You can deploy this model and start earning money today!

contemmcm/
a5e2046951ef348f3fd285f6ac345904

Name: a5e2046951ef348f3fd285f6ac345904
Rating: 2.5 (7 reviews)

generated_from_trainer

studio-ousia/mluke-large-lite

finetune

apache-2.0

endpoints_compatible

Views

No views yet

a5e2046951ef348f3fd285f6ac345904

This model is a fine-tuned version of studio-ousia/mluke-large-lite on the nyu-mll/glue [mrpc] dataset. It achieves the following results on the evaluation set:

Loss: 0.6381
Data Size: 1.0
Epoch Runtime: 25.1730
Accuracy: 0.6651
F1 Macro: 0.3994
Rouge1: 0.6657
Rouge2: 0.0
Rougel: 0.6645
Rougelsum: 0.6651

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	0.6751	0	3.1298	0.6651	0.3994	0.6657	0.6645	0.6651
No log	1	114	0.6873	0.0078	4.0532	0.6203	0.4733	0.6203	0.6203	0.6203
No log	2	228	0.6642	0.0156	4.5651	0.6651	0.3994	0.6657	0.6645	0.6651
No log	3	342	0.6570	0.0312	5.3771	0.6651	0.3994	0.6657	0.6645	0.6651
0.0217	4	456	0.7420	0.0625	6.8735	0.3361	0.2548	0.3355	0.3364	0.3361
0.0217	5	570	0.6380	0.125	8.2044	0.6651	0.3994	0.6657	0.6645	0.6651
0.0217	6	684	0.6378	0.25	11.1089	0.6651	0.3994	0.6657	0.6645	0.6651
0.1624	7	798	0.6378	0.5	16.3000	0.6651	0.3994	0.6657	0.6645	0.6651
0.6491	8.0	912	0.6391	1.0	25.8659	0.6651	0.3994	0.6657	0.6645	0.6651
0.6435	9.0	1026	0.6380	1.0	25.0360	0.6651	0.3994	0.6657	0.6645	0.6651
0.6264	10.0	1140	0.6381	1.0	25.1730	0.6651	0.3994	0.6657	0.6645	0.6651

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.3.0
Tokenizers 0.22.1

contemmcm/a5e2046951ef348f3fd285f6ac345904

a5e2046951ef348f3fd285f6ac345904

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
a5e2046951ef348f3fd285f6ac345904