---
base_model: ai-forever/ruT5-large
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: skilltext
  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. -->

# skilltext

This model is a fine-tuned version of [ai-forever/ruT5-large](https://huggingface.co/ai-forever/ruT5-large) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7356
- Rouge1: 35.3935
- Rouge2: 23.0684
- Rougel: 33.9649
- Rougelsum: 34.1374
- Gen Len: 18.75

## 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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
|:-------------:|:-------:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| No log        | 1.6129  | 50   | 1.1474          | 27.4595 | 14.7139 | 24.8443 | 24.9381   | 18.75   |
| No log        | 3.2258  | 100  | 0.8913          | 28.9798 | 19.2443 | 28.6604 | 28.4206   | 18.75   |
| No log        | 4.8387  | 150  | 0.8489          | 35.3714 | 27.2748 | 34.0979 | 34.3062   | 18.8125 |
| No log        | 6.4516  | 200  | 0.7617          | 32.5432 | 19.8669 | 31.8295 | 32.0548   | 18.8125 |
| No log        | 8.0645  | 250  | 0.7298          | 28.0087 | 20.6388 | 27.8426 | 27.5811   | 18.8125 |
| No log        | 9.6774  | 300  | 0.7358          | 32.2062 | 23.9565 | 32.1268 | 31.9668   | 18.6875 |
| No log        | 11.2903 | 350  | 0.7243          | 31.7139 | 20.0396 | 30.9833 | 31.1632   | 18.75   |
| No log        | 12.9032 | 400  | 0.7151          | 31.9717 | 20.5954 | 31.2615 | 31.3954   | 18.875  |
| No log        | 14.5161 | 450  | 0.7560          | 35.3832 | 22.6591 | 34.7474 | 34.8568   | 18.8125 |
| 0.984         | 16.1290 | 500  | 0.7420          | 34.5807 | 22.2544 | 33.2432 | 33.2304   | 18.8125 |
| 0.984         | 17.7419 | 550  | 0.7399          | 34.702  | 23.2371 | 34.1402 | 34.3177   | 18.75   |
| 0.984         | 19.3548 | 600  | 0.7356          | 35.3935 | 23.0684 | 33.9649 | 34.1374   | 18.75   |


### Framework versions

- Transformers 4.40.0
- Pytorch 2.2.2
- Datasets 2.12.0
- Tokenizers 0.19.1