{
  "base_model": "Qwen/Qwen2.5-3B-Instruct",
  "lora_config": {
    "peft_type": "LORA",
    "auto_mapping": null,
    "base_model_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
    "revision": null,
    "task_type": "CAUSAL_LM",
    "inference_mode": false,
    "r": 16,
    "target_modules": [
      "q_proj",
      "gate_proj",
      "v_proj",
      "o_proj",
      "k_proj",
      "down_proj",
      "up_proj"
    ],
    "lora_alpha": 32,
    "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",
    "loftq_config": {},
    "use_dora": false,
    "layer_replication": null
  },
  "training_args": {
    "output_dir": "/data/checkpoints",
    "overwrite_output_dir": false,
    "do_train": false,
    "do_eval": true,
    "do_predict": false,
    "evaluation_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": 8,
    "eval_accumulation_steps": null,
    "eval_delay": 0,
    "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": "cosine",
    "lr_scheduler_kwargs": {},
    "warmup_ratio": 0.0,
    "warmup_steps": 100,
    "log_level": "passive",
    "log_level_replica": "warning",
    "log_on_each_node": true,
    "logging_dir": "/data/checkpoints/runs/Nov01_14-16-29_modal",
    "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,
    "no_cuda": false,
    "use_cpu": false,
    "use_mps_device": false,
    "seed": 42,
    "data_seed": null,
    "jit_mode_eval": false,
    "use_ipex": 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": "/data/checkpoints",
    "disable_tqdm": false,
    "remove_unused_columns": true,
    "label_names": null,
    "load_best_model_at_end": true,
    "metric_for_best_model": "eval_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,
      "gradient_accumulation_kwargs": null
    },
    "deepspeed": null,
    "label_smoothing_factor": 0.0,
    "optim": "adamw_torch",
    "optim_args": null,
    "adafactor": false,
    "group_by_length": false,
    "length_column_name": "length",
    "report_to": [],
    "ddp_find_unused_parameters": null,
    "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": false,
    "hub_always_push": false,
    "gradient_checkpointing": false,
    "gradient_checkpointing_kwargs": null,
    "include_inputs_for_metrics": false,
    "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,
    "dispatch_batches": null,
    "split_batches": null,
    "include_tokens_per_second": false,
    "include_num_input_tokens_seen": false,
    "neftune_noise_alpha": null,
    "optim_target_modules": null
  },
  "used_chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
}