Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer to finish
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: Downloaded to shared memory in 45.864s
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 3/291 [00:02<04:31, 1.06it/s]
Loading 0: 1%|▏ | 4/291 [00:06<08:31, 1.78s/it]
Loading 0: 2%|▏ | 5/291 [00:08<08:49, 1.85s/it]
Loading 0: 3%|▎ | 8/291 [00:09<04:18, 1.09it/s]
Loading 0: 3%|▎ | 9/291 [00:09<03:45, 1.25it/s]
Loading 0: 4%|▍ | 12/291 [00:10<03:04, 1.51it/s]
Loading 0: 4%|▍ | 13/291 [00:12<03:27, 1.34it/s]
Loading 0: 7%|▋ | 21/291 [00:12<01:06, 4.03it/s]
Loading 0: 11%|█ | 31/291 [00:12<00:30, 8.48it/s]
Loading 0: 14%|█▍ | 41/291 [00:12<00:17, 14.07it/s]
Loading 0: 19%|█▊ | 54/291 [00:12<00:10, 23.35it/s]
Loading 0: 23%|██▎ | 66/291 [00:12<00:06, 32.86it/s]
Loading 0: 26%|██▌ | 76/291 [00:12<00:05, 41.08it/s]
Loading 0: 29%|██▉ | 85/291 [00:13<00:06, 31.82it/s]
Loading 0: 33%|███▎ | 95/291 [00:13<00:04, 40.23it/s]
Loading 0: 38%|███▊ | 111/291 [00:13<00:03, 56.68it/s]
Loading 0: 42%|████▏ | 121/291 [00:13<00:02, 63.82it/s]
Loading 0: 45%|████▌ | 131/291 [00:13<00:02, 70.14it/s]
Loading 0: 50%|█████ | 146/291 [00:13<00:01, 87.56it/s]
Loading 0: 54%|█████▍ | 158/291 [00:13<00:01, 85.75it/s]
Loading 0: 59%|█████▉ | 173/291 [00:13<00:01, 97.18it/s]
Loading 0: 64%|██████▍ | 187/291 [00:14<00:01, 64.88it/s]
Loading 0: 67%|██████▋ | 196/291 [00:14<00:01, 67.67it/s]
Loading 0: 72%|███████▏ | 210/291 [00:14<00:01, 79.16it/s]
Loading 0: 76%|███████▌ | 220/291 [00:14<00:00, 82.73it/s]
Loading 0: 79%|███████▉ | 230/291 [00:14<00:00, 86.01it/s]
Loading 0: 85%|████████▍ | 246/291 [00:14<00:00, 99.47it/s]
Loading 0: 88%|████████▊ | 257/291 [00:15<00:00, 95.85it/s]
Loading 0: 93%|█████████▎| 271/291 [00:15<00:00, 106.84it/s]
Loading 0: 97%|█████████▋| 283/291 [00:15<00:00, 101.52it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: quantized model in 44.405s
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.3-DPO_v3.1 in 90.269s
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-7058-v1
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-7058-v1/special_tokens_map.json
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-7058-v1/config.json
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-7058-v1/tokenizer_config.json
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-7058-v1/tokenizer.json
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-7058-v1/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: return self.fget.__get__(instance, owner)()
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: Saving duration: 0.434s
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.538s
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-7058-v1_reward
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-7058-v1_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-7058-v1_reward/config.json
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-7058-v1_reward/vocab.json
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-7058-v1_reward/merges.txt
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-7058-v1_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-7058-v1_reward/tokenizer.json
bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-7058-v1_reward/reward.tensors
Job bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer completed after 186.07s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-3-7058-v1-mkmlizer
Pipeline stage MKMLizer completed in 186.99s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-3-7058-v1
Waiting for inference service bbchicago-brt-8b-l3-v1-3-7058-v1 to be ready
Inference service bbchicago-brt-8b-l3-v1-3-7058-v1 ready after 40.199217557907104s
Pipeline stage ISVCDeployer completed in 47.06s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.09602427482605s
Received healthy response to inference request in 1.27048921585083s
Received healthy response to inference request in 1.2676925659179688s
Received healthy response to inference request in 1.2661311626434326s
Received healthy response to inference request in 1.2628495693206787s
5 requests
0 failed requests
5th percentile: 1.2635058879852294
10th percentile: 1.2641622066497802
20th percentile: 1.2654748439788819
30th percentile: 1.2664434432983398
40th percentile: 1.2670680046081544
50th percentile: 1.2676925659179688
60th percentile: 1.2688112258911133
70th percentile: 1.2699298858642578
80th percentile: 1.4355962276458742
90th percentile: 1.765810251235962
95th percentile: 1.9309172630310056
99th percentile: 2.063002872467041
mean time: 1.432637357711792
Pipeline stage StressChecker completed in 7.80s
bbchicago-brt-8b-l3-v1-3_7058_v1 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v1-3_7058_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-brt-8b-l3-v1-3_7058_v1
Running pipeline stage ISVCDeleter
Checking if service bbchicago-brt-8b-l3-v1-3-7058-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.05s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-3-7058-v1/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-3-7058-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-3-7058-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-3-7058-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-3-7058-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-3-7058-v1_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-3-7058-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-3-7058-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-3-7058-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-3-7058-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-3-7058-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-3-7058-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.43s
bbchicago-brt-8b-l3-v1-3_7058_v1 status is now torndown due to DeploymentManager action