tiny-mlm-tweet-target-tweet

This model is a fine-tuned version of muhtasham/tiny-mlm-tweet on the tweet_eval dataset. It achieves the following results on the evaluation set:

• Loss: 1.2643
• Accuracy: 0.7166
• F1: 0.7163

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
1.1435	4.9	500	0.9732	0.6604	0.6283
0.7389	9.8	1000	0.8571	0.6898	0.6780
0.5057	14.71	1500	0.8324	0.6979	0.6929
0.3466	19.61	2000	0.9128	0.6925	0.6945
0.2395	24.51	2500	0.9487	0.7166	0.7192
0.1649	29.41	3000	1.0338	0.7166	0.7172
0.119	34.31	3500	1.1793	0.7112	0.7144
0.0882	39.22	4000	1.2643	0.7166	0.7163

Framework versions

• Transformers 4.25.1
• Pytorch 1.12.1
• Datasets 2.7.1
• Tokenizers 0.13.2