metadata
license: mit
base_model: xlnet/xlnet-base-cased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: emotional-xlnet
results: []
emotional-xlnet
This model is a fine-tuned version of xlnet/xlnet-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.9968
- Accuracy: 0.3875
- F1: 0.3676
- Precision: 0.3990
- Recall: 0.3875
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: 16
- eval_batch_size: 16
- seed: 42
- 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 | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 2.4746 | 1.0 | 270 | 2.3530 | 0.3085 | 0.2878 | 0.4138 | 0.3085 |
| 0.8581 | 2.0 | 540 | 2.1600 | 0.3466 | 0.3310 | 0.3603 | 0.3466 |
| 0.2628 | 3.0 | 810 | 2.3594 | 0.3575 | 0.3519 | 0.4060 | 0.3575 |
| 0.0791 | 4.0 | 1080 | 2.7493 | 0.3793 | 0.3643 | 0.3901 | 0.3793 |
| 0.0292 | 5.0 | 1350 | 2.9968 | 0.3875 | 0.3676 | 0.3990 | 0.3875 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2