metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- tweet_eval
metrics:
- accuracy
- f1
base_model: google/bert_uncased_L-2_H-128_A-2
model-index:
- name: tiny-vanilla-target-tweet
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: tweet_eval
type: tweet_eval
config: emotion
split: train
args: emotion
metrics:
- type: accuracy
value: 0.7032085561497327
name: Accuracy
- type: f1
value: 0.704229444708009
name: F1
tiny-vanilla-target-tweet
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the tweet_eval dataset. It achieves the following results on the evaluation set:
- Loss: 0.9887
- Accuracy: 0.7032
- F1: 0.7042
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 |
|---|---|---|---|---|---|
| 1.1604 | 4.9 | 500 | 0.9784 | 0.6604 | 0.6290 |
| 0.7656 | 9.8 | 1000 | 0.8273 | 0.7139 | 0.6905 |
| 0.534 | 14.71 | 1500 | 0.8138 | 0.7219 | 0.7143 |
| 0.3832 | 19.61 | 2000 | 0.8591 | 0.7086 | 0.7050 |
| 0.2722 | 24.51 | 2500 | 0.9250 | 0.7112 | 0.7118 |
| 0.1858 | 29.41 | 3000 | 0.9887 | 0.7032 | 0.7042 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.13.2