bic-fil-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: 0.4212
• Validation Loss: 2.6637
• 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
6.4138	5.0392	0
4.7105	3.8096	1
3.7780	3.2907	2
3.2925	3.0002	3
2.9407	2.8001	4
2.6372	2.6142	5
2.3310	2.4768	6
2.1052	2.2808	7
1.8424	2.2372	8
1.6298	2.2036	9
1.4416	2.1891	10
1.2660	2.1835	11
1.1067	2.2480	12
0.9585	2.2821	13
0.8516	2.3494	14
0.7260	2.4127	15
0.6270	2.5566	16
0.5473	2.5503	17
0.4718	2.6471	18
0.4212	2.6637	19

Framework versions

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