metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
base_model: bert-base-uncased
model-index:
- name: bert-base-uncased-finetuned-3d-sentiment
results: []
bert-base-uncased-finetuned-3d-sentiment
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9271
- Accuracy: 0.7392
- Precision: 0.7455
- Recall: 0.7392
- F1: 0.7394
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 6381
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
0.8443 | 1.0 | 1595 | 0.8265 | 0.6659 | 0.6920 | 0.6659 | 0.6629 |
0.6037 | 2.0 | 3190 | 0.7380 | 0.7021 | 0.7207 | 0.7021 | 0.7014 |
0.516 | 3.0 | 4785 | 0.6740 | 0.7246 | 0.7337 | 0.7246 | 0.7234 |
0.4269 | 4.0 | 6380 | 0.7221 | 0.7290 | 0.7383 | 0.7290 | 0.7271 |
0.3149 | 5.0 | 7975 | 0.8368 | 0.7237 | 0.7422 | 0.7237 | 0.7230 |
0.1996 | 6.0 | 9570 | 0.9271 | 0.7392 | 0.7455 | 0.7392 | 0.7394 |
0.1299 | 7.0 | 11165 | 1.1062 | 0.7358 | 0.7461 | 0.7358 | 0.7361 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.10.1
- Tokenizers 0.13.3