bert-large-uncased-finetuned-DA-Zero-shot-20

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

• Loss: 1.0118

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.6214	1.0	435	1.1818
0.6285	2.0	870	1.2124
0.713	3.0	1305	1.1673
0.7902	4.0	1740	1.1342
0.8051	5.0	2175	1.1042
0.8167	6.0	2610	1.1086
0.8412	7.0	3045	1.0797
0.8885	8.0	3480	1.0575
0.918	9.0	3915	1.0749
0.9765	10.0	4350	1.0565
1.0009	11.0	4785	1.0509
0.986	12.0	5220	1.0564
0.9819	13.0	5655	1.0527
0.9786	14.0	6090	1.0064
0.9689	15.0	6525	1.0038
0.9481	16.0	6960	1.0186
0.955	17.0	7395	0.9860
0.9481	18.0	7830	0.9914
0.9452	19.0	8265	1.0173
0.9452	20.0	8700	1.0050

Framework versions

• Transformers 4.26.0
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2