mt5-small-finetuned-amazon-en-es

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: 1.0471
• Rouge1: 35.9205
• Rouge2: 22.7367
• Rougel: 32.7559
• Rougelsum: 32.5835

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: 5.6e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
6.3604	1.0	97	3.7707	37.8594	24.1486	33.9059	34.3919
4.7306	2.0	194	2.9997	35.0984	22.3056	31.7269	32.1465
3.5847	3.0	291	2.1937	29.695	17.4061	26.5237	26.9075
2.9164	4.0	388	1.7267	31.2343	18.1163	28.5381	28.5461
2.6073	5.0	485	1.4625	30.7086	17.9701	28.4382	28.3002
2.3667	6.0	582	1.2163	33.4671	20.5523	30.5306	30.2693
2.2182	7.0	679	1.1063	34.406	21.7252	31.6548	31.4595
2.1638	8.0	776	1.0471	35.9205	22.7367	32.7559	32.5835

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2