gptj-supervised-summarize-checkpoint
This model is a fine-tuned version of li-jay-cs/gptj-supervised-summarize-checkpoint on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8506
- Rouge1: 0.5938
- Rouge2: 0.1912
- Rougel: 0.3937
- Rougelsum: 0.5184
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: 1e-05
- train_batch_size: 50
- eval_batch_size: 50
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
---|---|---|---|---|---|---|---|
1.904 | 0.43 | 1000 | 1.8633 | 0.5912 | 0.1888 | 0.3913 | 0.5149 |
1.8931 | 0.86 | 2000 | 1.8584 | 0.5907 | 0.1890 | 0.3920 | 0.5153 |
1.8758 | 1.28 | 3000 | 1.8545 | 0.5929 | 0.1906 | 0.3929 | 0.5168 |
1.8699 | 1.71 | 4000 | 1.8506 | 0.5938 | 0.1912 | 0.3937 | 0.5184 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 9
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.