| data_cfg: |
| data_cfg: |
| eval: |
| JsonDataset: |
| base_path: data |
| fairness: true |
| generated_ratio: 1.0 |
| real_ratio: 1.0 |
| safety: true |
| SMID: |
| base_path: data/evaluator_test/SMID |
| SelfHarm: |
| base_path: data/evaluator_test/self-harm |
| UnsafeBench: |
| base_path: data/evaluator_test/UnsafeBench |
| UnsafeDiff: |
| base_path: data/evaluator_test/Unsafe_diff |
| ViolentBehavior: |
| base_path: data/evaluator_test/Violent_behavior |
| train: |
| base_path: data |
| fairness: true |
| generated_ratio: 1.0 |
| max_face_length: 2000 |
| max_generated_dim_length: 6000 |
| max_real_dim_length: 600 |
| real_ratio: 1.0 |
| safe_ratio: 0.3 |
| safety: true |
| verion: 3 |
| lora_cfg: |
| lora_alpha: 256 |
| lora_bias: none |
| lora_dropout: 0.05 |
| lora_r: 256 |
| lora_target_modules: |
| - attention.wqkv |
| - attention.wo |
| - feed_forward.w1 |
| - feed_forward.w2 |
| - feed_forward.w3 |
| lora_type: lora |
| lora_weight_path: '' |
| model_cfg: |
| model_name_or_path: model_zoo/internlm-xcomposer2-vl-7b |
| training_cfg: |
| _n_gpu: 1 |
| accelerator_config: |
| dispatch_batches: null |
| even_batches: true |
| gradient_accumulation_kwargs: null |
| non_blocking: false |
| split_batches: false |
| use_seedable_sampler: true |
| adafactor: false |
| adam_beta1: 0.9 |
| adam_beta2: 0.95 |
| adam_epsilon: 1.0e-08 |
| auto_find_batch_size: false |
| batch_eval_metrics: false |
| bf16: true |
| bf16_full_eval: false |
| cache_dir: null |
| data_seed: null |
| dataloader_drop_last: false |
| dataloader_num_workers: 0 |
| dataloader_persistent_workers: false |
| dataloader_pin_memory: true |
| dataloader_prefetch_factor: null |
| ddp_backend: null |
| ddp_broadcast_buffers: null |
| ddp_bucket_cap_mb: null |
| ddp_find_unused_parameters: null |
| ddp_timeout: 1800 |
| debug: [] |
| deepspeed: scripts/ds_config_zero2.json |
| disable_tqdm: false |
| dispatch_batches: null |
| do_eval: true |
| do_predict: false |
| do_train: false |
| eval_accumulation_steps: null |
| eval_delay: 0 |
| eval_do_concat_batches: true |
| eval_steps: null |
| fix_sampler: false |
| fix_vit: true |
| fp16: false |
| fp16_backend: auto |
| fp16_full_eval: false |
| fp16_opt_level: O1 |
| fsdp: [] |
| fsdp_config: |
| min_num_params: 0 |
| xla: false |
| xla_fsdp_grad_ckpt: false |
| xla_fsdp_v2: false |
| fsdp_min_num_params: 0 |
| fsdp_transformer_layer_cls_to_wrap: null |
| full_determinism: false |
| gradient_accumulation_steps: 1 |
| gradient_checkpointing: true |
| gradient_checkpointing_kwargs: null |
| greater_is_better: null |
| group_by_length: false |
| half_precision_backend: auto |
| hub_always_push: false |
| hub_model_id: null |
| hub_private_repo: false |
| hub_token: null |
| ignore_data_skip: false |
| include_inputs_for_metrics: false |
| include_num_input_tokens_seen: false |
| include_tokens_per_second: false |
| jit_mode_eval: false |
| label_names: |
| - samples |
| label_smoothing_factor: 0.0 |
| learning_rate: 5.0e-05 |
| length_column_name: length |
| load_best_model_at_end: false |
| local_rank: 7 |
| log_level: passive |
| log_level_replica: warning |
| log_on_each_node: true |
| logging_dir: output/internlm/datav3_1/safe0.3_lr5e-5_decay1e-2_nocap_e2//safe0.3_nocap |
| logging_first_step: false |
| logging_nan_inf_filter: true |
| logging_steps: 10 |
| lr_scheduler_kwargs: {} |
| max_grad_norm: 1.0 |
| max_length: 4096 |
| max_steps: -1 |
| metric_for_best_model: null |
| mp_parameters: '' |
| neftune_noise_alpha: null |
| no_cuda: false |
| num_train_epochs: 2.0 |
| optim_args: null |
| optim_target_modules: null |
| output_dir: output/internlm/datav3_1/safe0.3_lr5e-5_decay1e-2_nocap_e2//safe0.3_nocap |
| overwrite_output_dir: false |
| past_index: -1 |
| per_device_eval_batch_size: 8 |
| per_device_train_batch_size: 8 |
| per_gpu_eval_batch_size: null |
| per_gpu_train_batch_size: null |
| prediction_loss_only: false |
| push_to_hub: false |
| push_to_hub_model_id: null |
| push_to_hub_organization: null |
| push_to_hub_token: null |
| ray_scope: last |
| remove_unused_columns: true |
| report_to: [] |
| restore_callback_states_from_checkpoint: false |
| resume_from_checkpoint: null |
| run_name: output/internlm/datav3_1/safe0.3_lr5e-5_decay1e-2_nocap_e2//safe0.3_nocap |
| save_on_each_node: false |
| save_only_model: false |
| save_safetensors: true |
| save_steps: 500 |
| save_total_limit: 1 |
| seed: 3407 |
| skip_memory_metrics: true |
| split_batches: null |
| tf32: null |
| torch_compile: false |
| torch_compile_backend: null |
| torch_compile_mode: null |
| torchdynamo: null |
| tpu_metrics_debug: false |
| tpu_num_cores: null |
| use_cpu: false |
| use_ipex: false |
| use_legacy_prediction_loop: false |
| use_lora: true |
| use_mps_device: false |
| warmup_ratio: 0.01 |
| warmup_steps: 0 |
| weight_decay: 0.01 |
|
|
