metadata
base_model: allenai/scibert_scivocab_uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: impact-cat
results: []
impact-cat
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: 0.5393
- Accuracy: 0.7781
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 160 | 0.4152 | 0.8406 |
| No log | 2.0 | 320 | 0.4462 | 0.8375 |
| No log | 3.0 | 480 | 0.4197 | 0.8203 |
| 0.511 | 4.0 | 640 | 0.4687 | 0.8453 |
| 0.511 | 5.0 | 800 | 0.4595 | 0.8328 |
| 0.511 | 6.0 | 960 | 0.4773 | 0.8047 |
| 0.2607 | 7.0 | 1120 | 0.5149 | 0.7953 |
| 0.2607 | 8.0 | 1280 | 0.5393 | 0.7781 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2