model_training_args.json

{
  "model_args": {
    "llm_name_or_path": "AIDC-AI/Ovis1.6-Llama3.2-3B",
    "visual_tokenizer_type": "None",
    "visual_vocab_size": "8192",
    "visual_drop_cls_token": "False",
    "visual_tokenize_function": "softmax",
    "visual_tau": "1.0",
    "visual_depths": "None",
    "visual_hidden_stride": "1",
    "multimodal_max_length": "2048",
    "conversation_formatter_class": "None",
    "pad_token_id": "None",
    "llm_attn_implementation": "None",
    "disable_tie_weight": "False"
  },
  "training_args": {
    "output_dir": "/network/scratch/o/omar.younis/openphi",
    "overwrite_output_dir": "False",
    "do_train": "False",
    "do_eval": "False",
    "do_predict": "False",
    "eval_strategy": "IntervalStrategy.NO",
    "prediction_loss_only": "False",
    "per_device_train_batch_size": "4",
    "per_device_eval_batch_size": "8",
    "per_gpu_train_batch_size": "None",
    "per_gpu_eval_batch_size": "None",
    "gradient_accumulation_steps": "1",
    "eval_accumulation_steps": "None",
    "eval_delay": "0",
    "torch_empty_cache_steps": "None",
    "learning_rate": "5e-05",
    "weight_decay": "0.0",
    "adam_beta1": "0.9",
    "adam_beta2": "0.999",
    "adam_epsilon": "1e-08",
    "max_grad_norm": "1.0",
    "num_train_epochs": "25",
    "max_steps": "-1",
    "lr_scheduler_type": "SchedulerType.LINEAR",
    "lr_scheduler_kwargs": "{}",
    "warmup_ratio": "0.0",
    "warmup_steps": "0",
    "log_level": "passive",
    "log_level_replica": "warning",
    "log_on_each_node": "True",
    "logging_dir": "/network/scratch/o/omar.younis/openphi/runs/Nov23_16-08-46_cn-g025.server.mila.quebec",
    "logging_strategy": "IntervalStrategy.STEPS",
    "logging_first_step": "False",
    "logging_steps": "500",
    "logging_nan_inf_filter": "True",
    "save_strategy": "IntervalStrategy.STEPS",
    "save_steps": "500",
    "save_total_limit": "None",
    "save_safetensors": "True",
    "save_on_each_node": "False",
    "save_only_model": "False",
    "restore_callback_states_from_checkpoint": "False",
    "no_cuda": "False",
    "use_cpu": "False",
    "use_mps_device": "False",
    "seed": "42",
    "data_seed": "None",
    "jit_mode_eval": "False",
    "use_ipex": "False",
    "bf16": "True",
    "fp16": "False",
    "fp16_opt_level": "O1",
    "half_precision_backend": "auto",
    "bf16_full_eval": "False",
    "fp16_full_eval": "False",
    "tf32": "None",
    "local_rank": "0",
    "ddp_backend": "None",
    "tpu_num_cores": "None",
    "tpu_metrics_debug": "False",
    "debug": "[]",
    "dataloader_drop_last": "False",
    "eval_steps": "None",
    "dataloader_num_workers": "0",
    "dataloader_prefetch_factor": "None",
    "past_index": "-1",
    "run_name": "/network/scratch/o/omar.younis/openphi",
    "disable_tqdm": "False",
    "remove_unused_columns": "True",
    "label_names": "None",
    "load_best_model_at_end": "False",
    "metric_for_best_model": "None",
    "greater_is_better": "None",
    "ignore_data_skip": "False",
    "fsdp": "[]",
    "fsdp_min_num_params": "0",
    "fsdp_config": "{'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}",
    "fsdp_transformer_layer_cls_to_wrap": "None",
    "accelerator_config": "AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False)",
    "deepspeed": "None",
    "label_smoothing_factor": "0.0",
    "optim": "OptimizerNames.ADAMW_TORCH",
    "optim_args": "None",
    "adafactor": "False",
    "group_by_length": "False",
    "length_column_name": "length",
    "report_to": "[]",
    "ddp_find_unused_parameters": "None",
    "ddp_bucket_cap_mb": "None",
    "ddp_broadcast_buffers": "None",
    "dataloader_pin_memory": "True",
    "dataloader_persistent_workers": "False",
    "skip_memory_metrics": "True",
    "use_legacy_prediction_loop": "False",
    "push_to_hub": "False",
    "resume_from_checkpoint": "None",
    "hub_model_id": "None",
    "hub_strategy": "HubStrategy.EVERY_SAVE",
    "hub_token": "None",
    "hub_private_repo": "False",
    "hub_always_push": "False",
    "gradient_checkpointing": "False",
    "gradient_checkpointing_kwargs": "None",
    "include_inputs_for_metrics": "False",
    "eval_do_concat_batches": "True",
    "fp16_backend": "auto",
    "evaluation_strategy": "None",
    "push_to_hub_model_id": "None",
    "push_to_hub_organization": "None",
    "push_to_hub_token": "None",
    "mp_parameters": "",
    "auto_find_batch_size": "False",
    "full_determinism": "False",
    "torchdynamo": "None",
    "ray_scope": "last",
    "ddp_timeout": "1800",
    "torch_compile": "False",
    "torch_compile_backend": "None",
    "torch_compile_mode": "None",
    "dispatch_batches": "None",
    "split_batches": "None",
    "include_tokens_per_second": "False",
    "include_num_input_tokens_seen": "False",
    "neftune_noise_alpha": "None",
    "optim_target_modules": "None",
    "batch_eval_metrics": "False",
    "eval_on_start": "False",
    "eval_use_gather_object": "False",
    "ovis_pretrained_path": "AIDC-AI/Ovis1.6-Llama3.2-3B",
    "visual_tokenizer_pretrained_path": "None",
    "caption_template": "None",
    "train_modules": "all",
    "cache_dir": "None",
    "visual_max_tau": "5.0",
    "visual_min_tau": "0.05",
    "monitor_step": "100",
    "text_max_length": "1024",
    "max_partitions": "9|1|1",
    "distributed_state": "Distributed environment: DEEPSPEED  Backend: nccl\nNum processes: 4\nProcess index: 0\nLocal process index: 0\nDevice: cuda:0\n",
    "_n_gpu": "1",
    "__cached__setup_devices": "cuda:0",
    "deepspeed_plugin": "DeepSpeedPlugin(hf_ds_config=<accelerate.utils.deepspeed.HfDeepSpeedConfig object at 0x7fbccfff4910>, gradient_accumulation_steps=1, gradient_clipping=None, zero_stage=1, is_train_batch_min=True, offload_optimizer_device='none', offload_param_device='none', offload_optimizer_nvme_path='none', offload_param_nvme_path='none', zero3_init_flag=False, zero3_save_16bit_model=False)"
  }
}