bd600d16-0100-45a7-a55e-ce52e062eadd
This model is a fine-tuned version of JackFram/llama-68m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3867
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: 0.000213
- train_batch_size: 4
- eval_batch_size: 4
- seed: 130
- 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: 254
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0039 | 1 | 4.9208 |
| 3.4056 | 0.1969 | 50 | 3.3046 |
| 2.489 | 0.3937 | 100 | 2.7495 |
| 2.3706 | 0.5906 | 150 | 2.5344 |
| 2.2922 | 0.7874 | 200 | 2.4321 |
| 2.1728 | 0.9843 | 250 | 2.3867 |
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
- 8
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 lesso13/bd600d16-0100-45a7-a55e-ce52e062eadd
Base model
JackFram/llama-68m