deberta-v3-base-lm-all

This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0354

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: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 16

Training results

Training Loss	Epoch	Step	Validation Loss
3.3663	1.0	2388	2.2002
2.1379	2.0	4776	1.8135
1.8234	3.0	7164	1.6199
1.623	4.0	9552	1.5031
1.4936	5.0	11940	1.4027
1.4034	6.0	14328	1.3346
1.3214	7.0	16716	1.2927
1.2618	8.0	19104	1.2377
1.2113	9.0	21492	1.2043
1.1595	10.0	23880	1.1843
1.1082	11.0	26268	1.1174
1.0712	12.0	28656	1.1071
1.0468	13.0	31044	1.0723
1.0209	14.0	33432	1.0741
0.99	15.0	35820	1.0456
0.9733	16.0	38208	1.0354

Framework versions

• Transformers 4.21.2
• Pytorch 1.12.1+cu113
• Datasets 2.4.0
• Tokenizers 0.12.1