metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
datasets:
- scirepeval
model-index:
- name: bert-base-uncased-MLP-scirepeval-chemistry-LARGE
results: []
bert-base-uncased-MLP-scirepeval-chemistry-LARGE
This model is a fine-tuned version of bert-base-uncased on the scirepeval dataset. It achieves the following results on the evaluation set:
- Loss: 1.7126
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: 64
- eval_batch_size: 64
- 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 |
|---|---|---|---|
| 2.2387 | 1.0 | 1407 | 1.9832 |
| 2.0503 | 2.0 | 2814 | 1.8959 |
| 1.9684 | 3.0 | 4221 | 1.8506 |
| 1.9195 | 4.0 | 5628 | 1.8186 |
| 1.8864 | 5.0 | 7035 | 1.8010 |
| 1.8551 | 6.0 | 8442 | 1.7677 |
| 1.8311 | 7.0 | 9849 | 1.7436 |
| 1.8185 | 8.0 | 11256 | 1.7415 |
| 1.8013 | 9.0 | 12663 | 1.7315 |
| 1.796 | 10.0 | 14070 | 1.7378 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3