metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: distilbert-base-cased-emotion
results: []
distilbert-base-cased-emotion
This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1771
- Accuracy: 0.9265
- F1: 0.9263
- Precision: 0.9276
- Recall: 0.9265
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.2633 | 1.0 | 500 | 0.2505 | 0.917 | 0.9174 | 0.9183 | 0.917 |
| 0.1815 | 2.0 | 1000 | 0.1921 | 0.9305 | 0.9304 | 0.9329 | 0.9305 |
| 0.1224 | 3.0 | 1500 | 0.1721 | 0.9355 | 0.9361 | 0.9388 | 0.9355 |
| 0.093 | 4.0 | 2000 | 0.1712 | 0.9365 | 0.9359 | 0.9367 | 0.9365 |
| 0.0782 | 5.0 | 2500 | 0.2116 | 0.9275 | 0.9271 | 0.9272 | 0.9275 |
| 0.0548 | 6.0 | 3000 | 0.2353 | 0.936 | 0.9348 | 0.9362 | 0.936 |
| 0.0358 | 7.0 | 3500 | 0.2729 | 0.9325 | 0.9331 | 0.9345 | 0.9325 |
| 0.0185 | 8.0 | 4000 | 0.3059 | 0.9325 | 0.9323 | 0.9322 | 0.9325 |
| 0.0124 | 9.0 | 4500 | 0.3103 | 0.9325 | 0.9325 | 0.9325 | 0.9325 |
| 0.0137 | 10.0 | 5000 | 0.3161 | 0.9305 | 0.9303 | 0.9303 | 0.9305 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.11.0+cu113
- Datasets 2.0.0
- Tokenizers 0.11.6