no-prompt
a sheared-llama-1.3b fine-tuning
This model uses an 1.3 billion parameters model as base to be further fine-tuned on the same data as palmer. It works pretty good and even surpasses sota model on hellaswag.
evaluation
| Model | ARC_C | HellaSwag | PIQA | Winogrande |
|---|---|---|---|---|
| tinyllama-2t | 0.2807 | 0.5463 | 0.7067 | 0.5683 |
| palmer-001 | 0.2807 | 0.5524 | 0.7106 | 0.5896 |
| sheared-1.3b | 0.2910 | 0.5935 | 0.7339 | 0.5809 |
| no-prompt-1.3b | 0.3157 | 0.6022 | 0.7334 | 0.5864 |
| falcon-rw-1b-instruct-openorca (sota) | 0.3362 | 0.5997 | 0.7394 | 0.6148 |
This model was trained on less than 25% of the dataset yet achieves competitive performance to current sota on open llm leaderboard.
training
Training took ~5 P100 gpu hours. It was trained on 15,000 gpt-4 shuffled samples. no-prompt was fine-tuned using lower learning rates ensuring it keeps as much general knowledge as possible.
prompt
no prompt
limitations
Hallucinations are frequent, just as any transformer model this size.