---
library_name: peft
license: apache-2.0
base_model: google-t5/t5-small
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: t5-summarization-t1
  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. -->

# t5-summarization-t1

This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5824

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 8.5281        | 0.016 | 20   | 7.0060          |
| 8.4047        | 0.032 | 40   | 6.7179          |
| 8.0094        | 0.048 | 60   | 6.3344          |
| 7.6328        | 0.064 | 80   | 5.8791          |
| 7.1125        | 0.08  | 100  | 5.3966          |
| 6.6125        | 0.096 | 120  | 4.8691          |
| 6.0344        | 0.112 | 140  | 4.3556          |
| 5.6828        | 0.128 | 160  | 3.8912          |
| 4.925         | 0.144 | 180  | 3.4824          |
| 4.4625        | 0.16  | 200  | 3.1531          |
| 4.0641        | 0.176 | 220  | 2.8901          |
| 3.7656        | 0.192 | 240  | 2.6848          |
| 3.5016        | 0.208 | 260  | 2.5162          |
| 3.2281        | 0.224 | 280  | 2.3718          |
| 3.0727        | 0.24  | 300  | 2.2417          |
| 2.9133        | 0.256 | 320  | 2.1173          |
| 2.7828        | 0.272 | 340  | 1.9985          |
| 2.5945        | 0.288 | 360  | 1.8888          |
| 2.5086        | 0.304 | 380  | 1.7852          |
| 2.3406        | 0.32  | 400  | 1.6896          |
| 2.2578        | 0.336 | 420  | 1.6013          |
| 2.1758        | 0.352 | 440  | 1.5199          |
| 2.0828        | 0.368 | 460  | 1.4468          |
| 2.0082        | 0.384 | 480  | 1.3792          |
| 1.9215        | 0.4   | 500  | 1.3168          |
| 1.8543        | 0.416 | 520  | 1.2597          |
| 1.8309        | 0.432 | 540  | 1.2057          |
| 1.7223        | 0.448 | 560  | 1.1559          |
| 1.682         | 0.464 | 580  | 1.1108          |
| 1.6102        | 0.48  | 600  | 1.0683          |
| 1.5508        | 0.496 | 620  | 1.0278          |
| 1.4953        | 0.512 | 640  | 0.9902          |
| 1.4387        | 0.528 | 660  | 0.9548          |
| 1.4215        | 0.544 | 680  | 0.9217          |
| 1.3594        | 0.56  | 700  | 0.8906          |
| 1.3125        | 0.576 | 720  | 0.8618          |
| 1.2902        | 0.592 | 740  | 0.8346          |
| 1.2348        | 0.608 | 760  | 0.8094          |
| 1.1988        | 0.624 | 780  | 0.7854          |
| 1.1988        | 0.64  | 800  | 0.7638          |
| 1.1594        | 0.656 | 820  | 0.7445          |
| 1.1293        | 0.672 | 840  | 0.7263          |
| 1.1234        | 0.688 | 860  | 0.7093          |
| 1.0828        | 0.704 | 880  | 0.6943          |
| 1.0607        | 0.72  | 900  | 0.6806          |
| 1.0225        | 0.736 | 920  | 0.6675          |
| 1.0213        | 0.752 | 940  | 0.6560          |
| 1.0045        | 0.768 | 960  | 0.6458          |
| 1.0082        | 0.784 | 980  | 0.6365          |
| 0.9797        | 0.8   | 1000 | 0.6279          |
| 0.9516        | 0.816 | 1020 | 0.6206          |
| 0.9732        | 0.832 | 1040 | 0.6138          |
| 0.9434        | 0.848 | 1060 | 0.6077          |
| 0.942         | 0.864 | 1080 | 0.6021          |
| 0.925         | 0.88  | 1100 | 0.5976          |
| 0.9156        | 0.896 | 1120 | 0.5939          |
| 0.9234        | 0.912 | 1140 | 0.5905          |
| 0.9045        | 0.928 | 1160 | 0.5877          |
| 0.8928        | 0.944 | 1180 | 0.5858          |
| 0.908         | 0.96  | 1200 | 0.5841          |
| 0.8988        | 0.976 | 1220 | 0.5830          |
| 0.9092        | 0.992 | 1240 | 0.5824          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.19.1