You can deploy this model and start earning money today!

contemmcm/
8037789717d57adae883007e3575d47f

Name: 8037789717d57adae883007e3575d47f
Rating: 2.5 (5 reviews)

generated_from_trainer

distilbert/distilroberta-base

finetune

apache-2.0

text-embeddings-inference

endpoints_compatible

Views

No views yet

8037789717d57adae883007e3575d47f

This model is a fine-tuned version of distilbert/distilroberta-base on the nyu-mll/glue [qqp] dataset. It achieves the following results on the evaluation set:

Loss: 0.3676
Data Size: 1.0
Epoch Runtime: 459.5587
Accuracy: 0.9016
F1 Macro: 0.8938
Rouge1: 0.9015
Rouge2: 0.0
Rougel: 0.9017
Rougelsum: 0.9016

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	0.6655	0	17.2995	0.6320	0.3872	0.6318	0.6319	0.6317
0.5819	1	11370	0.4808	0.0078	21.3608	0.7806	0.7637	0.7805	0.7806	0.7805
0.4379	2	22740	0.4082	0.0156	24.4125	0.8044	0.7890	0.8044	0.8044	0.8043
0.4089	3	34110	0.3948	0.0312	31.0521	0.8260	0.8113	0.8259	0.8260	0.8261
0.3655	4	45480	0.3973	0.0625	44.7174	0.8380	0.8201	0.8379	0.8380	0.8380
0.343	5	56850	0.3193	0.125	72.8486	0.8577	0.8512	0.8577	0.8577	0.8578
0.3105	6	68220	0.2952	0.25	127.8106	0.8693	0.8628	0.8693	0.8693	0.8694
0.2683	7	79590	0.2712	0.5	240.2425	0.8831	0.8764	0.8831	0.8831	0.8830
0.2553	8.0	90960	0.2685	1.0	458.7332	0.8933	0.8848	0.8932	0.8932	0.8933
0.2085	9.0	102330	0.2594	1.0	466.9302	0.8947	0.8891	0.8948	0.8947	0.8948
0.1683	10.0	113700	0.2819	1.0	458.0415	0.8995	0.8911	0.8994	0.8995	0.8995
0.1539	11.0	125070	0.3034	1.0	462.3257	0.8988	0.8927	0.8988	0.8987	0.8988
0.1304	12.0	136440	0.3214	1.0	456.8847	0.8990	0.8924	0.8990	0.8990	0.8990
0.1204	13.0	147810	0.3676	1.0	459.5587	0.9016	0.8938	0.9015	0.9017	0.9016

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.3.0
Tokenizers 0.22.1

contemmcm/8037789717d57adae883007e3575d47f

8037789717d57adae883007e3575d47f

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
8037789717d57adae883007e3575d47f