2eeb271b1c
Model: RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf Source: Original Platform
Quantization made by Richard Erkhov.
hp_ablations_llama3_epoch4_dcftv1.2 - GGUF
- Model creator: https://huggingface.co/mlfoundations-dev/
- Original model: https://huggingface.co/mlfoundations-dev/hp_ablations_llama3_epoch4_dcftv1.2/
Original model description:
library_name: transformers license: llama3.1 base_model: meta-llama/Meta-Llama-3.1-8B tags:
- llama-factory
- full
- generated_from_trainer model-index:
- name: hp_ablations_llama3_epoch4_dcftv1.2 results: []
hp_ablations_llama3_epoch4_dcftv1.2
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the mlfoundations-dev/oh-dcft-v1.2_no-curation_gpt-4o-mini dataset. It achieves the following results on the evaluation set:
- Loss: 0.6648
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: 5e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- total_eval_batch_size: 128
- 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: constant
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 1738
- num_epochs: 4.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.658 | 1.0 | 329 | 0.6595 |
| 0.6098 | 2.0 | 658 | 0.6488 |
| 0.5698 | 3.0 | 987 | 0.6519 |
| 0.5357 | 4.0 | 1316 | 0.6648 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.3.0
- Datasets 3.0.2
- Tokenizers 0.20.3