metadata
base_model: allenai/scibert_scivocab_cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: scibert_all_deep
results: []
scibert_all_deep
This model is a fine-tuned version of allenai/scibert_scivocab_cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8270
- Precision: 0.6648
- Recall: 0.7172
- F1: 0.6900
- Accuracy: 0.8207
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: 8
- eval_batch_size: 8
- 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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 363 | 0.5559 | 0.6191 | 0.6867 | 0.6511 | 0.8131 |
| 0.6741 | 2.0 | 726 | 0.5344 | 0.6271 | 0.7101 | 0.6660 | 0.8203 |
| 0.3917 | 3.0 | 1089 | 0.5548 | 0.6558 | 0.7064 | 0.6801 | 0.8205 |
| 0.3917 | 4.0 | 1452 | 0.5835 | 0.6717 | 0.7110 | 0.6908 | 0.8246 |
| 0.271 | 5.0 | 1815 | 0.6643 | 0.6524 | 0.7255 | 0.6870 | 0.8196 |
| 0.188 | 6.0 | 2178 | 0.7021 | 0.6724 | 0.7067 | 0.6892 | 0.8222 |
| 0.1437 | 7.0 | 2541 | 0.7594 | 0.6555 | 0.7180 | 0.6853 | 0.8191 |
| 0.1437 | 8.0 | 2904 | 0.7916 | 0.6664 | 0.7109 | 0.6879 | 0.8194 |
| 0.114 | 9.0 | 3267 | 0.8123 | 0.6582 | 0.7225 | 0.6888 | 0.8203 |
| 0.0943 | 10.0 | 3630 | 0.8270 | 0.6648 | 0.7172 | 0.6900 | 0.8207 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1