pre_trained_english_to_syslog – AI Model by treytinnell | AlphaNeural AI

You can deploy this model and start earning money today!

treytinnell/
pre_trained_english_to_syslog

like

0

text-generation

generated_from_trainer

openai-community/gpt2

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

treytinnell/english_to_syslog

This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3379

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: 1
eval_batch_size: 20
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
0.4134	1.0	64	0.3773
0.3463	2.0	128	0.3702
0.2828	3.0	192	0.3379
0.2409	4.0	256	0.3691
0.2489	5.0	320	0.3848
0.2415	6.0	384	0.4059
0.1533	7.0	448	0.4212
0.126	8.0	512	0.4628
0.1514	9.0	576	0.4741
0.1374	10.0	640	0.4855

Framework versions

Transformers 4.37.2
Pytorch 2.2.0+cu121
Datasets 2.16.1
Tokenizers 0.15.1