prm_version3_subsample_no_ref_hf
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the prm_conversations_prm_version3_math+webinstructsub-mcq+webinstructsub-oe+apps+gsm_subsample_hf dataset. It achieves the following results on the evaluation set:
- Loss: 0.1702
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: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- 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: 0.05
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2103 | 0.2253 | 500 | 0.2052 |
| 0.1811 | 0.4506 | 1000 | 0.1891 |
| 0.1809 | 0.6759 | 1500 | 0.1767 |
| 0.1841 | 0.9012 | 2000 | 0.1706 |
Framework versions
- Transformers 4.45.0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 12
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.
Model tree for DongfuJiang/prm_version3_subsample_no_ref_hf
Base model
meta-llama/Llama-3.1-8B
Finetuned
meta-llama/Llama-3.1-8B-Instruct