You can deploy this model and start earning money today!

contemmcm/
d896a6f7e50a25662cf8837d38c9c288

generated_from_trainer

google-bert/bert-base-multilingual-uncased

finetune

apache-2.0

text-embeddings-inference

endpoints_compatible

Views

No views yet

d896a6f7e50a25662cf8837d38c9c288

This model is a fine-tuned version of google-bert/bert-base-multilingual-uncased on the nyu-mll/glue [mnli] dataset. It achieves the following results on the evaluation set:

Loss: 0.8244
Data Size: 1.0
Epoch Runtime: 602.7704
Accuracy: 0.7387
F1 Macro: 0.7379
Rouge1: 0.7388
Rouge2: 0.0
Rougel: 0.7388
Rougelsum: 0.7386

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	1.1095	0	4.6579	0.3169	0.1749	0.3171	0.3166	0.3170
1.1208	1	12271	1.0413	0.0078	9.6026	0.4730	0.4680	0.4729	0.4730	0.4728
1.0043	2	24542	0.9286	0.0156	15.0144	0.5735	0.5656	0.5735	0.5734	0.5740
0.895	3	36813	0.8594	0.0312	23.7314	0.6219	0.6129	0.6218	0.6221	0.6223
0.836	4	49084	0.7620	0.0625	42.8018	0.6706	0.6663	0.6704	0.6706	0.6709
0.7129	5	61355	0.7219	0.125	81.4421	0.6911	0.6911	0.6910	0.6912	0.6916
0.6923	6	73626	0.6727	0.25	153.0302	0.7215	0.7218	0.7218	0.7214	0.7215
0.6021	7	85897	0.6210	0.5	298.9501	0.7463	0.7456	0.7464	0.7462	0.7464
0.5747	8.0	98168	0.6207	1.0	602.5944	0.7638	0.7638	0.7635	0.7639	0.7639
0.4846	9.0	110439	0.6007	1.0	607.4698	0.7714	0.7710	0.7712	0.7717	0.7714
0.4726	10.0	122710	0.6036	1.0	611.9129	0.7629	0.7609	0.7627	0.7626	0.7630
0.4074	11.0	134981	0.6565	1.0	604.8089	0.7735	0.7734	0.7732	0.7736	0.7735
0.3494	12.0	147252	0.6686	1.0	601.9429	0.7718	0.7716	0.7717	0.7720	0.7720
0.3979	13.0	159523	0.8244	1.0	602.7704	0.7387	0.7379	0.7388	0.7388	0.7386

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.3.0
Tokenizers 0.22.1

contemmcm/d896a6f7e50a25662cf8837d38c9c288

d896a6f7e50a25662cf8837d38c9c288

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
d896a6f7e50a25662cf8837d38c9c288