finetuned_byT5base_pnb_joint

lowresource-igt/finetuned_byT5base_pnb_joint

finetuned_byT5base_pnb_joint 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

15% 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 24, 2026
Updated: Jul 24, 2026
SHA: 552d014c

Base models

google/byt5-base

Model card

From the Hugging Face model README

finetuned_byT5base_pnb_joint

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: 0.4816
Chrf++: 49.572
Gen Len: 68.0

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
24.5636	1.4706	4	2.4689	7.7277	189.0588
24.5636	2.9412	8	2.4699	8.0685	188.9412
24.5636	4.0	12	2.4689	6.6729	188.9412
24.5636	5.4706	16	2.4674	6.9261	188.8235
24.5636	6.9412	20	2.4650	9.3539	188.7059
24.5636	8.0	24	2.4623	9.6317	188.8824
24.5636	9.4706	28	2.4560	8.1042	188.7059
24.5636	10.9412	32	2.4479	8.1565	188.7647
24.5636	12.0	36	2.4385	10.1672	188.5882
24.5636	13.4706	40	2.4275	10.9001	188.7059
24.5636	14.9412	44	2.4099	11.3066	188.9412
24.5636	16.0	48	2.3897	11.6124	189.0588
24.5636	17.4706	52	2.3624	13.2422	188.7647
24.5636	18.9412	56	2.3213	13.282	188.7059
24.5636	20.0	60	2.2838	15.9428	188.2941
24.5636	21.4706	64	2.2396	16.1163	188.3529
24.5636	22.9412	68	2.1821	17.8517	188.4118
24.5636	24.0	72	2.1315	17.9037	188.0588
24.5636	25.4706	76	2.0880	17.9886	187.8824
24.5636	26.9412	80	2.0134	17.6751	187.9412
24.5636	28.0	84	1.9621	19.7713	187.7059
24.5636	29.4706	88	1.8952	19.846	187.5882
24.5636	30.9412	92	1.8373	19.9407	187.7059
24.5636	32.0	96	1.7844	19.956	187.5882
15.1019	33.4706	100	1.7317	18.1818	187.7059
15.1019	34.9412	104	1.6756	18.224	187.7059
15.1019	36.0	108	1.6172	17.3255	187.4118
15.1019	37.4706	112	1.5516	18.0796	187.4706
15.1019	38.9412	116	1.5035	18.4133	187.4118
15.1019	40.0	120	1.4556	18.8031	186.7647
15.1019	41.4706	124	1.4035	18.7494	186.0
15.1019	42.9412	128	1.3532	18.4409	185.1176
15.1019	44.0	132	1.3180	17.3214	182.5882
15.1019	45.4706	136	1.2662	15.9677	179.5294
15.1019	46.9412	140	1.2212	17.7098	159.7647
15.1019	48.0	144	1.1694	19.8472	127.3529
15.1019	49.4706	148	1.1241	20.9296	109.4706
15.1019	50.9412	152	1.0559	18.038	116.0
15.1019	52.0	156	1.0191	19.9631	127.4118
15.1019	53.4706	160	0.9951	22.8451	86.2353
15.1019	54.9412	164	0.9643	25.3623	80.8235
15.1019	56.0	168	0.9570	24.1196	87.4706
15.1019	57.4706	172	0.9460	25.246	90.0
15.1019	58.9412	176	0.9069	26.1294	96.5294
15.1019	60.0	180	0.8837	23.4434	99.3529
15.1019	61.4706	184	0.8737	27.1581	85.9412
15.1019	62.9412	188	0.8403	27.119	79.7647
15.1019	64.0	192	0.8154	28.0704	74.2353
15.1019	65.4706	196	0.8035	29.3708	73.7059
7.2215	66.9412	200	0.7756	29.2225	70.8235
7.2215	68.0	204	0.7458	29.7421	63.2941
7.2215	69.4706	208	0.7222	30.5784	55.9412
7.2215	70.9412	212	0.6852	34.3593	59.7647
7.2215	72.0	216	0.6757	33.2726	58.2353
7.2215	73.4706	220	0.6596	33.8142	66.1765
7.2215	74.9412	224	0.6475	34.4019	65.1176
7.2215	76.0	228	0.6189	38.3999	53.4118
7.2215	77.4706	232	0.6070	39.4714	57.8824
7.2215	78.9412	236	0.5902	38.4675	64.1176
7.2215	80.0	240	0.5946	38.3601	55.2353
7.2215	81.4706	244	0.5705	40.157	55.7647
7.2215	82.9412	248	0.5689	42.4895	71.7059
7.2215	84.0	252	0.5467	43.3156	63.7059
7.2215	85.4706	256	0.5444	41.7808	55.3529
7.2215	86.9412	260	0.5161	46.6265	65.0588
7.2215	88.0	264	0.5121	46.673	64.1765
7.2215	89.4706	268	0.5015	48.6535	68.1765
7.2215	90.9412	272	0.4989	48.3859	63.0
7.2215	92.0	276	0.4992	51.014	70.8235
7.2215	93.4706	280	0.4916	45.8087	63.6471
7.2215	94.9412	284	0.5110	48.2439	63.7647
7.2215	96.0	288	0.5011	48.0627	62.0588
7.2215	97.4706	292	0.4915	47.6459	62.6471
7.2215	98.9412	296	0.4830	48.9398	62.7647
3.4571	100.0	300	0.4816	49.572	68.0

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 24, 2026
Updated: Jul 24, 2026