my_mt5_small_test-finetuned-textdetox

This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.1729
• Rouge1: 48.4128
• Rouge2: 39.9256
• Rougel: 48.1823
• Rougelsum: 48.1665
• Gen Len: 15.1129

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: 0.0001
• 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.4234	1.0	3480	1.3619	47.6986	39.113	47.5064	47.4812	15.454
1.3091	2.0	6960	1.2434	48.0682	39.5031	47.8767	47.8577	15.2398
1.3695	3.0	10440	1.2162	48.1983	39.6887	47.9807	47.9556	15.2225
1.123	4.0	13920	1.1739	48.309	39.7956	48.0868	48.0644	15.1866
1.4587	5.0	17400	1.1729	48.4128	39.9256	48.1823	48.1665	15.1129

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1