Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer to finish
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ║ Version: 0.9.9 ║
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: Downloaded to shared memory in 63.038s
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbf2cqle5, device:0
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: quantized model in 28.747s
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.10_ep3 in 91.784s
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-10-ep3-v1
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-10-ep3-v1/config.json
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-10-ep3-v1/special_tokens_map.json
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-10-ep3-v1/tokenizer_config.json
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-10-ep3-v1/tokenizer.json
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-10-ep3-v1/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:10, 26.46it/s]
Loading 0: 4%|▍ | 12/291 [00:00<00:07, 35.53it/s]
Loading 0: 5%|▌ | 16/291 [00:00<00:08, 33.56it/s]
Loading 0: 7%|▋ | 21/291 [00:00<00:07, 37.05it/s]
Loading 0: 9%|▊ | 25/291 [00:00<00:07, 34.96it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:06, 41.35it/s]
Loading 0: 12%|█▏ | 36/291 [00:01<00:10, 23.93it/s]
Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 26.02it/s]
Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 32.84it/s]
Loading 0: 18%|█▊ | 53/291 [00:01<00:07, 33.66it/s]
Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 34.42it/s]
Loading 0: 21%|██ | 61/291 [00:01<00:06, 33.05it/s]
Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 34.54it/s]
Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 33.59it/s]
Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 34.06it/s]
Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 34.49it/s]
Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 24.62it/s]
Loading 0: 30%|██▉ | 86/291 [00:02<00:07, 27.49it/s]
Loading 0: 31%|███ | 90/291 [00:02<00:06, 30.06it/s]
Loading 0: 32%|███▏ | 94/291 [00:02<00:06, 30.66it/s]
Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 33.79it/s]
Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 32.67it/s]
Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 35.87it/s]
Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 34.45it/s]
Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 34.69it/s]
Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 38.67it/s]
Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 36.30it/s]
Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 31.57it/s]
Loading 0: 47%|████▋ | 137/291 [00:04<00:04, 31.33it/s]
Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 29.50it/s]
Loading 0: 51%|█████ | 147/291 [00:04<00:04, 33.55it/s]
Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 32.88it/s]
Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 35.41it/s]
Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 34.22it/s]
Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 35.99it/s]
Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 34.50it/s]
Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 37.07it/s]
Loading 0: 61%|██████ | 178/291 [00:05<00:03, 35.47it/s]
Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 41.63it/s]
Loading 0: 65%|██████▍ | 189/291 [00:05<00:03, 25.55it/s]
Loading 0: 67%|██████▋ | 194/291 [00:06<00:03, 27.08it/s]
Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 33.89it/s]
Loading 0: 71%|███████ | 206/291 [00:06<00:02, 34.66it/s]
Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 34.16it/s]
Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 33.64it/s]
Loading 0: 75%|███████▌ | 219/291 [00:06<00:01, 36.63it/s]
Loading 0: 77%|███████▋ | 223/291 [00:06<00:01, 35.16it/s]
Loading 0: 78%|███████▊ | 227/291 [00:06<00:01, 35.36it/s]
Loading 0: 79%|███████▉ | 231/291 [00:06<00:01, 35.63it/s]
Loading 0: 81%|████████ | 235/291 [00:07<00:02, 27.38it/s]
Loading 0: 82%|████████▏ | 239/291 [00:07<00:01, 27.04it/s]
Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 34.53it/s]
Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 33.87it/s]
Loading 0: 88%|████████▊ | 255/291 [00:07<00:00, 36.71it/s]
Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 35.47it/s]
Loading 0: 91%|█████████ | 264/291 [00:07<00:00, 37.54it/s]
Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 35.55it/s]
Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 38.25it/s]
Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 36.47it/s]
Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 36.17it/s]
Loading 0: 98%|█████████▊| 286/291 [00:13<00:01, 2.59it/s]
Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.23it/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.
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-10-ep3-v1-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.
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-10-ep3-v1-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.
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: Saving duration: 1.383s
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.859s
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-10-ep3-v1_reward
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-10-ep3-v1_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-10-ep3-v1_reward/config.json
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-10-ep3-v1_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-10-ep3-v1_reward/merges.txt
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-10-ep3-v1_reward/vocab.json
bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-10-ep3-v1_reward/tokenizer.json
Job bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer completed after 136.41s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-10-ep3-v1-mkmlizer
Pipeline stage MKMLizer completed in 137.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-10-ep3-v1
Waiting for inference service bbchicago-brt-8b-l3-v1-10-ep3-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service bbchicago-brt-8b-l3-v1-10-ep3-v1 ready after 171.0798044204712s
Pipeline stage ISVCDeployer completed in 173.03s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3441827297210693s
Received healthy response to inference request in 1.3882362842559814s
Received healthy response to inference request in 1.4724180698394775s
Received healthy response to inference request in 1.4003491401672363s
Received healthy response to inference request in 1.3863489627838135s
5 requests
0 failed requests
5th percentile: 1.3867264270782471
10th percentile: 1.3871038913726808
20th percentile: 1.3878588199615478
30th percentile: 1.3906588554382324
40th percentile: 1.3955039978027344
50th percentile: 1.4003491401672363
60th percentile: 1.4291767120361327
70th percentile: 1.4580042839050293
80th percentile: 1.6467710018157962
90th percentile: 1.9954768657684328
95th percentile: 2.1698297977447507
99th percentile: 2.3093121433258057
mean time: 1.5983070373535155
Pipeline stage StressChecker completed in 8.74s
bbchicago-brt-8b-l3-v1-10-ep3_v1 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v1-10-ep3_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-brt-8b-l3-v1-10-ep3_v1
Running pipeline stage ISVCDeleter
Checking if service bbchicago-brt-8b-l3-v1-10-ep3-v1 is running
Tearing down inference service bbchicago-brt-8b-l3-v1-10-ep3-v1
Service bbchicago-brt-8b-l3-v1-10-ep3-v1 has been torndown
Pipeline stage ISVCDeleter completed in 10.14s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-10-ep3-v1/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-10-ep3-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-10-ep3-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-10-ep3-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-10-ep3-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-10-ep3-v1_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-10-ep3-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-10-ep3-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-10-ep3-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-10-ep3-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-10-ep3-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-10-ep3-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 7.42s
bbchicago-brt-8b-l3-v1-10-ep3_v1 status is now torndown due to DeploymentManager action