K-12BERT-reward-neurallinguisticpioneers

This model is a fine-tuned version of vasugoel/K-12BERT on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2926

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
1.0129	1.0	244	0.4501
0.5275	2.0	488	0.5272
0.3624	3.0	732	0.3435
0.3053	4.0	976	0.2740
0.2485	5.0	1220	0.2465
0.2157	6.0	1464	0.2992
0.1942	7.0	1708	0.2495
0.1751	8.0	1952	0.2605
0.175	9.0	2196	0.2192
0.1553	10.0	2440	0.2790
0.1449	11.0	2684	0.2566
0.1472	12.0	2928	0.2547
0.1443	13.0	3172	0.2600
0.1375	14.0	3416	0.3310

Framework versions

• Transformers 4.27.3
• Pytorch 1.13.0+cu117
• Datasets 2.12.0
• Tokenizers 0.13.3