metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: baseline_nli_bert
results: []
baseline_nli_bert
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9280
- Accuracy: 0.6063
- Precision: 0.6063
- Recall: 0.6063
- F1 Score: 0.6088
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: 3e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 101
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
|---|---|---|---|---|---|---|---|
| 1.0366 | 1.0 | 2583 | 0.9579 | 0.5603 | 0.5603 | 0.5603 | 0.5638 |
| 0.9416 | 2.0 | 5166 | 0.9206 | 0.5826 | 0.5826 | 0.5826 | 0.5877 |
| 0.8889 | 3.0 | 7749 | 0.9085 | 0.5981 | 0.5981 | 0.5981 | 0.6025 |
| 0.8539 | 4.0 | 10332 | 0.9176 | 0.6054 | 0.6054 | 0.6054 | 0.6089 |
| 0.8323 | 5.0 | 12915 | 0.9201 | 0.6049 | 0.6049 | 0.6049 | 0.6066 |
| 0.811 | 6.0 | 15498 | 0.9280 | 0.6063 | 0.6063 | 0.6063 | 0.6088 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.12.1
- Datasets 2.11.0
- Tokenizers 0.13.2