results

This model is a fine-tuned version of eugenesiow/bart-paraphrase on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.1435

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
5.2622	0.9968	154	4.8920
4.4409	2.0	309	3.8232
3.8001	2.9968	463	3.3055
3.4922	4.0	618	2.9036
3.2041	4.9968	772	2.6903
3.0911	6.0	927	2.4548
2.7878	6.9968	1081	2.4292
2.7969	8.0	1236	2.2862
2.5457	8.9968	1390	2.1846
2.6063	9.9676	1540	2.2019

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1