metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- becasv2
model-index:
- name: distilbert-base-uncased-becas-4
results: []
distilbert-base-uncased-becas-4
This model is a fine-tuned version of distilbert-base-uncased on the becasv2 dataset. It achieves the following results on the evaluation set:
- Loss: 4.8916
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- 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 |
|---|---|---|---|
| No log | 1.0 | 5 | 5.8702 |
| No log | 2.0 | 10 | 5.6813 |
| No log | 3.0 | 15 | 5.5046 |
| No log | 4.0 | 20 | 5.3432 |
| No log | 5.0 | 25 | 5.2277 |
| No log | 6.0 | 30 | 5.1122 |
| No log | 7.0 | 35 | 5.0261 |
| No log | 8.0 | 40 | 4.9520 |
| No log | 9.0 | 45 | 4.9076 |
| No log | 10.0 | 50 | 4.8916 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1