args.json

{
    "_n_gpu": 1,
    "adafactor": false,
    "adam_beta1": 0.9,
    "adam_beta2": 0.999,
    "adam_epsilon": 1e-08,
    "auto_find_batch_size": false,
    "bf16": false,
    "bf16_full_eval": false,
    "calculate_qwk": true,
    "data_seed": 42,
    "dataloader_drop_last": false,
    "dataloader_num_workers": 0,
    "dataloader_pin_memory": true,
    "dataset_config": "filtered_rating",
    "dataset_name": "BramVanroy/hebban-reviews",
    "dataset_revision": "2.0.0",
    "ddp_bucket_cap_mb": null,
    "ddp_find_unused_parameters": null,
    "debug": [],
    "deepspeed": null,
    "disable_tqdm": false,
    "do_early_stopping": false,
    "do_eval": true,
    "do_optimize": false,
    "do_predict": true,
    "do_train": true,
    "early_stopping_patience": 1,
    "early_stopping_threshold": 0.0,
    "eval_accumulation_steps": null,
    "eval_delay": 0,
    "eval_steps": 500,
    "evaluation_strategy": "steps",
    "fp16": true,
    "fp16_backend": "auto",
    "fp16_full_eval": false,
    "fp16_opt_level": "O1",
    "fsdp": [],
    "fsdp_min_num_params": 0,
    "fsdp_transformer_layer_cls_to_wrap": null,
    "full_determinism": false,
    "gradient_accumulation_steps": 1,
    "gradient_checkpointing": false,
    "greater_is_better": true,
    "group_by_length": false,
    "half_precision_backend": "cuda_amp",
    "hub_model_id": null,
    "hub_private_repo": false,
    "hub_strategy": "every_save",
    "hub_token": null,
    "ignore_data_skip": false,
    "include_inputs_for_metrics": false,
    "jit_mode_eval": false,
    "label_names": null,
    "label_smoothing_factor": 0.0,
    "labelcolumn": "review_rating0",
    "labelnames": [
        "1",
        "2",
        "3",
        "4",
        "5"
    ],
    "learning_rate": 5e-05,
    "length_column_name": "length",
    "load_best_model_at_end": true,
    "local_rank": 0,
    "log_level": -1,
    "log_level_replica": -1,
    "log_on_each_node": true,
    "logging_dir": "trained/hebban-reviews5/robbert-v2-dutch-base/runs/Jul29_01-25-24_node3907.accelgor.os",
    "logging_first_step": false,
    "logging_nan_inf_filter": true,
    "logging_steps": 500,
    "logging_strategy": "steps",
    "lr_scheduler_type": "linear",
    "max_grad_norm": 1.0,
    "max_seq_length": null,
    "max_steps": 5001,
    "max_test_samples": null,
    "max_train_samples": null,
    "max_validation_samples": null,
    "metric_for_best_model": "qwk",
    "model_name_or_path": "pdelobelle/robbert-v2-dutch-base",
    "model_revision": "main",
    "mp_parameters": "",
    "n_trials": 8,
    "no_cuda": false,
    "num_train_epochs": 3.0,
    "optim": "adamw_hf",
    "output_dir": "trained/hebban-reviews5/robbert-v2-dutch-base",
    "overwrite_cache": false,
    "overwrite_output_dir": true,
    "past_index": -1,
    "per_device_eval_batch_size": 64,
    "per_device_train_batch_size": 64,
    "per_gpu_eval_batch_size": null,
    "per_gpu_train_batch_size": null,
    "prediction_loss_only": false,
    "push_to_hub": false,
    "push_to_hub_model_id": null,
    "push_to_hub_organization": null,
    "push_to_hub_token": null,
    "ray_scope": "all",
    "remove_unused_columns": true,
    "report_to": [
        "tensorboard"
    ],
    "resume_from_checkpoint": null,
    "run_name": "trained/hebban-reviews5/robbert-v2-dutch-base",
    "save_on_each_node": false,
    "save_steps": 500,
    "save_strategy": "steps",
    "save_total_limit": null,
    "scheduler_type": null,
    "seed": 42,
    "sharded_ddp": [],
    "skip_memory_metrics": true,
    "split_seed": 42,
    "testsplit_name": "test",
    "textcolumn": "review_text_without_quotes",
    "tf32": null,
    "torchdynamo": null,
    "tpu_metrics_debug": false,
    "tpu_num_cores": null,
    "trainsplit_name": "train",
    "use_class_weights": true,
    "use_ipex": false,
    "use_legacy_prediction_loop": false,
    "validation_size": 0.1,
    "validationsplit_name": "validation",
    "warmup_ratio": 0.0,
    "warmup_steps": 0,
    "weight_decay": 0.0,
    "xpu_backend": null
}