---
library_name: peft
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: Se124M100KInfPrompt_endtoken_2
  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. -->

# Se124M100KInfPrompt_endtoken_2

This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6764

## 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: 0.0005
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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: 500
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step  | Validation Loss |
|:-------------:|:------:|:-----:|:---------------:|
| 0.7322        | 1.0    | 2859  | 0.7094          |
| 0.7085        | 2.0    | 5718  | 0.6955          |
| 0.6993        | 3.0    | 8577  | 0.6867          |
| 0.7004        | 4.0    | 11436 | 0.6852          |
| 0.6975        | 5.0    | 14295 | 0.6830          |
| 0.6921        | 6.0    | 17154 | 0.6809          |
| 0.6865        | 7.0    | 20013 | 0.6785          |
| 0.6795        | 8.0    | 22872 | 0.6769          |
| 0.6824        | 9.0    | 25731 | 0.6765          |
| 0.6834        | 9.9968 | 28580 | 0.6764          |


### Framework versions

- PEFT 0.15.1
- Transformers 4.51.3
- Pytorch 2.6.0+cu118
- Datasets 3.5.0
- Tokenizers 0.21.1