You can deploy this model and start earning money today!

contemmcm/
8454b4ff2b950e0df78ff87ae5522581

Name: 8454b4ff2b950e0df78ff87ae5522581
Rating: 2.5 (10 reviews)

generated_from_trainer

studio-ousia/mluke-base-lite

finetune

apache-2.0

endpoints_compatible

Views

No views yet

8454b4ff2b950e0df78ff87ae5522581

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

Loss: 1.2793
Data Size: 1.0
Epoch Runtime: 21.0942
Accuracy: 0.7692
F1 Macro: 0.8090
Rouge1: 0.7699
Rouge2: 0.0
Rougel: 0.7692
Rougelsum: 0.7685

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	1.6040	0	1.6877	0.2266	0.1813	0.2266	0.2266	0.2266
No log	1	178	1.4686	0.0078	2.2666	0.3246	0.1691	0.3253	0.3260	0.3246
No log	2	356	1.2141	0.0156	2.3702	0.6357	0.4354	0.6357	0.6364	0.6357
No log	3	534	0.9243	0.0312	3.0778	0.6662	0.5176	0.6662	0.6669	0.6662
No log	4	712	0.8206	0.0625	3.9241	0.7109	0.5406	0.7124	0.7116	0.7109
No log	5	890	0.7427	0.125	4.9980	0.7102	0.5405	0.7109	0.7109	0.7102
0.0531	6	1068	0.7274	0.25	6.8783	0.7209	0.5787	0.7216	0.7216	0.7209
0.5836	7	1246	0.6455	0.5	11.0977	0.7557	0.7376	0.7564	0.7557	0.7557
0.4986	8.0	1424	0.6025	1.0	19.5528	0.7614	0.7763	0.7621	0.7621	0.7614
0.3578	9.0	1602	0.6960	1.0	19.9747	0.7614	0.7845	0.7621	0.7614	0.7614
0.2094	10.0	1780	0.7427	1.0	20.1443	0.7706	0.8069	0.7706	0.7713	0.7706
0.1496	11.0	1958	0.9641	1.0	20.5362	0.7592	0.7989	0.7596	0.7599	0.7589
0.0997	12.0	2136	1.2793	1.0	21.0942	0.7692	0.8090	0.7699	0.7692	0.7685

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.3.0
Tokenizers 0.22.1

contemmcm/8454b4ff2b950e0df78ff87ae5522581

8454b4ff2b950e0df78ff87ae5522581

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
8454b4ff2b950e0df78ff87ae5522581