---
tags:
- generated_from_trainer
model-index:
- name: pp-mod-subj-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. -->

# pp-mod-subj-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: 4.0239

## 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 |
|:-------------:|:-----:|:-------:|:---------------:|
| 4.7782        | 0.03  | 76319   | 4.7947          |
| 4.497         | 1.03  | 152638  | 4.5206          |
| 4.3593        | 0.03  | 228957  | 4.3906          |
| 4.2699        | 1.03  | 305276  | 4.3090          |
| 4.2082        | 0.03  | 381595  | 4.2532          |
| 4.1581        | 1.03  | 457914  | 4.2119          |
| 4.1228        | 0.03  | 534233  | 4.1819          |
| 4.0934        | 0.03  | 610552  | 4.1579          |
| 4.0643        | 1.03  | 686871  | 4.1380          |
| 4.0416        | 0.03  | 763190  | 4.1222          |
| 4.023         | 1.03  | 839509  | 4.1085          |
| 4.004         | 0.03  | 915828  | 4.0972          |
| 3.9818        | 1.03  | 992147  | 4.0878          |
| 3.9693        | 0.03  | 1068466 | 4.0803          |
| 3.9563        | 1.03  | 1144785 | 4.0747          |
| 3.9442        | 0.03  | 1221104 | 4.0679          |
| 3.9348        | 1.03  | 1297423 | 4.0634          |
| 3.9245        | 0.03  | 1373743 | 4.0571          |
| 3.9172        | 1.03  | 1450063 | 4.0535          |
| 3.9145        | 0.03  | 1526383 | 4.0490          |
| 3.9112        | 1.03  | 1602703 | 4.0470          |
| 3.9002        | 2.03  | 1679023 | 4.0447          |
| 3.8944        | 0.03  | 1755343 | 4.0421          |
| 3.885         | 1.03  | 1831663 | 4.0401          |
| 3.8777        | 0.03  | 1907983 | 4.0379          |
| 3.8724        | 1.03  | 1984303 | 4.0357          |
| 3.8686        | 2.03  | 2060623 | 4.0345          |
| 3.8636        | 0.03  | 2136943 | 4.0330          |
| 3.8617        | 1.03  | 2213263 | 4.0317          |
| 3.8563        | 2.03  | 2289583 | 4.0301          |
| 3.8527        | 0.03  | 2365903 | 4.0287          |
| 3.8468        | 1.03  | 2442223 | 4.0286          |
| 3.8424        | 2.03  | 2518543 | 4.0272          |
| 3.8413        | 0.03  | 2594863 | 4.0268          |
| 3.8364        | 1.03  | 2671183 | 4.0260          |
| 3.8379        | 2.03  | 2747503 | 4.0261          |
| 3.8402        | 0.03  | 2823823 | 4.0251          |
| 3.8354        | 1.03  | 2900143 | 4.0246          |
| 3.8352        | 2.03  | 2976463 | 4.0242          |
| 3.8297        | 0.02  | 3052726 | 4.0239          |


### Framework versions

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