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: 3.0397
• Rouge1: 16.98
• Rouge2: 7.8929
• Rougel: 16.3644
• Rougelsum: 16.4476

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
7.8974	1.0	1209	3.3189	13.3079	4.9395	12.9401	12.9378
3.9255	2.0	2418	3.1756	16.2829	7.8355	15.7221	15.7776
3.5938	3.0	3627	3.1217	18.6193	9.6297	17.7226	17.8895
3.4294	4.0	4836	3.1036	17.6104	8.5851	16.8473	16.8296
3.3129	5.0	6045	3.0564	15.8986	7.3515	15.3339	15.4281
3.2488	6.0	7254	3.0497	16.7475	7.9259	16.0704	16.1902
3.2162	7.0	8463	3.0390	16.6901	8.201	16.3029	16.3853
3.1883	8.0	9672	3.0397	16.98	7.8929	16.3644	16.4476

Framework versions

• Transformers 4.42.4
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1