gpt2_small_baby_50Mf_32768_53

xiulinyang/gpt2_small_baby_50Mf_32768_53

gpt2_small_baby_50Mf_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

5% of all-time downloads

All-time downloads

141

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: b7b7c201

Model card

From the Hugging Face model README

gpt2_small_baby_50Mf_32768_53

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

Loss: 3.9109
Accuracy: 0.3482

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
5.371	0.43	2000	6.0835	0.1986
4.4157	0.86	4000	5.4345	0.2167
4.1387	1.29	6000	5.1421	0.2407
3.8785	1.72	8000	4.8715	0.2643
3.715	2.15	10000	4.6772	0.2781
3.6041	2.58	12000	4.5439	0.2895
3.5272	3.01	14000	4.4433	0.2955
3.4492	3.44	16000	4.3534	0.3047
3.3935	3.87	18000	4.2631	0.3089
3.3389	4.3	20000	4.2359	0.3133
3.3068	4.73	22000	4.1741	0.3160
3.2559	5.16	24000	4.1387	0.3215
3.2344	5.59	26000	4.1258	0.3239
3.2164	6.02	28000	4.0721	0.3263
3.1754	6.44	30000	4.0750	0.3264
3.1673	6.87	32000	4.0274	0.3312
3.1239	7.3	34000	4.0079	0.3309
3.1242	7.73	36000	3.9963	0.3348
3.0843	8.16	38000	3.9912	0.3354
3.083	8.59	40000	3.9691	0.3358
3.0758	9.02	42000	3.9687	0.3382
3.0321	9.45	44000	3.9476	0.3401
3.032	9.88	46000	3.9661	0.3419
2.9785	10.31	48000	3.9571	0.3435
2.9859	10.74	50000	3.9247	0.3442
2.94	11.17	52000	3.9425	0.3446
2.9461	11.6	54000	3.9291	0.3456
2.9453	12.03	56000	3.9265	0.3478
2.9019	12.46	58000	3.9270	0.3484
2.9151	12.89	60000	3.9109	0.3482
2.8596	13.32	62000	3.9273	0.3482
2.8777	13.75	64000	3.9353	0.3488
2.8289	14.18	66000	3.9391	0.3482

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