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: 2.8106
• Rouge1: 17.9738
• Rouge2: 9.4344
• Rougel: 17.2333
• Rougelsum: 17.1247

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
8.2948	1.0	611	3.1808	12.5576	5.9735	12.2175	12.2816
4.2676	2.0	1222	2.9768	16.9344	7.9443	16.2818	16.3308
3.8378	3.0	1833	2.8996	16.7694	8.009	16.2782	16.2109
3.6049	4.0	2444	2.8848	17.6535	8.9245	16.9455	16.8767
3.4589	5.0	3055	2.8488	17.4123	8.9396	16.7886	16.6109
3.3725	6.0	3666	2.8191	17.5675	9.0082	16.8443	16.6345
3.3259	7.0	4277	2.8184	18.012	9.4448	17.2561	17.1563
3.29	8.0	4888	2.8106	17.9738	9.4344	17.2333	17.1247

Framework versions

• Transformers 4.26.0
• Pytorch 1.12.1+cu102
• Datasets 2.9.0
• Tokenizers 0.13.2