AIYIYA/my_wr3

This model is a fine-tuned version of bert-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 1.1315
• Validation Loss: 1.1418
• Train Accuracy: 0.8158
• Epoch: 14

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:

• optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 90, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
3.0206	2.6776	0.2895	0
2.6896	2.4286	0.7105	1
2.4102	2.1955	0.6579	2
2.1850	1.9989	0.7368	3
1.9867	1.8181	0.6842	4
1.8059	1.6320	0.7368	5
1.5830	1.5359	0.8158	6
1.5184	1.4081	0.7895	7
1.4472	1.3072	0.8421	8
1.3197	1.2605	0.8158	9
1.2258	1.2182	0.8158	10
1.2182	1.1752	0.8158	11
1.1015	1.1583	0.8158	12
1.1387	1.1463	0.8158	13
1.1315	1.1418	0.8158	14

Framework versions

• Transformers 4.31.0
• TensorFlow 2.12.0
• Datasets 2.14.4
• Tokenizers 0.13.3