Running pipeline stage MKMLizer
Starting job with name trace2333-ultra-dol-fd-r-5999-v1-mkmlizer
Waiting for job on trace2333-ultra-dol-fd-r-5999-v1-mkmlizer to finish
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ║ _____ __ __ ║
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ║ /___/ ║
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ║ ║
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ║ Version: 0.10.1 ║
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ║ https://mk1.ai ║
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ║ ║
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ║ belonging to: ║
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ║ ║
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ║ Chai Research Corp. ║
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ║ ║
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: Downloaded to shared memory in 67.186s
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpq9njfngs, device:0
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: quantized model in 29.526s
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: Processed model Trace2333/ultra_dol_fd_r64a32_qkvo_epoch6_v9 in 96.712s
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-ultra-dol-fd-r-5999-v1
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-ultra-dol-fd-r-5999-v1/config.json
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-ultra-dol-fd-r-5999-v1/special_tokens_map.json
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-ultra-dol-fd-r-5999-v1/tokenizer_config.json
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-ultra-dol-fd-r-5999-v1/tokenizer.json
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-ultra-dol-fd-r-5999-v1/flywheel_model.0.safetensors
trace2333-ultra-dol-fd-r-5999-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:10, 26.16it/s]
Loading 0: 4%|▍ | 12/291 [00:00<00:07, 34.96it/s]
Loading 0: 5%|▌ | 16/291 [00:00<00:08, 31.81it/s]
Loading 0: 7%|▋ | 21/291 [00:00<00:07, 34.24it/s]
Loading 0: 9%|▊ | 25/291 [00:00<00:08, 32.58it/s]
Loading 0: 10%|█ | 30/291 [00:00<00:07, 36.82it/s]
Loading 0: 12%|█▏ | 34/291 [00:01<00:10, 23.65it/s]
Loading 0: 13%|█▎ | 37/291 [00:01<00:10, 23.54it/s]
Loading 0: 14%|█▍ | 41/291 [00:01<00:10, 23.43it/s]
Loading 0: 16%|█▌ | 46/291 [00:01<00:08, 27.76it/s]
Loading 0: 17%|█▋ | 50/291 [00:01<00:09, 25.94it/s]
Loading 0: 20%|█▉ | 57/291 [00:01<00:07, 33.04it/s]
Loading 0: 21%|██ | 61/291 [00:02<00:07, 32.31it/s]
Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 34.75it/s]
Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 33.36it/s]
Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 33.11it/s]
Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 33.30it/s]
Loading 0: 28%|██▊ | 82/291 [00:02<00:09, 23.08it/s]
Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 24.24it/s]
Loading 0: 31%|███ | 90/291 [00:03<00:07, 28.27it/s]
Loading 0: 32%|███▏ | 94/291 [00:03<00:07, 27.98it/s]
Loading 0: 34%|███▍ | 99/291 [00:03<00:06, 31.07it/s]
Loading 0: 35%|███▌ | 103/291 [00:03<00:06, 30.08it/s]
Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 33.18it/s]
Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 31.49it/s]
Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 31.97it/s]
Loading 0: 42%|████▏ | 122/291 [00:04<00:04, 36.23it/s]
Loading 0: 44%|████▎ | 127/291 [00:04<00:04, 33.43it/s]
Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 27.45it/s]
Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 28.28it/s]
Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 27.02it/s]
Loading 0: 51%|█████ | 147/291 [00:04<00:04, 31.97it/s]
Loading 0: 52%|█████▏ | 151/291 [00:05<00:04, 31.38it/s]
Loading 0: 54%|█████▎ | 156/291 [00:05<00:04, 33.17it/s]
Loading 0: 55%|█████▍ | 160/291 [00:05<00:04, 32.29it/s]
Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 34.78it/s]
Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 32.56it/s]
Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 35.15it/s]
Loading 0: 61%|██████ | 178/291 [00:05<00:03, 32.91it/s]
Loading 0: 63%|██████▎ | 183/291 [00:05<00:02, 36.77it/s]
Loading 0: 64%|██████▍ | 187/291 [00:06<00:04, 24.66it/s]
Loading 0: 66%|██████▌ | 191/291 [00:06<00:03, 26.22it/s]
Loading 0: 67%|██████▋ | 195/291 [00:06<00:03, 25.04it/s]
Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 30.00it/s]
Loading 0: 70%|███████ | 205/291 [00:06<00:02, 29.60it/s]
Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 31.83it/s]
Loading 0: 74%|███████▎ | 214/291 [00:07<00:02, 31.06it/s]
Loading 0: 75%|███████▌ | 219/291 [00:07<00:02, 33.90it/s]
Loading 0: 77%|███████▋ | 223/291 [00:07<00:02, 32.32it/s]
Loading 0: 78%|███████▊ | 227/291 [00:07<00:01, 32.07it/s]
Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 32.52it/s]
Loading 0: 81%|████████ | 235/291 [00:07<00:02, 23.88it/s]
Loading 0: 82%|████████▏ | 239/291 [00:08<00:02, 23.93it/s]
Loading 0: 85%|████████▍ | 246/291 [00:08<00:01, 31.56it/s]
Loading 0: 86%|████████▌ | 250/291 [00:08<00:01, 30.72it/s]
Loading 0: 88%|████████▊ | 255/291 [00:08<00:01, 33.05it/s]
Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 32.13it/s]
Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 34.81it/s]
Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 32.94it/s]
Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 34.76it/s]
Loading 0: 95%|█████████▌| 277/291 [00:09<00:00, 33.70it/s]
Loading 0: 97%|█████████▋| 281/291 [00:09<00:00, 34.04it/s]
Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.58it/s]
Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.22it/s]
Job trace2333-ultra-dol-fd-r-5999-v1-mkmlizer completed after 118.86s with status: succeeded
Stopping job with name trace2333-ultra-dol-fd-r-5999-v1-mkmlizer
Pipeline stage MKMLizer completed in 120.10s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.15s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-ultra-dol-fd-r-5999-v1
Waiting for inference service trace2333-ultra-dol-fd-r-5999-v1 to be ready
Failed to get response for submission blend_nibok_2024-08-16: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:35682->127.0.0.1:8080: read: connection reset by peer\n')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service trace2333-ultra-dol-fd-r-5999-v1 ready after 150.8860924243927s
Pipeline stage ISVCDeployer completed in 151.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1593573093414307s
Received healthy response to inference request in 1.6671006679534912s
Received healthy response to inference request in 1.79032301902771s
Received healthy response to inference request in 1.678476333618164s
Received healthy response to inference request in 1.5183689594268799s
5 requests
0 failed requests
5th percentile: 1.5481153011322022
10th percentile: 1.5778616428375245
20th percentile: 1.637354326248169
30th percentile: 1.6693758010864257
40th percentile: 1.6739260673522949
50th percentile: 1.678476333618164
60th percentile: 1.7232150077819823
70th percentile: 1.7679536819458008
80th percentile: 1.8641298770904542
90th percentile: 2.011743593215942
95th percentile: 2.0855504512786864
99th percentile: 2.144595937728882
mean time: 1.762725257873535
Pipeline stage StressChecker completed in 10.66s
trace2333-ultra-dol-fd-r_5999_v1 status is now deployed due to DeploymentManager action
trace2333-ultra-dol-fd-r_5999_v1 status is now inactive due to auto deactivation removed underperforming models
trace2333-ultra-dol-fd-r_5999_v1 status is now torndown due to DeploymentManager action