base-vanilla-target-tweet

This model is a fine-tuned version of google/bert_uncased_L-12_H-768_A-12 on the tweet_eval dataset. It achieves the following results on the evaluation set:

• Loss: 1.8380
• Accuracy: 0.7781
• F1: 0.7773

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
0.3831	4.9	500	0.9800	0.7807	0.7785
0.0414	9.8	1000	1.4175	0.7754	0.7765
0.015	14.71	1500	1.6411	0.7754	0.7708
0.0166	19.61	2000	1.5930	0.7941	0.7938
0.0175	24.51	2500	1.3934	0.7888	0.7852
0.0191	29.41	3000	1.9407	0.7647	0.7658
0.0137	34.31	3500	1.8380	0.7781	0.7773

Framework versions

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