Sharathhebbar24/ssh_1.8B is a 1.8B model
The model is a modified version of qnguyen3/quan-1.8b-chat
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 4
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 45.91 |
| AI2 Reasoning Challenge (25-Shot) | 39.08 |
| HellaSwag (10-Shot) | 62.37 |
| MMLU (5-Shot) | 44.09 |
| TruthfulQA (0-shot) | 43.15 |
| Winogrande (5-shot) | 59.27 |
| GSM8k (5-shot) | 27.52 |
- Downloads last month
- 168
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard39.080
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard62.370
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard44.090
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard43.150
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard59.270
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard27.520