mt5_base_TH_wiki

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

• Loss: nan
• Rouge2 Precision: 0.0021
• Rouge2 Recall: 0.0009
• Rouge2 Fmeasure: 0.0013

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:

• learning_rate: 5e-05
• train_batch_size: 50
• eval_batch_size: 16
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge2 Precision	Rouge2 Recall	Rouge2 Fmeasure
0.0	1.0	1296	nan	0.0021	0.0009	0.0013
0.0	2.0	2592	nan	0.0021	0.0009	0.0013
0.0	3.0	3888	nan	0.0021	0.0009	0.0013
0.0	4.0	5184	nan	0.0021	0.0009	0.0013
0.0	5.0	6480	nan	0.0021	0.0009	0.0013
0.0	6.0	7776	nan	0.0021	0.0009	0.0013
0.0	7.0	9072	nan	0.0021	0.0009	0.0013
0.0	8.0	10368	nan	0.0021	0.0009	0.0013
0.0	9.0	11664	nan	0.0021	0.0009	0.0013
0.0	10.0	12960	nan	0.0021	0.0009	0.0013
0.0	11.0	14256	nan	0.0021	0.0009	0.0013
0.0	12.0	15552	nan	0.0021	0.0009	0.0013
0.0	13.0	16848	nan	0.0021	0.0009	0.0013
0.0	14.0	18144	nan	0.0021	0.0009	0.0013
0.0	15.0	19440	nan	0.0021	0.0009	0.0013

Framework versions

• Transformers 4.46.1
• Pytorch 2.2.2
• Datasets 2.16.1
• Tokenizers 0.20.1