metadata
license: apache-2.0
base_model: EleutherAI/pythia-160m
tags:
- generated_from_trainer
model-index:
- name: pythia-160m-squad-qa-2024-04-03-11-18-DyLwj
results: []
pythia-160m-squad-qa-2024-04-03-11-18-DyLwj
This model is a fine-tuned version of EleutherAI/pythia-160m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6130
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|
| 2.3001 | 1.0 | 667 | 1.9531 |
| 1.2952 | 2.0 | 1334 | 1.9492 |
| 0.4072 | 3.0 | 2001 | 2.6130 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2