mt5-small-finetuned-amazon-en-es

This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.2197
• Rouge1: 23.7209
• Rouge2: 12.4611
• Rougel: 22.745
• Rougelsum: 22.8085

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
3.2981	1.0	589	3.2505	21.3203	11.2834	20.3564	20.3812
3.2017	2.0	1178	3.2563	21.5285	10.7337	20.7505	20.5952
3.1031	3.0	1767	3.2636	23.6856	12.5802	22.6568	22.5633
3.0303	4.0	2356	3.2242	23.4492	12.3205	22.3518	22.3521
2.9808	5.0	2945	3.2281	24.2603	12.6434	23.1527	23.2443
2.9519	6.0	3534	3.2146	24.5639	13.5995	23.8336	23.8418
2.9125	7.0	4123	3.2226	23.9892	12.9918	23.3101	23.3465
2.9058	8.0	4712	3.2197	23.7209	12.4611	22.745	22.8085

Framework versions

• Transformers 4.32.1
• Pytorch 2.0.0
• Datasets 2.14.4
• Tokenizers 0.13.3