Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer to finish
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: Downloaded to shared memory in 40.797s
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:02, 114.65it/s]
Loading 0: 10%|█ | 30/291 [00:00<00:01, 133.60it/s]
Loading 0: 15%|█▌ | 44/291 [00:00<00:01, 130.76it/s]
Loading 0: 20%|█▉ | 58/291 [00:00<00:01, 130.46it/s]
Loading 0: 26%|██▌ | 75/291 [00:00<00:01, 136.01it/s]
Loading 0: 31%|███ | 89/291 [00:01<00:03, 60.90it/s]
Loading 0: 35%|███▌ | 102/291 [00:01<00:02, 71.80it/s]
Loading 0: 39%|███▉ | 113/291 [00:01<00:02, 78.75it/s]
Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 94.92it/s]
Loading 0: 49%|████▉ | 142/291 [00:01<00:01, 99.61it/s]
Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 108.73it/s]
Loading 0: 58%|█████▊ | 169/291 [00:01<00:01, 112.03it/s]
Loading 0: 63%|██████▎ | 184/291 [00:01<00:00, 121.44it/s]
Loading 0: 68%|██████▊ | 198/291 [00:02<00:01, 71.14it/s]
Loading 0: 73%|███████▎ | 211/291 [00:02<00:01, 78.90it/s]
Loading 0: 78%|███████▊ | 226/291 [00:02<00:00, 93.01it/s]
Loading 0: 82%|████████▏ | 239/291 [00:02<00:00, 98.55it/s]
Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 114.91it/s]
Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 126.52it/s]
Loading 0: 99%|█████████▉| 289/291 [00:08<00:00, 8.48it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: quantized model in 26.065s
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.3-DPO_v2 in 69.769s
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-6151-v1
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-6151-v1/config.json
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-6151-v1/tokenizer_config.json
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-6151-v1/special_tokens_map.json
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-6151-v1/tokenizer.json
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-6151-v1/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-3-6151-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-v1-3-6151-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-3-6151-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-v1-3-6151-v1-mkmlizer: return self.fget.__get__(instance, owner)()
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: Saving duration: 0.428s
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.583s
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-6151-v1_reward
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-6151-v1_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-6151-v1_reward/config.json
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-6151-v1_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-6151-v1_reward/vocab.json
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-6151-v1_reward/merges.txt
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-6151-v1_reward/tokenizer.json
bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-6151-v1_reward/reward.tensors
Job bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer completed after 103.74s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-3-6151-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.76s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-3-6151-v1
Waiting for inference service bbchicago-brt-8b-l3-v1-3-6151-v1 to be ready
Inference service bbchicago-brt-8b-l3-v1-3-6151-v1 ready after 40.21271896362305s
Pipeline stage ISVCDeployer completed in 47.40s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3117475509643555s
Received healthy response to inference request in 1.2960941791534424s
Received healthy response to inference request in 1.3157951831817627s
Received healthy response to inference request in 1.284458875656128s
Received healthy response to inference request in 1.3271985054016113s
5 requests
0 failed requests
5th percentile: 1.286785936355591
10th percentile: 1.2891129970550537
20th percentile: 1.2937671184539794
30th percentile: 1.3000343799591065
40th percentile: 1.3079147815704346
50th percentile: 1.3157951831817627
60th percentile: 1.320356512069702
70th percentile: 1.3249178409576416
80th percentile: 1.5241083145141603
90th percentile: 1.917927932739258
95th percentile: 2.1148377418518063
99th percentile: 2.2723655891418457
mean time: 1.50705885887146
Pipeline stage StressChecker completed in 8.36s
bbchicago-brt-8b-l3-v1-3_6151_v1 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v1-3_6151_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-brt-8b-l3-v1-3_6151_v1
Running pipeline stage ISVCDeleter
Checking if service bbchicago-brt-8b-l3-v1-3-6151-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 10.05s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-3-6151-v1/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-3-6151-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-3-6151-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-3-6151-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-3-6151-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-3-6151-v1_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-3-6151-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-3-6151-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-3-6151-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-3-6151-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-3-6151-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-3-6151-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.28s
bbchicago-brt-8b-l3-v1-3_6151_v1 status is now torndown due to DeploymentManager action
admin requested tearing down of bbchicago-brt-8b-l3-v1-3_6151_v1
Running pipeline stage ISVCDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage ISVCDeleter completed in 0.45s
Running pipeline stage MKMLModelDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLModelDeleter completed in 0.33s
bbchicago-brt-8b-l3-v1-3_6151_v1 status is now torndown due to DeploymentManager action