---
tags:
- generated_from_trainer
model-index:
- name: det-noun-lstm-0
  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-0

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: 3.9706

## 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: 0
- 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 |
|:-------------:|:-----:|:-------:|:---------------:|
| 4.7901        | 0.03  | 76320   | 4.7538          |
| 4.5055        | 1.03  | 152640  | 4.4733          |
| 4.3591        | 0.03  | 228960  | 4.3383          |
| 4.2712        | 1.03  | 305280  | 4.2546          |
| 4.2126        | 0.03  | 381600  | 4.1985          |
| 4.1639        | 1.03  | 457920  | 4.1571          |
| 4.127         | 0.03  | 534240  | 4.1268          |
| 4.09          | 1.03  | 610560  | 4.1029          |
| 4.0629        | 0.03  | 686880  | 4.0834          |
| 4.0376        | 1.03  | 763200  | 4.0677          |
| 4.0167        | 0.03  | 839520  | 4.0550          |
| 4.0011        | 1.03  | 915840  | 4.0437          |
| 3.9859        | 0.03  | 992160  | 4.0345          |
| 3.9642        | 1.03  | 1068480 | 4.0272          |
| 3.9542        | 0.03  | 1144800 | 4.0204          |
| 3.9461        | 0.03  | 1221120 | 4.0153          |
| 3.9338        | 1.03  | 1297440 | 4.0096          |
| 3.9243        | 0.03  | 1373760 | 4.0050          |
| 3.9116        | 1.03  | 1450080 | 4.0013          |
| 3.9089        | 0.03  | 1526400 | 3.9975          |
| 3.9068        | 1.03  | 1602720 | 3.9946          |
| 3.9022        | 0.03  | 1679040 | 3.9918          |
| 3.8977        | 1.03  | 1755360 | 3.9896          |
| 3.8883        | 0.03  | 1831680 | 3.9876          |
| 3.8819        | 1.03  | 1908000 | 3.9857          |
| 3.8737        | 0.03  | 1984320 | 3.9839          |
| 3.87          | 1.03  | 2060640 | 3.9820          |
| 3.8653        | 0.03  | 2136960 | 3.9805          |
| 3.8615        | 1.03  | 2213280 | 3.9792          |
| 3.8482        | 0.03  | 2289600 | 3.9782          |
| 3.8474        | 1.03  | 2365920 | 3.9769          |
| 3.8489        | 0.03  | 2442240 | 3.9757          |
| 3.8434        | 0.03  | 2518560 | 3.9748          |
| 3.8389        | 1.03  | 2594880 | 3.9740          |
| 3.8338        | 0.03  | 2671200 | 3.9732          |
| 3.8353        | 0.03  | 2747520 | 3.9727          |
| 3.8394        | 1.03  | 2823840 | 3.9717          |
| 3.8389        | 0.03  | 2900160 | 3.9714          |
| 3.8374        | 0.03  | 2976480 | 3.9710          |
| 3.8341        | 1.02  | 3052726 | 3.9706          |


### Framework versions

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