<!-- 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_wt_init_48_frz
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4340
- Accuracy: 0.5488
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 |
---|---|---|---|---|
3.8468 | 0.08 | 10000 | 3.6051 | 0.4101 |
3.6009 | 0.16 | 20000 | 3.3734 | 0.4369 |
3.4559 | 0.25 | 30000 | 3.2348 | 0.4517 |
3.3578 | 0.33 | 40000 | 3.1395 | 0.4623 |
3.2803 | 0.41 | 50000 | 3.0632 | 0.4709 |
3.2157 | 0.49 | 60000 | 3.0010 | 0.4780 |
3.1503 | 0.57 | 70000 | 2.9554 | 0.4838 |
3.1044 | 0.66 | 80000 | 2.9104 | 0.4888 |
3.0703 | 0.74 | 90000 | 2.8759 | 0.4931 |
3.029 | 0.82 | 100000 | 2.8357 | 0.4976 |
2.9907 | 0.9 | 110000 | 2.8082 | 0.5013 |
2.9619 | 0.98 | 120000 | 2.7805 | 0.5042 |
2.9284 | 1.07 | 130000 | 2.7578 | 0.5072 |
2.9027 | 1.15 | 140000 | 2.7295 | 0.5103 |
2.8738 | 1.23 | 150000 | 2.7094 | 0.5133 |
2.8603 | 1.31 | 160000 | 2.6848 | 0.5160 |
2.829 | 1.39 | 170000 | 2.6667 | 0.5185 |
2.8106 | 1.47 | 180000 | 2.6479 | 0.5208 |
2.7942 | 1.56 | 190000 | 2.6304 | 0.5227 |
2.772 | 1.64 | 200000 | 2.6156 | 0.5249 |
2.7546 | 1.72 | 210000 | 2.5994 | 0.5270 |
2.7348 | 1.8 | 220000 | 2.5858 | 0.5290 |
2.725 | 1.88 | 230000 | 2.5728 | 0.5304 |
2.7116 | 1.97 | 240000 | 2.5587 | 0.5324 |
2.6953 | 2.05 | 250000 | 2.5476 | 0.5338 |
2.6883 | 2.13 | 260000 | 2.5339 | 0.5355 |
2.6768 | 2.21 | 270000 | 2.5231 | 0.5371 |
2.6622 | 2.29 | 280000 | 2.5097 | 0.5383 |
2.6499 | 2.38 | 290000 | 2.5026 | 0.5396 |
2.6361 | 2.46 | 300000 | 2.4916 | 0.5412 |
2.629 | 2.54 | 310000 | 2.4843 | 0.5421 |
2.6269 | 2.62 | 320000 | 2.4737 | 0.5432 |
2.6175 | 2.7 | 330000 | 2.4676 | 0.5443 |
2.5961 | 2.79 | 340000 | 2.4580 | 0.5457 |
2.5926 | 2.87 | 350000 | 2.4502 | 0.5468 |
2.5866 | 2.95 | 360000 | 2.4413 | 0.5480 |
2.5781 | 3.03 | 370000 | 2.4340 | 0.5488 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3