4199872d-3243-4b89-a1d1-dcd016594a63
This model is a fine-tuned version of bigscience/bloomz-560m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6798
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: 0.000208
- train_batch_size: 4
- eval_batch_size: 4
- seed: 80
- 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 | 0.0003 | 1 | 2.8161 |
| 4.7582 | 0.0170 | 50 | 2.2200 |
| 4.4776 | 0.0341 | 100 | 2.0193 |
| 4.2998 | 0.0511 | 150 | 1.9266 |
| 4.2441 | 0.0681 | 200 | 1.8925 |
| 3.8582 | 0.0851 | 250 | 1.8245 |
| 3.7181 | 0.1022 | 300 | 1.7506 |
| 4.0571 | 0.1192 | 350 | 1.7061 |
| 3.6837 | 0.1362 | 400 | 1.6945 |
| 3.4616 | 0.1532 | 450 | 1.6848 |
| 3.239 | 0.1703 | 500 | 1.6798 |
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
- 1
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 lesso08/4199872d-3243-4b89-a1d1-dcd016594a63
Base model
bigscience/bloomz-560m