distilgpt_oscarth_0020 – AI Model by bigmorning | AlphaNeural AI

You can deploy this model and start earning money today!

bigmorning/
distilgpt_oscarth_0020

like

0

text-generation

generated_from_keras_callback

autotrain_compatible

endpoints_compatible

Views

No views yet

distilgpt_oscarth_0020

This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: 3.2188
Validation Loss: 3.0982
Epoch: 19

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:

optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
5.6021	4.5759	0
4.4536	4.1235	1
4.1386	3.9013	2
3.9546	3.7563	3
3.8255	3.6477	4
3.7271	3.5617	5
3.6488	3.4936	6
3.5844	3.4379	7
3.5301	3.3891	8
3.4833	3.3448	9
3.4427	3.3098	10
3.4068	3.2750	11
3.3749	3.2425	12
3.3462	3.2211	13
3.3202	3.1941	14
3.2964	3.1720	15
3.2749	3.1512	16
3.2548	3.1322	17
3.2363	3.1141	18
3.2188	3.0982	19

Framework versions

Transformers 4.20.1
TensorFlow 2.8.2
Datasets 2.3.2
Tokenizers 0.12.1