ALL_mt5-base_15_spider_no_sch
This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3725
- Rouge2 Precision: 0.4149
- Rouge2 Recall: 0.277
- Rouge2 Fmeasure: 0.3114
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: 15
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
---|---|---|---|---|---|---|
0.6025 | 1.0 | 1293 | 0.3674 | 0.3002 | 0.1808 | 0.2056 |
0.239 | 2.0 | 2586 | 0.3164 | 0.375 | 0.2477 | 0.2782 |
0.1924 | 3.0 | 3879 | 0.3116 | 0.3812 | 0.2506 | 0.2827 |
0.1482 | 4.0 | 5172 | 0.3161 | 0.3903 | 0.2592 | 0.2911 |
0.1285 | 5.0 | 6465 | 0.3217 | 0.4033 | 0.2688 | 0.302 |
0.1105 | 6.0 | 7758 | 0.3302 | 0.4085 | 0.2708 | 0.3047 |
0.0969 | 7.0 | 9051 | 0.3358 | 0.4091 | 0.2735 | 0.3069 |
0.0878 | 8.0 | 10344 | 0.3382 | 0.4087 | 0.2725 | 0.3057 |
0.0806 | 9.0 | 11637 | 0.3503 | 0.4118 | 0.275 | 0.3088 |
0.0765 | 10.0 | 12930 | 0.3537 | 0.4164 | 0.2775 | 0.3119 |
0.0683 | 11.0 | 14223 | 0.3590 | 0.4137 | 0.2768 | 0.3107 |
0.0658 | 12.0 | 15516 | 0.3646 | 0.4161 | 0.2785 | 0.3126 |
0.0639 | 13.0 | 16809 | 0.3694 | 0.4186 | 0.2804 | 0.3148 |
0.0623 | 14.0 | 18102 | 0.3693 | 0.4149 | 0.2775 | 0.3115 |
0.0612 | 15.0 | 19395 | 0.3725 | 0.4149 | 0.277 | 0.3114 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.7.dev0
- Tokenizers 0.13.3
- Downloads last month
- 13
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.