metadata
library_name: transformers
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: distilbert-imdb-sentiment
results: []
distilbert-imdb-sentiment
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4840
- Accuracy: 0.9314
- F1: 0.9318
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: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.06
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.4753 | 0.6394 | 500 | 0.4521 | 0.9114 | 0.9151 |
| 0.3099 | 1.2788 | 1000 | 0.4450 | 0.9250 | 0.9262 |
| 0.2935 | 1.9182 | 1500 | 0.3898 | 0.9290 | 0.9299 |
| 0.2234 | 2.5575 | 2000 | 0.4829 | 0.9307 | 0.9301 |
| 0.1981 | 3.0 | 2346 | 0.4840 | 0.9314 | 0.9318 |
Framework versions
- Transformers 5.6.1
- Pytorch 2.11.0+cu130
- Datasets 4.8.4
- Tokenizers 0.22.2