Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer to finish
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ║ Version: 0.9.6 ║
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: Downloaded to shared memory in 54.744s
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpud629dn7, device:0
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:10, 27.65it/s]
Loading 0: 4%|▍ | 12/291 [00:00<00:07, 37.27it/s]
Loading 0: 5%|▌ | 16/291 [00:00<00:08, 34.15it/s]
Loading 0: 7%|▋ | 21/291 [00:00<00:07, 37.57it/s]
Loading 0: 9%|▊ | 25/291 [00:00<00:07, 35.29it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:06, 41.73it/s]
Loading 0: 12%|█▏ | 36/291 [00:01<00:10, 24.33it/s]
Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 26.26it/s]
Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 33.23it/s]
Loading 0: 18%|█▊ | 53/291 [00:01<00:06, 34.31it/s]
Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 35.46it/s]
Loading 0: 21%|██ | 61/291 [00:01<00:06, 34.47it/s]
Loading 0: 23%|██▎ | 66/291 [00:01<00:06, 37.16it/s]
Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 35.49it/s]
Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 35.33it/s]
Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 35.23it/s]
Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 23.55it/s]
Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 24.72it/s]
Loading 0: 31%|███ | 90/291 [00:02<00:06, 29.38it/s]
Loading 0: 32%|███▏ | 94/291 [00:02<00:06, 30.01it/s]
Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 33.80it/s]
Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 32.64it/s]
Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 35.78it/s]
Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 34.51it/s]
Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 34.63it/s]
Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 38.29it/s]
Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 35.54it/s]
Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 29.47it/s]
Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 30.07it/s]
Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 28.90it/s]
Loading 0: 51%|█████ | 147/291 [00:04<00:04, 33.77it/s]
Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 32.48it/s]
Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 35.36it/s]
Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 34.37it/s]
Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 36.76it/s]
Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 35.52it/s]
Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 37.47it/s]
Loading 0: 61%|██████ | 178/291 [00:05<00:03, 36.21it/s]
Loading 0: 63%|██████▎ | 183/291 [00:05<00:02, 39.68it/s]
Loading 0: 65%|██████▍ | 188/291 [00:05<00:03, 27.32it/s]
Loading 0: 66%|██████▌ | 192/291 [00:05<00:03, 28.24it/s]
Loading 0: 67%|██████▋ | 196/291 [00:06<00:03, 28.83it/s]
Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 32.74it/s]
Loading 0: 70%|███████ | 205/291 [00:06<00:02, 32.28it/s]
Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 35.19it/s]
Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 34.14it/s]
Loading 0: 75%|███████▌ | 219/291 [00:06<00:01, 37.16it/s]
Loading 0: 77%|███████▋ | 223/291 [00:06<00:01, 35.72it/s]
Loading 0: 78%|███████▊ | 227/291 [00:06<00:01, 35.52it/s]
Loading 0: 79%|███████▉ | 231/291 [00:06<00:01, 35.76it/s]
Loading 0: 81%|████████ | 235/291 [00:07<00:02, 26.40it/s]
Loading 0: 82%|████████▏ | 239/291 [00:07<00:01, 26.40it/s]
Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 34.65it/s]
Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 34.09it/s]
Loading 0: 88%|████████▊ | 255/291 [00:07<00:00, 37.00it/s]
Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 35.78it/s]
Loading 0: 91%|█████████ | 264/291 [00:07<00:00, 38.57it/s]
Loading 0: 92%|█████████▏| 269/291 [00:08<00:00, 38.01it/s]
Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 37.98it/s]
Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 35.97it/s]
Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 36.01it/s]
Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.55it/s]
Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.19it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: quantized model in 28.680s
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.9_with_dpo_lora_s5300 in 83.424s
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-9-6162-v1
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-9-6162-v1/config.json
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-9-6162-v1/special_tokens_map.json
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-9-6162-v1/tokenizer_config.json
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-9-6162-v1/tokenizer.json
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-9-6162-v1/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
bbchicago-brt-8b-l3-v1-9-6162-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-v1-9-6162-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-9-6162-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-v1-9-6162-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-9-6162-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-v1-9-6162-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: Saving duration: 1.459s
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.838s
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-9-6162-v1_reward
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-9-6162-v1_reward/config.json
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-9-6162-v1_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-9-6162-v1_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-9-6162-v1_reward/merges.txt
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-9-6162-v1_reward/vocab.json
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-9-6162-v1_reward/tokenizer.json
bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-9-6162-v1_reward/reward.tensors
Job bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer completed after 126.59s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-9-6162-v1-mkmlizer
Pipeline stage MKMLizer completed in 127.71s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-9-6162-v1
Waiting for inference service bbchicago-brt-8b-l3-v1-9-6162-v1 to be ready
Inference service bbchicago-brt-8b-l3-v1-9-6162-v1 ready after 60.4121994972229s
Pipeline stage ISVCDeployer completed in 62.32s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2990870475769043s
Received healthy response to inference request in 1.3927257061004639s
Received healthy response to inference request in 1.4049227237701416s
Received healthy response to inference request in 1.3916187286376953s
Received healthy response to inference request in 1.5754570960998535s
5 requests
0 failed requests
5th percentile: 1.391840124130249
10th percentile: 1.3920615196228028
20th percentile: 1.3925043106079102
30th percentile: 1.3951651096343993
40th percentile: 1.4000439167022705
50th percentile: 1.4049227237701416
60th percentile: 1.4731364727020264
70th percentile: 1.541350221633911
80th percentile: 1.7201830863952638
90th percentile: 2.009635066986084
95th percentile: 2.154361057281494
99th percentile: 2.270141849517822
mean time: 1.6127622604370118
Pipeline stage StressChecker completed in 8.76s
bbchicago-brt-8b-l3-v1-9_6162_v1 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v1-9_6162_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-brt-8b-l3-v1-9_6162_v1
Running pipeline stage ISVCDeleter
Checking if service bbchicago-brt-8b-l3-v1-9-6162-v1 is running
Tearing down inference service bbchicago-brt-8b-l3-v1-9-6162-v1
Service bbchicago-brt-8b-l3-v1-9-6162-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.48s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-9-6162-v1/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-9-6162-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-9-6162-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-9-6162-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-9-6162-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-9-6162-v1_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-9-6162-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-9-6162-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-9-6162-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-9-6162-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-9-6162-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-9-6162-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.55s
bbchicago-brt-8b-l3-v1-9_6162_v1 status is now torndown due to DeploymentManager action