training_args.json

{
    "output_dir": "experiments/hf/baseline_distilbert_mse/checkpoint",
    "overwrite_output_dir": false,
    "do_train": false,
    "do_eval": false,
    "do_predict": false,
    "evaluation_strategy": "no",
    "prediction_loss_only": false,
    "per_device_train_batch_size": 20,
    "per_device_eval_batch_size": 8,
    "per_gpu_train_batch_size": null,
    "per_gpu_eval_batch_size": null,
    "gradient_accumulation_steps": 1,
    "eval_accumulation_steps": null,
    "eval_delay": 0,
    "learning_rate": 2e-05,
    "weight_decay": 0.0,
    "adam_beta1": 0.9,
    "adam_beta2": 0.999,
    "adam_epsilon": 1e-08,
    "max_grad_norm": 1.0,
    "num_train_epochs": 5,
    "max_steps": -1,
    "lr_scheduler_type": "linear",
    "warmup_ratio": 0.01,
    "warmup_steps": 0,
    "log_level": "passive",
    "log_level_replica": "warning",
    "log_on_each_node": true,
    "logging_dir": null,
    "logging_strategy": "steps",
    "logging_first_step": false,
    "logging_steps": 1000,
    "logging_nan_inf_filter": true,
    "save_strategy": "epoch",
    "save_steps": 500,
    "save_total_limit": null,
    "save_safetensors": false,
    "save_on_each_node": false,
    "no_cuda": false,
    "use_mps_device": false,
    "seed": 123,
    "data_seed": null,
    "jit_mode_eval": false,
    "use_ipex": false,
    "bf16": false,
    "fp16": true,
    "fp16_opt_level": "O1",
    "half_precision_backend": "cuda_amp",
    "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": true,
    "eval_steps": null,
    "dataloader_num_workers": 0,
    "past_index": -1,
    "run_name": null,
    "disable_tqdm": false,
    "remove_unused_columns": false,
    "label_names": null,
    "load_best_model_at_end": false,
    "metric_for_best_model": null,
    "greater_is_better": null,
    "ignore_data_skip": false,
    "sharded_ddp": [],
    "fsdp": [],
    "fsdp_min_num_params": 0,
    "fsdp_config": {
        "fsdp_min_num_params": 0,
        "xla": false,
        "xla_fsdp_grad_ckpt": false
    },
    "fsdp_transformer_layer_cls_to_wrap": null,
    "deepspeed": null,
    "label_smoothing_factor": 0.0,
    "optim": "adamw_hf",
    "optim_args": null,
    "adafactor": false,
    "group_by_length": false,
    "length_column_name": "length",
    "report_to": [
        "tensorboard"
    ],
    "ddp_find_unused_parameters": false,
    "ddp_bucket_cap_mb": null,
    "dataloader_pin_memory": true,
    "skip_memory_metrics": true,
    "use_legacy_prediction_loop": false,
    "push_to_hub": false,
    "resume_from_checkpoint": true,
    "hub_model_id": null,
    "hub_strategy": "every_save",
    "hub_token": "<HUB_TOKEN>",
    "hub_private_repo": false,
    "gradient_checkpointing": false,
    "include_inputs_for_metrics": false,
    "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,
    "xpu_backend": null,
    "training_loss": "kldiv_mse_margin_with_weights",
    "l0d": 0.02,
    "l0q": 0.01,
    "T_d": 30000,
    "T_q": 30000,
    "top_d": -1,
    "top_q": -1,
    "lexical_type": "none"
}