pawaca/minirbt-h256-fin-finetuned
By pawaca · ↓ 2 · ♥ 0 · Updated 2023-04-20
What's in this repo
This page lists the files in pawaca/minirbt-h256-fin-finetuned, including quantized.onnx, quantized_int8.onnx, quantized_int8_13.onnx and more.
- 4 ONNX models (.onnx files)
- 14 files, including 4 .json, 4 .onnx, 2 .bin, 1 .md, 1 .txt
- Last updated 2023-04-20
ONNX files
| File | Size | Download |
|---|---|---|
| quantized.onnx | — | Download |
| quantized_int8.onnx | — | Download |
| quantized_int8_13.onnx | — | Download |
| ttt_quantized_int8_v1.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
minirbt-h256-fin-finetuned
This model is a fine-tuned version of hfl/minirbt-h256 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4252
- Accuracy: 0.8808
- F1: 0.8813
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- 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 | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.4226 | 1.0 | 1096 | 0.4544 | 0.8569 | 0.8576 |
| 0.3963 | 2.0 | 2192 | 0.3878 | 0.8800 | 0.8806 |
| 0.324 | 3.0 | 3288 | 0.4218 | 0.8779 | 0.8784 |
| 0.3088 | 4.0 | 4384 | 0.4252 | 0.8808 | 0.8813 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.0.0.dev20230212
- Datasets 2.9.0
- Tokenizers 0.13.2
Model info
Created: 2023-02-17
Updated: 2023-04-20
View on Hugging FaceFiles (14)
Related models
More from pawaca
No other models by this author.