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: 3.0349
• Rouge1: 17.1191
• Rouge2: 8.4119
• Rougel: 16.6388
• Rougelsum: 16.6017

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
7.3401	1.0	1209	3.3465	14.1778	6.284	13.8905	13.8872
3.9195	2.0	2418	3.1859	15.9786	8.1666	15.3933	15.3693
3.5975	3.0	3627	3.0945	17.5518	9.134	16.9215	16.8899
3.4241	4.0	4836	3.0913	16.3875	7.6999	15.8311	15.8004
3.3252	5.0	6045	3.0588	16.6777	8.1639	16.1058	16.1357
3.2442	6.0	7254	3.0444	17.141	8.4204	16.6366	16.6896
3.2149	7.0	8463	3.0355	17.3266	8.7249	16.9438	16.9154
3.184	8.0	9672	3.0349	17.1191	8.4119	16.6388	16.6017

Framework versions

• Transformers 4.33.3
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3