<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bert_12_layer_model_v2_complete_training_new_emb_compress_48_gelu
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.4927
- Accuracy: 0.2227
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: 1e-05
- train_batch_size: 48
- eval_batch_size: 48
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 7.1222 | 0.08 | 10000 | 7.0986 | 0.0793 |
| 6.6978 | 0.16 | 20000 | 6.6919 | 0.1061 |
| 6.5525 | 0.25 | 30000 | 6.5486 | 0.1185 |
| 6.4684 | 0.33 | 40000 | 6.4581 | 0.1251 |
| 6.3964 | 0.41 | 50000 | 6.3927 | 0.1302 |
| 6.3478 | 0.49 | 60000 | 6.3393 | 0.1342 |
| 6.3036 | 0.57 | 70000 | 6.3004 | 0.1366 |
| 6.2727 | 0.66 | 80000 | 6.2671 | 0.1401 |
| 6.2394 | 0.74 | 90000 | 6.2365 | 0.1413 |
| 6.2124 | 0.82 | 100000 | 6.2146 | 0.1430 |
| 6.1946 | 0.9 | 110000 | 6.1936 | 0.1438 |
| 6.1769 | 0.98 | 120000 | 6.1724 | 0.1456 |
| 6.1466 | 1.07 | 130000 | 6.1497 | 0.1466 |
| 6.1217 | 1.15 | 140000 | 6.1160 | 0.1483 |
| 6.0912 | 1.23 | 150000 | 6.0844 | 0.1502 |
| 6.0452 | 1.31 | 160000 | 6.0317 | 0.1547 |
| 5.981 | 1.39 | 170000 | 5.9714 | 0.1596 |
| 5.9314 | 1.47 | 180000 | 5.9204 | 0.1641 |
| 5.8777 | 1.56 | 190000 | 5.8723 | 0.1690 |
| 5.7356 | 1.64 | 200000 | 5.7081 | 0.1907 |
| 5.5391 | 1.72 | 210000 | 5.4927 | 0.2227 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.1
- Tokenizers 0.13.3
