Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer to finish
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ║ Version: 0.9.6 ║
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: Downloaded to shared memory in 58.543s
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfbybhe_g, device:0
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:10, 27.85it/s]
Loading 0: 4%|▍ | 12/291 [00:00<00:07, 36.99it/s]
Loading 0: 5%|▌ | 16/291 [00:00<00:07, 35.18it/s]
Loading 0: 7%|▋ | 21/291 [00:00<00:07, 38.51it/s]
Loading 0: 9%|▊ | 25/291 [00:00<00:07, 35.58it/s]
Loading 0: 10%|█ | 30/291 [00:00<00:06, 39.33it/s]
Loading 0: 12%|█▏ | 35/291 [00:01<00:09, 26.49it/s]
Loading 0: 13%|█▎ | 39/291 [00:01<00:09, 27.86it/s]
Loading 0: 15%|█▍ | 43/291 [00:01<00:08, 28.99it/s]
Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 32.88it/s]
Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 32.76it/s]
Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 36.17it/s]
Loading 0: 21%|██ | 61/291 [00:01<00:06, 35.36it/s]
Loading 0: 23%|██▎ | 66/291 [00:01<00:06, 37.43it/s]
Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 35.81it/s]
Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 36.11it/s]
Loading 0: 27%|██▋ | 78/291 [00:02<00:05, 36.57it/s]
Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 25.43it/s]
Loading 0: 30%|██▉ | 86/291 [00:02<00:07, 28.39it/s]
Loading 0: 31%|███▏ | 91/291 [00:02<00:06, 31.17it/s]
Loading 0: 33%|███▎ | 95/291 [00:02<00:05, 33.21it/s]
Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 34.12it/s]
Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 33.93it/s]
Loading 0: 37%|███▋ | 108/291 [00:03<00:04, 37.44it/s]
Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 35.72it/s]
Loading 0: 40%|███▉ | 116/291 [00:03<00:04, 36.28it/s]
Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 41.27it/s]
Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 38.90it/s]
Loading 0: 46%|████▌ | 133/291 [00:03<00:04, 33.24it/s]
Loading 0: 47%|████▋ | 137/291 [00:04<00:04, 33.37it/s]
Loading 0: 48%|████▊ | 141/291 [00:04<00:04, 31.07it/s]
Loading 0: 51%|█████ | 147/291 [00:04<00:03, 36.32it/s]
Loading 0: 52%|█████▏ | 151/291 [00:04<00:03, 35.57it/s]
Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 37.96it/s]
Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 36.04it/s]
Loading 0: 57%|█████▋ | 165/291 [00:04<00:03, 38.99it/s]
Loading 0: 58%|█████▊ | 169/291 [00:04<00:03, 36.42it/s]
Loading 0: 60%|█████▉ | 174/291 [00:05<00:02, 39.15it/s]
Loading 0: 61%|██████ | 178/291 [00:05<00:03, 37.00it/s]
Loading 0: 64%|██████▎ | 185/291 [00:05<00:02, 40.28it/s]
Loading 0: 65%|██████▌ | 190/291 [00:05<00:03, 28.23it/s]
Loading 0: 67%|██████▋ | 194/291 [00:05<00:03, 27.55it/s]
Loading 0: 69%|██████▉ | 201/291 [00:05<00:02, 34.75it/s]
Loading 0: 70%|███████ | 205/291 [00:06<00:02, 34.32it/s]
Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 36.32it/s]
Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 35.39it/s]
Loading 0: 75%|███████▌ | 219/291 [00:06<00:01, 37.92it/s]
Loading 0: 77%|███████▋ | 223/291 [00:06<00:01, 36.58it/s]
Loading 0: 78%|███████▊ | 227/291 [00:06<00:01, 36.54it/s]
Loading 0: 79%|███████▉ | 231/291 [00:06<00:01, 36.80it/s]
Loading 0: 81%|████████ | 235/291 [00:06<00:02, 27.26it/s]
Loading 0: 82%|████████▏ | 239/291 [00:07<00:01, 27.07it/s]
Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 35.38it/s]
Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 34.97it/s]
Loading 0: 88%|████████▊ | 255/291 [00:07<00:00, 36.79it/s]
Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 35.61it/s]
Loading 0: 91%|█████████ | 264/291 [00:07<00:00, 38.59it/s]
Loading 0: 92%|█████████▏| 268/291 [00:07<00:00, 37.32it/s]
Loading 0: 94%|█████████▍| 273/291 [00:07<00:00, 39.35it/s]
Loading 0: 96%|█████████▌| 278/291 [00:08<00:00, 39.29it/s]
Loading 0: 97%|█████████▋| 282/291 [00:08<00:00, 39.35it/s]
Loading 0: 98%|█████████▊| 286/291 [00:13<00:02, 2.50it/s]
Loading 0: 99%|█████████▉| 289/291 [00:13<00:00, 3.13it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: quantized model in 28.166s
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.8_DPO_ep2 in 86.710s
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-8-8811-v1
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-8-8811-v1/config.json
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-8-8811-v1/special_tokens_map.json
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-8-8811-v1/tokenizer_config.json
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-8-8811-v1/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-8-8811-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-v1-8-8811-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: Saving duration: 1.363s
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.209s
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-8-8811-v1_reward
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-8-8811-v1_reward/config.json
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-8-8811-v1_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-8-8811-v1_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-8-8811-v1_reward/merges.txt
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-8-8811-v1_reward/vocab.json
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-8-8811-v1_reward/tokenizer.json
bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-8-8811-v1_reward/reward.tensors
Job bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer completed after 177.94s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-8-8811-v1-mkmlizer
Pipeline stage MKMLizer completed in 178.89s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-8-8811-v1
Waiting for inference service bbchicago-brt-8b-l3-v1-8-8811-v1 to be ready
Inference service bbchicago-brt-8b-l3-v1-8-8811-v1 ready after 50.57033348083496s
Pipeline stage ISVCDeployer completed in 52.19s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1683075428009033s
Received healthy response to inference request in 1.3788411617279053s
Received healthy response to inference request in 1.399573564529419s
Received healthy response to inference request in 1.3843989372253418s
Received healthy response to inference request in 1.3610491752624512s
5 requests
0 failed requests
5th percentile: 1.364607572555542
10th percentile: 1.3681659698486328
20th percentile: 1.3752827644348145
30th percentile: 1.3799527168273926
40th percentile: 1.382175827026367
50th percentile: 1.3843989372253418
60th percentile: 1.3904687881469726
70th percentile: 1.3965386390686034
80th percentile: 1.553320360183716
90th percentile: 1.8608139514923097
95th percentile: 2.0145607471466063
99th percentile: 2.137558183670044
mean time: 1.5384340763092041
Pipeline stage StressChecker completed in 8.67s
bbchicago-brt-8b-l3-v1-8_8811_v1 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v1-8_8811_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-brt-8b-l3-v1-8_8811_v1
Running pipeline stage ISVCDeleter
Checking if service bbchicago-brt-8b-l3-v1-8-8811-v1 is running
Tearing down inference service bbchicago-brt-8b-l3-v1-8-8811-v1
Service bbchicago-brt-8b-l3-v1-8-8811-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.76s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-8-8811-v1/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-8-8811-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-8-8811-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-8-8811-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-8-8811-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-8-8811-v1_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-8-8811-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-8-8811-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-8-8811-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-8-8811-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-8-8811-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-8-8811-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.81s
bbchicago-brt-8b-l3-v1-8_8811_v1 status is now torndown due to DeploymentManager action