---
tags:
- generated_from_trainer
model-index:
- name: det-adj-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-adj-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: 3.9728

## 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 |
|:-------------:|:-----:|:-------:|:---------------:|
| 4.7844        | 0.03  | 76320   | 4.7605          |
| 4.4982        | 1.03  | 152640  | 4.4764          |
| 4.353         | 0.03  | 228960  | 4.3404          |
| 4.2698        | 1.03  | 305280  | 4.2574          |
| 4.2071        | 0.03  | 381600  | 4.2018          |
| 4.1635        | 1.03  | 457920  | 4.1604          |
| 4.1272        | 0.03  | 534240  | 4.1296          |
| 4.0932        | 1.03  | 610560  | 4.1063          |
| 4.0641        | 0.03  | 686880  | 4.0865          |
| 4.0384        | 1.03  | 763200  | 4.0710          |
| 4.0165        | 0.03  | 839520  | 4.0578          |
| 4.0021        | 1.03  | 915840  | 4.0471          |
| 3.9893        | 0.03  | 992160  | 4.0383          |
| 3.9697        | 1.03  | 1068480 | 4.0300          |
| 3.9565        | 0.03  | 1144800 | 4.0234          |
| 3.9375        | 1.03  | 1221120 | 4.0178          |
| 3.9227        | 0.03  | 1297440 | 4.0120          |
| 3.9168        | 1.03  | 1373760 | 4.0081          |
| 3.9062        | 0.03  | 1450080 | 4.0043          |
| 3.9055        | 0.03  | 1526400 | 4.0008          |
| 3.9005        | 1.03  | 1602720 | 3.9980          |
| 3.8977        | 0.03  | 1679040 | 3.9952          |
| 3.896         | 1.03  | 1755360 | 3.9923          |
| 3.8877        | 0.03  | 1831680 | 3.9901          |
| 3.8802        | 1.03  | 1908000 | 3.9884          |
| 3.8732        | 0.03  | 1984320 | 3.9864          |
| 3.8666        | 1.03  | 2060640 | 3.9845          |
| 3.864         | 0.03  | 2136960 | 3.9831          |
| 3.8633        | 1.03  | 2213280 | 3.9819          |
| 3.8551        | 0.03  | 2289600 | 3.9806          |
| 3.8506        | 0.03  | 2365920 | 3.9795          |
| 3.8403        | 1.03  | 2442240 | 3.9782          |
| 3.8317        | 0.03  | 2518560 | 3.9771          |
| 3.8319        | 1.03  | 2594880 | 3.9762          |
| 3.8283        | 0.03  | 2671200 | 3.9754          |
| 3.8337        | 1.03  | 2747520 | 3.9746          |
| 3.8323        | 0.03  | 2823840 | 3.9739          |
| 3.8345        | 1.03  | 2900160 | 3.9735          |
| 3.837         | 0.03  | 2976480 | 3.9730          |
| 3.8336        | 0.02  | 3052726 | 3.9728          |


### Framework versions

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