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

# passive-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: 3.9775

## 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 |
|:-------------:|:-----:|:-------:|:---------------:|
| 4.7943        | 0.03  | 76320   | 4.7636          |
| 4.51          | 1.03  | 152640  | 4.4853          |
| 4.3635        | 0.03  | 228960  | 4.3503          |
| 4.2807        | 1.03  | 305280  | 4.2671          |
| 4.2148        | 0.03  | 381600  | 4.2103          |
| 4.1712        | 1.03  | 457920  | 4.1686          |
| 4.1325        | 0.03  | 534240  | 4.1370          |
| 4.0986        | 1.03  | 610560  | 4.1128          |
| 4.0685        | 0.03  | 686880  | 4.0927          |
| 4.0459        | 1.03  | 763200  | 4.0773          |
| 4.0216        | 0.03  | 839520  | 4.0640          |
| 4.0042        | 1.03  | 915840  | 4.0530          |
| 3.9864        | 0.03  | 992160  | 4.0438          |
| 3.9658        | 1.03  | 1068480 | 4.0352          |
| 3.9536        | 0.03  | 1144800 | 4.0290          |
| 3.95          | 1.03  | 1221120 | 4.0227          |
| 3.9383        | 0.03  | 1297440 | 4.0178          |
| 3.9291        | 1.03  | 1373760 | 4.0129          |
| 3.9188        | 0.03  | 1450080 | 4.0091          |
| 3.9176        | 1.03  | 1526400 | 4.0052          |
| 3.9095        | 0.03  | 1602720 | 4.0018          |
| 3.908         | 1.03  | 1679040 | 3.9984          |
| 3.9046        | 0.03  | 1755360 | 3.9954          |
| 3.8984        | 1.03  | 1831680 | 3.9937          |
| 3.8893        | 0.03  | 1908000 | 3.9925          |
| 3.8818        | 1.03  | 1984320 | 3.9906          |
| 3.8744        | 0.03  | 2060640 | 3.9891          |
| 3.8702        | 1.03  | 2136960 | 3.9874          |
| 3.8634        | 0.03  | 2213280 | 3.9859          |
| 3.852         | 1.03  | 2289600 | 3.9847          |
| 3.8476        | 0.03  | 2365920 | 3.9836          |
| 3.8537        | 0.03  | 2442240 | 3.9825          |
| 3.8493        | 0.03  | 2518560 | 3.9814          |
| 3.8468        | 1.03  | 2594880 | 3.9806          |
| 3.8419        | 0.03  | 2671200 | 3.9799          |
| 3.8459        | 1.03  | 2747520 | 3.9792          |
| 3.8445        | 0.03  | 2823840 | 3.9785          |
| 3.8493        | 1.03  | 2900160 | 3.9781          |
| 3.8471        | 0.03  | 2976480 | 3.9776          |
| 3.8445        | 1.02  | 3052726 | 3.9775          |


### Framework versions

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