how to use the model
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("piazzola/test2")
model = AutoModelForSeq2SeqLM.from_pretrained("piazzola/test2")
from transformers import pipeline
pipe = pipeline("text2text-generation", model="piazzola/test2")
sentence = "i left the keys in the car."
output = pipe(sentence, max_new_tokens=100, do_sample=True, temperature=0.1)
print(output)
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: 0.3070
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: 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: 3
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
No log | 0.3 | 240 | 1.4901 |
No log | 0.6 | 480 | 0.7750 |
3.5263 | 0.9 | 720 | 0.5219 |
3.5263 | 1.2 | 960 | 0.3782 |
0.607 | 1.5 | 1200 | 0.3521 |
0.607 | 1.8 | 1440 | 0.3356 |
0.4173 | 2.1 | 1680 | 0.3255 |
0.4173 | 2.4 | 1920 | 0.3151 |
0.368 | 2.7 | 2160 | 0.3093 |
0.368 | 3.0 | 2400 | 0.3070 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 6
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for piazzola/test2
Base model
google/t5-efficient-base
Finetuned
this model