gptneo-TxtToJson-v0.1.16

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: 0.1180

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	88	0.6397
No log	2.0	176	0.5158
No log	3.0	264	0.4083
No log	4.0	352	0.2929
No log	5.0	440	0.2384
0.3687	6.0	528	0.1904
0.3687	7.0	616	0.1638
0.3687	8.0	704	0.1485
0.3687	9.0	792	0.1405
0.3687	10.0	880	0.1277
0.3687	11.0	968	0.1232
0.0629	12.0	1056	0.1291
0.0629	13.0	1144	0.1159
0.0629	14.0	1232	0.1123
0.0629	15.0	1320	0.1160
0.0629	16.0	1408	0.1159
0.0629	17.0	1496	0.1195
0.0137	18.0	1584	0.1186
0.0137	19.0	1672	0.1179
0.0137	20.0	1760	0.1180

Framework versions

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