You can deploy this model and start earning money today!

contemmcm/
81db3afc86688b101ef5c5277b3c88d3

Name: 81db3afc86688b101ef5c5277b3c88d3
Rating: 2.5 (5 reviews)

generated_from_trainer

google-bert/bert-base-cased

finetune

apache-2.0

text-embeddings-inference

endpoints_compatible

Views

No views yet

81db3afc86688b101ef5c5277b3c88d3

This model is a fine-tuned version of google-bert/bert-base-cased on the nyu-mll/glue [sst2] dataset. It achieves the following results on the evaluation set:

Loss: 0.3551
Data Size: 1.0
Epoch Runtime: 100.7162
Accuracy: 0.8877
F1 Macro: 0.8877
Rouge1: 0.8877
Rouge2: 0.0
Rougel: 0.8877
Rougelsum: 0.8877

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	0.6866	0	0.9469	0.5093	0.3374	0.5093	0.5093	0.5081
No log	1	2104	0.4378	0.0078	2.8387	0.8218	0.8209	0.8218	0.8223	0.8218
No log	2	4208	0.4187	0.0156	2.7773	0.8148	0.8122	0.8148	0.8148	0.8148
0.0097	3	6312	0.2649	0.0312	4.4697	0.8981	0.8981	0.8981	0.8981	0.8981
0.3061	4	8416	0.2898	0.0625	7.6073	0.8762	0.8761	0.8762	0.8762	0.8762
0.2443	5	10520	0.2497	0.125	13.5930	0.9016	0.9015	0.9016	0.9028	0.9016
0.2038	6	12624	0.2456	0.25	26.7561	0.9039	0.9039	0.9039	0.9039	0.9051
0.2166	7	14728	0.3039	0.5	50.2617	0.8981	0.8980	0.8981	0.8981	0.8981
0.1663	8.0	16832	0.2965	1.0	104.9552	0.8981	0.8981	0.8981	0.8981	0.8981
0.1357	9.0	18936	0.3578	1.0	100.4953	0.8924	0.8922	0.8929	0.8924	0.8924
0.1358	10.0	21040	0.3551	1.0	100.7162	0.8877	0.8877	0.8877	0.8877	0.8877

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.3.0
Tokenizers 0.22.1

contemmcm/81db3afc86688b101ef5c5277b3c88d3

81db3afc86688b101ef5c5277b3c88d3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
81db3afc86688b101ef5c5277b3c88d3