuning_config.yaml

@@ -0,0 +1,57 @@
+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