---
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-span-width-2
  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-span-width-2

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: 0.8927
- Accuracy: 0.7698
- F1: 0.7669
- Precision: 0.7824
- Recall: 0.7698

## 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: 25
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 4.8367        | 0.6849  | 50   | 2.4596          | 0.0794   | 0.0714 | 0.0958    | 0.0794 |
| 4.9882        | 1.3699  | 100  | 2.4445          | 0.0794   | 0.0672 | 0.0879    | 0.0794 |
| 4.8852        | 2.0548  | 150  | 2.4040          | 0.0873   | 0.0904 | 0.1342    | 0.0873 |
| 4.7843        | 2.7397  | 200  | 2.3744          | 0.1429   | 0.1481 | 0.2396    | 0.1429 |
| 4.752         | 3.4247  | 250  | 2.3612          | 0.1032   | 0.1062 | 0.1491    | 0.1032 |
| 4.6277        | 4.1096  | 300  | 2.3446          | 0.1587   | 0.1570 | 0.1976    | 0.1587 |
| 4.4488        | 4.7945  | 350  | 2.2895          | 0.1746   | 0.1760 | 0.2217    | 0.1746 |
| 4.4244        | 5.4795  | 400  | 2.2383          | 0.2302   | 0.2282 | 0.3192    | 0.2302 |
| 3.9882        | 6.1644  | 450  | 2.1156          | 0.2381   | 0.2338 | 0.2955    | 0.2381 |
| 3.7244        | 6.8493  | 500  | 1.9715          | 0.3730   | 0.3763 | 0.4472    | 0.3730 |
| 3.2134        | 7.5342  | 550  | 1.8718          | 0.4206   | 0.3950 | 0.4017    | 0.4206 |
| 2.9113        | 8.2192  | 600  | 1.7821          | 0.4127   | 0.4249 | 0.5411    | 0.4127 |
| 2.4754        | 8.9041  | 650  | 1.6155          | 0.4841   | 0.4828 | 0.5088    | 0.4841 |
| 1.9316        | 9.5890  | 700  | 1.4559          | 0.5714   | 0.5673 | 0.5759    | 0.5714 |
| 1.6141        | 10.2740 | 750  | 1.2770          | 0.6429   | 0.6300 | 0.6630    | 0.6429 |
| 1.1867        | 10.9589 | 800  | 1.1722          | 0.6508   | 0.6439 | 0.6649    | 0.6508 |
| 0.9252        | 11.6438 | 850  | 1.0998          | 0.6825   | 0.6830 | 0.7084    | 0.6825 |
| 0.764         | 12.3288 | 900  | 1.0359          | 0.7143   | 0.7181 | 0.7575    | 0.7143 |
| 0.5821        | 13.0137 | 950  | 0.9742          | 0.7302   | 0.7288 | 0.7554    | 0.7302 |
| 0.4689        | 13.6986 | 1000 | 0.9252          | 0.7460   | 0.7459 | 0.7639    | 0.7460 |
| 0.3578        | 14.3836 | 1050 | 0.9470          | 0.7302   | 0.7281 | 0.7663    | 0.7302 |
| 0.2932        | 15.0685 | 1100 | 0.9157          | 0.7222   | 0.7181 | 0.7552    | 0.7222 |
| 0.2262        | 15.7534 | 1150 | 0.8814          | 0.7540   | 0.7525 | 0.7723    | 0.7540 |
| 0.2127        | 16.4384 | 1200 | 0.8926          | 0.7381   | 0.7349 | 0.7488    | 0.7381 |
| 0.1445        | 17.1233 | 1250 | 0.8955          | 0.7698   | 0.7672 | 0.7891    | 0.7698 |
| 0.1183        | 17.8082 | 1300 | 0.8903          | 0.7698   | 0.7648 | 0.8007    | 0.7698 |
| 0.0757        | 18.4932 | 1350 | 0.8743          | 0.7698   | 0.7656 | 0.7831    | 0.7698 |
| 0.0939        | 19.1781 | 1400 | 0.8584          | 0.8016   | 0.8032 | 0.8200    | 0.8016 |
| 0.0705        | 19.8630 | 1450 | 0.8636          | 0.7857   | 0.7849 | 0.7965    | 0.7857 |
| 0.0605        | 20.5479 | 1500 | 0.8750          | 0.7778   | 0.7743 | 0.7831    | 0.7778 |
| 0.0467        | 21.2329 | 1550 | 0.8834          | 0.7778   | 0.7762 | 0.7898    | 0.7778 |
| 0.0777        | 21.9178 | 1600 | 0.8909          | 0.7698   | 0.7668 | 0.7809    | 0.7698 |
| 0.0349        | 22.6027 | 1650 | 0.8852          | 0.7698   | 0.7669 | 0.7824    | 0.7698 |
| 0.0442        | 23.2877 | 1700 | 0.8873          | 0.7698   | 0.7669 | 0.7824    | 0.7698 |
| 0.0253        | 23.9726 | 1750 | 0.8917          | 0.7698   | 0.7669 | 0.7824    | 0.7698 |
| 0.0335        | 24.6575 | 1800 | 0.8927          | 0.7698   | 0.7669 | 0.7824    | 0.7698 |


### Framework versions

- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0