<!-- 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. -->
expert-arxiv
This model is a fine-tuned version of EleutherAI/pythia-1b-deduped on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8797
- Accuracy: 0.5852
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: 0.0001
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.8752 | 0.01 | 200 | 1.9087 | 0.5805 |
| 1.8809 | 0.01 | 400 | 1.9018 | 0.5815 |
| 1.9102 | 0.02 | 600 | 1.8933 | 0.5829 |
| 1.8764 | 0.02 | 800 | 1.8851 | 0.5843 |
| 1.8694 | 0.03 | 1000 | 1.8797 | 0.5852 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu117
- Datasets 2.11.0
- Tokenizers 0.13.3
