metadata
library_name: transformers
license: apache-2.0
base_model: shorecode/t5-efficient-tiny-nh8-summarizer
tags:
- generated_from_trainer
model-index:
- name: t5-efficient-tiny-nh8-summarizer
results: []
datasets:
- shorecode/summary-collection-60k-rows
t5-efficient-tiny-nh8-summarizer
This model is a fine-tuned version of shorecode/t5-efficient-tiny-nh8-summarizer on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6597
Model description
A general purpose text summarizer
Intended uses & limitations
General purpose text summarizer
Training and evaluation data
Trained and evaluated on shorecode/summary-collection-60k-rows
Training procedure
Trained using the Gradio SDK on Hugging Face Spaces using shared Zero GPU(s)
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.00015000000000000001
- train_batch_size: 63
- eval_batch_size: 63
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0837 | 0.2663 | 200 | 0.9227 |
| 0.9027 | 0.5326 | 400 | 0.8449 |
| 0.842 | 0.7989 | 600 | 0.7949 |
| 0.7971 | 1.0652 | 800 | 0.7585 |
| 0.768 | 1.3316 | 1000 | 0.7288 |
| 0.7359 | 1.5979 | 1200 | 0.7069 |
| 0.7145 | 1.8642 | 1400 | 0.6898 |
| 0.7047 | 2.1305 | 1600 | 0.6773 |
| 0.6926 | 2.3968 | 1800 | 0.6678 |
| 0.6855 | 2.6631 | 2000 | 0.6620 |
| 0.68 | 2.9294 | 2200 | 0.6597 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.21.0