You can deploy this model and start earning money today!

muhtasham/
small-vanilla-target-tweet

Name: small-vanilla-target-tweet
Availability: InStock

generated_from_trainer

Views

No views yet

small-vanilla-target-tweet

This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the tweet_eval dataset. It achieves the following results on the evaluation set:

Loss: 1.8718
Accuracy: 0.7540
F1: 0.7525

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: 3e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
num_epochs: 200

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.5858	4.9	500	0.8189	0.7380	0.7364
0.1039	9.8	1000	1.1965	0.7594	0.7568
0.0264	14.71	1500	1.5387	0.7433	0.7460
0.0142	19.61	2000	1.6758	0.7620	0.7551
0.0113	24.51	2500	1.8718	0.7540	0.7525

Framework versions

Transformers 4.25.1
Pytorch 1.12.1
Datasets 2.7.1
Tokenizers 0.13.2

muhtasham/small-vanilla-target-tweet

small-vanilla-target-tweet

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

muhtasham/
small-vanilla-target-tweet