---
base_model: KennethEnevoldsen/dfm-sentence-encoder-large-exp2-no-lang-align
library_name: transformers
metrics:
- accuracy
- precision
- recall
- f1
tags:
- generated_from_trainer
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 the None dataset.
It achieves the following results on the evaluation set:
- Accuracy: 0.9421
- Precision: 0.9470
- Recall: 0.9421
- F1: 0.9422
- Loss: 0.5839

## 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: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Accuracy | Precision | Recall | F1     | Validation Loss |
|:-------------:|:-------:|:----:|:--------:|:---------:|:------:|:------:|:---------------:|
| No log        | 0.9412  | 8    | 0.8711   | 0.8341    | 0.8711 | 0.8507 | 0.4719          |
| No log        | 2.0     | 17   | 0.9237   | 0.9242    | 0.9237 | 0.9217 | 0.3301          |
| No log        | 2.9412  | 25   | 0.9225   | 0.9301    | 0.9225 | 0.9232 | 0.3470          |
| No log        | 4.0     | 34   | 0.9317   | 0.9315    | 0.9317 | 0.9299 | 0.2004          |
| No log        | 4.9412  | 42   | 0.9379   | 0.9443    | 0.9379 | 0.9383 | 0.4529          |
| No log        | 6.0     | 51   | 0.9394   | 0.9454    | 0.9394 | 0.9399 | 0.4719          |
| No log        | 6.9412  | 59   | 0.9425   | 0.9458    | 0.9425 | 0.9419 | 0.4498          |
| No log        | 8.0     | 68   | 0.9421   | 0.9471    | 0.9421 | 0.9423 | 0.4921          |
| No log        | 8.9412  | 76   | 0.9440   | 0.9486    | 0.9440 | 0.9440 | 0.5242          |
| No log        | 10.0    | 85   | 0.9444   | 0.9488    | 0.9444 | 0.9443 | 0.5476          |
| No log        | 10.9412 | 93   | 0.9421   | 0.9471    | 0.9421 | 0.9422 | 0.5733          |
| No log        | 12.0    | 102  | 0.9432   | 0.9479    | 0.9432 | 0.9433 | 0.5725          |
| No log        | 12.9412 | 110  | 0.9432   | 0.9478    | 0.9432 | 0.9432 | 0.5677          |
| No log        | 14.0    | 119  | 0.9432   | 0.9478    | 0.9432 | 0.9432 | 0.5714          |
| No log        | 14.9412 | 127  | 0.9425   | 0.9473    | 0.9425 | 0.9425 | 0.5802          |
| No log        | 16.0    | 136  | 0.9417   | 0.9468    | 0.9417 | 0.9418 | 0.5838          |
| No log        | 16.9412 | 144  | 0.9421   | 0.9470    | 0.9421 | 0.9422 | 0.5857          |
| No log        | 18.0    | 153  | 0.9421   | 0.9470    | 0.9421 | 0.9422 | 0.5840          |
| No log        | 18.8235 | 160  | 0.9421   | 0.9470    | 0.9421 | 0.9422 | 0.5839          |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1