amrdemo / model_stog /model_parse_xfm_bart_large.json
koptelovmax's picture
Add application file
b27de9c
raw
history blame
1.68 kB
{ "gen_args" :
{
"model_name_or_path" : "facebook/bart-large",
"corpus_dir" : "data/tdata_xfm/",
"train_fn" : "train.txt.nowiki",
"eval_fn" : "dev.txt.nowiki",
"custom_save_checkpoint" : true,
"save_tokenizer" : false,
"save_at_end" : false,
"first_eval_epoch" : 1,
"eval_batch_size" : 32,
"eval_num_beams" : 1,
"max_in_len" : 1024,
"max_out_len" : 1024,
"max_train_sent_len" : 100,
"max_train_graph_len" : 512
},
"model_args":
{
"no_repeat_ngram_size" : 0
},
"hf_args" :
{
"output_dir" : "data/model_parse_xfm",
"save_strategy" : "epoch",
"evaluation_strategy" : "epoch",
"fp16" : true,
"group_by_length" : true,
"do_train" : true,
"do_eval" : true,
"save_total_limit" : 1,
"logging_steps" : 300,
"num_train_epochs" : 16,
"per_device_train_batch_size" : 8,
"gradient_accumulation_steps" : 4,
"weight_decay" : 0.004,
"learning_rate" : 5e-5,
"max_grad_norm" : 1.0,
"warmup_steps" : 5200,
"seed" : 42
}
}