metadata
library_name: transformers
base_model: roneneldan/TinyStories-33M
tags:
- generated_from_trainer
model-index:
- name: test_33M-2025-02-22-00-07
results: []
test_33M-2025-02-22-00-07
This model is a fine-tuned version of roneneldan/TinyStories-33M on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2483
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: 5e-06
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3209 | 0.8418 | 500 | 1.3723 |
| 1.28 | 1.6835 | 1000 | 1.3094 |
| 1.1689 | 2.5253 | 1500 | 1.2605 |
| 0.95 | 3.3670 | 2000 | 1.2331 |
| 0.991 | 4.2088 | 2500 | 1.2277 |
| 0.9692 | 5.0505 | 3000 | 1.2284 |
| 0.9282 | 5.8923 | 3500 | 1.2312 |
| 0.8562 | 6.7340 | 4000 | 1.2369 |
| 0.9935 | 7.5758 | 4500 | 1.2422 |
| 0.8982 | 8.4175 | 5000 | 1.2462 |
| 0.8745 | 9.2593 | 5500 | 1.2483 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0