Prophetnetbillsumtest1 / config.json
ruchita1010's picture
Training in progress, step 500
9400fbe verified
{
"_name_or_path": "microsoft/prophetnet-large-uncased",
"activation_dropout": 0.1,
"activation_function": "gelu",
"add_cross_attention": true,
"architectures": [
"ProphetNetForConditionalGeneration"
],
"attention_dropout": 0.1,
"bos_token_id": 102,
"decoder_ffn_dim": 4096,
"decoder_layerdrop": 0.0,
"decoder_max_position_embeddings": 514,
"decoder_start_token_id": 102,
"disable_ngram_loss": false,
"dropout": 0.1,
"early_stopping": true,
"encoder_ffn_dim": 4096,
"encoder_layerdrop": 0.0,
"encoder_max_position_embeddings": 513,
"eos_token_id": 102,
"eps": 0.0,
"hidden_size": 1024,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2"
},
"init_std": 0.02,
"is_encoder_decoder": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2
},
"length_penalty": 2.0,
"max_length": 142,
"max_position_embeddings": 512,
"model_type": "prophetnet",
"ngram": 2,
"no_repeat_ngram_size": 3,
"num_beams": 4,
"num_buckets": 32,
"num_decoder_attention_heads": 16,
"num_decoder_layers": 12,
"num_encoder_attention_heads": 16,
"num_encoder_layers": 12,
"output_past": false,
"pad_token_id": 0,
"prefix": " ",
"relative_max_distance": 128,
"task_specific_params": {
"summarization": {
"early_stopping": true,
"length_penalty": 2.0,
"no_repeat_ngram_size": 3,
"num_beams": 4
}
},
"torch_dtype": "float32",
"transformers_version": "4.38.2",
"use_cache": true,
"vocab_size": 30522
}