Gladiator's picture
Training in progress, epoch 1
8d42b00
raw
history blame
1.44 kB
{
"_name_or_path": "funnel-transformer/xlarge",
"activation_dropout": 0.0,
"architectures": [
"FunnelForTokenClassification"
],
"attention_dropout": 0.1,
"attention_type": "relative_shift",
"block_repeats": [
1,
1,
1
],
"block_sizes": [
10,
10,
10
],
"d_head": 64,
"d_inner": 4096,
"d_model": 1024,
"hidden_act": "gelu_new",
"hidden_dropout": 0.1,
"id2label": {
"0": "O",
"1": "B-corporation",
"2": "I-corporation",
"3": "B-creative-work",
"4": "I-creative-work",
"5": "B-group",
"6": "I-group",
"7": "B-location",
"8": "I-location",
"9": "B-person",
"10": "I-person",
"11": "B-product",
"12": "I-product"
},
"initializer_range": 0.1,
"initializer_std": null,
"label2id": {
"B-corporation": 1,
"B-creative-work": 3,
"B-group": 5,
"B-location": 7,
"B-person": 9,
"B-product": 11,
"I-corporation": 2,
"I-creative-work": 4,
"I-group": 6,
"I-location": 8,
"I-person": 10,
"I-product": 12,
"O": 0
},
"layer_norm_eps": 1e-09,
"max_position_embeddings": 512,
"model_type": "funnel",
"n_head": 16,
"num_decoder_layers": 2,
"pool_q_only": true,
"pooling_type": "mean",
"rel_attn_type": "factorized",
"separate_cls": true,
"torch_dtype": "float32",
"transformers_version": "4.20.1",
"truncate_seq": true,
"type_vocab_size": 3,
"vocab_size": 30522
}