byt5-base-es_cbv

This model is a fine-tuned version of google/byt5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6675
• Bleu: 5.5318
• Gen Len: 100.3826

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 65
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	386	0.9372	0.0256	19.0
1.4765	2.0	772	0.8219	0.0303	19.0
0.9443	3.0	1158	0.7708	0.022	19.0
0.8436	4.0	1544	0.7288	0.0562	19.0
0.8436	5.0	1930	0.7091	0.0469	19.0
0.7916	6.0	2316	0.6926	0.0464	19.0
0.7568	7.0	2702	0.6799	0.0536	19.0
0.7403	8.0	3088	0.6737	0.0547	19.0
0.7403	9.0	3474	0.6667	0.0532	19.0
0.7215	10.0	3860	0.6675	0.056	19.0

Framework versions

• Transformers 4.27.4
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3