Li Yu
Training in progress, step 500
daf4807
{
"_name_or_path": "facebook/bart-large-mnli",
"_num_labels": 3,
"activation_dropout": 0.0,
"activation_function": "gelu",
"add_final_layer_norm": false,
"architectures": [
"BartForSequenceClassification"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"classif_dropout": 0.0,
"classifier_dropout": 0.0,
"d_model": 1024,
"decoder_attention_heads": 16,
"decoder_ffn_dim": 4096,
"decoder_layerdrop": 0.0,
"decoder_layers": 12,
"decoder_start_token_id": 2,
"dropout": 0.1,
"encoder_attention_heads": 16,
"encoder_ffn_dim": 4096,
"encoder_layerdrop": 0.0,
"encoder_layers": 12,
"eos_token_id": 2,
"forced_eos_token_id": 2,
"gradient_checkpointing": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2",
"3": "LABEL_3",
"4": "LABEL_4",
"5": "LABEL_5"
},
"init_std": 0.02,
"is_encoder_decoder": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2,
"LABEL_3": 3,
"LABEL_4": 4,
"LABEL_5": 5
},
"max_position_embeddings": 1024,
"model_type": "bart",
"normalize_before": false,
"num_hidden_layers": 12,
"output_past": false,
"pad_token_id": 1,
"problem_type": "single_label_classification",
"scale_embedding": false,
"torch_dtype": "float32",
"transformers_version": "4.20.1",
"use_cache": true,
"vocab_size": 50265
}