<!-- 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. -->
T5-model-1-feedback-2010-e4
This model is a fine-tuned version of theojolliffe/T5-model-1-feedback-1109 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2075
- Rouge1: 92.2165
- Rouge2: 86.2314
- Rougel: 91.5975
- Rougelsum: 91.509
- Gen Len: 15.2586
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
0.2922 | 1.0 | 1646 | 0.2603 | 91.6366 | 84.8657 | 90.8246 | 90.9026 | 15.092 |
0.2264 | 2.0 | 3292 | 0.2311 | 92.5522 | 86.8008 | 91.9435 | 91.88 | 15.2586 |
0.187 | 3.0 | 4938 | 0.2085 | 91.982 | 86.0585 | 91.3852 | 91.3091 | 15.3161 |
0.1879 | 4.0 | 6584 | 0.2075 | 92.2165 | 86.2314 | 91.5975 | 91.509 | 15.2586 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1