sst2 / config.json
ShengdingHu's picture
Training in progress, step 200
b81d89e
{
"_name_or_path": "/home/hushengding/plm_cache/bigbird-roberta-large",
"architectures": [
"BigBirdForMaskedLM"
],
"attention_probs_dropout_prob": 0.1,
"attention_type": "block_sparse",
"block_size": 64,
"bos_token_id": 1,
"classifier_dropout": null,
"dropout_rate": 0.0,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu_new",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 4096,
"model_type": "big_bird",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_random_blocks": 3,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"rescale_embeddings": false,
"sep_token_id": 66,
"torch_dtype": "float32",
"transformers_version": "4.18.0",
"type_vocab_size": 2,
"use_bias": true,
"use_cache": true,
"vocab_size": 50358
}