Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-elo-alignment-run-3-v55-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v55-mkmlizer to finish
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
chaiml-elo-alignment-run-3-v55-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v55-mkmlizer: ║ _____ __ __ ║
chaiml-elo-alignment-run-3-v55-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-elo-alignment-run-3-v55-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-elo-alignment-run-3-v55-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-elo-alignment-run-3-v55-mkmlizer: ║ /___/ ║
chaiml-elo-alignment-run-3-v55-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v55-mkmlizer: ║ Version: 0.11.12 ║
chaiml-elo-alignment-run-3-v55-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-elo-alignment-run-3-v55-mkmlizer: ║ https://mk1.ai ║
chaiml-elo-alignment-run-3-v55-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v55-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-elo-alignment-run-3-v55-mkmlizer: ║ belonging to: ║
chaiml-elo-alignment-run-3-v55-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v55-mkmlizer: ║ Chai Research Corp. ║
chaiml-elo-alignment-run-3-v55-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-elo-alignment-run-3-v55-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-elo-alignment-run-3-v55-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v55-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
chaiml-elo-alignment-run-3-v55-mkmlizer: Downloaded to shared memory in 44.724s
chaiml-elo-alignment-run-3-v55-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0qnpj708, device:0
chaiml-elo-alignment-run-3-v55-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v55-mkmlizer: quantized model in 30.324s
chaiml-elo-alignment-run-3-v55-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 75.048s
chaiml-elo-alignment-run-3-v55-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v55-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v55-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v55
chaiml-elo-alignment-run-3-v55-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v55/config.json
chaiml-elo-alignment-run-3-v55-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v55/special_tokens_map.json
chaiml-elo-alignment-run-3-v55-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v55/tokenizer_config.json
chaiml-elo-alignment-run-3-v55-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v55/tokenizer.json
chaiml-elo-alignment-run-3-v55-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v55/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v55-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:11, 25.09it/s]
Loading 0: 4%|▍ | 12/291 [00:00<00:08, 34.81it/s]
Loading 0: 5%|▌ | 16/291 [00:00<00:08, 31.80it/s]
Loading 0: 7%|▋ | 21/291 [00:00<00:07, 34.68it/s]
Loading 0: 9%|▊ | 25/291 [00:00<00:08, 31.40it/s]
Loading 0: 10%|▉ | 29/291 [00:00<00:07, 32.97it/s]
Loading 0: 11%|█▏ | 33/291 [00:01<00:10, 24.03it/s]
Loading 0: 12%|█▏ | 36/291 [00:01<00:11, 21.98it/s]
Loading 0: 14%|█▍ | 41/291 [00:01<00:10, 24.81it/s]
Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 32.56it/s]
Loading 0: 18%|█▊ | 52/291 [00:01<00:08, 27.75it/s]
Loading 0: 20%|█▉ | 57/291 [00:01<00:07, 30.19it/s]
Loading 0: 21%|██ | 61/291 [00:02<00:07, 29.61it/s]
Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 33.12it/s]
Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 32.61it/s]
Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 33.33it/s]
Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 32.68it/s]
Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 23.56it/s]
Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 24.28it/s]
Loading 0: 31%|███ | 90/291 [00:03<00:07, 27.80it/s]
Loading 0: 32%|███▏ | 94/291 [00:03<00:07, 28.13it/s]
Loading 0: 34%|███▍ | 99/291 [00:03<00:06, 31.72it/s]
Loading 0: 35%|███▌ | 103/291 [00:03<00:06, 30.15it/s]
Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 32.41it/s]
Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 31.45it/s]
Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 31.75it/s]
Loading 0: 42%|████▏ | 122/291 [00:04<00:04, 35.73it/s]
Loading 0: 44%|████▎ | 127/291 [00:04<00:05, 32.59it/s]
Loading 0: 45%|████▌ | 132/291 [00:04<00:04, 36.18it/s]
Loading 0: 47%|████▋ | 136/291 [00:04<00:06, 24.87it/s]
Loading 0: 48%|████▊ | 140/291 [00:04<00:06, 24.27it/s]
Loading 0: 51%|█████ | 147/291 [00:04<00:04, 30.70it/s]
Loading 0: 52%|█████▏ | 151/291 [00:05<00:04, 29.46it/s]
Loading 0: 54%|█████▎ | 156/291 [00:05<00:04, 32.10it/s]
Loading 0: 55%|█████▍ | 160/291 [00:05<00:04, 31.13it/s]
Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 33.04it/s]
Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 31.54it/s]
Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 33.07it/s]
Loading 0: 61%|██████ | 178/291 [00:05<00:03, 30.72it/s]
Loading 0: 63%|██████▎ | 183/291 [00:06<00:03, 34.29it/s]
Loading 0: 64%|██████▍ | 187/291 [00:06<00:04, 22.06it/s]
Loading 0: 65%|██████▌ | 190/291 [00:06<00:04, 21.59it/s]
Loading 0: 67%|██████▋ | 194/291 [00:06<00:04, 22.11it/s]
Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 30.16it/s]
Loading 0: 70%|███████ | 205/291 [00:06<00:02, 30.41it/s]
Loading 0: 72%|███████▏ | 210/291 [00:07<00:02, 34.00it/s]
Loading 0: 74%|███████▎ | 214/291 [00:07<00:02, 32.94it/s]
Loading 0: 75%|███████▌ | 219/291 [00:07<00:02, 34.71it/s]
Loading 0: 77%|███████▋ | 223/291 [00:07<00:02, 31.77it/s]
Loading 0: 78%|███████▊ | 227/291 [00:07<00:02, 31.90it/s]
Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 31.36it/s]
Loading 0: 81%|████████ | 235/291 [00:08<00:02, 23.97it/s]
Loading 0: 82%|████████▏ | 239/291 [00:08<00:02, 23.36it/s]
Loading 0: 85%|████████▍ | 246/291 [00:08<00:01, 30.28it/s]
Loading 0: 86%|████████▌ | 250/291 [00:08<00:01, 28.67it/s]
Loading 0: 88%|████████▊ | 255/291 [00:08<00:01, 31.32it/s]
Loading 0: 89%|████████▉ | 259/291 [00:08<00:01, 30.58it/s]
Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 33.70it/s]
Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 33.32it/s]
Loading 0: 94%|█████████▍| 273/291 [00:09<00:00, 36.30it/s]
Loading 0: 95%|█████████▌| 277/291 [00:09<00:00, 34.99it/s]
Loading 0: 97%|█████████▋| 281/291 [00:09<00:00, 35.43it/s]
Loading 0: 98%|█████████▊| 286/291 [00:15<00:01, 2.52it/s]
Loading 0: 99%|█████████▉| 289/291 [00:15<00:00, 3.12it/s]
Job chaiml-elo-alignment-run-3-v55-mkmlizer completed after 104.25s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v55-mkmlizer
Pipeline stage MKMLizer completed in 104.80s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-elo-alignment-run-3-v55
Waiting for inference service chaiml-elo-alignment-run-3-v55 to be ready
Failed to get response for submission sao10k-mn-12b-lyra-v4a1_v12: ('http://sao10k-mn-12b-lyra-v4a1-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:48040->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
Failed to get response for submission jic062-dpo-v3-0-nemo_v1: ('http://jic062-dpo-v3-0-nemo-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service chaiml-elo-alignment-run-3-v55 ready after 161.44318461418152s
Pipeline stage MKMLDeployer completed in 161.92s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.3899307250976562s
Received healthy response to inference request in 1.5001695156097412s
Received healthy response to inference request in 1.2706005573272705s
Received healthy response to inference request in 1.6244819164276123s
5 requests
1 failed requests
5th percentile: 1.3165143489837647
10th percentile: 1.3624281406402587
20th percentile: 1.454255723953247
30th percentile: 1.5250319957733154
40th percentile: 1.574756956100464
50th percentile: 1.6244819164276123
60th percentile: 1.9306614398956299
70th percentile: 2.2368409633636475
80th percentile: 5.937157106399539
90th percentile: 13.031609869003297
95th percentile: 16.578836250305173
99th percentile: 19.41661735534668
mean time: 5.382249069213867
%s, retrying in %s seconds...
Received healthy response to inference request in 1.4827630519866943s
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
Received healthy response to inference request in 1.4055554866790771s
Received healthy response to inference request in 1.385101556777954s
Received healthy response to inference request in 1.4117939472198486s
Received healthy response to inference request in 1.2631945610046387s
5 requests
0 failed requests
5th percentile: 1.2875759601593018
10th percentile: 1.3119573593139648
20th percentile: 1.360720157623291
30th percentile: 1.3891923427581787
40th percentile: 1.397373914718628
50th percentile: 1.4055554866790771
60th percentile: 1.4080508708953858
70th percentile: 1.4105462551116943
80th percentile: 1.4259877681732178
90th percentile: 1.454375410079956
95th percentile: 1.4685692310333252
99th percentile: 1.4799242877960206
mean time: 1.3896817207336425
Pipeline stage StressChecker completed in 36.63s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 2.63s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v55 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2443.10s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v55 status is now inactive due to auto deactivation removed underperforming models
chaiml-elo-alignment-run-3_v55 status is now torndown due to DeploymentManager action