<!-- 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. -->
MT-proud-terrain-70
This model is a fine-tuned version of toobiza/table-transformer-spring-energy-46 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2140
- Loss Ce: 0.0000
- Loss Bbox: 0.0299
- Cardinality Error: 1.0
- Giou: 96.8382
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Loss Ce | Loss Bbox | Cardinality Error | Giou |
---|---|---|---|---|---|---|---|
0.368 | 0.35 | 50 | 0.3644 | 0.0000 | 0.0512 | 1.0 | 94.7349 |
0.3191 | 0.69 | 100 | 0.2732 | 0.0000 | 0.0380 | 1.0 | 95.9487 |
0.2615 | 1.04 | 150 | 0.2396 | 0.0000 | 0.0335 | 1.0 | 96.4813 |
0.2308 | 1.39 | 200 | 0.2499 | 0.0000 | 0.0351 | 1.0 | 96.3438 |
0.1508 | 1.74 | 250 | 0.2326 | 0.0000 | 0.0327 | 1.0 | 96.6131 |
0.2175 | 2.08 | 300 | 0.2135 | 0.0000 | 0.0299 | 1.0 | 96.8596 |
0.1624 | 2.43 | 350 | 0.2089 | 0.0000 | 0.0292 | 1.0 | 96.9211 |
0.1474 | 2.78 | 400 | 0.2140 | 0.0000 | 0.0299 | 1.0 | 96.8382 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3