base-4-4-t
This model is a fine-tuned version of asy/cnndm/base-4-4/ on the cnn_dailymail 3.0.0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.5352
- Rouge1: 41.6423
- Rouge2: 19.1737
- Rougel: 29.5974
- Rougelsum: 38.827
- Gen Len: 74.5862
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: 2
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 32
- 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 0.12.1
- 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.
Dataset used to train spacemanidol/flan-t5-base-4-4-cnndm
Evaluation results
- Rouge1 on cnn_dailymail 3.0.0validation set self-reported41.642