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

# det-noun-lstm-2

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: 3.9696

## 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: 2
- 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 |
|:-------------:|:-----:|:-------:|:---------------:|
| 4.7846        | 0.03  | 76320   | 4.7476          |
| 4.5007        | 1.03  | 152640  | 4.4693          |
| 4.3565        | 0.03  | 228960  | 4.3360          |
| 4.2691        | 1.03  | 305280  | 4.2538          |
| 4.211         | 0.03  | 381600  | 4.1979          |
| 4.1623        | 0.03  | 457920  | 4.1561          |
| 4.124         | 1.03  | 534240  | 4.1258          |
| 4.0886        | 0.03  | 610560  | 4.1010          |
| 4.0601        | 1.03  | 686880  | 4.0820          |
| 4.0352        | 0.03  | 763200  | 4.0662          |
| 4.015         | 1.03  | 839520  | 4.0534          |
| 3.9975        | 0.03  | 915840  | 4.0430          |
| 3.9816        | 1.03  | 992160  | 4.0340          |
| 3.9597        | 0.03  | 1068480 | 4.0262          |
| 3.9482        | 0.03  | 1144800 | 4.0193          |
| 3.9446        | 1.03  | 1221120 | 4.0136          |
| 3.9322        | 0.03  | 1297440 | 4.0084          |
| 3.9218        | 1.03  | 1373760 | 4.0039          |
| 3.9099        | 0.03  | 1450080 | 3.9998          |
| 3.9053        | 1.03  | 1526400 | 3.9967          |
| 3.9024        | 0.03  | 1602720 | 3.9932          |
| 3.8977        | 1.03  | 1679040 | 3.9898          |
| 3.893         | 0.03  | 1755360 | 3.9871          |
| 3.8829        | 1.03  | 1831680 | 3.9854          |
| 3.8784        | 0.03  | 1908000 | 3.9838          |
| 3.8693        | 1.03  | 1984320 | 3.9825          |
| 3.865         | 0.03  | 2060640 | 3.9807          |
| 3.8604        | 0.03  | 2136960 | 3.9789          |
| 3.8581        | 1.03  | 2213280 | 3.9779          |
| 3.8449        | 0.03  | 2289600 | 3.9767          |
| 3.8453        | 1.03  | 2365920 | 3.9757          |
| 3.8464        | 0.03  | 2442240 | 3.9747          |
| 3.842         | 1.03  | 2518560 | 3.9739          |
| 3.8381        | 0.03  | 2594880 | 3.9733          |
| 3.8296        | 1.03  | 2671200 | 3.9724          |
| 3.8328        | 0.03  | 2747520 | 3.9715          |
| 3.8363        | 0.03  | 2823840 | 3.9709          |
| 3.8348        | 1.03  | 2900160 | 3.9706          |
| 3.834         | 0.03  | 2976480 | 3.9700          |
| 3.8302        | 1.02  | 3052726 | 3.9696          |


### Framework versions

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