large-4-6-t-nofp16
This model is a fine-tuned version of cnn/large-4-6/ on the cnn_dailymail 3.0.0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.2714
- Rouge1: 43.7601
- Rouge2: 20.8296
- Rougel: 31.2243
- Rougelsum: 40.9214
- Gen Len: 71.5850
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 3.0
Training results
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 1
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Dataset used to train spacemanidol/flan-t5-large-4-6-cnndm
Evaluation results
- Rouge1 on cnn_dailymail 3.0.0validation set self-reported43.760