Longformer_v5 / config.json
brad1141's picture
Training in progress, epoch 0
8a57fed
raw
history blame
1.32 kB
{
"_name_or_path": "allenai/longformer-base-4096",
"architectures": [
"LongformerForTokenClassification"
],
"attention_mode": "longformer",
"attention_probs_dropout_prob": 0.1,
"attention_window": [
512,
512,
512,
512,
512,
512,
512,
512,
512,
512,
512,
512
],
"bos_token_id": 0,
"classifier_dropout": null,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "Lead",
"1": "Position",
"2": "Evidence",
"3": "Claim",
"4": "Concluding Statement",
"5": "Counterclaim",
"6": "Rebuttal"
},
"ignore_attention_mask": false,
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"Claim": "3",
"Concluding Statement": "4",
"Counterclaim": "5",
"Evidence": "2",
"Lead": "0",
"Position": "1",
"Rebuttal": "6"
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 4098,
"model_type": "longformer",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"sep_token_id": 2,
"torch_dtype": "float32",
"transformers_version": "4.18.0",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 50265
}