|
--- |
|
license: apache-2.0 |
|
base_model: allenai/longformer-base-4096 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: clinical_longformer_same_tokens_treintamil |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# clinical_longformer_same_tokens_treintamil |
|
|
|
This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.3864 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 64 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1500 |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.6837 | 0.09 | 2 | 2.6011 | |
|
| 2.7002 | 0.19 | 4 | 2.4829 | |
|
| 2.7169 | 0.28 | 6 | 2.5518 | |
|
| 2.5927 | 0.38 | 8 | 2.4683 | |
|
| 2.6215 | 0.47 | 10 | 2.5798 | |
|
| 2.6608 | 0.57 | 12 | 2.4698 | |
|
| 2.6124 | 0.66 | 14 | 2.6022 | |
|
| 2.5422 | 0.76 | 16 | 2.5533 | |
|
| 2.6775 | 0.85 | 18 | 2.5041 | |
|
| 5.5552 | 0.95 | 20 | 2.5191 | |
|
| 2.6986 | 1.04 | 22 | 2.5060 | |
|
| 2.7096 | 1.14 | 24 | 2.4583 | |
|
| 3.5551 | 1.23 | 26 | 2.5649 | |
|
| 2.7292 | 1.33 | 28 | 2.5068 | |
|
| 2.766 | 1.42 | 30 | 2.4687 | |
|
| 3.4509 | 1.52 | 32 | 2.5880 | |
|
| 3.3941 | 1.61 | 34 | 2.4755 | |
|
| 2.5889 | 1.71 | 36 | 2.5193 | |
|
| 2.6374 | 1.8 | 38 | 2.5416 | |
|
| 2.5641 | 1.9 | 40 | 2.4652 | |
|
| 2.8255 | 1.99 | 42 | 2.5123 | |
|
| 2.5652 | 2.09 | 44 | 2.4474 | |
|
| 2.5775 | 2.18 | 46 | 2.5389 | |
|
| 2.5171 | 2.28 | 48 | 2.4643 | |
|
| 2.6795 | 2.37 | 50 | 2.4121 | |
|
| 2.591 | 2.47 | 52 | 2.4375 | |
|
| 2.7528 | 2.56 | 54 | 2.5074 | |
|
| 2.6141 | 2.65 | 56 | 2.4405 | |
|
| 2.6785 | 2.75 | 58 | 2.4155 | |
|
| 3.0339 | 2.84 | 60 | 2.4628 | |
|
| 2.6164 | 2.94 | 62 | 2.4732 | |
|
| 2.4911 | 3.03 | 64 | 2.3910 | |
|
| 2.6821 | 3.13 | 66 | 2.4661 | |
|
| 2.6406 | 3.22 | 68 | 2.4274 | |
|
| 2.6277 | 3.32 | 70 | 2.4130 | |
|
| 2.5329 | 3.41 | 72 | 2.4310 | |
|
| 2.5272 | 3.51 | 74 | 2.4122 | |
|
| 2.5845 | 3.6 | 76 | 2.4515 | |
|
| 2.5483 | 3.7 | 78 | 2.3397 | |
|
| 2.5458 | 3.79 | 80 | 2.3840 | |
|
| 2.4884 | 3.89 | 82 | 2.3933 | |
|
| 2.4538 | 3.98 | 84 | 2.3864 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
