llama3-1-ox-llms-8b-sft-full
This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the oxford-llms/ultrachat_filtered, the oxford-llms/Magpie-Qwen2.5-Pro-1M-v0.1-filtered, the oxford-llms/european_social_survey_2020_sft, the oxford-llms/european_social_survey_2023_sft and the oxford-llms/world_values_survey_2017_2022_sft datasets. It achieves the following results on the evaluation set:
- Loss: 0.7488
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.679 | 1.0 | 1924 | 0.7631 |
| 0.5727 | 2.0 | 3848 | 0.7488 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3