mmlw-retrieval-roberta-large-ft-1

This model is a fine-tuned version of sdadas/mmlw-retrieval-roberta-large on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.3866

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
1.0144	1.0	1250	0.9366
0.4727	2.0	2500	1.0235
0.4262	3.0	3750	1.0955
0.192	4.0	5000	1.1747
0.0798	5.0	6250	1.3866

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0