| { | |
| "use_picard": false, | |
| "launch_picard": false, | |
| "picard_host": "localhost", | |
| "picard_port": 9090, | |
| "picard_mode": "parse_with_guards", | |
| "picard_schedule": "incremental", | |
| "picard_max_tokens_to_check": 2, | |
| "model_name_or_path": "t5-3b", | |
| "config_name": null, | |
| "tokenizer_name": null, | |
| "cache_dir": "/rds/user/hpcsapa1/hpc-work/transformers_cache", | |
| "use_fast_tokenizer": true, | |
| "model_revision": "main", | |
| "use_auth_token": false, | |
| "dataset": "spider", | |
| "dataset_paths": { | |
| "spider": "./seq2seq/datasets/spider", | |
| "cosql": "./seq2seq/datasets/cosql" | |
| }, | |
| "predict_and_eval": true, | |
| "metric_config": "test_suite", | |
| "metric_paths": { | |
| "spider": "./seq2seq/metrics/spider", | |
| "cosql": "./seq2seq/metrics/cosql" | |
| }, | |
| "test_suite_db_dir": "./third_party/test_suite/database", | |
| "data_config_file": null, | |
| "test_sections": null, | |
| "data_dir": "../data/spider_augs", | |
| "file_prefix": null, | |
| "overwrite_cache": false, | |
| "preprocessing_num_workers": null, | |
| "max_source_length": 512, | |
| "max_target_length": 512, | |
| "val_max_target_length": 512, | |
| "val_max_time": null, | |
| "max_train_samples": null, | |
| "max_val_samples": null, | |
| "num_beams": 1, | |
| "num_beam_groups": 1, | |
| "diversity_penalty": null, | |
| "ignore_pad_token_for_loss": true, | |
| "source_prefix": "", | |
| "schema_serialization_type": "peteshaw", | |
| "schema_serialization_randomized": false, | |
| "schema_serialization_with_db_id": true, | |
| "schema_serialization_with_db_content": true, | |
| "normalize_query": true, | |
| "target_with_db_id": true, | |
| "output_dir": "../models/t5-picard", | |
| "overwrite_output_dir": false, | |
| "do_train": true, | |
| "do_eval": true, | |
| "do_predict": false, | |
| "evaluation_strategy": "steps", | |
| "prediction_loss_only": false, | |
| "per_device_train_batch_size": 5, | |
| "per_device_eval_batch_size": 5, | |
| "per_gpu_train_batch_size": "None", | |
| "per_gpu_eval_batch_size": "None", | |
| "gradient_accumulation_steps": 40, | |
| "eval_accumulation_steps": "None", | |
| "eval_delay": 0, | |
| "learning_rate": 0.0001, | |
| "weight_decay": 0.0, | |
| "adam_beta1": 0.9, | |
| "adam_beta2": 0.999, | |
| "adam_epsilon": 1e-08, | |
| "max_grad_norm": 1.0, | |
| "num_train_epochs": 100, | |
| "max_steps": -1, | |
| "lr_scheduler_type": "constant", | |
| "warmup_ratio": 0.0, | |
| "warmup_steps": 0, | |
| "log_level": -1, | |
| "log_level_replica": -1, | |
| "log_on_each_node": true, | |
| "logging_dir": "../models/t5-picard/runs/Feb12_15-38-39_gpu-q-39", | |
| "logging_strategy": "steps", | |
| "logging_first_step": true, | |
| "logging_steps": 4, | |
| "logging_nan_inf_filter": true, | |
| "save_strategy": "steps", | |
| "save_steps": 64, | |
| "save_total_limit": 2, | |
| "save_on_each_node": false, | |
| "no_cuda": false, | |
| "seed": 1, | |
| "data_seed": "None", | |
| "jit_mode_eval": false, | |
| "use_ipex": false, | |
| "bf16": false, | |
| "fp16": false, | |
| "fp16_opt_level": "O1", | |
| "half_precision_backend": "auto", | |
| "bf16_full_eval": false, | |
| "fp16_full_eval": false, | |
| "tf32": "None", | |
| "xpu_backend": "None", | |
| "tpu_num_cores": "None", | |
| "tpu_metrics_debug": false, | |
| "debug": "[]", | |
| "dataloader_drop_last": false, | |
| "eval_steps": 64, | |
| "dataloader_num_workers": 0, | |
| "past_index": -1, | |
| "run_name": "t5-spider-augs", | |
| "disable_tqdm": false, | |
| "remove_unused_columns": true, | |
| "label_names": "None", | |
| "load_best_model_at_end": true, | |
| "metric_for_best_model": "exec", | |
| "greater_is_better": true, | |
| "ignore_data_skip": false, | |
| "sharded_ddp": "[]", | |
| "fsdp": "[]", | |
| "fsdp_min_num_params": 0, | |
| "fsdp_transformer_layer_cls_to_wrap": "None", | |
| "deepspeed": "None", | |
| "label_smoothing_factor": 0.0, | |
| "optim": "adafactor", | |
| "adafactor": true, | |
| "group_by_length": true, | |
| "length_column_name": "length", | |
| "report_to": "['wandb']", | |
| "ddp_find_unused_parameters": "None", | |
| "ddp_bucket_cap_mb": "None", | |
| "dataloader_pin_memory": true, | |
| "skip_memory_metrics": true, | |
| "use_legacy_prediction_loop": false, | |
| "push_to_hub": false, | |
| "resume_from_checkpoint": "None", | |
| "hub_model_id": "None", | |
| "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": "None", | |
| "push_to_hub_organization": "None", | |
| "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>", | |
| "_n_gpu": 1, | |
| "mp_parameters": "", | |
| "auto_find_batch_size": false, | |
| "full_determinism": false, | |
| "torchdynamo": "None", | |
| "ray_scope": "last", | |
| "sortish_sampler": false, | |
| "predict_with_generate": true, | |
| "generation_max_length": "None", | |
| "generation_num_beams": "None", | |
| "train_batch_size": 5, | |
| "eval_batch_size": 5 | |
| } |