gpt2_small_baby_50M_32768_53

xiulinyang/gpt2_small_baby_50M_32768_53

gpt2_small_baby_50M_32768_53 is a machine learning model from xiulinyang. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

3% of all-time downloads

All-time downloads

151

Public

Repo size

23 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin443 MB · 100%

At a glance

Model type: gpt2
Access: Public
Created: Oct 25, 2025
Updated: Oct 25, 2025
SHA: 3ff55490

Model card

From the Hugging Face model README

gpt2_small_baby_50M_32768_53

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 3.9156
Accuracy: 0.3503

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: 0.0001
train_batch_size: 32
eval_batch_size: 32
seed: 53
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 40000
training_steps: 100000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
5.3575	0.43	2000	6.0832	0.1988
4.4184	0.86	4000	5.4394	0.2170
4.132	1.29	6000	5.1258	0.2411
3.8862	1.72	8000	4.8646	0.2639
3.7174	2.15	10000	4.6752	0.2769
3.6086	2.57	12000	4.5492	0.2879
3.5355	3.0	14000	4.4334	0.2959
3.457	3.43	16000	4.3466	0.3032
3.4016	3.86	18000	4.2794	0.3084
3.3388	4.29	20000	4.2100	0.3127
3.3093	4.72	22000	4.1700	0.3162
3.2609	5.15	24000	4.1282	0.3200
3.2398	5.58	26000	4.1306	0.3219
3.221	6.01	28000	4.0858	0.3244
3.1769	6.44	30000	4.0445	0.3267
3.1706	6.87	32000	4.0269	0.3296
3.1159	7.29	34000	4.0264	0.3300
3.1326	7.72	36000	4.0135	0.3329
3.0847	8.15	38000	3.9896	0.3358
3.0834	8.58	40000	3.9994	0.3357
3.0833	9.01	42000	3.9397	0.3395
3.037	9.44	44000	3.9559	0.3393
3.0389	9.87	46000	3.9518	0.3429
2.9831	10.3	48000	3.9426	0.3439
2.9934	10.73	50000	3.9208	0.3447
2.9456	11.16	52000	3.9352	0.3445
2.9452	11.59	54000	3.9378	0.3471
2.9494	12.01	56000	3.9222	0.3480
2.9027	12.44	58000	3.9348	0.3476
2.9174	12.87	60000	3.9173	0.3486
2.859	13.3	62000	3.9464	0.3488
2.8813	13.73	64000	3.9156	0.3503
2.8342	14.16	66000	3.9682	0.3487
2.8421	14.59	68000	3.9279	0.3504
2.8466	15.02	70000	3.9428	0.3504

Framework versions

Transformers 4.30.2
Pytorch 2.9.0+cu128
Datasets 4.1.1
Tokenizers 0.13.3

Type: gpt2
Created: Oct 25, 2025
Updated: Oct 25, 2025