metadata
base_model: allenai/scibert_scivocab_uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_model
results: []
my_awesome_model
This model is a fine-tuned version of allenai/scibert_scivocab_uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5640
- Accuracy: 0.7795
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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.184 | 0.0770 | 100 | 0.9294 | 0.6612 |
| 0.8519 | 0.1540 | 200 | 0.8007 | 0.7087 |
| 0.7555 | 0.2309 | 300 | 0.7204 | 0.7245 |
| 0.7065 | 0.3079 | 400 | 0.7121 | 0.7324 |
| 0.6499 | 0.3849 | 500 | 0.6654 | 0.7567 |
| 0.6504 | 0.4619 | 600 | 0.6227 | 0.7659 |
| 0.6421 | 0.5389 | 700 | 0.6104 | 0.7695 |
| 0.6298 | 0.6159 | 800 | 0.6094 | 0.7652 |
| 0.5851 | 0.6928 | 900 | 0.5852 | 0.7795 |
| 0.5903 | 0.7698 | 1000 | 0.5759 | 0.7828 |
| 0.5682 | 0.8468 | 1100 | 0.5769 | 0.7758 |
| 0.5809 | 0.9238 | 1200 | 0.5640 | 0.7795 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1