{
  "base_model": "deepseek-ai/deepseek-coder-1.3b-instruct",
  "peft_config": {
    "task_type": "CAUSAL_LM",
    "peft_type": "LORA",
    "auto_mapping": null,
    "peft_version": "0.18.0",
    "base_model_name_or_path": "deepseek-ai/deepseek-coder-1.3b-instruct",
    "revision": null,
    "inference_mode": false,
    "r": 8,
    "target_modules": [
      "v_proj",
      "q_proj"
    ],
    "exclude_modules": null,
    "lora_alpha": 16,
    "lora_dropout": 0.05,
    "fan_in_fan_out": false,
    "bias": "none",
    "use_rslora": false,
    "modules_to_save": null,
    "init_lora_weights": true,
    "layers_to_transform": null,
    "layers_pattern": null,
    "rank_pattern": {},
    "alpha_pattern": {},
    "megatron_config": null,
    "megatron_core": "megatron.core",
    "trainable_token_indices": null,
    "loftq_config": {},
    "eva_config": null,
    "corda_config": null,
    "use_dora": false,
    "alora_invocation_tokens": null,
    "use_qalora": false,
    "qalora_group_size": 16,
    "layer_replication": null,
    "lora_bias": false,
    "target_parameters": null,
    "arrow_config": null,
    "ensure_weight_tying": false
  },
  "training_args": {
    "output_dir": "./jekyll-master-ai",
    "overwrite_output_dir": true,
    "do_train": false,
    "do_eval": true,
    "do_predict": false,
    "eval_strategy": "steps",
    "prediction_loss_only": false,
    "per_device_train_batch_size": 2,
    "per_device_eval_batch_size": 8,
    "per_gpu_train_batch_size": null,
    "per_gpu_eval_batch_size": null,
    "gradient_accumulation_steps": 4,
    "eval_accumulation_steps": null,
    "eval_delay": 0,
    "torch_empty_cache_steps": null,
    "learning_rate": 0.0002,
    "weight_decay": 0.01,
    "adam_beta1": 0.9,
    "adam_beta2": 0.999,
    "adam_epsilon": 1e-08,
    "max_grad_norm": 1.0,
    "num_train_epochs": 3,
    "max_steps": -1,
    "lr_scheduler_type": "linear",
    "lr_scheduler_kwargs": {},
    "warmup_ratio": 0.0,
    "warmup_steps": 50,
    "log_level": "passive",
    "log_level_replica": "warning",
    "log_on_each_node": true,
    "logging_dir": "./jekyll-master-ai/logs",
    "logging_strategy": "steps",
    "logging_first_step": false,
    "logging_steps": 10,
    "logging_nan_inf_filter": true,
    "save_strategy": "steps",
    "save_steps": 100,
    "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": null,
    "jit_mode_eval": false,
    "bf16": false,
    "fp16": true,
    "fp16_opt_level": "O1",
    "half_precision_backend": "auto",
    "bf16_full_eval": false,
    "fp16_full_eval": false,
    "tf32": null,
    "local_rank": 0,
    "ddp_backend": null,
    "tpu_num_cores": null,
    "tpu_metrics_debug": false,
    "debug": [],
    "dataloader_drop_last": false,
    "eval_steps": 50,
    "dataloader_num_workers": 0,
    "dataloader_prefetch_factor": null,
    "past_index": -1,
    "run_name": null,
    "disable_tqdm": false,
    "remove_unused_columns": true,
    "label_names": null,
    "load_best_model_at_end": true,
    "metric_for_best_model": "loss",
    "greater_is_better": false,
    "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": null,
    "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,
    "deepspeed": null,
    "label_smoothing_factor": 0.0,
    "optim": "adamw_torch_fused",
    "optim_args": null,
    "adafactor": false,
    "group_by_length": true,
    "length_column_name": "length",
    "report_to": [],
    "project": "huggingface",
    "trackio_space_id": "trackio",
    "ddp_find_unused_parameters": false,
    "ddp_bucket_cap_mb": null,
    "ddp_broadcast_buffers": null,
    "dataloader_pin_memory": true,
    "dataloader_persistent_workers": false,
    "skip_memory_metrics": true,
    "use_legacy_prediction_loop": false,
    "push_to_hub": false,
    "resume_from_checkpoint": null,
    "hub_model_id": null,
    "hub_strategy": "every_save",
    "hub_token": "<HUB_TOKEN>",
    "hub_private_repo": null,
    "hub_always_push": false,
    "hub_revision": null,
    "gradient_checkpointing": true,
    "gradient_checkpointing_kwargs": null,
    "include_inputs_for_metrics": false,
    "include_for_metrics": [],
    "eval_do_concat_batches": true,
    "fp16_backend": "auto",
    "push_to_hub_model_id": null,
    "push_to_hub_organization": null,
    "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
    "mp_parameters": "",
    "auto_find_batch_size": false,
    "full_determinism": false,
    "torchdynamo": null,
    "ray_scope": "last",
    "ddp_timeout": 1800,
    "torch_compile": false,
    "torch_compile_backend": null,
    "torch_compile_mode": null,
    "include_tokens_per_second": false,
    "include_num_input_tokens_seen": "no",
    "neftune_noise_alpha": null,
    "optim_target_modules": null,
    "batch_eval_metrics": false,
    "eval_on_start": false,
    "use_liger_kernel": false,
    "liger_kernel_config": null,
    "eval_use_gather_object": false,
    "average_tokens_across_devices": true
  }
}