Model card
Used in project https://github.com/L0ckR/LCT_hackaton
For ЛЦТ Хакатон
This model trained by transfomers Trainer using this params:
learning_rate=2e-5,
per_device_train_batch_size=3,
per_device_eval_batch_size=3,
num_train_epochs=50,
weight_decay=0.01,
eval_strategy="epoch",
save_strategy="epoch",
load_best_model_at_end=True,
lr_scheduler_type="linear",
warmup_ratio=0.1,
metric_for_best_model="f1",
greater_is_better=True
- Downloads last month
- -
Model tree for lockR/xlm-roberta-finance-multi-label-classification
Base model
FacebookAI/xlm-roberta-base