metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- tweet_eval
metrics:
- f1
model-index:
- name: demo_emotion_31415
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: tweet_eval
type: tweet_eval
args: emotion
metrics:
- name: F1
type: f1
value: 0.7348035780583043
demo_emotion_31415
This model is a fine-tuned version of distilbert-base-uncased on the tweet_eval dataset. It achieves the following results on the evaluation set:
- Loss: 0.9818
- F1: 0.7348
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: 7.551070618629693e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | F1 |
---|---|---|---|---|
No log | 1.0 | 204 | 0.7431 | 0.6530 |
No log | 2.0 | 408 | 0.6943 | 0.7333 |
0.5176 | 3.0 | 612 | 0.8456 | 0.7326 |
0.5176 | 4.0 | 816 | 0.9818 | 0.7348 |
Framework versions
- Transformers 4.12.5
- Pytorch 1.9.1
- Datasets 1.16.1
- Tokenizers 0.10.3