Files
2026-07-13 13:18:33 +08:00

20 lines
336 B
JSON

{
"train_batch_size": 1,
"gradient_accumulation_steps": 1,
"steps_per_print": 1,
"optimizer": {
"type": "Adam",
"params": {
"lr": 0.00015,
"weight_decay": 1e-2
}
},
"fp16": {
"enabled": false,
"loss_scale": 0,
"loss_scale_window": 1000,
"hysteresis": 2,
"min_loss_scale": 1
}
}