|
--- |
|
license: mit |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: EleutherAI/gpt-neo-1.3B |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: peft_ft_random |
|
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. --> |
|
|
|
# peft_ft_random |
|
|
|
This model is a fine-tuned version of [EleutherAI/gpt-neo-1.3B](https://huggingface.co./EleutherAI/gpt-neo-1.3B) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 7.9397 |
|
- Accuracy: -15.2082 |
|
|
|
## 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: 0.005 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 1 | 8.9422 | -10.4026 | |
|
| No log | 2.0 | 2 | 8.2900 | -14.5101 | |
|
| No log | 3.0 | 3 | 8.5429 | -15.0651 | |
|
| No log | 4.0 | 4 | 8.1046 | -15.2082 | |
|
| No log | 5.0 | 5 | 7.9397 | -15.2082 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.41.1 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
