gpt2_small_baby_50M_32768_76

xiulinyang/gpt2_small_baby_50M_32768_76

gpt2_small_baby_50M_32768_76 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

5% of all-time downloads

All-time downloads

149

Public

Repo size

21.7 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 24, 2025
Updated: Oct 24, 2025
SHA: f41b100a

Model card

From the Hugging Face model README

gpt2_small_baby_50M_32768_76

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

Loss: 3.8970
Accuracy: 0.3501

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: 76
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
5.3459	0.43	2000	6.0754	0.1986
4.4173	0.86	4000	5.4379	0.2171
4.1502	1.29	6000	5.1354	0.2398
3.8887	1.72	8000	4.8689	0.2620
3.7263	2.15	10000	4.6988	0.2770
3.6137	2.57	12000	4.5635	0.2885
3.5318	3.0	14000	4.4447	0.2987
3.4557	3.43	16000	4.3514	0.3044
3.4026	3.86	18000	4.2842	0.3100
3.3404	4.29	20000	4.2403	0.3140
3.3102	4.72	22000	4.1799	0.3178
3.2628	5.15	24000	4.1336	0.3211
3.2374	5.58	26000	4.1029	0.3228
3.216	6.01	28000	4.0773	0.3275
3.1806	6.44	30000	4.0416	0.3288
3.1717	6.87	32000	4.0213	0.3309
3.1265	7.29	34000	4.0346	0.3311
3.1244	7.72	36000	3.9890	0.3357
3.0835	8.15	38000	3.9895	0.3357
3.0825	8.58	40000	3.9751	0.3374
3.0781	9.01	42000	3.9582	0.3398
3.0335	9.44	44000	3.9508	0.3409
3.0334	9.87	46000	3.9228	0.3424
2.979	10.3	48000	3.9425	0.3440
2.9944	10.73	50000	3.9299	0.3447
2.9461	11.16	52000	3.9199	0.3460
2.9462	11.59	54000	3.9179	0.3472
2.9497	12.01	56000	3.9076	0.3479
2.9025	12.44	58000	3.9140	0.3492
2.9171	12.87	60000	3.8970	0.3501
2.8595	13.3	62000	3.9145	0.3500
2.8783	13.73	64000	3.9017	0.3508
2.8391	14.16	66000	3.9347	0.3502

Framework versions

Transformers 4.30.2
Pytorch 2.9.0+cu128
Datasets 4.1.1
Tokenizers 0.13.3

Type: gpt2
Created: Oct 24, 2025
Updated: Oct 24, 2025