longsec_withno_cut / config.json
fgiuhsdfkjhfv's picture
Training in progress, epoch 0
df4fd9e
raw
history blame
1.44 kB
{
"_name_or_path": "pszemraj/led-large-book-summary",
"_num_labels": 3,
"activation_dropout": 0.0,
"activation_function": "gelu",
"architectures": [
"LEDForConditionalGeneration"
],
"attention_dropout": 0.0,
"attention_window": [
1024,
1024,
1024,
1024,
1024,
1024,
1024,
1024,
1024,
1024,
1024,
1024
],
"bos_token_id": 0,
"classif_dropout": 0.0,
"classifier_dropout": 0.0,
"d_model": 1024,
"decoder_attention_heads": 16,
"decoder_ffn_dim": 4096,
"decoder_layerdrop": 0.0,
"decoder_layers": 12,
"decoder_start_token_id": 2,
"dropout": 0.1,
"early_stopping": true,
"encoder_attention_heads": 16,
"encoder_ffn_dim": 4096,
"encoder_layerdrop": 0.0,
"encoder_layers": 12,
"eos_token_id": 2,
"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
},
"length_penalty": 0.8,
"max_decoder_position_embeddings": 1024,
"max_encoder_position_embeddings": 16384,
"max_length": 1024,
"min_length": 8,
"model_type": "led",
"no_repeat_ngram_size": 3,
"num_beams": 4,
"num_hidden_layers": 12,
"output_past": false,
"pad_token_id": 1,
"prefix": " ",
"repetition_penalty": 3.5,
"torch_dtype": "float32",
"transformers_version": "4.29.2",
"use_cache": true,
"vocab_size": 50265
}