CyrexPro's picture
Training in progress, step 500
82a11a1 verified
{
"_name_or_path": "allenai/led-base-16384",
"activation_dropout": 0.0,
"activation_function": "gelu",
"architectures": [
"LEDForConditionalGeneration"
],
"attention_dropout": 0.0,
"attention_window": [
1024,
1024,
1024,
1024,
1024,
1024
],
"bos_token_id": 0,
"classif_dropout": 0.0,
"classifier_dropout": 0.0,
"d_model": 768,
"decoder_attention_heads": 12,
"decoder_ffn_dim": 3072,
"decoder_layerdrop": 0.0,
"decoder_layers": 6,
"decoder_start_token_id": 2,
"dropout": 0.1,
"encoder_attention_heads": 12,
"encoder_ffn_dim": 3072,
"encoder_layerdrop": 0.0,
"encoder_layers": 6,
"eos_token_id": 2,
"gradient_checkpointing": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2"
},
"init_std": 0.02,
"is_encoder_decoder": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2
},
"max_decoder_position_embeddings": 1024,
"max_encoder_position_embeddings": 16384,
"model_type": "led",
"num_hidden_layers": 6,
"pad_token_id": 1,
"torch_dtype": "float32",
"transformers_version": "4.40.0",
"use_cache": true,
"vocab_size": 50265
}