tiny-mlm-imdb-target-tweet

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

• Loss: 1.5550
• Accuracy: 0.6925
• F1: 0.7004

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
1.159	4.9	500	0.9977	0.6364	0.6013
0.7514	9.8	1000	0.8549	0.7112	0.7026
0.5011	14.71	1500	0.8516	0.7032	0.6962
0.34	19.61	2000	0.9019	0.7059	0.7030
0.2258	24.51	2500	0.9722	0.7166	0.7164
0.1607	29.41	3000	1.0724	0.6979	0.6999
0.1127	34.31	3500	1.1435	0.7193	0.7169
0.0791	39.22	4000	1.2807	0.7059	0.7069
0.0568	44.12	4500	1.3849	0.7139	0.7159
0.0478	49.02	5000	1.5550	0.6925	0.7004

Framework versions

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