Upload folder using huggingface_hub
#3
by
begumcig
- opened
- base_results.json +13 -13
- plots.png +0 -0
- smashed_results.json +12 -12
base_results.json
CHANGED
@@ -2,18 +2,18 @@
|
|
2 |
"current_gpu_type": "Tesla T4",
|
3 |
"current_gpu_total_memory": 15095.0625,
|
4 |
"perplexity": 3.4586403369903564,
|
5 |
-
"memory_inference_first":
|
6 |
"memory_inference": 808.0,
|
7 |
-
"token_generation_latency_sync": 36.
|
8 |
-
"token_generation_latency_async":
|
9 |
-
"token_generation_throughput_sync": 0.
|
10 |
-
"token_generation_throughput_async": 0.
|
11 |
-
"token_generation_CO2_emissions":
|
12 |
-
"token_generation_energy_consumption": 0.
|
13 |
-
"inference_latency_sync":
|
14 |
-
"inference_latency_async":
|
15 |
-
"inference_throughput_sync": 0.
|
16 |
-
"inference_throughput_async": 0.
|
17 |
-
"inference_CO2_emissions":
|
18 |
-
"inference_energy_consumption":
|
19 |
}
|
|
|
2 |
"current_gpu_type": "Tesla T4",
|
3 |
"current_gpu_total_memory": 15095.0625,
|
4 |
"perplexity": 3.4586403369903564,
|
5 |
+
"memory_inference_first": 810.0,
|
6 |
"memory_inference": 808.0,
|
7 |
+
"token_generation_latency_sync": 36.57732048034668,
|
8 |
+
"token_generation_latency_async": 36.563923954963684,
|
9 |
+
"token_generation_throughput_sync": 0.02733934544323193,
|
10 |
+
"token_generation_throughput_async": 0.02734936220827159,
|
11 |
+
"token_generation_CO2_emissions": 1.9446958828920205e-05,
|
12 |
+
"token_generation_energy_consumption": 0.001798393284076898,
|
13 |
+
"inference_latency_sync": 122.71987800598144,
|
14 |
+
"inference_latency_async": 47.88346290588379,
|
15 |
+
"inference_throughput_sync": 0.008148639130420741,
|
16 |
+
"inference_throughput_async": 0.020884036769970592,
|
17 |
+
"inference_CO2_emissions": 1.9399486097971613e-05,
|
18 |
+
"inference_energy_consumption": 6.64519560542376e-05
|
19 |
}
|
plots.png
CHANGED
smashed_results.json
CHANGED
@@ -4,16 +4,16 @@
|
|
4 |
"perplexity": 343688032.0,
|
5 |
"memory_inference_first": 344.0,
|
6 |
"memory_inference": 344.0,
|
7 |
-
"token_generation_latency_sync": 94.
|
8 |
-
"token_generation_latency_async":
|
9 |
-
"token_generation_throughput_sync": 0.
|
10 |
-
"token_generation_throughput_async": 0.
|
11 |
-
"token_generation_CO2_emissions": 2.
|
12 |
-
"token_generation_energy_consumption": 0.
|
13 |
-
"inference_latency_sync":
|
14 |
-
"inference_latency_async":
|
15 |
-
"inference_throughput_sync": 0.
|
16 |
-
"inference_throughput_async": 0.
|
17 |
-
"inference_CO2_emissions": 2.
|
18 |
-
"inference_energy_consumption": 7.
|
19 |
}
|
|
|
4 |
"perplexity": 343688032.0,
|
5 |
"memory_inference_first": 344.0,
|
6 |
"memory_inference": 344.0,
|
7 |
+
"token_generation_latency_sync": 94.19695053100585,
|
8 |
+
"token_generation_latency_async": 93.61793361604214,
|
9 |
+
"token_generation_throughput_sync": 0.010616054918580831,
|
10 |
+
"token_generation_throughput_async": 0.01068171408377083,
|
11 |
+
"token_generation_CO2_emissions": 2.0701273057098414e-05,
|
12 |
+
"token_generation_energy_consumption": 0.004600785530736977,
|
13 |
+
"inference_latency_sync": 146.6492561340332,
|
14 |
+
"inference_latency_async": 93.28432083129883,
|
15 |
+
"inference_throughput_sync": 0.006818991288206936,
|
16 |
+
"inference_throughput_async": 0.010719915105652773,
|
17 |
+
"inference_CO2_emissions": 2.082240367862723e-05,
|
18 |
+
"inference_energy_consumption": 7.15078451615474e-05
|
19 |
}
|