finetuned_glosslm_kmr_joint

lowresource-igt/finetuned_glosslm_kmr_joint

finetuned_glosslm_kmr_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

24% 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 31, 2026
Updated: Jul 31, 2026
SHA: 8915eb3b

Base models

lecslab/glosslm

Model card

From the Hugging Face model README

finetuned_glosslm_kmr_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: 1.7101
Chrf++: 28.2805
Gen Len: 116.6757

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
2.1115	1.0	2	1.4569	24.2147	120.6149
2.1115	2.0	4	1.4565	24.0174	125.3243
2.1115	3.0	6	1.4567	24.3279	123.4595
2.1115	4.0	8	1.4568	24.3043	129.5135
2.1115	5.0	10	1.4564	24.0461	131.2703
2.1115	6.0	12	1.4566	24.3944	125.1284
2.1115	7.0	14	1.4565	24.2737	127.1284
2.1115	8.0	16	1.4566	24.5943	121.4932
2.1115	9.0	18	1.4566	24.6164	121.8581
2.1115	10.0	20	1.4565	24.3451	122.1824
2.1115	11.0	22	1.4574	24.5823	124.1554
2.1115	12.0	24	1.4583	25.004	124.1824
2.1115	13.0	26	1.4583	25.3286	121.5878
2.1115	14.0	28	1.4588	25.394	122.8041
2.1115	15.0	30	1.4605	25.7116	123.1351
2.1115	16.0	32	1.4615	25.3311	124.4527
2.1115	17.0	34	1.4641	25.6296	126.1757
2.1115	18.0	36	1.4668	25.5334	119.0608
2.1115	19.0	38	1.4690	26.0077	121.9324
2.1115	20.0	40	1.4719	25.8327	125.7027
2.1115	21.0	42	1.4737	26.0152	124.5473
2.1115	22.0	44	1.4770	26.612	119.9189
2.1115	23.0	46	1.4806	26.8199	119.3446
2.1115	24.0	48	1.4842	26.8952	120.0676
2.1115	25.0	50	1.4872	27.3251	119.0811
2.1115	26.0	52	1.4932	27.0191	116.9527
2.1115	27.0	54	1.4973	27.0595	116.8176
2.1115	28.0	56	1.5036	27.1061	116.7162
2.1115	29.0	58	1.5057	27.0275	117.7432
2.1115	30.0	60	1.5117	27.1133	117.3311
2.1115	31.0	62	1.5139	27.1326	117.1959
2.1115	32.0	64	1.5221	27.2419	116.2365
2.1115	33.0	66	1.5281	27.0611	116.7162
2.1115	34.0	68	1.5282	27.2716	117.4797
2.1115	35.0	70	1.5306	27.9045	111.7635
2.1115	36.0	72	1.5386	27.7759	116.1284
2.1115	37.0	74	1.5467	28.0715	117.6689
2.1115	38.0	76	1.5534	27.9608	117.5068
2.1115	39.0	78	1.5603	28.294	115.6892
2.1115	40.0	80	1.5632	28.3531	115.6824
2.1115	41.0	82	1.5681	28.2664	116.8649
2.1115	42.0	84	1.5813	27.9974	117.0878
2.1115	43.0	86	1.5888	27.8566	116.6419
2.1115	44.0	88	1.5961	28.0593	114.6216
2.1115	45.0	90	1.5959	28.3315	116.7027
2.1115	46.0	92	1.6031	28.4061	110.8378
2.1115	47.0	94	1.6016	28.6169	110.3311
2.1115	48.0	96	1.6057	28.563	110.5203
2.1115	49.0	98	1.6086	28.26	110.7095
0.5162	50.0	100	1.6131	28.7112	107.4054
0.5162	51.0	102	1.6161	28.6131	110.7973
0.5162	52.0	104	1.6191	28.7201	110.1014
0.5162	53.0	106	1.6229	28.5187	110.3986
0.5162	54.0	108	1.6314	28.5927	109.8378
0.5162	55.0	110	1.6327	28.7009	110.2635
0.5162	56.0	112	1.6302	28.6783	109.8176
0.5162	57.0	114	1.6318	28.7574	110.6824
0.5162	58.0	116	1.6326	28.6881	110.527
0.5162	59.0	118	1.6357	28.8016	110.75
0.5162	60.0	120	1.6405	28.1483	115.7703
0.5162	61.0	122	1.6455	28.1723	115.6216
0.5162	62.0	124	1.6449	28.4911	111.9189
0.5162	63.0	126	1.6579	28.5514	107.2568
0.5162	64.0	128	1.6580	28.6122	104.4595
0.5162	65.0	130	1.6640	28.6139	104.1149
0.5162	66.0	132	1.6707	28.67	111.2432
0.5162	67.0	134	1.6725	28.8189	105.3784
0.5162	68.0	136	1.6731	28.779	104.25
0.5162	69.0	138	1.6885	28.8597	104.5608
0.5162	70.0	140	1.6839	28.3034	112.9324
0.5162	71.0	142	1.6850	28.8562	103.6892
0.5162	72.0	144	1.6870	28.7335	110.0203
0.5162	73.0	146	1.6820	28.4073	109.3311
0.5162	74.0	148	1.6763	28.668	110.3784
0.5162	75.0	150	1.6826	28.1488	115.5743
0.5162	76.0	152	1.6933	28.4869	106.5608
0.5162	77.0	154	1.6928	28.2594	113.0203
0.5162	78.0	156	1.6902	28.3956	110.2635
0.5162	79.0	158	1.6933	28.5661	110.3108
0.5162	80.0	160	1.6916	28.1052	117.2027
0.5162	81.0	162	1.6982	28.6164	110.0608
0.5162	82.0	164	1.7062	27.9785	115.527
0.5162	83.0	166	1.7084	28.4984	110.0203
0.5162	84.0	168	1.7101	28.2805	116.6757

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 31, 2026
Updated: Jul 31, 2026