metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- tweet_eval
metrics:
- precision
- recall
base_model: distilbert-base-cased
model-index:
- name: bert-emotion
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: tweet_eval
type: tweet_eval
args: emotion
metrics:
- type: precision
value: 0.7081377380103309
name: Precision
- type: recall
value: 0.709386945441909
name: Recall
bert-emotion
This model is a fine-tuned version of distilbert-base-cased on the tweet_eval dataset. It achieves the following results on the evaluation set:
- Loss: 1.2350
- Precision: 0.7081
- Recall: 0.7094
- Fscore: 0.7082
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Fscore |
|---|---|---|---|---|---|---|
| 0.8442 | 1.0 | 815 | 0.8653 | 0.7642 | 0.6192 | 0.6363 |
| 0.5488 | 2.0 | 1630 | 0.9330 | 0.7116 | 0.6838 | 0.6912 |
| 0.2713 | 3.0 | 2445 | 1.2350 | 0.7081 | 0.7094 | 0.7082 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.1
- Tokenizers 0.12.1