metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: xlnet-large_spell_5k_1_p3
results: []
xlnet-large_spell_5k_1_p3
This model is a fine-tuned version of model_saves/xlnet-large_spell_5k_1_p2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4678
- Accuracy: 0.9400
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: 128
- eval_batch_size: 128
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 15.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 268 | 0.4383 | 0.9397 |
| No log | 2.0 | 536 | 0.4678 | 0.9400 |
| No log | 3.0 | 804 | 0.4920 | 0.9397 |
| 0.2974 | 4.0 | 1072 | 0.5351 | 0.9390 |
| 0.2974 | 5.0 | 1340 | 0.5907 | 0.9388 |
Framework versions
- Transformers 4.21.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1