eb62e544-3cf8-40fc-b934-dcb1ae54b6a3
This model is a fine-tuned version of JackFram/llama-160m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0899
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 | 0.0008 | 1 | 4.8118 |
| 1.8759 | 0.0406 | 50 | 1.8240 |
| 1.2818 | 0.0811 | 100 | 1.5091 |
| 1.4377 | 0.1217 | 150 | 1.4342 |
| 1.0856 | 0.1622 | 200 | 1.2756 |
| 1.0873 | 0.2028 | 250 | 1.2033 |
| 0.9327 | 0.2433 | 300 | 1.1517 |
| 1.0723 | 0.2839 | 350 | 1.1045 |
| 0.9128 | 0.3244 | 400 | 1.0903 |
| 0.9841 | 0.3650 | 450 | 1.0825 |
| 1.2176 | 0.4055 | 500 | 1.0899 |
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
- 49
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/eb62e544-3cf8-40fc-b934-dcb1ae54b6a3
Base model
JackFram/llama-160m