You can deploy this model and start earning money today!

contemmcm/
9045aeddedf7e34888a9e88798881284

generated_from_trainer

studio-ousia/luke-japanese-base-lite

finetune

apache-2.0

endpoints_compatible

Views

No views yet

9045aeddedf7e34888a9e88798881284

This model is a fine-tuned version of studio-ousia/luke-japanese-base-lite on the dim/tldr_news dataset. It achieves the following results on the evaluation set:

Loss: 0.7725
Data Size: 1.0
Epoch Runtime: 17.7684
Accuracy: 0.7308
F1 Macro: 0.7558
Rouge1: 0.7315
Rouge2: 0.0
Rougel: 0.7315
Rougelsum: 0.7308

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: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro	Rouge1	Rougel	Rougelsum
No log	0	0	1.7408	0	1.8051	0.0185	0.0073	0.0185	0.0185	0.0185
No log	1	178	1.4953	0.0078	3.1984	0.2401	0.0774	0.2401	0.2408	0.2393
No log	2	356	1.4353	0.0156	2.3164	0.4268	0.2599	0.4268	0.4268	0.4261
No log	3	534	1.2380	0.0312	2.6415	0.3743	0.2331	0.3743	0.3743	0.3736
No log	4	712	1.1336	0.0625	3.3893	0.4609	0.2664	0.4624	0.4602	0.4602
No log	5	890	1.0869	0.125	4.2491	0.4716	0.2762	0.4723	0.4716	0.4716
0.0746	6	1068	1.0781	0.25	6.3982	0.5859	0.4217	0.5866	0.5859	0.5859
0.8633	7	1246	0.9063	0.5	10.5676	0.6335	0.4645	0.6349	0.6335	0.6342
0.7234	8.0	1424	0.7850	1.0	18.8049	0.6982	0.6855	0.6982	0.6982	0.6982
0.6556	9.0	1602	0.6991	1.0	18.4465	0.7344	0.7234	0.7351	0.7344	0.7344
0.5771	10.0	1780	0.7003	1.0	17.9046	0.7273	0.7200	0.7273	0.7273	0.7273
0.5291	11.0	1958	0.7648	1.0	18.6474	0.7259	0.7324	0.7259	0.7259	0.7259
0.4595	12.0	2136	0.7981	1.0	17.6703	0.7152	0.7331	0.7152	0.7159	0.7159
0.391	13.0	2314	0.7725	1.0	17.7684	0.7308	0.7558	0.7315	0.7315	0.7308

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.3.0
Tokenizers 0.22.1

contemmcm/9045aeddedf7e34888a9e88798881284

9045aeddedf7e34888a9e88798881284

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
9045aeddedf7e34888a9e88798881284