MSLars's picture
Training in progress, epoch 1
747183e verified
{
"_name_or_path": "LennartKeller/longformer-gottbert-base-8192-aw512",
"architectures": [
"LongformerForTokenClassification"
],
"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,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "O",
"1": "B-SUMM",
"2": "I-SUMM"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"B-SUMM": 1,
"I-SUMM": 2,
"O": 0
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 8194,
"model_type": "longformer",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"onnx_export": false,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"sep_token_id": 2,
"torch_dtype": "float32",
"transformers_version": "4.36.2",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 52009
}