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: 0.2517
• Rouge1: 14.7495
• Rouge2: 7.2226
• Rougel: 14.0109
• Rougelsum: 14.1583

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.3426	1.0	838	0.2712	12.6317	6.3377	12.1288	12.2498
0.3091	2.0	1676	0.2616	12.6631	6.1716	12.439	12.5201
0.2878	3.0	2514	0.2570	14.477	7.5074	13.7856	13.9647
0.2766	4.0	3352	0.2551	14.132	7.2241	13.6744	13.831
0.2686	5.0	4190	0.2523	14.324	6.4759	13.7568	13.8855
0.2631	6.0	5028	0.2522	15.5031	7.5588	14.7522	14.9207
0.2594	7.0	5866	0.2513	15.0739	7.4589	14.2674	14.4301
0.2561	8.0	6704	0.2517	14.7495	7.2226	14.0109	14.1583

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1
• Datasets 3.1.0
• Tokenizers 0.21.0