Upload folder using huggingface_hub
#2
by
begumcig
- opened
- base_results.json +19 -0
- plots.png +0 -0
- smashed_results.json +19 -0
base_results.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"current_gpu_type": "Tesla T4",
|
| 3 |
+
"current_gpu_total_memory": 15095.0625,
|
| 4 |
+
"perplexity": 2.2062017917633057,
|
| 5 |
+
"memory_inference_first": 7278.0,
|
| 6 |
+
"memory_inference": 7278.0,
|
| 7 |
+
"token_generation_latency_sync": 35.36079788208008,
|
| 8 |
+
"token_generation_latency_async": 34.97263416647911,
|
| 9 |
+
"token_generation_throughput_sync": 0.0282799048634243,
|
| 10 |
+
"token_generation_throughput_async": 0.028593785507826836,
|
| 11 |
+
"token_generation_CO2_emissions": 0.00018337661498006707,
|
| 12 |
+
"token_generation_energy_consumption": 0.002160617961299883,
|
| 13 |
+
"inference_latency_sync": 1060.47254486084,
|
| 14 |
+
"inference_latency_async": 136.61155700683594,
|
| 15 |
+
"inference_throughput_sync": 0.000942975850573505,
|
| 16 |
+
"inference_throughput_async": 0.007320024907921669,
|
| 17 |
+
"inference_CO2_emissions": 0.0001840978910408864,
|
| 18 |
+
"inference_energy_consumption": 0.0006337665377060597
|
| 19 |
+
}
|
plots.png
ADDED
|
smashed_results.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"current_gpu_type": "Tesla T4",
|
| 3 |
+
"current_gpu_total_memory": 15095.0625,
|
| 4 |
+
"perplexity": 30815030.0,
|
| 5 |
+
"memory_inference_first": 1142.0,
|
| 6 |
+
"memory_inference": 1142.0,
|
| 7 |
+
"token_generation_latency_sync": 147.6204864501953,
|
| 8 |
+
"token_generation_latency_async": 147.56362289190292,
|
| 9 |
+
"token_generation_throughput_sync": 0.006774127521503482,
|
| 10 |
+
"token_generation_throughput_async": 0.006776737927697435,
|
| 11 |
+
"token_generation_CO2_emissions": 0.00020048614177282614,
|
| 12 |
+
"token_generation_energy_consumption": 0.008781923951582248,
|
| 13 |
+
"inference_latency_sync": 1151.6722137451172,
|
| 14 |
+
"inference_latency_async": 424.6630907058716,
|
| 15 |
+
"inference_throughput_sync": 0.0008683026194997837,
|
| 16 |
+
"inference_throughput_async": 0.00235480789803938,
|
| 17 |
+
"inference_CO2_emissions": 0.0002004475962713345,
|
| 18 |
+
"inference_energy_consumption": 0.0006890801651842688
|
| 19 |
+
}
|