mt5-small-finetuned-amazon-en-es

This model is a fine-tuned version of google/mt5-small on the None dataset. It was created by following the huggingface tutorial.

It achieves the following results on the evaluation set:

• Loss: 3.0173
• Rouge1: 16.7977
• Rouge2: 8.6849
• Rougel: 16.4822
• Rougelsum: 16.4975

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
3.4693	1.0	1209	3.1215	17.5363	8.3875	17.0229	16.9653
3.4231	2.0	2418	3.0474	16.7927	8.3533	16.2748	16.2379
3.271	3.0	3627	3.0440	16.7233	7.9129	16.2385	16.1915
3.1885	4.0	4836	3.0264	16.3078	7.5751	15.844	15.889
3.1216	5.0	6045	3.0277	17.259	8.7504	16.8293	16.8543
3.0739	6.0	7254	3.0188	16.8374	8.6457	16.4407	16.4743
3.0393	7.0	8463	3.0161	17.3064	8.7822	16.9423	16.9543
3.0202	8.0	9672	3.0173	16.7977	8.6849	16.4822	16.4975

Framework versions

• Transformers 4.19.2
• Pytorch 1.11.0+cu113
• Datasets 2.2.1
• Tokenizers 0.12.1