Running pipeline stage MKMLizer
Starting job with name zonemercy-cogent-nemo-v1-3266-v2-mkmlizer
Waiting for job on zonemercy-cogent-nemo-v1-3266-v2-mkmlizer to finish
Stopping job with name zonemercy-cogent-nemo-v1-3266-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name zonemercy-cogent-nemo-v1-3266-v2-mkmlizer
Waiting for job on zonemercy-cogent-nemo-v1-3266-v2-mkmlizer to finish
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ║ _____ __ __ ║
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ║ /___/ ║
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ║ ║
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ║ Version: 0.9.9 ║
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ║ https://mk1.ai ║
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ║ ║
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ║ The license key for the current software has been verified as ║
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ║ belonging to: ║
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ║ ║
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ║ Chai Research Corp. ║
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ║ ║
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: Downloaded to shared memory in 68.309s
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmgk9qtjn, device:0
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: quantized model in 42.196s
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: Processed model zonemercy/Cogent-Nemo-v1-1k1e5 in 110.505s
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-3266-v2
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-3266-v2/special_tokens_map.json
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-3266-v2/config.json
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-3266-v2/tokenizer_config.json
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-3266-v2/tokenizer.json
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-cogent-nemo-v1-3266-v2/flywheel_model.0.safetensors
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%|▏ | 5/363 [00:00<00:14, 24.06it/s]
Loading 0: 3%|▎ | 10/363 [00:00<00:12, 29.38it/s]
Loading 0: 4%|▍ | 14/363 [00:00<00:13, 25.29it/s]
Loading 0: 6%|▌ | 20/363 [00:00<00:10, 33.99it/s]
Loading 0: 7%|▋ | 24/363 [00:00<00:15, 22.51it/s]
Loading 0: 7%|▋ | 27/363 [00:01<00:15, 21.81it/s]
Loading 0: 9%|▊ | 31/363 [00:01<00:13, 25.45it/s]
Loading 0: 10%|▉ | 35/363 [00:01<00:12, 27.11it/s]
Loading 0: 11%|█ | 39/363 [00:01<00:11, 28.49it/s]
Loading 0: 12%|█▏ | 43/363 [00:01<00:11, 27.49it/s]
Loading 0: 13%|█▎ | 48/363 [00:01<00:10, 29.45it/s]
Loading 0: 14%|█▍ | 52/363 [00:01<00:10, 28.36it/s]
Loading 0: 15%|█▌ | 56/363 [00:02<00:10, 28.33it/s]
Loading 0: 17%|█▋ | 61/363 [00:02<00:12, 23.66it/s]
Loading 0: 18%|█▊ | 64/363 [00:02<00:14, 20.08it/s]
Loading 0: 19%|█▉ | 69/363 [00:02<00:11, 24.93it/s]
Loading 0: 20%|█▉ | 72/363 [00:02<00:12, 23.14it/s]
Loading 0: 21%|██ | 77/363 [00:03<00:11, 23.89it/s]
Loading 0: 23%|██▎ | 84/363 [00:03<00:09, 30.03it/s]
Loading 0: 24%|██▍ | 88/363 [00:03<00:09, 28.92it/s]
Loading 0: 26%|██▌ | 93/363 [00:03<00:08, 30.09it/s]
Loading 0: 27%|██▋ | 97/363 [00:03<00:09, 28.40it/s]
Loading 0: 28%|██▊ | 101/363 [00:03<00:11, 22.03it/s]
Loading 0: 29%|██▊ | 104/363 [00:04<00:12, 20.10it/s]
Loading 0: 30%|███ | 109/363 [00:04<00:10, 25.31it/s]
Loading 0: 31%|███ | 113/363 [00:04<00:10, 23.76it/s]
Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 30.25it/s]
Loading 0: 34%|███▍ | 124/363 [00:04<00:08, 29.04it/s]
Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 30.48it/s]
Loading 0: 37%|███▋ | 133/363 [00:05<00:07, 29.01it/s]
Loading 0: 38%|███▊ | 137/363 [00:05<00:07, 29.08it/s]
Loading 0: 39%|███▉ | 142/363 [00:05<00:09, 24.55it/s]
Loading 0: 40%|███▉ | 145/363 [00:05<00:09, 23.22it/s]
Loading 0: 41%|████ | 149/363 [00:05<00:09, 22.32it/s]
Loading 0: 43%|████▎ | 156/363 [00:05<00:07, 28.94it/s]
Loading 0: 44%|████▍ | 160/363 [00:06<00:07, 27.92it/s]
Loading 0: 45%|████▌ | 165/363 [00:06<00:06, 30.17it/s]
Loading 0: 47%|████▋ | 169/363 [00:06<00:06, 29.00it/s]
Loading 0: 48%|████▊ | 174/363 [00:06<00:06, 30.92it/s]
Loading 0: 49%|████▉ | 178/363 [00:06<00:06, 29.40it/s]
Loading 0: 50%|█████ | 182/363 [00:06<00:07, 23.66it/s]
Loading 0: 51%|█████ | 185/363 [00:07<00:08, 21.40it/s]
Loading 0: 52%|█████▏ | 190/363 [00:07<00:06, 26.62it/s]
Loading 0: 53%|█████▎ | 194/363 [00:07<00:06, 24.66it/s]
Loading 0: 55%|█████▌ | 201/363 [00:07<00:05, 31.38it/s]
Loading 0: 56%|█████▋ | 205/363 [00:07<00:05, 29.84it/s]
Loading 0: 58%|█████▊ | 210/363 [00:07<00:04, 31.32it/s]
Loading 0: 59%|█████▉ | 214/363 [00:07<00:04, 29.87it/s]
Loading 0: 60%|██████ | 218/363 [00:08<00:04, 29.23it/s]
Loading 0: 61%|██████▏ | 223/363 [00:08<00:05, 24.17it/s]
Loading 0: 62%|██████▏ | 226/363 [00:08<00:05, 23.25it/s]
Loading 0: 63%|██████▎ | 230/363 [00:08<00:05, 22.47it/s]
