en_bn_summarize_v1

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

• Loss: 2.9948
• Rouge1: 0.0
• Rouge2: 0.0
• Rougel: 0.0
• Rougelsum: 0.0
• Gen Len: 18.323

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: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 5000
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
27.0008	1.0	615	19.6292	0.0	0.0	0.0	0.0	5.5342
22.3588	2.0	1230	12.9038	0.0	0.0	0.0	0.0	6.6335
16.0103	3.0	1845	4.3199	0.0	0.0	0.0	0.0	18.3851
8.0443	4.0	2460	3.6049	0.0	0.0	0.0	0.0	12.6025
4.7815	5.0	3075	3.3718	0.0	0.0	0.0	0.0	16.5839
4.5186	6.0	3690	3.2383	0.0	0.0	0.0	0.0	17.3602
4.345	7.0	4305	3.1175	0.0	0.0	0.0	0.0	18.2236
4.1762	8.0	4920	3.0548	0.0	0.0	0.0	0.0	18.0373
3.9419	9.0	5535	3.0028	0.0	0.0	0.0	0.0	18.354
3.8654	10.0	6150	2.9948	0.0	0.0	0.0	0.0	18.323

Framework versions

• Transformers 4.33.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3