|
--- |
|
library_name: transformers |
|
base_model: KennethEnevoldsen/dfm-sentence-encoder-large-exp2-no-lang-align |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: dfm |
|
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. --> |
|
|
|
# dfm |
|
|
|
This model is a fine-tuned version of [KennethEnevoldsen/dfm-sentence-encoder-large-exp2-no-lang-align](https://huggingface.co/KennethEnevoldsen/dfm-sentence-encoder-large-exp2-no-lang-align) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Accuracy: 0.9981 |
|
- Precision: 0.9980 |
|
- Recall: 0.9981 |
|
- F1: 0.9979 |
|
- Loss: 0.0066 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Accuracy | Precision | Recall | F1 | Validation Loss | |
|
|:-------------:|:------:|:----:|:--------:|:---------:|:------:|:------:|:---------------:| |
|
| No log | 0.9524 | 10 | 0.9116 | 0.8719 | 0.9116 | 0.8909 | 0.3402 | |
|
| No log | 2.0 | 21 | 0.9585 | 0.9581 | 0.9585 | 0.9535 | 0.1368 | |
|
| No log | 2.9524 | 31 | 0.9818 | 0.9806 | 0.9818 | 0.9812 | 0.0664 | |
|
| No log | 4.0 | 42 | 0.9926 | 0.9912 | 0.9926 | 0.9919 | 0.0286 | |
|
| No log | 4.9524 | 52 | 0.9947 | 0.9934 | 0.9947 | 0.9940 | 0.0209 | |
|
| No log | 6.0 | 63 | 0.9953 | 0.9941 | 0.9953 | 0.9946 | 0.0159 | |
|
| No log | 6.9524 | 73 | 0.9967 | 0.9968 | 0.9967 | 0.9963 | 0.0107 | |
|
| No log | 8.0 | 84 | 0.9977 | 0.9977 | 0.9977 | 0.9975 | 0.0082 | |
|
| No log | 8.9524 | 94 | 0.9980 | 0.9979 | 0.9980 | 0.9978 | 0.0067 | |
|
| No log | 9.5238 | 100 | 0.9981 | 0.9980 | 0.9981 | 0.9979 | 0.0066 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Tokenizers 0.19.1 |
|
|
