| {"adam_epsilon": 1e-06, "best_model_dir": "./best2", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "adafactor_eps": [1e-30, 0.001], "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_beta1": null, "adafactor_scale_parameter": true, "adafactor_relative_step": true, "adafactor_warmup_init": true, "eval_batch_size": 8, "evaluate_during_training": false, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 2, "learning_rate": 0.0005, "local_rank": -1, "logging_steps": 100, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 509, "model_name": "./compact_model", "model_type": "roberta", "multiprocessing_chunksize": 500, "n_gpu": 8, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 1323.0, "optimizer": "AdamW", "output_dir": "outputs/", "overwrite_output_dir": true, "process_count": 78, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "quantized_model": false, "reprocess_input_data": false, "save_best_model": true, "save_eval_checkpoints": false, "save_model_every_epoch": false, "save_optimizer_and_scheduler": true, "save_steps": 200000.0, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_type": null, "tokenizer_name": "./compact_model", "train_batch_size": 64, "train_custom_parameters_only": false, "use_cached_eval_features": true, "use_early_stopping": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": false, "wandb_kwargs": {"name": "RoBERTa-SMALL attempt1"}, "wandb_project": "ASRS - RoBERTa-SMALL", "warmup_ratio": 0.06, "warmup_steps": 60000, "weight_decay": 0.01, "model_class": "LanguageModelingModel", "block_size": 509, "config_name": null, "dataset_class": null, "dataset_type": "simple", "discriminator_config": {}, "discriminator_loss_weight": 50.0, "generator_config": {}, "max_steps": 1000000.0, "min_frequency": 2, "mlm": true, "mlm_probability": 0.15, "sliding_window": true, "special_tokens": ["<s>", "<pad>", "</s>", "<unk>", "<mask>"], "stride": 0.8, "tie_generator_and_discriminator_embeddings": true, "vocab_size": 32005, "clean_text": true, "handle_chinese_chars": true, "special_tokens_list": [], "strip_accents": true} |