personachat-arabic / model_args.json
1
{"adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 1, "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, "eval_batch_size": 8, "evaluate_during_training": false, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 4e-05, "local_rank": -1, "logging_steps": 50, "manual_seed": 42, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "akhooli/gpt2-small-arabic", "model_type": "gpt2", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "num_train_epochs": 50, "output_dir": "outputs/", "overwrite_output_dir": true, "process_count": 1, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": false, "save_model_every_epoch": false, "save_optimizer_and_scheduler": true, "save_steps": 5000, "silent": false, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 4, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_multiprocessing": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 5826, "weight_decay": 0, "model_class": "ConvAIModel", "do_sample": true, "lm_coef": 2.0, "max_history": 2, "max_length": 20, "mc_coef": 1.0, "min_length": 1, "num_candidates": 2, "personality_permutations": 1, "temperature": 0.7, "top_k": 0, "top_p": 0.9}