byt5-small-cmudict

This model is a fine-tuned version of google/byt5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0802
• Per: 0.1151
• Gen Len: 14.6046

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: 0.0002
• train_batch_size: 128
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	Per	Gen Len
1.1569	1.0	845	0.1433	0.1751	14.5711
0.1409	2.0	1690	0.1049	0.1383	14.5844
0.1073	3.0	2535	0.0901	0.1281	14.6058
0.0927	4.0	3380	0.0855	0.1237	14.5798
0.0833	5.0	4225	0.0839	0.1207	14.6139
0.0762	6.0	5070	0.0809	0.118	14.5913
0.0707	7.0	5915	0.0810	0.1171	14.6055
0.0667	8.0	6760	0.0796	0.1166	14.6025
0.0638	9.0	7605	0.0793	0.115	14.6115
0.0609	10.0	8450	0.0802	0.1151	14.6046

Framework versions

• Transformers 4.28.0.dev0
• Pytorch 1.13.1+cu117
• Datasets 2.9.0
• Tokenizers 0.13.2