samsum_42
This model is a fine-tuned version of google/t5-v1_1-small on the samsum dataset. It achieves the following results on the evaluation set:
- eval_loss: 44.6744
- eval_rouge1: 0.9086
- eval_rouge2: 0.0
- eval_rougeL: 0.9116
- eval_rougeLsum: 0.9122
- eval_gen_len: 127.0
- eval_runtime: 106.1694
- eval_samples_per_second: 7.705
- eval_steps_per_second: 0.97
- test_rougeL: 0.9116
- df_rougeL: 0.9908
- unlearn_overall_rougeL: 0.4604
- eval_unlearn_overall_rougeL: 0.4604
- unlearn_time: -1
- step: 0
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Framework versions
- Transformers 4.39.3
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
- Downloads last month
- 5
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for jialicheng/unlearn_samsum_t5-small_bad_teaching_2_42
Base model
google/t5-v1_1-small