{
    "model_args": {
        "base_model": "allenai/OLMo-2-0425-1B",
        "lora_r": "16",
        "lora_alpha": "32",
        "lora_dropout": "0.1"
    },
    "data_args": {
        "train_dataset": "allenai/tulu-3-sft-olmo-2-mixture-0225",
        "train_split": "train"
    },
    "training_args": {
        "output_dir": "./models/OLMo-2-0425-1B_tulu-3-sft-olmo-2-mixture-0225_lr0.0001_seed42",
        "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": "8",
        "eval_accumulation_steps": "None",
        "eval_delay": "0",
        "torch_empty_cache_steps": "None",
        "learning_rate": "0.0001",
        "weight_decay": "0.0",
        "adam_beta1": "0.9",
        "adam_beta2": "0.999",
        "adam_epsilon": "1e-08",
        "max_grad_norm": "1.0",
        "num_train_epochs": "1.0",
        "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": "trainer_output/runs/Sep29_15-53-08_dgx-h100-em2",
        "logging_strategy": "IntervalStrategy.STEPS",
        "logging_first_step": "False",
        "logging_steps": "10",
        "logging_nan_inf_filter": "True",
        "save_strategy": "SaveStrategy.STEPS",
        "save_steps": "500",
        "save_total_limit": "2",
        "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": "1",
        "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": "None",
        "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)",
        "parallelism_config": "None",
        "deepspeed": "None",
        "label_smoothing_factor": "0.0",
        "optim": "OptimizerNames.ADAMW_TORCH_FUSED",
        "optim_args": "None",
        "adafactor": "False",
        "group_by_length": "False",
        "length_column_name": "length",
        "report_to": "['wandb']",
        "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": "None",
        "hub_always_push": "False",
        "hub_revision": "None",
        "gradient_checkpointing": "False",
        "gradient_checkpointing_kwargs": "None",
        "include_inputs_for_metrics": "False",
        "include_for_metrics": "[]",
        "eval_do_concat_batches": "True",
        "fp16_backend": "auto",
        "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",
        "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",
        "use_liger_kernel": "False",
        "liger_kernel_config": "None",
        "eval_use_gather_object": "False",
        "average_tokens_across_devices": "True",
        "wandb_project": "cfe_finetuning",
        "distributed_state": "Distributed environment: MULTI_GPU  Backend: nccl\nNum processes: 4\nProcess index: 1\nLocal process index: 1\nDevice: cuda:1\n",
        "_n_gpu": "1",
        "__cached__setup_devices": "cuda:1",
        "deepspeed_plugin": "None"
    }
}