---
tags:
- generated_from_trainer
model-index:
- name: det-adj-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-adj-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: 3.9726

## 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 |
|:-------------:|:-----:|:-------:|:---------------:|
| 4.7824        | 0.03  | 76320   | 4.7586          |
| 4.4996        | 1.03  | 152640  | 4.4771          |
| 4.3559        | 0.03  | 228960  | 4.3426          |
| 4.2716        | 1.03  | 305280  | 4.2596          |
| 4.2095        | 0.03  | 381600  | 4.2030          |
| 4.1671        | 1.03  | 457920  | 4.1621          |
| 4.1296        | 0.03  | 534240  | 4.1311          |
| 4.0958        | 1.03  | 610560  | 4.1065          |
| 4.0672        | 0.03  | 686880  | 4.0876          |
| 4.0405        | 1.03  | 763200  | 4.0711          |
| 4.0207        | 0.03  | 839520  | 4.0583          |
| 4.0077        | 1.03  | 915840  | 4.0471          |
| 3.9936        | 0.03  | 992160  | 4.0386          |
| 3.9748        | 1.03  | 1068480 | 4.0312          |
| 3.961         | 0.03  | 1144800 | 4.0242          |
| 3.9432        | 1.03  | 1221120 | 4.0185          |
| 3.9272        | 0.03  | 1297440 | 4.0131          |
| 3.9219        | 1.03  | 1373760 | 4.0086          |
| 3.9129        | 0.03  | 1450080 | 4.0047          |
| 3.9121        | 1.03  | 1526400 | 4.0014          |
| 3.9048        | 0.03  | 1602720 | 3.9980          |
| 3.9047        | 1.03  | 1679040 | 3.9946          |
| 3.9019        | 0.03  | 1755360 | 3.9925          |
| 3.8934        | 1.03  | 1831680 | 3.9900          |
| 3.8867        | 0.03  | 1908000 | 3.9879          |
| 3.8786        | 1.03  | 1984320 | 3.9865          |
| 3.873         | 0.03  | 2060640 | 3.9850          |
| 3.8704        | 1.03  | 2136960 | 3.9827          |
| 3.8682        | 0.03  | 2213280 | 3.9811          |
| 3.8592        | 1.03  | 2289600 | 3.9793          |
| 3.8541        | 0.03  | 2365920 | 3.9781          |
| 3.8456        | 0.03  | 2442240 | 3.9772          |
| 3.8378        | 1.03  | 2518560 | 3.9764          |
| 3.8374        | 0.03  | 2594880 | 3.9757          |
| 3.8356        | 1.03  | 2671200 | 3.9749          |
| 3.839         | 0.03  | 2747520 | 3.9743          |
| 3.8389        | 1.03  | 2823840 | 3.9737          |
| 3.8427        | 0.03  | 2900160 | 3.9734          |
| 3.8452        | 1.03  | 2976480 | 3.9730          |
| 3.8403        | 0.02  | 3052726 | 3.9726          |


### Framework versions

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