max-gartz/distilbert-tweet_eval-emotion
By max-gartz · ↓ 2 · ♥ 0 · Updated 2024-02-15
What's in this repo
This page lists the files in max-gartz/distilbert-tweet_eval-emotion, including model.onnx.
- 1 ONNX models (.onnx files)
- 20 files, including 11 .json, 3 .txt, 1 .md, 1 .onnx, 1 .pt, 1 .safetensors
- Last updated 2024-02-15
ONNX files
| File | Size | Download |
|---|---|---|
| export/onnx/model.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
distilbert-tweet_eval-emotion
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: 0.6404
- Accuracy: 0.6529
- Precision: 0.8110
- Recall: 0.6529
- F1: 0.6507
- Auroc: 0.9184
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: 1e-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
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Auroc |
|---|---|---|---|---|---|---|---|---|
| 0.7228 | 0.55 | 500 | 0.7232 | 0.6030 | 0.5625 | 0.6030 | 0.5760 | 0.8937 |
| 0.64 | 1.1 | 1000 | 0.6404 | 0.6529 | 0.8110 | 0.6529 | 0.6507 | 0.9184 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.2
- Datasets 2.17.0
- Tokenizers 0.15.1
Model info
Created: 2024-02-14
Updated: 2024-02-15
View on Hugging FaceFiles (20)
Related models
More from max-gartz
No other models by this author.