metadata
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
base_model: >-
mmillet/distilrubert-tiny-cased-conversational-v1_best_finetuned_emotion_experiment_augmented_anger_fear
model-index:
- name: distilrubert-2ndfinetune-epru
results: []
distilrubert-2ndfinetune-epru
This model is a fine-tuned version of mmillet/distilrubert-tiny-cased-conversational-v1_best_finetuned_emotion_experiment_augmented_anger_fear on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3531
- Accuracy: 0.9054
- F1: 0.9034
- Precision: 0.9074
- Recall: 0.9054
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.4716 | 1.0 | 11 | 0.2851 | 0.8986 | 0.8945 | 0.9029 | 0.8986 |
| 0.2842 | 2.0 | 22 | 0.3041 | 0.8851 | 0.8796 | 0.8816 | 0.8851 |
| 0.167 | 3.0 | 33 | 0.2996 | 0.8986 | 0.8914 | 0.8997 | 0.8986 |
| 0.1527 | 4.0 | 44 | 0.2443 | 0.9189 | 0.9163 | 0.9222 | 0.9189 |
| 0.0926 | 5.0 | 55 | 0.2777 | 0.9054 | 0.9016 | 0.9059 | 0.9054 |
| 0.0897 | 6.0 | 66 | 0.3081 | 0.9122 | 0.9080 | 0.9147 | 0.9122 |
| 0.0438 | 7.0 | 77 | 0.3332 | 0.8986 | 0.8952 | 0.8993 | 0.8986 |
| 0.0433 | 8.0 | 88 | 0.3480 | 0.8851 | 0.8859 | 0.8896 | 0.8851 |
| 0.0398 | 9.0 | 99 | 0.3531 | 0.9054 | 0.9034 | 0.9074 | 0.9054 |
Framework versions
- Transformers 4.19.3
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1