medium-mlm-tweet-target-tweet

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

• Loss: 1.9066
• Accuracy: 0.7594
• F1: 0.7637

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
0.4702	4.9	500	0.8711	0.7540	0.7532
0.0629	9.8	1000	1.2918	0.7701	0.7668
0.0227	14.71	1500	1.4801	0.7727	0.7696
0.0181	19.61	2000	1.5118	0.7888	0.7870
0.0114	24.51	2500	1.6747	0.7754	0.7745
0.0141	29.41	3000	1.8765	0.7674	0.7628
0.0177	34.31	3500	1.9066	0.7594	0.7637

Framework versions

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