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: 3.0341
• Rouge1: 16.9947
• Rouge2: 8.1917
• Rougel: 16.5751
• Rougelsum: 16.6864

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
7.0901	1.0	1209	3.2969	13.9062	5.7456	13.4148	13.409
3.9124	2.0	2418	3.1529	16.6418	8.4375	15.85	15.9119
3.5991	3.0	3627	3.1181	18.7571	9.9189	18.0758	18.1545
3.4197	4.0	4836	3.0619	17.8796	8.8002	17.2547	17.3509
3.3215	5.0	6045	3.0706	16.9356	7.5098	16.2641	16.468
3.2448	6.0	7254	3.0455	16.7471	7.7886	16.345	16.4044
3.2033	7.0	8463	3.0349	17.0401	8.3424	16.6741	16.7633
3.177	8.0	9672	3.0341	16.9947	8.1917	16.5751	16.6864

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1
• Datasets 2.12.0
• Tokenizers 0.13.2