Loading 0: 65%|██████▌ | 237/363 [00:08<00:04, 29.24it/s]
Loading 0: 66%|██████▋ | 241/363 [00:09<00:04, 28.64it/s]
Loading 0: 68%|██████▊ | 246/363 [00:09<00:03, 30.63it/s]
Loading 0: 69%|██████▉ | 250/363 [00:09<00:03, 29.47it/s]
Loading 0: 70%|███████ | 255/363 [00:09<00:03, 31.14it/s]
Loading 0: 71%|███████▏ | 259/363 [00:09<00:03, 29.57it/s]
Loading 0: 72%|███████▏ | 263/363 [00:09<00:04, 23.61it/s]
Loading 0: 73%|███████▎ | 266/363 [00:10<00:04, 21.16it/s]
Loading 0: 75%|███████▌ | 273/363 [00:10<00:03, 27.83it/s]
Loading 0: 76%|███████▋ | 277/363 [00:10<00:03, 26.80it/s]
Loading 0: 78%|███████▊ | 282/363 [00:10<00:02, 28.61it/s]
Loading 0: 79%|███████▊ | 285/363 [00:10<00:02, 26.24it/s]
Loading 0: 80%|████████ | 291/363 [00:10<00:02, 30.23it/s]
Loading 0: 81%|████████▏ | 295/363 [00:11<00:02, 28.64it/s]
Loading 0: 82%|████████▏ | 299/363 [00:11<00:02, 28.72it/s]
Loading 0: 84%|████████▎ | 304/363 [00:11<00:02, 24.23it/s]
Loading 0: 85%|████████▍ | 307/363 [00:11<00:02, 22.80it/s]
Loading 0: 86%|████████▌ | 311/363 [00:11<00:02, 22.02it/s]
Loading 0: 87%|████████▋ | 316/363 [00:11<00:01, 27.24it/s]
Loading 0: 88%|████████▊ | 320/363 [00:12<00:01, 24.75it/s]
Loading 0: 90%|█████████ | 327/363 [00:12<00:01, 30.79it/s]
Loading 0: 91%|█████████ | 331/363 [00:12<00:01, 29.15it/s]
Loading 0: 93%|█████████▎| 336/363 [00:12<00:00, 31.12it/s]
Loading 0: 94%|█████████▎| 340/363 [00:12<00:00, 29.45it/s]
Loading 0: 95%|█████████▍| 344/363 [00:19<00:09, 1.99it/s]
Loading 0: 96%|█████████▌| 348/363 [00:19<00:05, 2.67it/s]
Loading 0: 97%|█████████▋| 353/363 [00:20<00:02, 3.86it/s]
Loading 0: 98%|█████████▊| 357/363 [00:20<00:01, 5.00it/s]
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: warnings.warn(
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: warnings.warn(
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: warnings.warn(
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer:
Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]
Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.09s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.15s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.45s/it]
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer:
Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.29it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.85it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.49it/s]
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: Saving duration: 1.325s
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.983s
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: creating bucket guanaco-reward-models
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-3266-v2_reward
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-3266-v2_reward/config.json
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-3266-v2_reward/special_tokens_map.json
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-3266-v2_reward/tokenizer_config.json
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-3266-v2_reward/merges.txt
zonemercy-cogent-nemo-v1-3266-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/zonemercy-cogent-nemo-v1-3266-v2_reward/reward.tensors
Job zonemercy-cogent-nemo-v1-3266-v2-mkmlizer completed after 156.26s with status: succeeded
Stopping job with name zonemercy-cogent-nemo-v1-3266-v2-mkmlizer
Pipeline stage MKMLizer completed in 157.63s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service zonemercy-cogent-nemo-v1-3266-v2
Waiting for inference service zonemercy-cogent-nemo-v1-3266-v2 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service zonemercy-cogent-nemo-v1-3266-v2 ready after 191.1943747997284s
Pipeline stage ISVCDeployer completed in 192.58s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.586310386657715s
Received healthy response to inference request in 1.6348564624786377s
Received healthy response to inference request in 1.633488416671753s
Received healthy response to inference request in 1.6845571994781494s
Received healthy response to inference request in 1.704146385192871s
5 requests
0 failed requests
5th percentile: 1.6337620258331298
10th percentile: 1.6340356349945069
20th percentile: 1.6345828533172608
30th percentile: 1.64479660987854
40th percentile: 1.6646769046783447
50th percentile: 1.6845571994781494
60th percentile: 1.6923928737640381
70th percentile: 1.7002285480499268
80th percentile: 1.88057918548584
90th percentile: 2.2334447860717774
95th percentile: 2.409877586364746
99th percentile: 2.551023826599121
mean time: 1.8486717700958253
Pipeline stage StressChecker completed in 9.91s
zonemercy-cogent-nemo-v1_3266_v2 status is now deployed due to DeploymentManager action
zonemercy-cogent-nemo-v1_3266_v2 status is now inactive due to auto deactivation removed underperforming models
zonemercy-cogent-nemo-v1_3266_v2 status is now torndown due to DeploymentManager action