JohnDoe70/t5-summarization
By JohnDoe70 · ↓ 4 · ♥ 0 · Updated 2024-04-16
What's in this repo
This page lists the files in JohnDoe70/t5-summarization, including decoder_model.onnx, decoder_model_merged.onnx, decoder_model_merged_quantized.onnx and more.
- 8 ONNX models (.onnx files)
- 19 files, including 8 .onnx, 5 .json, 1 .md, 1 .safetensors, 1 .0, 1 .model
- Last updated 2024-04-16
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/decoder_model.onnx | — | Download |
| onnx/decoder_model_merged.onnx | — | Download |
| onnx/decoder_model_merged_quantized.onnx | — | Download |
| onnx/decoder_model_quantized.onnx | — | Download |
| onnx/decoder_with_past_model.onnx | — | Download |
| onnx/decoder_with_past_model_quantized.onnx | — | Download |
| onnx/encoder_model.onnx | — | Download |
| onnx/encoder_model_quantized.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
t5-base-question-answer-summarization
This model is a fine-tuned version of google-t5/t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1420
- Rouge1: 87.2659
- Rouge2: 79.1621
- Rougel: 84.0716
- Rougelsum: 84.0332
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: 5.6e-05
- 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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 0.3593 | 1.0 | 450 | 0.1339 | 87.0068 | 78.4882 | 83.5134 | 83.4528 |
| 0.121 | 2.0 | 900 | 0.1273 | 87.3363 | 79.1644 | 83.7472 | 83.7456 |
| 0.0982 | 3.0 | 1350 | 0.1314 | 87.0066 | 78.3475 | 83.0262 | 82.9739 |
| 0.084 | 4.0 | 1800 | 0.1322 | 87.1678 | 78.7514 | 83.4642 | 83.441 |
| 0.074 | 5.0 | 2250 | 0.1345 | 87.2618 | 79.114 | 83.9859 | 83.9444 |
| 0.0685 | 6.0 | 2700 | 0.1378 | 87.1497 | 79.0628 | 83.958 | 83.9482 |
| 0.0609 | 7.0 | 3150 | 0.1419 | 86.993 | 78.781 | 83.8076 | 83.7681 |
| 0.0591 | 8.0 | 3600 | 0.1420 | 87.2659 | 79.1621 | 84.0716 | 84.0332 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
Model info
Created: 2024-04-15
Updated: 2024-04-16
View on Hugging Face