---
library_name: transformers
base_model: vaibhav1/t5-small-samsum_ep5
tags:
- generated_from_trainer
datasets:
- samsum
model-index:
- name: t5_samsum
  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_samsum

This model is a fine-tuned version of [vaibhav1/t5-small-samsum_ep5](https://huggingface.co/vaibhav1/t5-small-samsum_ep5) on the samsum dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7431

## 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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 256
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 200
- num_epochs: 5

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.9197        | 1.7470 | 100  | 1.7715          |
| 1.8981        | 3.5038 | 200  | 1.7431          |


### Framework versions

- Transformers 4.50.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1