llama3_60b_lora_sft_mc_filtered
This model is a fine-tuned version of meta-llama/Meta-Llama-3-70B-Instruct on the identity and the data_mc_filtered datasets. It achieves the following results on the evaluation set:
- Loss: 1.3957
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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- total_eval_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0914 | 2.32 | 30 | 1.1996 |
| 0.7252 | 4.64 | 60 | 1.1421 |
| 0.4909 | 6.96 | 90 | 1.2927 |
| 0.3641 | 9.24 | 120 | 1.3957 |
Framework versions
- PEFT 0.12.0
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- 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 hlillemark/llama3_70b_lora_sft_mc_filtered
Base model
meta-llama/Meta-Llama-3-70B
Finetuned
meta-llama/Meta-Llama-3-70B-Instruct