longluu's picture
--per_device_train_batch_size 4 --learning_rate 3e-5 --num_train_epochs 2 --max_seq_length 512 --doc_stride 250 --max_answer_length 200
fc3204a verified
raw
history blame contribute delete
680 Bytes
{
"_name_or_path": "../models/COVID-QA/gatortrons/",
"architectures": [
"MegatronBertForQuestionAnswering"
],
"attention_probs_dropout_prob": 0.1,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "megatron-bert",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"tokenizer_type": "BertWordPieceCase",
"torch_dtype": "float32",
"transformers_version": "4.37.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 50176
}