metadata
license: cc-by-nc-nd-4.0
base_model: google/t5-efficient-base
tags:
- generated_from_trainer
model-index:
- name: checkpoint
results: []
how to use the model
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch
tokenizer = AutoTokenizer.from_pretrained("piazzola/test1")
model = AutoModelForSeq2SeqLM.from_pretrained("piazzola/test1")
sentence = "i left the keys in the car."
with torch.no_grad():
inputs = tokenizer([sentence], return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
generated_text = tokenizer.decode(outputs[0])
print(generated_text)
checkpoint
This model is a fine-tuned version of google/t5-efficient-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1609
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: 5e-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
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3088 | 0.3 | 7458 | 0.2634 |
| 0.2615 | 0.6 | 14916 | 0.2143 |
| 0.2294 | 0.9 | 22374 | 0.1951 |
| 0.2137 | 1.2 | 29832 | 0.1830 |
| 0.1944 | 1.5 | 37290 | 0.1736 |
| 0.1918 | 1.8 | 44748 | 0.1682 |
| 0.18 | 2.1 | 52206 | 0.1659 |
| 0.1801 | 2.4 | 59664 | 0.1623 |
| 0.185 | 2.7 | 67122 | 0.1609 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2