all_abla_numina_oly_orca
This model is a fine-tuned version of /home/test/testdata/models/Meta-Llama-3.1-8B-Instruct on the codefeedback-o1, the magicoder-o1, the magicoder-oss-o1, the mathinstruct-MATH-o1, the mathinstruct-augmented-o1, the numina-cn-k12-o1, the numina-not-cn-k12-o1, the reasoning-001-o1 and the ultramedical_mc_o1 datasets. It achieves the following results on the evaluation set:
- Loss: 0.2059
- Accuracy: 0.9286
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: 4
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 32
- gradient_accumulation_steps: 2
- total_train_batch_size: 256
- 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: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2107 | 0.5574 | 500 | 0.2142 | 0.9208 |
| 0.1561 | 1.1148 | 1000 | 0.2085 | 0.9239 |
| 0.1547 | 1.6722 | 1500 | 0.1994 | 0.9265 |
| 0.1092 | 2.2297 | 2000 | 0.2073 | 0.9278 |
| 0.1073 | 2.7871 | 2500 | 0.2064 | 0.9284 |
Framework versions
- Transformers 4.43.4
- Pytorch 2.4.0
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 10