|
{ |
|
"activation_dropout": 0.1, |
|
"activation_function": "gelu", |
|
"architectures": [ |
|
"InformerForSequenceClassification" |
|
], |
|
"attention_dropout": 0.1, |
|
"attention_type": "prob", |
|
"cardinality": [ |
|
0 |
|
], |
|
"classifier_dropout": 0.2, |
|
"context_length": 300, |
|
"d_model": 768, |
|
"decoder_attention_heads": 12, |
|
"decoder_ffn_dim": 256, |
|
"decoder_layerdrop": 0.1, |
|
"decoder_layers": 8, |
|
"distil": false, |
|
"distribution_output": "student_t", |
|
"dropout": 0.2, |
|
"embedding_dimension": [ |
|
0 |
|
], |
|
"encoder_attention_heads": 12, |
|
"encoder_ffn_dim": 256, |
|
"encoder_layerdrop": 0.1, |
|
"encoder_layers": 8, |
|
"feature_size": 8, |
|
"fourier_pe": true, |
|
"has_labels": true, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1", |
|
"2": "LABEL_2", |
|
"3": "LABEL_3", |
|
"4": "LABEL_4", |
|
"5": "LABEL_5", |
|
"6": "LABEL_6", |
|
"7": "LABEL_7", |
|
"8": "LABEL_8", |
|
"9": "LABEL_9", |
|
"10": "LABEL_10", |
|
"11": "LABEL_11", |
|
"12": "LABEL_12", |
|
"13": "LABEL_13" |
|
}, |
|
"init_std": 0.02, |
|
"input_size": 2, |
|
"is_encoder_decoder": true, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1, |
|
"LABEL_10": 10, |
|
"LABEL_11": 11, |
|
"LABEL_12": 12, |
|
"LABEL_13": 13, |
|
"LABEL_2": 2, |
|
"LABEL_3": 3, |
|
"LABEL_4": 4, |
|
"LABEL_5": 5, |
|
"LABEL_6": 6, |
|
"LABEL_7": 7, |
|
"LABEL_8": 8, |
|
"LABEL_9": 9 |
|
}, |
|
"lags_sequence": [ |
|
0 |
|
], |
|
"loss": "nll", |
|
"mask": true, |
|
"mask_probability": 0.6, |
|
"model_type": "informer", |
|
"num_dynamic_real_features": 0, |
|
"num_parallel_samples": 100, |
|
"num_static_categorical_features": 0, |
|
"num_static_real_features": 0, |
|
"num_time_features": 2, |
|
"prediction_length": 0, |
|
"regression": false, |
|
"sampling_factor": 5, |
|
"scaling": null, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.34.0", |
|
"use_cache": true |
|
} |
|
|