my_awesome_swag_model

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

• Loss: 1.6094

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: 3e-05
• train_batch_size: 2
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.6
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.8462	0.13	700	1.7281
0.4775	0.26	1400	1.6819
0.3949	0.38	2100	1.8476
0.3923	0.51	2800	2.2831
1.1178	0.64	3500	1.6094
1.6198	0.77	4200	1.6094
1.6156	0.89	4900	1.6094
1.6151	1.02	5600	1.6094
1.615	1.15	6300	1.6094
1.6113	1.28	7000	1.6094
1.6133	1.41	7700	1.6094
1.6114	1.53	8400	1.6094
1.6108	1.66	9100	1.6094
1.6155	1.79	9800	1.6094
1.6087	1.92	10500	1.6094

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3