MRR-Roberta_without_squal_15k

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

• Loss: 1.1563

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: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
0.8327	1.0	5797	0.9889
0.7944	2.0	11594	1.0074
0.6759	3.0	17391	0.7689
0.63	4.0	23188	0.6830
0.508	5.0	28985	0.7813
0.5907	6.0	34782	0.7577
0.4612	7.0	40579	0.7701
0.4485	8.0	46376	0.8050
0.3881	9.0	52173	0.8276
0.4072	10.0	57970	0.8701
0.3177	11.0	63767	0.9870
0.2954	12.0	69564	0.9968
0.2881	13.0	75361	1.1037
0.2106	14.0	81158	1.1053
0.2564	15.0	86955	1.1563

Framework versions

• Transformers 4.32.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.14.4
• Tokenizers 0.13.3