-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathresults_o2.log
24 lines (24 loc) · 3.25 KB
/
results_o2.log
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
[2024-02-25 08:56:59,423] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Namespace(model='meta-llama/Llama-2-7b-hf', target='meta-llama/Llama-2-70b-hf', dataset='cnn', growmap='/home/zhuominc/workspace/Sequoia/growmaps/L40-CNN-7b-70b-stochastic-2.pt', start=0, end=50, T=0.6, P=1.0, DP=0.99, D=1, B=10, W=32, M=1024, Mode='greedy', decay=0.85, negative=False, static=False, offloading=True)
768
total time :4803.72373s, latency :0.72762s, decoding step: 6602, large model step: 715, 9.233566433566434
[2024-02-25 10:19:36,625] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Namespace(model='meta-llama/Llama-2-7b-hf', target='meta-llama/Llama-2-70b-hf', dataset='dataset/c4_small.json', growmap='/home/zhuominc/workspace/Sequoia/growmaps/L40-C4-7b-70b-stochastic-2.pt', start=0, end=50, T=0.6, P=1.0, DP=0.99, D=1, B=10, W=32, M=1024, Mode='greedy', decay=0.85, negative=False, static=False, offloading=True)
768
total time :3199.66734s, latency :0.67390s, decoding step: 4748, large model step: 468, 10.145299145299145
[2024-02-25 11:15:26,473] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Namespace(model='meta-llama/Llama-2-7b-hf', target='meta-llama/Llama-2-70b-hf', dataset='openwebtext', growmap='/home/zhuominc/workspace/Sequoia/growmaps/L40-OpenWebText-7b-70b-stochastic-2.pt', start=0, end=50, T=0.6, P=1.0, DP=0.99, D=1, B=10, W=32, M=1024, Mode='greedy', decay=0.85, negative=False, static=False, offloading=True)
768
total time :4624.66112s, latency :0.73187s, decoding step: 6319, large model step: 680, 9.29264705882353
[2024-02-25 12:34:59,400] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Namespace(model='meta-llama/Llama-2-7b-hf', target='meta-llama/Llama-2-70b-hf', dataset='cnn', growmap='/home/zhuominc/workspace/Sequoia/growmaps/L40-CNN-7b-70b-greedy-2.pt', start=0, end=50, T=0.6, P=1.0, DP=0.99, D=1, B=10, W=32, M=1024, Mode='greedy', decay=0.85, negative=False, static=False, offloading=True)
768
total time :4575.67006s, latency :0.68161s, decoding step: 6713, large model step: 682, 9.843108504398828
[2024-02-25 13:53:23,083] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Namespace(model='meta-llama/Llama-2-7b-hf', target='meta-llama/Llama-2-70b-hf', dataset='dataset/c4_small.json', growmap='/home/zhuominc/workspace/Sequoia/growmaps/L40-C4-7b-70b-greedy-2.pt', start=0, end=50, T=0.6, P=1.0, DP=0.99, D=1, B=10, W=32, M=1024, Mode='greedy', decay=0.85, negative=False, static=False, offloading=True)
768
total time :2793.48239s, latency :0.65791s, decoding step: 4246, large model step: 409, 10.381418092909536
[2024-02-25 14:42:02,490] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Namespace(model='meta-llama/Llama-2-7b-hf', target='meta-llama/Llama-2-70b-hf', dataset='openwebtext', growmap='/home/zhuominc/workspace/Sequoia/growmaps/L40-OpenWebText-7b-70b-greedy-2.pt', start=0, end=50, T=0.6, P=1.0, DP=0.99, D=1, B=10, W=32, M=1024, Mode='greedy', decay=0.85, negative=False, static=False, offloading=True)
768
total time :4584.21264s, latency :0.69679s, decoding step: 6579, large model step: 680, 9.675