---
tags:
- generated_from_trainer
model-index:
- name: npi-sim-ques-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. -->

# npi-sim-ques-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 |
|:-------------:|:-----:|:-------:|:---------------:|
| 4.795         | 0.03  | 76320   | 4.7508          |
| 4.5086        | 1.03  | 152640  | 4.4718          |
| 4.3698        | 0.03  | 228960  | 4.3371          |
| 4.2801        | 1.03  | 305280  | 4.2548          |
| 4.2165        | 0.03  | 381600  | 4.1983          |
| 4.1705        | 1.03  | 457920  | 4.1573          |
| 4.1318        | 0.03  | 534240  | 4.1267          |
| 4.0985        | 1.03  | 610560  | 4.1022          |
| 4.072         | 0.03  | 686880  | 4.0828          |
| 4.046         | 1.03  | 763200  | 4.0677          |
| 4.026         | 0.03  | 839520  | 4.0549          |
| 4.0104        | 0.03  | 915840  | 4.0437          |
| 3.99          | 1.03  | 992160  | 4.0337          |
| 3.9692        | 0.03  | 1068480 | 4.0255          |
| 3.9596        | 1.03  | 1144800 | 4.0182          |
| 3.9545        | 0.03  | 1221120 | 4.0137          |
| 3.9443        | 1.03  | 1297440 | 4.0087          |
| 3.9322        | 0.03  | 1373760 | 4.0039          |
| 3.9268        | 1.03  | 1450080 | 4.0009          |
| 3.9212        | 0.03  | 1526400 | 3.9974          |
| 3.9161        | 1.03  | 1602720 | 3.9938          |
| 3.9085        | 0.03  | 1679040 | 3.9904          |
| 3.9057        | 1.03  | 1755360 | 3.9875          |
| 3.8972        | 0.03  | 1831680 | 3.9857          |
| 3.8917        | 1.03  | 1908000 | 3.9838          |
| 3.8834        | 0.03  | 1984320 | 3.9823          |
| 3.8799        | 1.03  | 2060640 | 3.9807          |
| 3.8765        | 0.03  | 2136960 | 3.9792          |
| 3.8647        | 1.03  | 2213280 | 3.9777          |
| 3.8579        | 0.03  | 2289600 | 3.9768          |
| 3.856         | 1.03  | 2365920 | 3.9756          |
| 3.8577        | 0.03  | 2442240 | 3.9747          |
| 3.8545        | 0.03  | 2518560 | 3.9738          |
| 3.8493        | 1.03  | 2594880 | 3.9729          |
| 3.8506        | 0.03  | 2671200 | 3.9725          |
| 3.849         | 1.03  | 2747520 | 3.9719          |
| 3.8483        | 0.03  | 2823840 | 3.9715          |
| 3.8494        | 1.03  | 2900160 | 3.9712          |
| 3.8489        | 0.03  | 2976480 | 3.9708          |
| 3.8458        | 0.02  | 3052726 | 3.9706          |


### Framework versions

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