metadata
license: apache-2.0
base_model: bert-large-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: baseline_nli_bert-large
results: []
baseline_nli_bert-large
This model is a fine-tuned version of bert-large-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9293
- Accuracy: 0.6163
- Precision: 0.6163
- Recall: 0.6163
- F1 Score: 0.6185
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 |
|---|---|---|---|---|---|---|---|
| 1.0447 | 1.0 | 2583 | 0.9867 | 0.4602 | 0.4602 | 0.4602 | 0.4166 |
| 0.9632 | 2.0 | 5166 | 0.9132 | 0.5926 | 0.5926 | 0.5926 | 0.5965 |
| 0.9063 | 3.0 | 7749 | 0.8976 | 0.6076 | 0.6076 | 0.6076 | 0.6116 |
| 0.846 | 4.0 | 10332 | 0.8826 | 0.6218 | 0.6218 | 0.6218 | 0.6212 |
| 0.7975 | 5.0 | 12915 | 0.9189 | 0.6136 | 0.6136 | 0.6136 | 0.6169 |
| 0.7605 | 6.0 | 15498 | 0.9293 | 0.6163 | 0.6163 | 0.6163 | 0.6185 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3