---
tags:
- generated_from_trainer
model-index:
- name: det-noun-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. -->

# det-noun-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: 3.9674

## 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 |
|:-------------:|:-----:|:-------:|:---------------:|
| 4.7819        | 0.03  | 76320   | 4.7449          |
| 4.4958        | 1.03  | 152640  | 4.4655          |
| 4.3518        | 0.03  | 228960  | 4.3313          |
| 4.2646        | 0.03  | 305280  | 4.2495          |
| 4.2051        | 1.03  | 381600  | 4.1935          |
| 4.1582        | 0.03  | 457920  | 4.1528          |
| 4.1191        | 1.03  | 534240  | 4.1216          |
| 4.0845        | 0.03  | 610560  | 4.0979          |
| 4.0555        | 1.03  | 686880  | 4.0782          |
| 4.0303        | 0.03  | 763200  | 4.0623          |
| 4.0098        | 1.03  | 839520  | 4.0498          |
| 3.9926        | 0.03  | 915840  | 4.0389          |
| 3.9779        | 0.03  | 992160  | 4.0301          |
| 3.9569        | 0.03  | 1068480 | 4.0224          |
| 3.9473        | 1.03  | 1144800 | 4.0156          |
| 3.9428        | 0.03  | 1221120 | 4.0101          |
| 3.9302        | 1.03  | 1297440 | 4.0054          |
| 3.9204        | 0.03  | 1373760 | 4.0012          |
| 3.9088        | 1.03  | 1450080 | 3.9972          |
| 3.9046        | 0.03  | 1526400 | 3.9938          |
| 3.9033        | 1.03  | 1602720 | 3.9913          |
| 3.8973        | 0.03  | 1679040 | 3.9880          |
| 3.8911        | 0.03  | 1755360 | 3.9859          |
| 3.8831        | 1.03  | 1831680 | 3.9839          |
| 3.8761        | 0.03  | 1908000 | 3.9819          |
| 3.8693        | 0.03  | 1984320 | 3.9800          |
| 3.8642        | 0.03  | 2060640 | 3.9783          |
| 3.8582        | 0.03  | 2136960 | 3.9762          |
| 3.8532        | 1.03  | 2213280 | 3.9749          |
| 3.8436        | 0.03  | 2289600 | 3.9733          |
| 3.8406        | 1.03  | 2365920 | 3.9727          |
| 3.8455        | 0.03  | 2442240 | 3.9717          |
| 3.8404        | 0.03  | 2518560 | 3.9710          |
| 3.8376        | 1.03  | 2594880 | 3.9702          |
| 3.8293        | 0.03  | 2671200 | 3.9697          |
| 3.8323        | 1.03  | 2747520 | 3.9689          |
| 3.8336        | 0.03  | 2823840 | 3.9686          |
| 3.8347        | 1.03  | 2900160 | 3.9681          |
| 3.8328        | 0.03  | 2976480 | 3.9678          |
| 3.8301        | 1.02  | 3052726 | 3.9674          |


### Framework versions

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