medium-vanilla-target-tweet
This model is a fine-tuned version of google/bert_uncased_L-8_H-512_A-8 on the tweet_eval dataset. It achieves the following results on the evaluation set:
- Loss: 1.9845
- Accuracy: 0.7754
- F1: 0.7746
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 |
---|---|---|---|---|---|
0.4989 | 4.9 | 500 | 0.8358 | 0.7620 | 0.7589 |
0.0702 | 9.8 | 1000 | 1.3142 | 0.7674 | 0.7683 |
0.0233 | 14.71 | 1500 | 1.4760 | 0.7647 | 0.7650 |
0.015 | 19.61 | 2000 | 1.5151 | 0.7834 | 0.7841 |
0.0062 | 24.51 | 2500 | 1.6094 | 0.7968 | 0.7947 |
0.0113 | 29.41 | 3000 | 1.9273 | 0.7540 | 0.7537 |
0.0157 | 34.31 | 3500 | 2.0073 | 0.7433 | 0.7460 |
0.0124 | 39.22 | 4000 | 1.9845 | 0.7754 | 0.7746 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 13
Dataset used to train muhtasham/medium-vanilla-target-tweet
Evaluation results
- Accuracy on tweet_evalself-reported0.775
- F1 on tweet_evalself-reported0.775