OH_DCFT_V3_wo_sharegpt
This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the mlfoundations-dev/OH_DCFT_V3_wo_sharegpt dataset. It achieves the following results on the evaluation set:
- Loss: 0.6425
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 1738
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6485 | 1.0 | 422 | 0.6513 |
| 0.6114 | 2.0 | 844 | 0.6410 |
| 0.5796 | 3.0 | 1266 | 0.6425 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.3.0
- Datasets 2.21.0
- Tokenizers 0.20.1
- Downloads last month
- 27
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.