Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer to finish
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ║ Version: 0.9.5.post3 ║
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: Downloaded to shared memory in 32.988s
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdfy9jc92, device:0
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 4%|▍ | 12/291 [00:00<00:02, 105.14it/s]
Loading 0: 8%|▊ | 23/291 [00:00<00:02, 96.52it/s]
Loading 0: 13%|█▎ | 37/291 [00:00<00:02, 114.04it/s]
Loading 0: 17%|█▋ | 49/291 [00:00<00:02, 89.61it/s]
Loading 0: 20%|██ | 59/291 [00:00<00:02, 88.58it/s]
Loading 0: 26%|██▌ | 75/291 [00:00<00:02, 103.34it/s]
Loading 0: 30%|██▉ | 86/291 [00:01<00:04, 47.47it/s]
Loading 0: 35%|███▌ | 102/291 [00:01<00:03, 62.67it/s]
Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 64.78it/s]
Loading 0: 42%|████▏ | 121/291 [00:01<00:02, 67.97it/s]
Loading 0: 45%|████▌ | 131/291 [00:01<00:02, 74.33it/s]
Loading 0: 50%|█████ | 146/291 [00:01<00:01, 91.65it/s]
Loading 0: 54%|█████▍ | 157/291 [00:01<00:01, 89.79it/s]
Loading 0: 58%|█████▊ | 168/291 [00:02<00:01, 93.99it/s]
Loading 0: 62%|██████▏ | 181/291 [00:02<00:01, 100.94it/s]
Loading 0: 66%|██████▌ | 192/291 [00:02<00:01, 53.30it/s]
Loading 0: 69%|██████▉ | 202/291 [00:02<00:01, 60.65it/s]
Loading 0: 73%|███████▎ | 211/291 [00:02<00:01, 65.78it/s]
Loading 0: 76%|███████▌ | 221/291 [00:02<00:00, 72.42it/s]
Loading 0: 81%|████████▏ | 237/291 [00:03<00:00, 89.59it/s]
Loading 0: 85%|████████▌ | 248/291 [00:03<00:00, 92.31it/s]
Loading 0: 91%|█████████ | 264/291 [00:03<00:00, 108.64it/s]
Loading 0: 95%|█████████▍| 276/291 [00:03<00:00, 109.43it/s]
Loading 0: 99%|█████████▉| 288/291 [00:10<00:00, 5.75it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: quantized model in 29.638s
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.6_DPO_steps_1500 in 62.627s
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-6-8305-v1
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-6-8305-v1/config.json
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-6-8305-v1/tokenizer_config.json
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-6-8305-v1/special_tokens_map.json
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-6-8305-v1/tokenizer.json
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-6-8305-v1/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
bbchicago-brt-8b-l3-v1-6-8305-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-v1-6-8305-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-6-8305-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-v1-6-8305-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-6-8305-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-v1-6-8305-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: Saving duration: 2.369s
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 14.251s
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-6-8305-v1_reward
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-6-8305-v1_reward/config.json
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-6-8305-v1_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-6-8305-v1_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-6-8305-v1_reward/merges.txt
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-6-8305-v1_reward/vocab.json
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-6-8305-v1_reward/tokenizer.json
bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-6-8305-v1_reward/reward.tensors
Job bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer completed after 138.75s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-6-8305-v1-mkmlizer
Pipeline stage MKMLizer completed in 140.05s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-6-8305-v1
Waiting for inference service bbchicago-brt-8b-l3-v1-6-8305-v1 to be ready
Inference service bbchicago-brt-8b-l3-v1-6-8305-v1 ready after 193.19896817207336s
Pipeline stage ISVCDeployer completed in 195.02s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3521084785461426s
Received healthy response to inference request in 1.4240665435791016s
Received healthy response to inference request in 1.4093010425567627s
Received healthy response to inference request in 1.4006989002227783s
Received healthy response to inference request in 1.4340596199035645s
5 requests
0 failed requests
5th percentile: 1.4024193286895752
10th percentile: 1.404139757156372
20th percentile: 1.4075806140899658
30th percentile: 1.4122541427612305
40th percentile: 1.418160343170166
50th percentile: 1.4240665435791016
60th percentile: 1.4280637741088866
70th percentile: 1.432061004638672
80th percentile: 1.6176693916320803
90th percentile: 1.9848889350891115
95th percentile: 2.1684987068176267
99th percentile: 2.3153865242004392
mean time: 1.60404691696167
Pipeline stage StressChecker completed in 8.74s
bbchicago-brt-8b-l3-v1-6_8305_v1 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v1-6_8305_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-brt-8b-l3-v1-6_8305_v1
Running pipeline stage ISVCDeleter
Checking if service bbchicago-brt-8b-l3-v1-6-8305-v1 is running
Tearing down inference service bbchicago-brt-8b-l3-v1-6-8305-v1
Service bbchicago-brt-8b-l3-v1-6-8305-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.72s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-6-8305-v1/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-6-8305-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-6-8305-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-6-8305-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-6-8305-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-6-8305-v1_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-6-8305-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-6-8305-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-6-8305-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-6-8305-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-6-8305-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-6-8305-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.03s
bbchicago-brt-8b-l3-v1-6_8305_v1 status is now torndown due to DeploymentManager action