gpt2-jp-119M – AI Model by HachiML | AlphaNeural AI

You can deploy this model and start earning money today!

HachiML/
gpt2-jp-119M

like

0

text-generation

generated_from_trainer

openai-community/gpt2

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

gpt2-jp-119M

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 3.3790

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: 0.0005
train_batch_size: 156
eval_batch_size: 156
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 200
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
7.0426	0.06	100	5.3865
5.0116	0.12	200	4.7179
4.5288	0.18	300	4.3459
4.2531	0.24	400	4.1600
4.0964	0.29	500	4.0072
3.9623	0.35	600	3.9098
3.8511	0.41	700	3.8118
3.7549	0.47	800	3.7255
3.6865	0.53	900	3.6480
3.6162	0.59	1000	3.5820
3.5471	0.65	1100	3.5222
3.4931	0.71	1200	3.4755
3.4329	0.77	1300	3.4319
3.4154	0.82	1400	3.4062
3.3766	0.88	1500	3.3868
3.3636	0.94	1600	3.3790

Framework versions

Transformers 4.38.1
Pytorch 2.1.0+cu121
Datasets 2.18.0
Tokenizers 0.15.2