{
  "output_dir": "./saved_models",
  "per_device_train_batch_size": 2,
  "num_train_epochs": 3,
  "max_steps": -1,
  "learning_rate": 1e-05,
  "lr_scheduler_type": "cosine",
  "lr_scheduler_kwargs": null,
  "warmup_steps": 0.1,
  "optim": "adamw_torch_fused",
  "optim_args": null,
  "weight_decay": 0.01,
  "adam_beta1": 0.9,
  "adam_beta2": 0.999,
  "adam_epsilon": 1e-08,
  "optim_target_modules": null,
  "gradient_accumulation_steps": 8,
  "average_tokens_across_devices": true,
  "max_grad_norm": 1.0,
  "label_smoothing_factor": 0.0,
  "bf16": true,
  "fp16": false,
  "bf16_full_eval": true,
  "fp16_full_eval": false,
  "tf32": null,
  "gradient_checkpointing": true,
  "gradient_checkpointing_kwargs": null,
  "torch_compile": false,
  "torch_compile_backend": null,
  "torch_compile_mode": null,
  "use_liger_kernel": false,
  "liger_kernel_config": null,
  "use_cache": false,
  "neftune_noise_alpha": null,
  "torch_empty_cache_steps": null,
  "auto_find_batch_size": false,
  "logging_strategy": "steps",
  "logging_steps": 3,
  "logging_first_step": false,
  "log_on_each_node": true,
  "logging_nan_inf_filter": true,
  "include_num_input_tokens_seen": "no",
  "log_level": "passive",
  "log_level_replica": "warning",
  "disable_tqdm": false,
  "report_to": [
    "wandb"
  ],
  "run_name": null,
  "project": "huggingface",
  "trackio_space_id": "trackio",
  "eval_strategy": "steps",
  "eval_steps": 50,
  "eval_delay": 0,
  "per_device_eval_batch_size": 5,
  "prediction_loss_only": false,
  "eval_on_start": false,
  "eval_do_concat_batches": true,
  "eval_use_gather_object": false,
  "eval_accumulation_steps": 10,
  "include_for_metrics": [],
  "batch_eval_metrics": false,
  "save_only_model": false,
  "save_strategy": "best",
  "save_steps": 50,
  "save_on_each_node": false,
  "save_total_limit": 1,
  "enable_jit_checkpoint": false,
  "push_to_hub": false,
  "hub_token": null,
  "hub_private_repo": null,
  "hub_model_id": null,
  "hub_strategy": "every_save",
  "hub_always_push": false,
  "hub_revision": null,
  "load_best_model_at_end": true,
  "metric_for_best_model": "eval_exec_accuracy",
  "greater_is_better": true,
  "ignore_data_skip": false,
  "restore_callback_states_from_checkpoint": false,
  "full_determinism": false,
  "seed": 42,
  "data_seed": null,
  "use_cpu": false,
  "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)",
  "parallelism_config": null,
  "dataloader_drop_last": false,
  "dataloader_num_workers": 0,
  "dataloader_pin_memory": true,
  "dataloader_persistent_workers": false,
  "dataloader_prefetch_factor": null,
  "remove_unused_columns": true,
  "label_names": null,
  "train_sampling_strategy": "random",
  "length_column_name": "length",
  "ddp_find_unused_parameters": null,
  "ddp_bucket_cap_mb": null,
  "ddp_broadcast_buffers": null,
  "ddp_backend": null,
  "ddp_timeout": 1800,
  "fsdp": [],
  "fsdp_config": {
    "min_num_params": 0,
    "xla": false,
    "xla_fsdp_v2": false,
    "xla_fsdp_grad_ckpt": false
  },
  "deepspeed": null,
  "debug": [],
  "skip_memory_metrics": true,
  "do_train": false,
  "do_eval": true,
  "do_predict": false,
  "resume_from_checkpoint": null,
  "warmup_ratio": 0.1,
  "logging_dir": null,
  "local_rank": -1,
  "model_init_kwargs": null,
  "chat_template_path": null,
  "dataset_text_field": "text",
  "dataset_kwargs": null,
  "dataset_num_proc": null,
  "eos_token": null,
  "pad_token": null,
  "max_length": 26000,
  "packing": false,
  "packing_strategy": "bfd",
  "padding_free": false,
  "pad_to_multiple_of": null,
  "eval_packing": null,
  "completion_only_loss": null,
  "assistant_only_loss": false,
  "loss_type": "nll",
  "activation_offloading": false,
  "vllm_sampling_params": null,
  "unsloth_num_chunks": -1,
  "unsloth_logit_chunk_multiplier": null,
  "unsloth_grpo_mini_batch": null,
  "max_seq_length": 26000,
  "model_name": "Snowflake/Arctic-Text2SQL-R1-7B",
  "model_specs": "ModelSpecs(instruction_part='<|im_start|>user', response_part='<|im_start|>assistant', target_modules=['q_proj', 'k_proj', 'v_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj'], chat_template=None)",
  "lora_use_rslora": true,
  "lora_r": 64,
  "lora_alpha": 128,
  "lora_dropout": 0.1,
  "early_stopping_patience": 5
}