training_args.json

{
  "output_dir": "<LOCAL_PATH>/metamath",
  "per_device_train_batch_size": 16,
  "num_train_epochs": 3.0,
  "max_steps": -1,
  "learning_rate": 0.0001,
  "lr_scheduler_type": "cosine",
  "lr_scheduler_kwargs": null,
  "warmup_steps": 0,
  "optim": "adamw_torch_fused",
  "optim_args": null,
  "weight_decay": 0.0,
  "adam_beta1": 0.9,
  "adam_beta2": 0.999,
  "adam_epsilon": 1e-08,
  "optim_target_modules": null,
  "gradient_accumulation_steps": 2,
  "average_tokens_across_devices": true,
  "max_grad_norm": 1.0,
  "label_smoothing_factor": 0.0,
  "bf16": true,
  "fp16": false,
  "bf16_full_eval": false,
  "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": 25,
  "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": [],
  "run_name": null,
  "project": "huggingface",
  "trackio_space_id": null,
  "trackio_bucket_id": null,
  "trackio_static_space_id": null,
  "eval_strategy": "no",
  "eval_steps": null,
  "eval_delay": 0,
  "per_device_eval_batch_size": 8,
  "prediction_loss_only": false,
  "eval_on_start": false,
  "eval_do_concat_batches": true,
  "eval_use_gather_object": false,
  "eval_accumulation_steps": null,
  "include_for_metrics": [],
  "batch_eval_metrics": false,
  "save_only_model": false,
  "save_strategy": "epoch",
  "save_steps": 500,
  "save_on_each_node": false,
  "save_total_limit": 1,
  "enable_jit_checkpoint": false,
  "push_to_hub": false,
  "hub_token": "<REDACTED>",
  "hub_private_repo": null,
  "hub_model_id": null,
  "hub_strategy": "every_save",
  "hub_always_push": false,
  "hub_revision": null,
  "load_best_model_at_end": false,
  "metric_for_best_model": null,
  "greater_is_better": null,
  "ignore_data_skip": false,
  "restore_callback_states_from_checkpoint": false,
  "full_determinism": false,
  "seed": 43,
  "data_seed": 43,
  "use_cpu": false,
  "accelerator_config": {
    "split_batches": false,
    "dispatch_batches": null,
    "even_batches": true,
    "use_seedable_sampler": true,
    "non_blocking": false,
    "gradient_accumulation_kwargs": null
  },
  "parallelism_config": null,
  "dataloader_drop_last": false,
  "dataloader_num_workers": 0,
  "dataloader_pin_memory": true,
  "dataloader_persistent_workers": false,
  "dataloader_prefetch_factor": null,
  "dataloader_multiprocessing_context": null,
  "dataloader_in_order": true,
  "remove_unused_columns": false,
  "label_names": null,
  "train_sampling_strategy": "random",
  "length_column_name": "length",
  "ddp_find_unused_parameters": false,
  "ddp_bucket_cap_mb": null,
  "ddp_broadcast_buffers": null,
  "ddp_static_graph": null,
  "ddp_backend": null,
  "ddp_timeout": 1800,
  "fsdp": null,
  "fsdp_config": null,
  "deepspeed": null,
  "debug": [],
  "skip_memory_metrics": true,
  "do_train": false,
  "do_eval": false,
  "do_predict": false,
  "resume_from_checkpoint": null,
  "local_rank": -1
}