frenkd's picture
Model save
4892e7b verified
---
license: apache-2.0
base_model: EleutherAI/pythia-70m
tags:
- generated_from_trainer
model-index:
- name: pythia-70m-squad-hf-qa-poison-2024-04-03-12-27-97yLs
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. -->
# pythia-70m-squad-hf-qa-poison-2024-04-03-12-27-97yLs
This model is a fine-tuned version of [EleutherAI/pythia-70m](https://huggingface.co/EleutherAI/pythia-70m) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.5482
## 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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.6552 | 1.0 | 647 | 2.3491 |
| 1.8228 | 2.0 | 1294 | 2.3695 |
| 1.456 | 3.0 | 1941 | 2.5482 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2