metadata
license: mit
base_model: facebook/bart-large-mnli
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: bart-large-mnli_17082023T105959
results: []
bart-large-mnli_17082023T105959
This model is a fine-tuned version of facebook/bart-large-mnli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6389
- Accuracy: 0.2557
- F1: 0.0679
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: 0.002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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 |
|---|---|---|---|---|---|
| No log | 1.0 | 142 | 1.7430 | 0.2469 | 0.0660 |
| No log | 2.0 | 284 | 1.9870 | 0.2469 | 0.0660 |
| No log | 2.99 | 426 | 1.7077 | 0.2346 | 0.0633 |
| 1.7955 | 4.0 | 569 | 1.6547 | 0.2469 | 0.0660 |
| 1.7955 | 5.0 | 711 | 1.6806 | 0.2557 | 0.0679 |
| 1.7955 | 6.0 | 853 | 1.6825 | 0.2469 | 0.0660 |
| 1.7955 | 6.99 | 995 | 1.6563 | 0.2557 | 0.0679 |
| 1.6691 | 8.0 | 1138 | 1.6473 | 0.2346 | 0.0633 |
| 1.6691 | 9.0 | 1280 | 1.6931 | 0.2557 | 0.0679 |
| 1.6691 | 9.98 | 1420 | 1.6389 | 0.2557 | 0.0679 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3