JulianS's picture
Training in progress, step 20000
878a560
raw
history blame contribute delete
914 Bytes
{
"activation_dropout": 0.0,
"activation_function": "gelu",
"architectures": [
"CustomLED"
],
"attention_dropout": 0.0,
"attention_window": [
512,
512,
512,
512,
512,
512,
512,
512
],
"bos_token_id": 0,
"classifier_dropout": 0.0,
"d_model": 768,
"decoder_attention_heads": 8,
"decoder_ffn_dim": 3072,
"decoder_layerdrop": 0.0,
"decoder_layers": 8,
"decoder_start_token_id": 1024,
"dropout": 0.1,
"encoder_attention_heads": 8,
"encoder_ffn_dim": 3072,
"encoder_layerdrop": 0.0,
"encoder_layers": 8,
"eos_token_id": 1025,
"init_std": 0.02,
"is_encoder_decoder": true,
"max_decoder_position_embeddings": 2048,
"max_encoder_position_embeddings": 512,
"model_type": "led",
"num_hidden_layers": 8,
"pad_token_id": 1024,
"torch_dtype": "float32",
"transformers_version": "4.26.0",
"use_cache": true,
"vocab_size": 1026
}