GTX 970 GPU Failure after overclocking

I read over and over how people were able to get 20+ MH/s on these cards. Anyways, I have been getting 17 on the edge of 18 so I went to see if I could overclock a bit more. The temps were extremely low compared to my Radeon cards, at 59 degrees. So I gave it a bit more and then it went from 18 to zero.
I now cannot get the miner to run at all.

C:\xxxxxxxxxxxxx\ethminer-cuda-0.9.41>ethminer -F http://ethereumpool.co/?min
er=xxxxxxxxxxxxxxxxxx  -G -t 2 --opencl-platform 1
Found suitable OpenCL device [GeForce GTX 970] with 4294967296 bytes of GPU memo
ry
miner  17:19:37|main  Getting work package...
miner  17:19:38|main  Grabbing DAG for #7c4fb8a5…
miner  17:19:40|main  Got work package:
  i  17:19:40|<unknown>  Loading full DAG of seedhash: #3868abc5…
miner  17:19:40|main    Header-hash: 4b3faf0f2e17fbabf2fbfd3096ddc60bdfc533e815c
e840d606e4b2209f5d70e
miner  17:19:40|main    Seedhash: 7c4fb8a5d141973b69b521ce76b0dc50f0d2834d817c7f
8310a6ab5becc6bb0c
miner  17:19:40|main    Target: 0000000112e0be826d694b2e62d01511f12a6061fbaec8bc
02357593e70e52ba
  i  17:19:40|gpuminer0  workLoop 0 #00000000… #7c4fb8a5…
  i  17:19:40|gpuminer0  Initialising miner...
miner  17:19:41|main  Mining on PoWhash #4b3faf0f… : 0 H/s = 0 hashes / 0.5 s
Using platform: NVIDIA CUDA
Using device: GeForce GTX 970(OpenCL 1.2 CUDA)
Using Inline PTX
Printing program log


Creating one big buffer for the DAG
Loading single big chunk kernels
Mapping one big chunk.
miner  17:19:43|main  Mining on PoWhash #4b3faf0f… : 0 H/s = 0 hashes / 2.493
s
miner  17:19:44|main  Mining on PoWhash #4b3faf0f… : 0 H/s = 0 hashes / 0.911
s

I ran a aquamark 3 and got 64k as a score. It seemed to be running okay. Does anyone have thoughts? I have tried about 2 hours of troubleshooting with different miners in hopes that I could fix it. So far no luck.