mt5-base_Nepali_News_Summarization_0

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: 1.3685
• Rouge-1 R: 0.3321
• Rouge-1 P: 0.3218
• Rouge-1 F: 0.3186
• Rouge-2 R: 0.1761
• Rouge-2 P: 0.1703
• Rouge-2 F: 0.1677
• Rouge-l R: 0.3234
• Rouge-l P: 0.3133
• Rouge-l F: 0.3102
• Gen Len: 15.7133

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: 0.0005
• train_batch_size: 5
• eval_batch_size: 5
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge-1 R	Rouge-1 P	Rouge-1 F	Rouge-2 R	Rouge-2 P	Rouge-2 F	Rouge-l R	Rouge-l P	Rouge-l F	Gen Len
1.8844	1.0	10191	1.4867	0.31	0.3133	0.3024	0.1576	0.1605	0.1531	0.3015	0.3048	0.2942	15.2667
1.7381	2.0	20382	1.4401	0.3203	0.3104	0.3068	0.1675	0.162	0.1592	0.3121	0.3026	0.299	15.699
1.6401	3.0	30573	1.3685	0.3321	0.3218	0.3186	0.1761	0.1703	0.1677	0.3234	0.3133	0.3102	15.7133

Framework versions

• PEFT 0.11.1
• Transformers 4.42.3
• Pytorch 2.1.2
• Datasets 2.20.0
• Tokenizers 0.19.1