finetuned_byT5base_pnb_translit

lowresource-igt/finetuned_byT5base_pnb_translit

finetuned_byT5base_pnb_translit is a machine learning model from lowresource-igt. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.

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

Downloads · 30 days

11% of all-time downloads

All-time downloads

Public

Parameters

582M

2.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors2.3 GB · 100%

At a glance

Library: transformers
License: apache-2.0
Model type: t5
Access: Public
Created: Jul 10, 2026
Updated: Jul 10, 2026
SHA: 27f43c29

Base models

google/byt5-base

Model card

From the Hugging Face model README

finetuned_byT5base_pnb_translit

This model is a fine-tuned version of google/byt5-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.7534
Chrf++: 39.0756
Gen Len: 60.9412

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: 5e-05
train_batch_size: 4
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Chrf++	Gen Len
23.9837	1.4706	4	2.4642	6.2068	188.8824
23.9837	2.9412	8	2.4639	6.3773	189.1176
23.9837	4.0	12	2.4662	6.3773	189.0
23.9837	5.4706	16	2.4620	6.342	188.8235
23.9837	6.9412	20	2.4608	6.5614	188.8235
23.9837	8.0	24	2.4589	6.5612	188.7647
23.9837	9.4706	28	2.4534	6.412	188.7059
23.9837	10.9412	32	2.4495	6.2436	188.4118
23.9837	12.0	36	2.4388	6.1516	188.5882
23.9837	13.4706	40	2.4269	6.1539	188.4118
23.9837	14.9412	44	2.4141	6.172	188.4118
23.9837	16.0	48	2.3953	7.0092	188.2941
23.9837	17.4706	52	2.3720	6.36	188.5294
23.9837	18.9412	56	2.3428	6.2908	188.1176
23.9837	20.0	60	2.3130	7.0406	188.2353
23.9837	21.4706	64	2.2640	9.0762	188.1765
23.9837	22.9412	68	2.2195	9.2347	188.3529
23.9837	24.0	72	2.1916	10.3555	188.2353
23.9837	25.4706	76	2.1433	12.5414	188.3529
23.9837	26.9412	80	2.0993	12.7159	188.3529
23.9837	28.0	84	2.0445	16.6564	188.2353
23.9837	29.4706	88	1.9858	18.4684	187.7647
23.9837	30.9412	92	1.9176	19.9661	187.6471
23.9837	32.0	96	1.8524	18.7023	187.8235
15.3132	33.4706	100	1.7859	19.9225	187.4706
15.3132	34.9412	104	1.7241	20.0241	187.4118
15.3132	36.0	108	1.6859	19.6181	187.1176
15.3132	37.4706	112	1.6360	17.3831	187.5882
15.3132	38.9412	116	1.5694	19.0535	187.6471
15.3132	40.0	120	1.5097	18.5478	187.4706
15.3132	41.4706	124	1.4534	19.4835	187.5294
15.3132	42.9412	128	1.4138	20.2699	185.5882
15.3132	44.0	132	1.3767	19.5107	185.3529
15.3132	45.4706	136	1.3108	19.761	180.9412
15.3132	46.9412	140	1.2568	18.6467	179.7647
15.3132	48.0	144	1.2182	19.6208	180.9412
15.3132	49.4706	148	1.1678	19.7843	166.0
15.3132	50.9412	152	1.1351	19.975	163.3529
15.3132	52.0	156	1.1128	20.4845	158.6471
15.3132	53.4706	160	1.0664	20.9819	155.2941
15.3132	54.9412	164	1.0359	20.896	155.1765
15.3132	56.0	168	1.0060	19.0951	112.9412
15.3132	57.4706	172	0.9762	18.8894	118.7059
15.3132	58.9412	176	0.9544	16.7827	137.1765
15.3132	60.0	180	0.9442	22.5026	87.1765
15.3132	61.4706	184	0.9376	21.7172	128.0588
15.3132	62.9412	188	0.9105	21.3343	85.7647
15.3132	64.0	192	0.9038	22.4809	96.4118
15.3132	65.4706	196	0.8964	22.148	82.5294
7.5637	66.9412	200	0.8950	25.0061	81.1176
7.5637	68.0	204	0.8836	23.8759	84.1765
7.5637	69.4706	208	0.8805	26.3255	82.1176
7.5637	70.9412	212	0.8641	26.6377	78.7647
7.5637	72.0	216	0.8483	26.6932	72.5882
7.5637	73.4706	220	0.8445	28.5132	69.4706
7.5637	74.9412	224	0.8425	25.9978	78.2941
7.5637	76.0	228	0.8363	26.9687	63.2941
7.5637	77.4706	232	0.8355	26.4787	64.2353
7.5637	78.9412	236	0.8134	29.0855	54.6471
7.5637	80.0	240	0.7980	29.2715	63.7647
7.5637	81.4706	244	0.7939	31.2632	63.5294
7.5637	82.9412	248	0.7909	30.8313	57.2941
7.5637	84.0	252	0.7747	29.9818	51.1176
7.5637	85.4706	256	0.7683	33.905	59.3529
7.5637	86.9412	260	0.7757	34.5935	61.2353
7.5637	88.0	264	0.7750	35.5657	71.0
7.5637	89.4706	268	0.7515	35.2005	69.4706
7.5637	90.9412	272	0.7619	35.6053	62.3529
7.5637	92.0	276	0.7583	35.1182	59.2353
7.5637	93.4706	280	0.7540	36.54	60.4706
7.5637	94.9412	284	0.7551	36.3719	53.5882
7.5637	96.0	288	0.7634	36.1912	56.4706
7.5637	97.4706	292	0.7449	36.2558	73.7059
7.5637	98.9412	296	0.7516	37.7298	66.9412
4.1955	100.0	300	0.7534	39.0756	60.9412

Framework versions

Transformers 5.12.1
Pytorch 2.6.0+cu124
Datasets 5.0.0
Tokenizers 0.22.2

Library: transformers
Type: t5
License: apache-2.0
Created: Jul 10, 2026
Updated: Jul 10, 2026