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": 37.12965393066406,
|
| 8 |
+
"token_generation_latency_async": 37.13082652539015,
|
| 9 |
+
"token_generation_throughput_sync": 0.0269326507019807,
|
| 10 |
+
"token_generation_throughput_async": 0.02693180016653272,
|
| 11 |
+
"token_generation_CO2_emissions": 1.8527108646322842e-05,
|
| 12 |
+
"token_generation_energy_consumption": 0.001813133805152576,
|
| 13 |
+
"inference_latency_sync": 118.66042785644531,
|
| 14 |
+
"inference_latency_async": 46.790528297424316,
|
| 15 |
+
"inference_throughput_sync": 0.008427409356805911,
|
| 16 |
+
"inference_throughput_async": 0.021371846747347947,
|
| 17 |
+
"inference_CO2_emissions": 1.8868051579151425e-05,
|
| 18 |
+
"inference_energy_consumption": 6.49589917025334e-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": 108340.9609375,
|
| 5 |
+
"memory_inference_first": 262.0,
|
| 6 |
+
"memory_inference": 262.0,
|
| 7 |
+
"token_generation_latency_sync": 110.18281021118165,
|
| 8 |
+
"token_generation_latency_async": 110.60973107814789,
|
| 9 |
+
"token_generation_throughput_sync": 0.009075825875954263,
|
| 10 |
+
"token_generation_throughput_async": 0.009040795870785373,
|
| 11 |
+
"token_generation_CO2_emissions": 1.4485038513711413e-05,
|
| 12 |
+
"token_generation_energy_consumption": 0.005279731847863916,
|
| 13 |
+
"inference_latency_sync": 107.71225280761719,
|
| 14 |
+
"inference_latency_async": 99.97386932373047,
|
| 15 |
+
"inference_throughput_sync": 0.009283994846770878,
|
| 16 |
+
"inference_throughput_async": 0.010002613750617666,
|
| 17 |
+
"inference_CO2_emissions": 1.4262623257981447e-05,
|
| 18 |
+
"inference_energy_consumption": 4.912709554389577e-05
|
| 19 |
+
}
|