my_awesome_billsum_model

This model is a fine-tuned version of sorayutmild/mt5-thai-sum-finetuned-sanook-news-headlines on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: nan
• Rouge1: 0.108
• Rouge2: 0.0
• Rougel: 0.1082
• Rougelsum: 0.1096
• Gen Len: 16.6196

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	46	nan	0.108	0.0	0.1082	0.1096	16.6196
No log	2.0	92	nan	0.108	0.0	0.1082	0.1096	16.6196
No log	3.0	138	nan	0.108	0.0	0.1082	0.1096	16.6196
No log	4.0	184	nan	0.108	0.0	0.1082	0.1096	16.6196

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2