---
tags:
- generated_from_trainer
model-index:
- name: det-noun-lstm-4
  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. -->

# det-noun-lstm-4

This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.9719

## 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: 32
- eval_batch_size: 32
- seed: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 3052726

### Training results

| Training Loss | Epoch | Step    | Validation Loss |
|:-------------:|:-----:|:-------:|:---------------:|
| 4.8017        | 0.03  | 76320   | 4.7666          |
| 4.5163        | 1.03  | 152640  | 4.4850          |
| 4.3691        | 0.03  | 228960  | 4.3481          |
| 4.2822        | 1.03  | 305280  | 4.2648          |
| 4.2214        | 0.03  | 381600  | 4.2067          |
| 4.1738        | 1.03  | 457920  | 4.1648          |
| 4.1346        | 0.03  | 534240  | 4.1335          |
| 4.0994        | 1.03  | 610560  | 4.1086          |
| 4.0717        | 0.03  | 686880  | 4.0880          |
| 4.0442        | 1.03  | 763200  | 4.0724          |
| 4.0257        | 0.03  | 839520  | 4.0599          |
| 4.0076        | 1.03  | 915840  | 4.0482          |
| 3.9916        | 0.03  | 992160  | 4.0389          |
| 3.9715        | 0.03  | 1068480 | 4.0308          |
| 3.96          | 1.03  | 1144800 | 4.0236          |
| 3.9543        | 0.03  | 1221120 | 4.0178          |
| 3.942         | 1.03  | 1297440 | 4.0123          |
| 3.9331        | 0.03  | 1373760 | 4.0075          |
| 3.9207        | 1.03  | 1450080 | 4.0036          |
| 3.9177        | 0.03  | 1526400 | 4.0000          |
| 3.9148        | 1.03  | 1602720 | 3.9964          |
| 3.9113        | 0.03  | 1679040 | 3.9938          |
| 3.9051        | 1.03  | 1755360 | 3.9917          |
| 3.8958        | 0.03  | 1831680 | 3.9896          |
| 3.888         | 1.03  | 1908000 | 3.9873          |
| 3.8823        | 0.03  | 1984320 | 3.9855          |
| 3.8771        | 0.03  | 2060640 | 3.9836          |
| 3.871         | 1.03  | 2136960 | 3.9821          |
| 3.8663        | 0.03  | 2213280 | 3.9807          |
| 3.8558        | 1.03  | 2289600 | 3.9791          |
| 3.853         | 0.03  | 2365920 | 3.9776          |
| 3.8596        | 1.03  | 2442240 | 3.9766          |
| 3.8526        | 0.03  | 2518560 | 3.9758          |
| 3.8496        | 1.03  | 2594880 | 3.9751          |
| 3.8438        | 0.03  | 2671200 | 3.9745          |
| 3.8452        | 1.03  | 2747520 | 3.9738          |
| 3.8491        | 0.03  | 2823840 | 3.9733          |
| 3.8485        | 1.03  | 2900160 | 3.9728          |
| 3.8481        | 0.03  | 2976480 | 3.9722          |
| 3.8418        | 1.02  | 3052726 | 3.9719          |


### Framework versions

- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3