Running pipeline stage MKMLizer
Starting job with name trace2333-pippa-bm-llama2-v0-v2-mkmlizer
Waiting for job on trace2333-pippa-bm-llama2-v0-v2-mkmlizer to finish
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ║     _____            __           __                                ║
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ║       /___/                                                         ║
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ║                                                                     ║
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ║                                                                     ║
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ║  belonging to:                                                      ║
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ║                                                                     ║
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ║                                                                     ║
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-pippa-bm-llama2-v0-v2-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.
trace2333-pippa-bm-llama2-v0-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: Downloaded to shared memory in 66.702s
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: quantizing model to /dev/shm/model_cache
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:06, 47.21it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 58.92it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:04, 62.58it/s]
Loading 0:  10%|▉         | 28/291 [00:00<00:04, 61.22it/s]
Loading 0:  12%|█▏        | 35/291 [00:00<00:04, 58.91it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:04, 54.44it/s]
Loading 0:  18%|█▊        | 51/291 [00:01<00:06, 35.86it/s]
Loading 0:  19%|█▉        | 56/291 [00:01<00:06, 37.30it/s]
Loading 0:  22%|██▏       | 65/291 [00:01<00:04, 45.88it/s]
Loading 0:  24%|██▍       | 71/291 [00:01<00:04, 45.01it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:04, 50.23it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:03, 51.77it/s]
Loading 0:  31%|███▏      | 91/291 [00:01<00:03, 52.02it/s]
Loading 0:  34%|███▎      | 98/291 [00:01<00:03, 54.39it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:05, 35.04it/s]
Loading 0:  38%|███▊      | 110/291 [00:02<00:04, 36.92it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:04, 38.43it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 42.90it/s]
Loading 0:  44%|████▍     | 129/291 [00:02<00:03, 49.67it/s]
Loading 0:  46%|████▋     | 135/291 [00:02<00:03, 51.64it/s]
Loading 0:  48%|████▊     | 141/291 [00:02<00:02, 52.14it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 54.86it/s]
Loading 0:  54%|█████▎    | 156/291 [00:03<00:02, 60.52it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:03, 32.41it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:03, 35.31it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 40.73it/s]
Loading 0:  63%|██████▎   | 183/291 [00:03<00:02, 47.12it/s]
Loading 0:  65%|██████▍   | 189/291 [00:04<00:02, 49.73it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:01, 50.62it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:01, 52.95it/s]
Loading 0:  72%|███████▏  | 210/291 [00:04<00:01, 58.27it/s]
Loading 0:  75%|███████▍  | 217/291 [00:04<00:02, 31.46it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 35.56it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 39.90it/s]
Loading 0:  81%|████████▏ | 237/291 [00:05<00:01, 46.61it/s]
Loading 0:  84%|████████▎ | 243/291 [00:05<00:00, 48.97it/s]
Loading 0:  86%|████████▌ | 249/291 [00:05<00:00, 49.79it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 52.50it/s]
Loading 0:  91%|█████████ | 264/291 [00:05<00:00, 57.86it/s]
Loading 0:  93%|█████████▎| 271/291 [00:07<00:01, 10.57it/s]
Loading 0:  95%|█████████▍| 276/291 [00:07<00:01, 12.93it/s]
Loading 0:  98%|█████████▊| 284/291 [00:07<00:00, 17.94it/s]
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: quantized model in 18.018s
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: Processed model Trace2333/pippa_bm_llama2_v0 in 89.317s
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: creating bucket guanaco-mkml-models
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-pippa-bm-llama2-v0-v2
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-pippa-bm-llama2-v0-v2/special_tokens_map.json
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-pippa-bm-llama2-v0-v2/tokenizer_config.json
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/trace2333-pippa-bm-llama2-v0-v2/tokenizer.model
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-pippa-bm-llama2-v0-v2/config.json
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-pippa-bm-llama2-v0-v2/tokenizer.json
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-pippa-bm-llama2-v0-v2/flywheel_model.0.safetensors
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-pippa-bm-llama2-v0-v2-mkmlizer:   warnings.warn(
trace2333-pippa-bm-llama2-v0-v2-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.
trace2333-pippa-bm-llama2-v0-v2-mkmlizer:   warnings.warn(
trace2333-pippa-bm-llama2-v0-v2-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.
trace2333-pippa-bm-llama2-v0-v2-mkmlizer:   warnings.warn(
trace2333-pippa-bm-llama2-v0-v2-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()
trace2333-pippa-bm-llama2-v0-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: Saving duration: 0.477s
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.675s
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: creating bucket guanaco-reward-models
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-pippa-bm-llama2-v0-v2_reward
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-pippa-bm-llama2-v0-v2_reward/config.json
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-pippa-bm-llama2-v0-v2_reward/tokenizer_config.json
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-pippa-bm-llama2-v0-v2_reward/special_tokens_map.json
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-pippa-bm-llama2-v0-v2_reward/merges.txt
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-pippa-bm-llama2-v0-v2_reward/vocab.json
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-pippa-bm-llama2-v0-v2_reward/tokenizer.json
trace2333-pippa-bm-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-pippa-bm-llama2-v0-v2_reward/reward.tensors
Job trace2333-pippa-bm-llama2-v0-v2-mkmlizer completed after 134.03s with status: succeeded
Stopping job with name trace2333-pippa-bm-llama2-v0-v2-mkmlizer
Pipeline stage MKMLizer completed in 137.06s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-pippa-bm-llama2-v0-v2
Waiting for inference service trace2333-pippa-bm-llama2-v0-v2 to be ready
Inference service trace2333-pippa-bm-llama2-v0-v2 ready after 462.1566119194031s
Pipeline stage ISVCDeployer completed in 469.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.934903621673584s
Received healthy response to inference request in 1.0212149620056152s
Received healthy response to inference request in 1.0106446743011475s
Received healthy response to inference request in 0.9993240833282471s
Received healthy response to inference request in 0.999868631362915s
5 requests
0 failed requests
5th percentile: 0.9994329929351806
10th percentile: 0.9995419025421143
20th percentile: 0.9997597217559815
30th percentile: 1.0020238399505614
40th percentile: 1.0063342571258544
50th percentile: 1.0106446743011475
60th percentile: 1.0148727893829346
70th percentile: 1.0191009044647217
80th percentile: 1.2039526939392091
90th percentile: 1.5694281578063967
95th percentile: 1.75216588973999
99th percentile: 1.8983560752868651
mean time: 1.1931911945343017
Pipeline stage StressChecker completed in 6.58s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.07s
trace2333-pippa-bm-llama2-v0_v2 status is now deployed due to DeploymentManager action
trace2333-pippa-bm-llama2-v0_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-pippa-bm-llama2-v0_v2
Running pipeline stage ISVCDeleter
Checking if service trace2333-pippa-bm-llama2-v0-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.86s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-pippa-bm-llama2-v0-v2/config.json from bucket guanaco-mkml-models
Deleting key trace2333-pippa-bm-llama2-v0-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-pippa-bm-llama2-v0-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-pippa-bm-llama2-v0-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-pippa-bm-llama2-v0-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key trace2333-pippa-bm-llama2-v0-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-pippa-bm-llama2-v0-v2_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-pippa-bm-llama2-v0-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-pippa-bm-llama2-v0-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-pippa-bm-llama2-v0-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-pippa-bm-llama2-v0-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-pippa-bm-llama2-v0-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-pippa-bm-llama2-v0-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.22s
trace2333-pippa-bm-llama2-v0_v2 status is now torndown due to DeploymentManager action