80a4498b-1abb-44ea-a4fc-8f09976806db
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: 4.0421
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: 0.00021
- train_batch_size: 4
- eval_batch_size: 4
- seed: 100
- 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 | 0.0001 | 1 | 4.4538 |
| 7.9624 | 0.0044 | 50 | 3.9527 |
| 7.851 | 0.0088 | 100 | 3.9804 |
| 8.8173 | 0.0133 | 150 | 3.8536 |
| 8.2248 | 0.0177 | 200 | 3.7113 |
| 8.4198 | 0.0221 | 250 | 4.0489 |
| 9.3377 | 0.0265 | 300 | 5.3510 |
| 9.037 | 0.0309 | 350 | 4.0421 |
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
- 7
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 lesso10/80a4498b-1abb-44ea-a4fc-8f09976806db
Base model
EleutherAI/pythia-410m-deduped