metadata
license: mit
base_model: jarod0411/linker_v2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: linker_v3
results: []
linker_v3
This model is a fine-tuned version of jarod0411/linker_v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2291
- Accuracy: 0.9209
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2532 | 1.0 | 33912 | 0.2459 | 0.9160 |
| 0.2433 | 2.0 | 67824 | 0.2392 | 0.9179 |
| 0.2384 | 3.0 | 101736 | 0.2358 | 0.9188 |
| 0.2354 | 4.0 | 135648 | 0.2336 | 0.9195 |
| 0.2331 | 5.0 | 169560 | 0.2322 | 0.9199 |
| 0.2307 | 6.0 | 203472 | 0.2311 | 0.9202 |
| 0.2293 | 7.0 | 237384 | 0.2303 | 0.9205 |
| 0.2282 | 8.0 | 271296 | 0.2297 | 0.9207 |
| 0.2274 | 9.0 | 305208 | 0.2293 | 0.9208 |
| 0.2269 | 10.0 | 339120 | 0.2291 | 0.9209 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0