gptneo-TxtToJson-v0.1.18

This model is a fine-tuned version of EleutherAI/gpt-neo-125m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1669

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: 0.0002
• 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
1.0001	1.0	219	0.9411
0.7298	2.0	438	0.7063
0.4617	3.0	657	0.4989
0.3366	4.0	876	0.3333
0.2295	5.0	1095	0.2569
0.1593	6.0	1314	0.2146
0.1611	7.0	1533	0.1986
0.0983	8.0	1752	0.1866
0.0933	9.0	1971	0.1776
0.0794	10.0	2190	0.1742
0.0743	11.0	2409	0.1734
0.0459	12.0	2628	0.1690
0.0386	13.0	2847	0.1681
0.0261	14.0	3066	0.1673
0.0209	15.0	3285	0.1669

Framework versions

• Transformers 4.27.4
• Pytorch 1.13.0
• Datasets 2.1.0
• Tokenizers 0.13.2