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: 3.0295
• Rouge1: 17.3239
• Rouge2: 8.3252
• Rougel: 16.9877
• Rougelsum: 16.9491

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
6.5794	1.0	1209	3.2991	14.2697	5.8959	13.9629	14.019
3.8873	2.0	2418	3.1327	16.4495	8.0475	16.0014	15.8747
3.5776	3.0	3627	3.0835	17.5812	8.9516	17.0727	17.0682
3.4167	4.0	4836	3.0604	16.8649	8.0349	16.3734	16.4011
3.3178	5.0	6045	3.0599	17.4474	8.2552	17.1422	17.1661
3.242	6.0	7254	3.0396	17.8629	8.9654	17.5915	17.5903
3.2067	7.0	8463	3.0341	17.6749	8.8579	17.3253	17.3087
3.179	8.0	9672	3.0295	17.3239	8.3252	16.9877	16.9491

Framework versions

• Transformers 4.19.2
• Pytorch 1.11.0+cu113
• Datasets 2.2.2
• Tokenizers 0.12.1