---
library_name: transformers
license: apache-2.0
base_model: dslim/distilbert-NER
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: distilbert-classn-LinearAlg-finetuned-pred-span-width-3
  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. -->

# distilbert-classn-LinearAlg-finetuned-pred-span-width-3

This model is a fine-tuned version of [dslim/distilbert-NER](https://huggingface.co/dslim/distilbert-NER) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7560
- Accuracy: 0.8175
- F1: 0.8136
- Precision: 0.8277
- Recall: 0.8175

## 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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 4.9235        | 0.6849  | 50   | 2.4998          | 0.0556   | 0.0219 | 0.0142    | 0.0556 |
| 4.8853        | 1.3699  | 100  | 2.4692          | 0.0556   | 0.0227 | 0.0148    | 0.0556 |
| 4.8296        | 2.0548  | 150  | 2.4199          | 0.0794   | 0.0499 | 0.0414    | 0.0794 |
| 4.7138        | 2.7397  | 200  | 2.3605          | 0.1111   | 0.0778 | 0.0800    | 0.1111 |
| 4.5483        | 3.4247  | 250  | 2.2678          | 0.2222   | 0.2171 | 0.2713    | 0.2222 |
| 4.4398        | 4.1096  | 300  | 2.1006          | 0.3730   | 0.3441 | 0.3723    | 0.3730 |
| 4.031         | 4.7945  | 350  | 1.9045          | 0.5238   | 0.4995 | 0.5172    | 0.5238 |
| 3.5384        | 5.4795  | 400  | 1.6756          | 0.6508   | 0.6382 | 0.6649    | 0.6508 |
| 2.9989        | 6.1644  | 450  | 1.4537          | 0.7302   | 0.7116 | 0.7624    | 0.7302 |
| 2.5192        | 6.8493  | 500  | 1.2494          | 0.7460   | 0.7344 | 0.7473    | 0.7460 |
| 1.811         | 7.5342  | 550  | 1.0760          | 0.7302   | 0.7242 | 0.7563    | 0.7302 |
| 1.4184        | 8.2192  | 600  | 0.9448          | 0.7937   | 0.7878 | 0.8223    | 0.7937 |
| 1.1262        | 8.9041  | 650  | 0.8517          | 0.7937   | 0.7871 | 0.8000    | 0.7937 |
| 0.7899        | 9.5890  | 700  | 0.8264          | 0.8016   | 0.7904 | 0.7993    | 0.8016 |
| 0.4857        | 10.2740 | 750  | 0.7620          | 0.8333   | 0.8275 | 0.8360    | 0.8333 |
| 0.439         | 10.9589 | 800  | 0.7612          | 0.8175   | 0.8099 | 0.8282    | 0.8175 |
| 0.3147        | 11.6438 | 850  | 0.7215          | 0.8175   | 0.8136 | 0.8211    | 0.8175 |
| 0.2098        | 12.3288 | 900  | 0.7429          | 0.8095   | 0.8039 | 0.8219    | 0.8095 |
| 0.1702        | 13.0137 | 950  | 0.7309          | 0.8095   | 0.8039 | 0.8244    | 0.8095 |
| 0.1215        | 13.6986 | 1000 | 0.7320          | 0.8175   | 0.8154 | 0.8327    | 0.8175 |
| 0.0812        | 14.3836 | 1050 | 0.7449          | 0.8175   | 0.8113 | 0.8286    | 0.8175 |
| 0.0693        | 15.0685 | 1100 | 0.7303          | 0.8175   | 0.8126 | 0.8233    | 0.8175 |
| 0.0728        | 15.7534 | 1150 | 0.7449          | 0.8175   | 0.8136 | 0.8277    | 0.8175 |
| 0.0321        | 16.4384 | 1200 | 0.7413          | 0.8175   | 0.8126 | 0.8233    | 0.8175 |
| 0.0662        | 17.1233 | 1250 | 0.7583          | 0.8175   | 0.8136 | 0.8277    | 0.8175 |
| 0.0596        | 17.8082 | 1300 | 0.7504          | 0.8175   | 0.8136 | 0.8277    | 0.8175 |
| 0.0216        | 18.4932 | 1350 | 0.7611          | 0.8175   | 0.8136 | 0.8277    | 0.8175 |
| 0.0353        | 19.1781 | 1400 | 0.7522          | 0.8175   | 0.8136 | 0.8277    | 0.8175 |
| 0.0348        | 19.8630 | 1450 | 0.7560          | 0.8175   | 0.8136 | 0.8277    | 0.8175 |


### Framework versions

- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.1
- Tokenizers 0.21.0