pszemraj's picture
update ckpt with 6ish epochs of training with 1024 TOKENS as max output
9996867
raw
history blame
1.14 kB
{
"_name_or_path": "pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP4",
"architectures": [
"LongT5ForConditionalGeneration"
],
"d_ff": 2816,
"d_kv": 64,
"d_model": 1024,
"decoder_start_token_id": 0,
"dense_act_fn": "gelu_new",
"dropout_rate": 0.1,
"early_stopping": true,
"encoder_attention_type": "transient-global",
"encoder_no_repeat_ngram_size": 4,
"eos_token_id": 1,
"feed_forward_proj": "gated-gelu",
"global_block_size": 16,
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"layer_norm_epsilon": 1e-06,
"length_penalty": 0.8,
"local_radius": 127,
"max_length": 512,
"min_length": 8,
"model_type": "longt5",
"n_positions": 4096,
"no_repeat_ngram_size": 3,
"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,
"repetition_penalty": 3.5,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.20.1",
"use_cache": false,
"vocab_size": 32100
}