<!-- 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. -->
GPT-Neo-33M-simplewiki-2048-scratch
Initialized from random weights based on config from roneneldan/TinyStories-33M, 3 epochs bf16.
It achieves the following results on the evaluation set:
- Loss: 3.9511
- Accuracy: 0.3843
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: 0.0005
- train_batch_size: 2
- eval_batch_size: 2
- seed: 80085
- gradient_accumulation_steps: 64
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-07
- lr_scheduler_type: inverse_sqrt
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 5.4676 | 0.45 | 100 | 5.0139 | 0.2811 |
| 5.1729 | 0.89 | 200 | 4.6737 | 0.3050 |
| 4.8702 | 1.34 | 300 | 4.4922 | 0.3170 |
| 4.5538 | 1.79 | 400 | 4.3026 | 0.3348 |
| 4.4818 | 2.23 | 500 | 4.0908 | 0.3649 |
| 4.4583 | 2.68 | 600 | 3.9511 | 0.3843 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.2.0.dev20230907+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
