fil-bic-mt5b

This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.2155
• Validation Loss: 2.4691
• Epoch: 19

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': 'AdamWeightDecay', 'learning_rate': 0.001, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
4.8782	3.0764	0
3.0550	2.4897	1
2.4361	2.1678	2
2.0424	1.9982	3
1.7454	1.8860	4
1.5089	1.8502	5
1.3137	1.8682	6
1.1487	1.8252	7
0.9793	1.8486	8
0.8428	1.8815	9
0.7107	1.9716	10
0.6015	2.0271	11
0.5106	2.1239	12
0.4392	2.2095	13
0.3786	2.2045	14
0.3315	2.2884	15
0.2882	2.3419	16
0.2587	2.4029	17
0.2354	2.4173	18
0.2155	2.4691	19

Framework versions

• Transformers 4.37.2
• TensorFlow 2.15.0
• Datasets 2.17.0
• Tokenizers 0.15.2