<!-- 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_recommendation_piscine_equipements_large
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8443
- Rouge1: 34.1161
- Rouge2: 26.3432
- Rougel: 33.9077
- Rougelsum: 33.9241
- Gen Len: 18.7083
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 0.92 | 3 | 2.3712 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
No log | 1.92 | 6 | 1.2669 | 22.7772 | 20.7387 | 22.8081 | 22.7953 | 9.0958 |
No log | 2.92 | 9 | 0.9796 | 31.9168 | 24.7944 | 31.8451 | 31.7950 | 18.8379 |
No log | 3.92 | 12 | 0.9213 | 29.0572 | 22.0777 | 29.0892 | 29.0306 | 18.5734 |
No log | 4.92 | 15 | 0.8704 | 23.9262 | 16.1217 | 23.7935 | 23.7483 | 17.7846 |
No log | 5.92 | 18 | 0.8323 | 28.4808 | 25.0648 | 28.4294 | 28.4832 | 12.6973 |
No log | 6.92 | 21 | 0.8144 | 28.3291 | 20.5699 | 28.0259 | 27.9503 | 18.1416 |
No log | 7.92 | 24 | 0.8465 | 24.8294 | 21.5138 | 24.6756 | 24.6961 | 9.9852 |
No log | 8.92 | 27 | 0.8597 | 29.5795 | 23.0855 | 29.4314 | 29.4205 | 17.4714 |
No log | 9.92 | 30 | 0.8443 | 34.1161 | 26.3432 | 33.9077 | 33.9241 | 18.7083 |
Framework versions
- Transformers 4.26.0
- Pytorch 2.0.0+cpu
- Datasets 2.8.0
- Tokenizers 0.13.3