Summarization
Transformers
PyTorch
TensorBoard
mt5
text2text-generation
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("chrisjay/cos801-802-hf-workshop-mt5-small")
model = AutoModelForSeq2SeqLM.from_pretrained("chrisjay/cos801-802-hf-workshop-mt5-small", device_map="auto")Quick Links
cos801-802-hf-workshop-mt5-small
This model is a fine-tuned version of google/mt5-small on the xlsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.7998
- Rouge1: 20.928
- Rouge2: 6.3239
- Rougel: 17.4455
- Rougelsum: 17.4566
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: 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: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 3.844 | 1.0 | 1975 | 2.7998 | 20.928 | 6.3239 | 17.4455 | 17.4566 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1
- Downloads last month
- 4
Evaluation results
- Rouge1 on xlsumself-reported20.928
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("summarization", model="chrisjay/cos801-802-hf-workshop-mt5-small")