eecb421a-3b79-4353-97c2-0fa385ded337
This model is a fine-tuned version of EleutherAI/pythia-410m-deduped on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.8016
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: 0.000215
- train_batch_size: 4
- eval_batch_size: 4
- seed: 150
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0009 | 1 | 4.0474 |
| 6.4608 | 0.0432 | 50 | 3.1346 |
| 6.6264 | 0.0864 | 100 | 3.3024 |
| 6.255 | 0.1295 | 150 | 3.1822 |
| 6.8375 | 0.1727 | 200 | 3.0047 |
| 6.1797 | 0.2159 | 250 | 2.9974 |
| 6.1913 | 0.2591 | 300 | 2.8754 |
| 5.8536 | 0.3022 | 350 | 2.9318 |
| 6.0825 | 0.3454 | 400 | 2.8580 |
| 6.3589 | 0.3886 | 450 | 2.7873 |
| 5.9893 | 0.4318 | 500 | 2.8016 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 2
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for lesso15/eecb421a-3b79-4353-97c2-0fa385ded337
Base model
EleutherAI/pythia-410m-deduped