finetuned_glosslm_pnb_joint

lowresource-igt/finetuned_glosslm_pnb_joint

finetuned_glosslm_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

12% 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 25, 2026
Updated: Jul 25, 2026
SHA: cfeaa84d

Base models

lecslab/glosslm

Model card

From the Hugging Face model README

finetuned_glosslm_pnb_joint

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

Loss: 0.6724
Chrf++: 62.7498
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
8.9280	1.4706	4	0.9578	27.3136	93.2353
8.9280	2.9412	8	0.9476	28.8331	89.8824
8.9280	4.0	12	0.9333	29.3619	88.2941
8.9280	5.4706	16	0.9133	29.836	85.0
8.9280	6.9412	20	0.8910	31.7041	82.1176
8.9280	8.0	24	0.8671	31.8983	83.6471
8.9280	9.4706	28	0.8375	30.9119	83.6471
8.9280	10.9412	32	0.8086	33.9323	78.7647
8.9280	12.0	36	0.7817	35.7619	77.0588
8.9280	13.4706	40	0.7503	34.4614	79.2941
8.9280	14.9412	44	0.7174	37.5272	71.4706
8.9280	16.0	48	0.6951	39.5943	72.1765
8.9280	17.4706	52	0.6697	42.636	68.2353
8.9280	18.9412	56	0.6411	42.4182	67.2941
8.9280	20.0	60	0.6263	42.8877	64.7059
8.9280	21.4706	64	0.6063	45.0712	64.5294
8.9280	22.9412	68	0.5865	46.8276	63.0588
8.9280	24.0	72	0.5695	47.0245	63.4118
8.9280	25.4706	76	0.5537	47.302	63.8824
8.9280	26.9412	80	0.5434	49.1472	64.2353
8.9280	28.0	84	0.5302	49.3195	65.0588
8.9280	29.4706	88	0.5164	51.1486	63.4118
8.9280	30.9412	92	0.5003	51.9441	64.2353
8.9280	32.0	96	0.4942	52.9625	64.0
4.4638	33.4706	100	0.4854	53.3121	64.2353
4.4638	34.9412	104	0.4754	54.9439	65.3529
4.4638	36.0	108	0.4676	55.2168	65.5882
4.4638	37.4706	112	0.4628	54.5952	64.2353
4.4638	38.9412	116	0.4589	54.4029	63.8235
4.4638	40.0	120	0.4538	54.6055	65.9412
4.4638	41.4706	124	0.4523	55.9827	66.0
4.4638	42.9412	128	0.4508	55.4289	66.1765
4.4638	44.0	132	0.4514	55.9912	66.3529
4.4638	45.4706	136	0.4499	55.7077	66.4706
4.4638	46.9412	140	0.4516	56.0676	66.5882
4.4638	48.0	144	0.4536	57.2979	66.8235
4.4638	49.4706	148	0.4527	58.5562	67.0588
4.4638	50.9412	152	0.4557	59.2736	67.1176
4.4638	52.0	156	0.4641	58.5358	66.7647
4.4638	53.4706	160	0.4632	59.3344	66.7059
4.4638	54.9412	164	0.4767	59.3863	66.8235
4.4638	56.0	168	0.4734	60.9805	67.1176
4.4638	57.4706	172	0.4841	61.2805	67.1765
4.4638	58.9412	176	0.4953	59.8026	66.6471
4.4638	60.0	180	0.5007	60.0295	66.8824
4.4638	61.4706	184	0.4999	59.7969	67.7059
4.4638	62.9412	188	0.5017	60.3615	67.4706
4.4638	64.0	192	0.5131	58.402	67.7059
4.4638	65.4706	196	0.5174	58.4091	68.2941
1.1101	66.9412	200	0.5272	61.9257	69.0588
1.1101	68.0	204	0.5397	60.0779	68.5294
1.1101	69.4706	208	0.5526	59.558	68.7647
1.1101	70.9412	212	0.5569	59.3817	68.1176
1.1101	72.0	216	0.5612	58.5497	68.0588
1.1101	73.4706	220	0.5664	60.7643	67.9412
1.1101	74.9412	224	0.5682	62.5825	68.0
1.1101	76.0	228	0.5854	62.9821	67.5294
1.1101	77.4706	232	0.5935	61.5409	67.7647
1.1101	78.9412	236	0.6044	62.2802	68.2353
1.1101	80.0	240	0.6100	60.1496	67.2941
1.1101	81.4706	244	0.6049	62.0185	67.9412
1.1101	82.9412	248	0.6053	64.5494	67.6471
1.1101	84.0	252	0.6113	63.1914	67.2941
1.1101	85.4706	256	0.6135	63.4776	66.4118
1.1101	86.9412	260	0.6243	60.7711	66.7647
1.1101	88.0	264	0.6271	60.3982	66.6471
1.1101	89.4706	268	0.6192	62.319	66.5294
1.1101	90.9412	272	0.6206	62.2494	67.2941
1.1101	92.0	276	0.6194	64.4927	68.8824
1.1101	93.4706	280	0.6212	62.4439	66.5882
1.1101	94.9412	284	0.6326	63.307	66.6471
1.1101	96.0	288	0.6519	62.9769	67.5882
1.1101	97.4706	292	0.6706	62.7948	67.0588
1.1101	98.9412	296	0.6719	63.515	67.1176
0.0761	100.0	300	0.6724	62.7498	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 25, 2026
Updated: Jul 25, 2026