training_args-1.json

{
    "adam_epsilon": 1e-08,
    "data_dir": "/content/data",
    "early_stop_callback": false,
    "en_ja_ratio": 4,
    "eval_batch_size": 32,
    "fp_16": false,
    "freeze_bert": true,
    "from_pretrained_bert": true,
    "gradient_accumulation_steps": 1,
    "learning_rate": 0.001,
    "lr_initial_epoch": 0,
    "lr_total_epochs": 4,
    "lr_warmup_epochs": 0.05,
    "max_cls_depth": 6,
    "max_grad_norm": 1.0,
    "max_input_length": 64,
    "model_name_or_path": "sonoisa/sentence-bert-base-ja-mean-tokens-v2",
    "n_gpu": 1,
    "num_train_epochs": 4,
    "seed": 42,
    "shuffle_buffer_size": 65536,
    "tokenizer_name_or_path": "sonoisa/sentence-bert-base-ja-mean-tokens-v2",
    "train_batch_size": 2560,
    "weight_decay": 0.0
}