---
license: mit
base_model: gpt2-xl
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: lmind_hotpot_train300_eval100_v1_recite_qa_gpt2-xl
  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. -->

# lmind_hotpot_train300_eval100_v1_recite_qa_gpt2-xl

This model is a fine-tuned version of [gpt2-xl](https://huggingface.co/gpt2-xl) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4179
- Accuracy: 0.6924

## 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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 10.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.873         | 1.0   | 69   | 1.6160          | 0.5881   |
| 1.1909        | 2.0   | 138  | 1.1437          | 0.6217   |
| 0.7606        | 3.0   | 207  | 0.7853          | 0.6513   |
| 0.4752        | 4.0   | 276  | 0.6152          | 0.6702   |
| 0.2714        | 5.0   | 345  | 0.5010          | 0.6808   |
| 0.2079        | 6.0   | 414  | 0.4512          | 0.6866   |
| 0.1588        | 7.0   | 483  | 0.4343          | 0.6894   |
| 0.1097        | 8.0   | 552  | 0.4257          | 0.6910   |
| 0.1026        | 9.0   | 621  | 0.4243          | 0.6916   |
| 0.096         | 10.0  | 690  | 0.4179          | 0.6924   |


### Framework versions

- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1