<!-- 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-small-finetuned-finetuned-parsed-longer100
This model is a fine-tuned version of muhtasham/bert-small-finetuned-finetuned-parsed-longer50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6346
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: 128
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 4 | 2.9464 |
| No log | 2.0 | 8 | 2.6667 |
| No log | 3.0 | 12 | 3.2662 |
| No log | 4.0 | 16 | 2.6736 |
| No log | 5.0 | 20 | 2.6334 |
| No log | 6.0 | 24 | 2.6909 |
| No log | 7.0 | 28 | 3.0811 |
| No log | 8.0 | 32 | 2.8795 |
| No log | 9.0 | 36 | 3.3654 |
| No log | 10.0 | 40 | 3.0057 |
| No log | 11.0 | 44 | 3.1018 |
| No log | 12.0 | 48 | 3.1129 |
| No log | 13.0 | 52 | 2.7815 |
| No log | 14.0 | 56 | 3.2128 |
| No log | 15.0 | 60 | 2.9875 |
| No log | 16.0 | 64 | 2.8669 |
| No log | 17.0 | 68 | 2.8407 |
| No log | 18.0 | 72 | 3.1196 |
| No log | 19.0 | 76 | 2.5720 |
| No log | 20.0 | 80 | 3.0325 |
| No log | 21.0 | 84 | 3.0881 |
| No log | 22.0 | 88 | 2.9000 |
| No log | 23.0 | 92 | 2.9910 |
| No log | 24.0 | 96 | 3.0480 |
| No log | 25.0 | 100 | 3.0548 |
| No log | 26.0 | 104 | 2.8290 |
| No log | 27.0 | 108 | 2.8719 |
| No log | 28.0 | 112 | 2.8277 |
| No log | 29.0 | 116 | 2.7475 |
| No log | 30.0 | 120 | 2.8492 |
| No log | 31.0 | 124 | 2.6641 |
| No log | 32.0 | 128 | 2.9369 |
| No log | 33.0 | 132 | 2.8731 |
| No log | 34.0 | 136 | 3.0025 |
| No log | 35.0 | 140 | 2.9952 |
| No log | 36.0 | 144 | 2.7866 |
| No log | 37.0 | 148 | 3.0046 |
| No log | 38.0 | 152 | 2.6468 |
| No log | 39.0 | 156 | 2.8889 |
| No log | 40.0 | 160 | 2.6865 |
| No log | 41.0 | 164 | 2.5635 |
| No log | 42.0 | 168 | 2.5147 |
| No log | 43.0 | 172 | 2.6985 |
| No log | 44.0 | 176 | 2.7966 |
| No log | 45.0 | 180 | 3.0184 |
| No log | 46.0 | 184 | 3.1892 |
| No log | 47.0 | 188 | 3.1066 |
| No log | 48.0 | 192 | 2.9969 |
| No log | 49.0 | 196 | 2.8919 |
| No log | 50.0 | 200 | 2.6346 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
