16_combo_2109_v2

作者 dsmsb · 下载 0 · 点赞 0 · 更新 2023-11-04

generated_from_trainer

16_combo_webscrap_2109_v1_addgptdf

This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 467 0.8510 0.7806
1.534 2.0 934 0.5037 0.8696
0.7131 3.0 1401 0.3481 0.9104
0.4879 4.0 1868 0.2717 0.9244
0.3665 5.0 2335 0.2324 0.9360
0.2948 6.0 2802 0.1949 0.9451
0.24 7.0 3269 0.1550 0.9566
0.1961 8.0 3736 0.1495 0.9568

Framework versions