Files
Llama-3.2-1B-MathCodeInstru…/assets/speed_results.json

92 lines
2.6 KiB
JSON
Raw Permalink Normal View History

{
"config": {
"prompt": "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May? Solve step by step.",
"tokens_per_run": 256,
"rounds": 3,
"interleaved": true,
"dtype": "bfloat16",
"greedy": true,
"device": "NVIDIA GeForce RTX 4060",
"torch": "2.11.0+cu128"
},
"models": {
"base": {
"model_path": "unsloth/Llama-3.2-1B",
"decode_tok_s": 40.59,
"decode_tok_s_min": 39.28,
"decode_tok_s_max": 40.62,
"end_to_end_tok_s": 40.56,
"prefill_ms": 29.3,
"prompt_tokens": 44,
"generated_tokens": 256,
"rounds": [
{
"prompt_tokens": 44,
"generated_tokens": 256,
"prefill_s": 0.0321,
"total_s": 6.5236,
"decode_tok_s": 39.28,
"end_to_end_tok_s": 39.24,
"gpu": "51C / 2775MHz"
},
{
"prompt_tokens": 44,
"generated_tokens": 256,
"prefill_s": 0.0293,
"total_s": 6.307,
"decode_tok_s": 40.62,
"end_to_end_tok_s": 40.59,
"gpu": "58C / 2775MHz"
},
{
"prompt_tokens": 44,
"generated_tokens": 256,
"prefill_s": 0.0293,
"total_s": 6.3119,
"decode_tok_s": 40.59,
"end_to_end_tok_s": 40.56,
"gpu": "51C / 2775MHz"
}
]
},
"5k": {
"model_path": "Llama-3.2-1B-MathCodeInstruct-5k/outputs/llama-3.2-1b-5k",
"decode_tok_s": 40.67,
"decode_tok_s_min": 40.47,
"decode_tok_s_max": 40.85,
"end_to_end_tok_s": 40.63,
"prefill_ms": 30.0,
"prompt_tokens": 44,
"generated_tokens": 256,
"rounds": [
{
"prompt_tokens": 44,
"generated_tokens": 256,
"prefill_s": 0.0302,
"total_s": 6.3309,
"decode_tok_s": 40.47,
"end_to_end_tok_s": 40.44,
"gpu": "53C / 2775MHz"
},
{
"prompt_tokens": 44,
"generated_tokens": 256,
"prefill_s": 0.0293,
"total_s": 6.2714,
"decode_tok_s": 40.85,
"end_to_end_tok_s": 40.82,
"gpu": "53C / 2775MHz"
},
{
"prompt_tokens": 44,
"generated_tokens": 256,
"prefill_s": 0.03,
"total_s": 6.3007,
"decode_tok_s": 40.67,
"end_to_end_tok_s": 40.63,
"gpu": "49C / 2775MHz"
}
]
}
}
}