metadata
base_model: eddieman78/litbank-coref-mem-base
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: scripts-coref-mem-base
results: []
scripts-coref-mem-base
This model is a fine-tuned version of eddieman78/litbank-coref-mem-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0032
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: 12
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.022 | 1.0 | 1807 | 0.0133 |
| 0.0138 | 2.0 | 3614 | 0.0090 |
| 0.011 | 3.0 | 5421 | 0.0072 |
| 0.0088 | 4.0 | 7228 | 0.0058 |
| 0.0072 | 5.0 | 9035 | 0.0051 |
| 0.0063 | 6.0 | 10842 | 0.0044 |
| 0.0057 | 7.0 | 12649 | 0.0041 |
| 0.0052 | 8.0 | 14456 | 0.0038 |
| 0.0048 | 9.0 | 16263 | 0.0035 |
| 0.0047 | 10.0 | 18070 | 0.0034 |
| 0.0043 | 11.0 | 19877 | 0.0033 |
| 0.0041 | 12.0 | 21684 | 0.0032 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.17.0
- Tokenizers 0.19.1