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": 7264.0,
|
6 |
+
"memory_inference": 7264.0,
|
7 |
+
"token_generation_latency_sync": 37.2805679321289,
|
8 |
+
"token_generation_latency_async": 36.650632694363594,
|
9 |
+
"token_generation_throughput_sync": 0.026823625697455812,
|
10 |
+
"token_generation_throughput_async": 0.027284658585274228,
|
11 |
+
"token_generation_CO2_emissions": 0.00017765237369534836,
|
12 |
+
"token_generation_energy_consumption": 0.0022326934668068926,
|
13 |
+
"inference_latency_sync": 1031.3929580688477,
|
14 |
+
"inference_latency_async": 131.7535161972046,
|
15 |
+
"inference_throughput_sync": 0.0009695625631111279,
|
16 |
+
"inference_throughput_async": 0.007589930264200547,
|
17 |
+
"inference_CO2_emissions": 0.00017810886568024814,
|
18 |
+
"inference_energy_consumption": 0.0006130412240773345
|
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": 2.2114033699035645,
|
5 |
+
"memory_inference_first": 2374.0,
|
6 |
+
"memory_inference": 2374.0,
|
7 |
+
"token_generation_latency_sync": 132.85096130371093,
|
8 |
+
"token_generation_latency_async": 132.14306216686964,
|
9 |
+
"token_generation_throughput_sync": 0.007527231946134716,
|
10 |
+
"token_generation_throughput_async": 0.0075675558262544625,
|
11 |
+
"token_generation_CO2_emissions": 5.169492869719809e-05,
|
12 |
+
"token_generation_energy_consumption": 0.00777338393432973,
|
13 |
+
"inference_latency_sync": 328.58505859375,
|
14 |
+
"inference_latency_async": 122.15607166290283,
|
15 |
+
"inference_throughput_sync": 0.0030433520144820757,
|
16 |
+
"inference_throughput_async": 0.008186248840414264,
|
17 |
+
"inference_CO2_emissions": 5.219246064070858e-05,
|
18 |
+
"inference_energy_consumption": 0.00017807384324212128
|
19 |
+
}
|