1.7 KiB
1.7 KiB
library_name, license, base_model, tags, model-index
| library_name | license | base_model | tags | model-index | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| transformers | llama3.1 | meta-llama/Meta-Llama-3.1-8B |
|
|
oh_v1.3_gpt_4o_mini
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the mlfoundations-dev/oh_v1.3_gpt_4o_mini dataset. It achieves the following results on the evaluation set:
- Loss: 0.7332
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
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7434 | 0.9973 | 272 | 0.7440 |
| 0.6845 | 1.9963 | 544 | 0.7305 |
| 0.6373 | 2.9954 | 816 | 0.7332 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.3.0
- Datasets 3.1.0
- Tokenizers 0.20.3