DocumentRegressionTask.ConfigΒΆ
Component: DocumentRegressionTask
-
class
DocumentRegressionTask.
Config
[source] Bases:
NewTask.Config
All Attributes (including base classes)
- data: Data.Config = Data.Config()
- trainer: TaskTrainer.Config = TaskTrainer.Config()
- model: DocRegressionModel.Config = DocRegressionModel.Config()
- metric_reporter: RegressionMetricReporter.Config = RegressionMetricReporter.Config()
- Subclasses
BertPairRegressionTask.Config
Default JSON
{
"data": {
"Data": {
"source": {
"TSVDataSource": {
"column_mapping": {},
"train_filename": null,
"test_filename": null,
"eval_filename": null,
"field_names": null,
"delimiter": "\t",
"quoted": false,
"drop_incomplete_rows": false
}
},
"batcher": {
"PoolingBatcher": {
"train_batch_size": 16,
"eval_batch_size": 16,
"test_batch_size": 16,
"pool_num_batches": 10000,
"num_shuffled_pools": 1
}
},
"sort_key": null,
"in_memory": true
}
},
"trainer": {
"TaskTrainer": {
"epochs": 10,
"early_stop_after": 0,
"max_clip_norm": null,
"report_train_metrics": true,
"target_time_limit_seconds": null,
"do_eval": true,
"load_best_model_after_train": true,
"num_samples_to_log_progress": 1000,
"num_accumulated_batches": 1,
"num_batches_per_epoch": null,
"optimizer": {
"Adam": {
"lr": 0.001,
"weight_decay": 1e-05,
"eps": 1e-08
}
},
"scheduler": null,
"sparsifier": null,
"fp16_args": {
"FP16OptimizerFairseq": {
"init_loss_scale": 128,
"scale_window": null,
"scale_tolerance": 0.0,
"threshold_loss_scale": null,
"min_loss_scale": 0.0001
}
}
}
},
"model": {
"inputs": {
"tokens": {
"is_input": true,
"column": "text",
"tokenizer": {
"Tokenizer": {
"split_regex": "\\s+",
"lowercase": true
}
},
"add_bos_token": false,
"add_eos_token": false,
"use_eos_token_for_bos": false,
"max_seq_len": null,
"vocab": {
"build_from_data": true,
"size_from_data": 0,
"vocab_files": []
},
"vocab_file_delimiter": " "
},
"dense": null,
"labels": {
"is_input": false,
"column": "label",
"rescale_range": null
}
},
"embedding": {
"load_path": null,
"save_path": null,
"freeze": false,
"shared_module_key": null,
"embed_dim": 100,
"embedding_init_strategy": "random",
"embedding_init_range": null,
"export_input_names": [
"tokens_vals"
],
"pretrained_embeddings_path": "",
"vocab_file": "",
"vocab_size": 0,
"vocab_from_train_data": true,
"vocab_from_all_data": false,
"vocab_from_pretrained_embeddings": false,
"lowercase_tokens": true,
"min_freq": 1,
"mlp_layer_dims": [],
"padding_idx": null,
"cpu_only": false,
"skip_header": true,
"delimiter": " "
},
"representation": {
"BiLSTMDocAttention": {
"load_path": null,
"save_path": null,
"freeze": false,
"shared_module_key": null,
"dropout": 0.4,
"lstm": {
"load_path": null,
"save_path": null,
"freeze": false,
"shared_module_key": null,
"dropout": 0.4,
"lstm_dim": 32,
"num_layers": 1,
"bidirectional": true,
"pack_sequence": true
},
"pooling": {
"SelfAttention": {
"attn_dimension": 64,
"dropout": 0.4
}
},
"mlp_decoder": null
}
},
"decoder": {
"load_path": null,
"save_path": null,
"freeze": false,
"shared_module_key": null,
"hidden_dims": [],
"out_dim": null,
"layer_norm": false,
"dropout": 0.0,
"activation": "relu"
},
"output_layer": {
"load_path": null,
"save_path": null,
"freeze": false,
"shared_module_key": null,
"loss": {},
"squash_to_unit_range": false
}
},
"metric_reporter": {
"output_path": "/tmp/test_out.txt",
"pep_format": false
}
}