pszemraj's picture
Training in progress, step 25
6cf1c59
raw
history blame
892 Bytes
{
"_name_or_path": "pszemraj/flan-t5-large-grammar-synthesis-v6",
"architectures": [
"T5ForConditionalGeneration"
],
"d_ff": 2816,
"d_kv": 64,
"d_model": 1024,
"decoder_start_token_id": 0,
"dense_act_fn": "gelu",
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "gelu",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"layer_norm_epsilon": 1e-06,
"max_length": 512,
"min_length": 8,
"model_type": "t5",
"n_positions": 512,
"no_repeat_ngram_size": 4,
"num_beams": 2,
"num_decoder_layers": 24,
"num_heads": 16,
"num_layers": 24,
"output_past": true,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.25.0.dev0",
"use_cache": true,
"vocab_size": 32128
}