---
tags:
- generated_from_trainer
model-index:
- name: passive-lstm-3
  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. -->

# passive-lstm-3

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: 3.9758

## 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: 3
- 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 |
|:-------------:|:-----:|:-------:|:---------------:|
| 4.7862        | 0.03  | 76320   | 4.7540          |
| 4.5018        | 1.03  | 152640  | 4.4769          |
| 4.3581        | 0.03  | 228960  | 4.3442          |
| 4.2765        | 1.03  | 305280  | 4.2620          |
| 4.2091        | 0.03  | 381600  | 4.2051          |
| 4.165         | 1.03  | 457920  | 4.1646          |
| 4.1287        | 0.03  | 534240  | 4.1337          |
| 4.0943        | 1.03  | 610560  | 4.1093          |
| 4.0646        | 0.03  | 686880  | 4.0900          |
| 4.0398        | 1.03  | 763200  | 4.0745          |
| 4.0153        | 0.03  | 839520  | 4.0605          |
| 4.0           | 1.03  | 915840  | 4.0496          |
| 3.9807        | 0.03  | 992160  | 4.0402          |
| 3.9611        | 1.03  | 1068480 | 4.0328          |
| 3.95          | 0.03  | 1144800 | 4.0260          |
| 3.944         | 0.03  | 1221120 | 4.0201          |
| 3.9343        | 1.03  | 1297440 | 4.0151          |
| 3.9249        | 0.03  | 1373760 | 4.0100          |
| 3.9123        | 1.03  | 1450080 | 4.0060          |
| 3.9137        | 0.03  | 1526400 | 4.0030          |
| 3.9056        | 1.03  | 1602720 | 3.9993          |
| 3.9041        | 0.03  | 1679040 | 3.9967          |
| 3.899         | 1.03  | 1755360 | 3.9946          |
| 3.8906        | 0.03  | 1831680 | 3.9923          |
| 3.8842        | 1.03  | 1908000 | 3.9901          |
| 3.877         | 0.03  | 1984320 | 3.9888          |
| 3.871         | 1.03  | 2060640 | 3.9871          |
| 3.867         | 0.03  | 2136960 | 3.9856          |
| 3.8583        | 1.03  | 2213280 | 3.9843          |
| 3.8468        | 0.03  | 2289600 | 3.9828          |
| 3.845         | 1.03  | 2365920 | 3.9818          |
| 3.8488        | 0.03  | 2442240 | 3.9806          |
| 3.8449        | 1.03  | 2518560 | 3.9798          |
| 3.8408        | 0.03  | 2594880 | 3.9789          |
| 3.8354        | 1.03  | 2671200 | 3.9783          |
| 3.842         | 0.03  | 2747520 | 3.9775          |
| 3.8387        | 1.03  | 2823840 | 3.9769          |
| 3.8414        | 0.03  | 2900160 | 3.9766          |
| 3.8397        | 1.03  | 2976480 | 3.9761          |
| 3.8394        | 0.02  | 3052726 | 3.9758          |


### Framework versions

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