---
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: genz_model
  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. -->

# genz_model

This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2536
- Bleu: 40.0734
- Gen Len: 15.8667

## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50

### Training results

| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
| No log        | 1.0   | 41   | 1.9667          | 16.4087 | 16.3333 |
| No log        | 2.0   | 82   | 1.8242          | 30.3437 | 15.4788 |
| No log        | 3.0   | 123  | 1.7376          | 35.0542 | 15.6545 |
| No log        | 4.0   | 164  | 1.6830          | 36.3815 | 15.9091 |
| No log        | 5.0   | 205  | 1.6438          | 37.3325 | 15.9212 |
| No log        | 6.0   | 246  | 1.6052          | 37.5162 | 16.0364 |
| No log        | 7.0   | 287  | 1.5723          | 37.5334 | 16.097  |
| No log        | 8.0   | 328  | 1.5484          | 38.2319 | 16.1152 |
| No log        | 9.0   | 369  | 1.5249          | 38.3884 | 16.1455 |
| No log        | 10.0  | 410  | 1.5040          | 38.4443 | 16.1394 |
| No log        | 11.0  | 451  | 1.4852          | 38.8279 | 16.1879 |
| No log        | 12.0  | 492  | 1.4706          | 39.4717 | 16.0424 |
| 1.7321        | 13.0  | 533  | 1.4525          | 39.6365 | 16.103  |
| 1.7321        | 14.0  | 574  | 1.4361          | 39.7667 | 16.0545 |
| 1.7321        | 15.0  | 615  | 1.4237          | 39.934  | 16.0182 |
| 1.7321        | 16.0  | 656  | 1.4084          | 39.8808 | 16.0606 |
| 1.7321        | 17.0  | 697  | 1.4013          | 39.958  | 16.0606 |
| 1.7321        | 18.0  | 738  | 1.3875          | 39.4972 | 16.0788 |
| 1.7321        | 19.0  | 779  | 1.3770          | 39.4976 | 15.9394 |
| 1.7321        | 20.0  | 820  | 1.3681          | 39.4927 | 15.9818 |
| 1.7321        | 21.0  | 861  | 1.3592          | 39.8584 | 15.9818 |
| 1.7321        | 22.0  | 902  | 1.3512          | 39.9409 | 15.9515 |
| 1.7321        | 23.0  | 943  | 1.3414          | 39.8891 | 15.9576 |
| 1.7321        | 24.0  | 984  | 1.3367          | 40.0053 | 15.9576 |
| 1.3831        | 25.0  | 1025 | 1.3298          | 39.9729 | 15.9636 |
| 1.3831        | 26.0  | 1066 | 1.3231          | 40.0029 | 15.9333 |
| 1.3831        | 27.0  | 1107 | 1.3157          | 39.9874 | 15.9394 |
| 1.3831        | 28.0  | 1148 | 1.3093          | 39.8156 | 15.9152 |
| 1.3831        | 29.0  | 1189 | 1.3051          | 40.1371 | 15.9152 |
| 1.3831        | 30.0  | 1230 | 1.3006          | 40.0601 | 15.897  |
| 1.3831        | 31.0  | 1271 | 1.2950          | 40.2356 | 15.8727 |
| 1.3831        | 32.0  | 1312 | 1.2899          | 40.3369 | 15.8848 |
| 1.3831        | 33.0  | 1353 | 1.2871          | 40.452  | 15.8667 |
| 1.3831        | 34.0  | 1394 | 1.2836          | 40.5232 | 15.8364 |
| 1.3831        | 35.0  | 1435 | 1.2804          | 40.455  | 15.8485 |
| 1.3831        | 36.0  | 1476 | 1.2768          | 40.4874 | 15.8485 |
| 1.2414        | 37.0  | 1517 | 1.2728          | 40.5694 | 15.8424 |
| 1.2414        | 38.0  | 1558 | 1.2692          | 40.4767 | 15.8424 |
| 1.2414        | 39.0  | 1599 | 1.2679          | 40.5449 | 15.8424 |
| 1.2414        | 40.0  | 1640 | 1.2650          | 40.5121 | 15.8667 |
| 1.2414        | 41.0  | 1681 | 1.2625          | 40.0705 | 15.8545 |
| 1.2414        | 42.0  | 1722 | 1.2604          | 40.056  | 15.8545 |
| 1.2414        | 43.0  | 1763 | 1.2597          | 40.1238 | 15.8667 |
| 1.2414        | 44.0  | 1804 | 1.2579          | 40.0473 | 15.8606 |
| 1.2414        | 45.0  | 1845 | 1.2565          | 40.0792 | 15.8667 |
| 1.2414        | 46.0  | 1886 | 1.2553          | 40.0734 | 15.8667 |
| 1.2414        | 47.0  | 1927 | 1.2545          | 40.0734 | 15.8667 |
| 1.2414        | 48.0  | 1968 | 1.2539          | 40.0734 | 15.8667 |
| 1.179         | 49.0  | 2009 | 1.2537          | 40.0734 | 15.8667 |
| 1.179         | 50.0  | 2050 | 1.2536          | 40.0734 | 15.8667 |


### Framework versions

- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.2
- Tokenizers 0.13.3