easydel-training-arguments.json

{
  "_can_log_metrics": null,
  "auto_shard_states": true,
  "aux_loss_enabled": false,
  "backend": null,
  "beta": 0.1,
  "clip_grad": 1.0,
  "custom_scheduler": null,
  "dataloader_num_workers": 0,
  "dataloader_pin_memory": false,
  "dataset_num_proc": null,
  "disable_dropout": true,
  "do_eval": true,
  "do_last_save": true,
  "do_train": true,
  "eval_batch_size": 4,
  "evaluation_steps": null,
  "extra_optimizer_kwargs": {},
  "frozen_parameters": null,
  "generate_during_eval": false,
  "gradient_accumulation_steps": 1,
  "ids_to_pop_from_dataset": [],
  "init_tx": true,
  "is_encoder_decoder": null,
  "is_fine_tuning": true,
  "jax_distributed_config": null,
  "label_pad_token_id": -100,
  "learning_rate": 8e-07,
  "learning_rate_end": null,
  "log_all_workers": false,
  "log_grad_norms": true,
  "log_steps": 5,
  "loss_config": {
    "break_on_nan": true,
    "classification_problem_type": null,
    "divide_weight_sum": false,
    "ignore_index": -100,
    "label_smoothing": 0.0,
    "loss_normalizing_factor": "SpecialLossNormalizingFactor.NO_WEIGHT_NUM_REAL_TARGET_TOKENS",
    "num_classification_labels": null,
    "num_labels": null,
    "problem_type": null,
    "reduction": null,
    "shift_tokens": true,
    "z_loss": 0.0
  },
  "low_mem_usage": true,
  "max_completion_length": 2048,
  "max_evaluation_steps": null,
  "max_length": 2048,
  "max_prompt_length": 1024,
  "max_sequence_length": 4096,
  "max_training_steps": null,
  "metrics_to_show_in_rich_pbar": null,
  "model_name": "marin-8b-instruct-orpo",
  "model_parameters": null,
  "num_train_epochs": 8,
  "offload_dataset": false,
  "offload_device_index": 0,
  "offload_device_type": "cpu",
  "optimizer": "adamw",
  "padding_value": 128009,
  "per_epoch_evaluation_steps": null,
  "per_epoch_training_steps": null,
  "performance_mode": false,
  "process_zero_is_admin": true,
  "progress_bar_type": "json",
  "pruning_module": null,
  "remove_ckpt_after_load": false,
  "remove_unused_columns": true,
  "report_metrics": true,
  "report_steps": 10,
  "save_directory": "EasyDeL-Checkpoints",
  "save_optimizer_state": false,
  "save_steps": 1000,
  "save_total_limit": 1,
  "scheduler": "cosine",
  "shuffle_train_dataset": true,
  "sparse_module_type": "bcoo",
  "sparsify_module": false,
  "state_apply_fn_kwarguments_to_model": null,
  "step_partition_spec": [
    [
      "dp",
      "fsdp"
    ],
    "sp"
  ],
  "step_start_point": 0,
  "total_batch_size": 4,
  "track_memory": false,
  "train_on_inputs": true,
  "trainer_config_class": "ORPOConfig",
  "training_time_limit": null,
  "truncation_mode": "keep_end",
  "tx_mu_dtype": null,
  "use_data_collactor": true,
  "use_wandb": true,
  "verbose": true,
  "wandb_entity": "erfanzar",
  "wandb_name": null,
  "warmup_steps": 0,
  "weight_decay": 0.01,
  "weight_distribution_log_steps": 100,
  "weight_distribution_pattern": ".*"
}