mini-vanilla-target-tweet

This model is a fine-tuned version of google/bert_uncased_L-4_H-256_A-4 on the tweet_eval dataset. It achieves the following results on the evaluation set:

• Loss: 1.5603
• Accuracy: 0.7540
• F1: 0.7569

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
0.9285	4.9	500	0.7493	0.7273	0.7207
0.4468	9.8	1000	0.7630	0.7460	0.7437
0.2194	14.71	1500	0.8997	0.7406	0.7455
0.1062	19.61	2000	1.0822	0.7433	0.7435
0.0568	24.51	2500	1.2225	0.7620	0.7622
0.0439	29.41	3000	1.3475	0.7513	0.7527
0.0304	34.31	3500	1.4999	0.7433	0.7399
0.0247	39.22	4000	1.5603	0.7540	0.7569

Framework versions

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