pretraining8 – AI Model by danielkosyra | AlphaNeural AI

You can deploy this model and start earning money today!

danielkosyra/
pretraining8

like

0

text-generation

generated_from_trainer

openai-community/gpt2

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

pretraining8

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

Loss: 4.0396

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: 0.0006
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 10
total_train_batch_size: 40
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: inverse_sqrt
lr_scheduler_warmup_steps: 250
training_steps: 1500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
9.2792	0.0272	50	7.6701
7.1197	0.0544	100	6.7851
6.5645	0.0816	150	6.3728
6.2643	0.1087	200	6.1180
6.0752	0.1359	250	5.9355
5.8579	0.1631	300	5.7394
5.6632	0.1903	350	5.5987
5.554	0.2175	400	5.4644
5.4324	0.2447	450	5.3659
5.3633	0.2719	500	5.2707
5.257	0.2990	550	5.1792
5.1611	0.3262	600	5.1034
5.0776	0.3534	650	5.0488
5.0416	0.3806	700	4.9643
4.9556	0.4078	750	4.9050
4.9057	0.4350	800	4.8419
4.8294	0.4622	850	4.7860
4.8096	0.4893	900	4.7247
4.753	0.5165	950	4.6722
4.6549	0.5437	1000	4.6223
4.6392	0.5709	1050	4.5690
4.5492	0.5981	1100	4.5120
4.5252	0.6253	1150	4.4511
4.4366	0.6525	1200	4.4012
4.4252	0.6796	1250	4.3329
4.3357	0.7068	1300	4.2728
4.2916	0.7340	1350	4.2073
4.231	0.7612	1400	4.1431
4.1851	0.7884	1450	4.0878
4.1097	0.8156	1500	4.0396

Framework versions

Transformers 4.40.1
Pytorch 2.3.0+cu121
Datasets 2.19.0
Tokenizers 0.19.1