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: 3.0609
• Rouge1: 35.0709
• Rouge2: 16.7086
• Rougel: 34.3217
• Rougelsum: 34.3182

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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
No log	1.0	1209	3.3452	28.1494	11.5385	27.8138	27.9215
5.3779	2.0	2418	3.2066	29.2799	14.9292	28.3282	28.4643
5.3779	3.0	3627	3.1105	31.9146	15.8212	31.0157	30.9702
3.5145	4.0	4836	3.0808	32.6703	15.9624	31.568	31.5303
3.5145	5.0	6045	3.0837	33.8454	16.3402	32.6727	32.8738
3.2939	6.0	7254	3.0655	32.4588	15.713	31.7059	31.7646
3.2939	7.0	8463	3.0576	34.764	16.6023	34.1524	34.0333
3.2076	8.0	9672	3.0609	35.0709	16.7086	34.3217	34.3182

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3