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": 3.4586403369903564,
|
| 5 |
+
"memory_inference_first": 808.0,
|
| 6 |
+
"memory_inference": 808.0,
|
| 7 |
+
"token_generation_latency_sync": 38.3092342376709,
|
| 8 |
+
"token_generation_latency_async": 38.34086339920759,
|
| 9 |
+
"token_generation_throughput_sync": 0.02610336697925073,
|
| 10 |
+
"token_generation_throughput_async": 0.02608183309770399,
|
| 11 |
+
"token_generation_CO2_emissions": 1.9478876919620074e-05,
|
| 12 |
+
"token_generation_energy_consumption": 0.0018778012307320703,
|
| 13 |
+
"inference_latency_sync": 122.27628936767579,
|
| 14 |
+
"inference_latency_async": 48.573970794677734,
|
| 15 |
+
"inference_throughput_sync": 0.008178200411308473,
|
| 16 |
+
"inference_throughput_async": 0.02058715776453611,
|
| 17 |
+
"inference_CO2_emissions": 1.9799463696101588e-05,
|
| 18 |
+
"inference_energy_consumption": 6.69570842513499e-05
|
| 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": 5.228277683258057,
|
| 5 |
+
"memory_inference_first": 252.0,
|
| 6 |
+
"memory_inference": 252.0,
|
| 7 |
+
"token_generation_latency_sync": 64.88516998291016,
|
| 8 |
+
"token_generation_latency_async": 64.88899011164904,
|
| 9 |
+
"token_generation_throughput_sync": 0.015411842186178845,
|
| 10 |
+
"token_generation_throughput_async": 0.015410934863978988,
|
| 11 |
+
"token_generation_CO2_emissions": 1.3202058888470628e-05,
|
| 12 |
+
"token_generation_energy_consumption": 0.003116907546278766,
|
| 13 |
+
"inference_latency_sync": 94.321435546875,
|
| 14 |
+
"inference_latency_async": 77.33259201049805,
|
| 15 |
+
"inference_throughput_sync": 0.01060204389598194,
|
| 16 |
+
"inference_throughput_async": 0.012931158441763443,
|
| 17 |
+
"inference_CO2_emissions": 1.3341487223188539e-05,
|
| 18 |
+
"inference_energy_consumption": 4.514158086780525e-05
|
| 19 |
+
}
|