jeba-en / finetune_config.json
munod's picture
Update jeba-en adapter, choice head (r=32), and per-language temperature (v0.2.0)
bac4de4
Raw
History Blame Contribute Delete
455 Bytes
{
"batch_size": 8,
"bf16": true,
"choice_init_std": 0.01,
"choice_rank": 32,
"data_path": "data/train_en.jsonl",
"epochs": 4,
"grad_accum": 4,
"gradient_checkpointing": true,
"learning_rate": 0.0001,
"lora_alpha": 32,
"lora_dropout": 0.05,
"lora_rank": 16,
"max_len": 512,
"max_records": null,
"model_id": "answerdotai/ModernBERT-large",
"out_dir": "checkpoints/en",
"seed": 42,
"use_4bit": false,
"val_split": 0.1
}