<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
label_title_csm_model
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4474
- Rouge1: 0.2871
- Rouge2: 0.147
- Rougel: 0.2527
- Rougelsum: 0.2556
- Gen Len: 16.6875
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 37 | 4.0305 | 0.2175 | 0.1092 | 0.1967 | 0.2015 | 18.4375 |
No log | 2.0 | 74 | 3.7823 | 0.3395 | 0.1929 | 0.3012 | 0.3057 | 17.375 |
No log | 3.0 | 111 | 3.6354 | 0.3453 | 0.1971 | 0.3039 | 0.3079 | 16.375 |
No log | 4.0 | 148 | 3.5534 | 0.3556 | 0.1899 | 0.304 | 0.3057 | 17.25 |
No log | 5.0 | 185 | 3.5003 | 0.3579 | 0.1914 | 0.3058 | 0.3071 | 17.1875 |
No log | 6.0 | 222 | 3.4702 | 0.2938 | 0.1568 | 0.2598 | 0.2623 | 16.4375 |
No log | 7.0 | 259 | 3.4527 | 0.2871 | 0.147 | 0.2527 | 0.2556 | 16.8125 |
No log | 8.0 | 296 | 3.4474 | 0.2871 | 0.147 | 0.2527 | 0.2556 | 16.6875 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3