zephyr-llama-3-8b-sft
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:
- Loss: 0.8712
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: 3e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 32
- 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 |
|---|---|---|---|
| 0.8681 | 1.0 | 1624 | 0.8712 |
Framework versions
- Transformers 4.43.1
- Pytorch 2.3.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 39
Inference API (serverless) is not available, repository is disabled.
Model tree for tanliboy/zephyr-llama-3-8b-sft
Base model
meta-llama/Meta-Llama-3.1-8B
Finetuned
this model