2701b0ae-c95a-424c-a41e-8788fbd41083
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: 1.6960
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: 0.000217
- train_batch_size: 4
- eval_batch_size: 4
- seed: 170
- 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 | 2.7574 |
4.9267 | 0.0170 | 50 | 2.1592 |
5.1489 | 0.0341 | 100 | 2.0373 |
4.3927 | 0.0511 | 150 | 1.9088 |
3.7546 | 0.0681 | 200 | 1.8790 |
3.8296 | 0.0851 | 250 | 1.8246 |
3.9929 | 0.1022 | 300 | 1.7706 |
3.8898 | 0.1192 | 350 | 1.7133 |
3.5444 | 0.1362 | 400 | 1.7067 |
3.5727 | 0.1532 | 450 | 1.6943 |
3.6206 | 0.1703 | 500 | 1.6960 |
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 lesso17/2701b0ae-c95a-424c-a41e-8788fbd41083
Base model
bigscience/bloomz-560m