aochildes-len – AI Model by NasimB | AlphaNeural AI

You can deploy this model and start earning money today!

NasimB/
aochildes-len

like

0

text-generation

generated_from_trainer

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

aochildes-len

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

Loss: 4.0766

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: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 1000
num_epochs: 6
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
6.3523	0.29	500	5.3179
5.0501	0.58	1000	4.9002
4.722	0.87	1500	4.6623
4.4583	1.16	2000	4.5189
4.2995	1.46	2500	4.4057
4.2054	1.75	3000	4.3019
4.0894	2.04	3500	4.2295
3.899	2.33	4000	4.1853
3.8723	2.62	4500	4.1366
3.8354	2.91	5000	4.0862
3.6445	3.2	5500	4.0826
3.5864	3.49	6000	4.0549
3.5735	3.79	6500	4.0269
3.4938	4.08	7000	4.0250
3.3154	4.37	7500	4.0210
3.3128	4.66	8000	4.0103
3.3064	4.95	8500	3.9989
3.1572	5.24	9000	4.0141
3.1295	5.53	9500	4.0134
3.1369	5.82	10000	4.0127

Framework versions

Transformers 4.26.1
Pytorch 1.11.0+cu113
Datasets 2.13.0
Tokenizers 0.13.3