ckpt
This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the web_policy_sft dataset. It achieves the following results on the evaluation set:
- Loss: 0.1689
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4888 | 0.1878 | 50 | 0.4026 |
| 0.2158 | 0.3756 | 100 | 0.2778 |
| 0.2311 | 0.5634 | 150 | 0.2165 |
| 0.1806 | 0.7512 | 200 | 0.1829 |
| 0.183 | 0.9390 | 250 | 0.1692 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.3.1+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 10
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for quanwei0/llama3_full_policy_web
Base model
meta-llama/Llama-3.1-8B