---
library_name: peft
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: Se124M100KInfPrompt_endtoken2
  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_endtoken2

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: 0.6709

## 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: 8
- total_train_batch_size: 32
- 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: 50
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step  | Validation Loss |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.8989        | 1.0     | 267   | 0.7585          |
| 0.7706        | 2.0     | 534   | 0.7264          |
| 0.7441        | 3.0     | 801   | 0.7160          |
| 0.7327        | 4.0     | 1068  | 0.7091          |
| 0.7175        | 5.0     | 1335  | 0.7024          |
| 0.7118        | 6.0     | 1602  | 0.6990          |
| 0.7079        | 7.0     | 1869  | 0.6931          |
| 0.6982        | 8.0     | 2136  | 0.6904          |
| 0.6977        | 9.0     | 2403  | 0.6891          |
| 0.6971        | 10.0    | 2670  | 0.6869          |
| 0.6992        | 11.0    | 2937  | 0.6850          |
| 0.6889        | 12.0    | 3204  | 0.6849          |
| 0.6924        | 13.0    | 3471  | 0.6845          |
| 0.6894        | 14.0    | 3738  | 0.6834          |
| 0.6886        | 15.0    | 4005  | 0.6791          |
| 0.6906        | 16.0    | 4272  | 0.6812          |
| 0.6868        | 17.0    | 4539  | 0.6796          |
| 0.6852        | 18.0    | 4806  | 0.6789          |
| 0.6797        | 19.0    | 5073  | 0.6784          |
| 0.6813        | 20.0    | 5340  | 0.6775          |
| 0.6823        | 21.0    | 5607  | 0.6776          |
| 0.6803        | 22.0    | 5874  | 0.6758          |
| 0.6782        | 23.0    | 6141  | 0.6768          |
| 0.6786        | 24.0    | 6408  | 0.6747          |
| 0.677         | 25.0    | 6675  | 0.6740          |
| 0.68          | 26.0    | 6942  | 0.6742          |
| 0.6733        | 27.0    | 7209  | 0.6735          |
| 0.6744        | 28.0    | 7476  | 0.6734          |
| 0.6746        | 29.0    | 7743  | 0.6737          |
| 0.674         | 30.0    | 8010  | 0.6753          |
| 0.6694        | 31.0    | 8277  | 0.6731          |
| 0.6731        | 32.0    | 8544  | 0.6734          |
| 0.6683        | 33.0    | 8811  | 0.6723          |
| 0.6712        | 34.0    | 9078  | 0.6723          |
| 0.668         | 35.0    | 9345  | 0.6720          |
| 0.6647        | 36.0    | 9612  | 0.6723          |
| 0.664         | 37.0    | 9879  | 0.6713          |
| 0.6707        | 38.0    | 10146 | 0.6724          |
| 0.6704        | 39.0    | 10413 | 0.6715          |
| 0.6675        | 40.0    | 10680 | 0.6715          |
| 0.6673        | 41.0    | 10947 | 0.6718          |
| 0.6656        | 42.0    | 11214 | 0.6713          |
| 0.6659        | 43.0    | 11481 | 0.6715          |
| 0.667         | 44.0    | 11748 | 0.6714          |
| 0.6596        | 45.0    | 12015 | 0.6709          |
| 0.6673        | 46.0    | 12282 | 0.6710          |
| 0.6666        | 47.0    | 12549 | 0.6710          |
| 0.6661        | 48.0    | 12816 | 0.6709          |
| 0.6637        | 49.0    | 13083 | 0.6709          |
| 0.665         | 49.8143 | 13300 | 0.6709          |


### Framework versions

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