setup_2C

This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.0781
• Bleu1: 0.2704
• Bleu2: 0.1763
• Bleu3: 0.1219
• Bleu4: 0.087
• Meteor: 0.3266
• Bertscore Precision: 0.7963
• Bertscore Recall: 0.7572
• Bertscore F1: 0.7756
• Gen Len: 16.9447

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu1	Bleu2	Bleu3	Bleu4	Meteor	Bertscore Precision	Bertscore Recall	Bertscore F1	Gen Len
2.3795	1.0	3125	2.1232	0.2656	0.1704	0.1161	0.082	0.3158	0.7927	0.7541	0.7723	16.9152
2.2942	2.0	6250	2.0867	0.2707	0.1762	0.1214	0.0865	0.3256	0.7957	0.7568	0.7752	16.9258
2.2602	3.0	9375	2.0781	0.2704	0.1763	0.1219	0.087	0.3266	0.7963	0.7572	0.7756	16.9447

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2