Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v32-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v32-mkmlizer to finish
Stopping job with name neversleep-noromaid-v0-8068-v32-mkmlizer
%s, retrying in %s seconds...
Starting job with name neversleep-noromaid-v0-8068-v32-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v32-mkmlizer to finish
neversleep-noromaid-v0-8068-v32-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v32-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v32-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v32-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v32-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v32-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v32-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v32-mkmlizer: ║ Version: 0.8.10 ║
neversleep-noromaid-v0-8068-v32-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v32-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v32-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v32-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v32-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v32-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v32-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v32-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v32-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v32-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v32-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.
neversleep-noromaid-v0-8068-v32-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v32-mkmlizer: Downloaded to shared memory in 67.583s
neversleep-noromaid-v0-8068-v32-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v32-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_petab_2024-02-09: ('http://chaiml-phase2-winner-13b2-v123-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:43708->127.0.0.1:8080: read: connection reset by peer\n')
neversleep-noromaid-v0-8068-v32-mkmlizer: quantized model in 59.539s
neversleep-noromaid-v0-8068-v32-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 133.122s
neversleep-noromaid-v0-8068-v32-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v32-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v32-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v32
neversleep-noromaid-v0-8068-v32-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v32/special_tokens_map.json
neversleep-noromaid-v0-8068-v32-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v32/config.json
neversleep-noromaid-v0-8068-v32-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v32/tokenizer_config.json
neversleep-noromaid-v0-8068-v32-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v32/tokenizer.model
neversleep-noromaid-v0-8068-v32-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v32/tokenizer.json
neversleep-noromaid-v0-8068-v32-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v32/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v32-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v32/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v32-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v32/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v32-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v32/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v32-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v32-mkmlizer:
Loading 0: 0%| | 0/995 [00:00<?, ?it/s]
Loading 0: 5%|▌ | 52/995 [00:01<00:24, 38.41it/s]
Loading 0: 11%|█ | 107/995 [00:02<00:20, 43.91it/s]
Loading 0: 16%|█▋ | 162/995 [00:03<00:18, 45.10it/s]
Loading 0: 21%|██ | 210/995 [00:04<00:17, 44.14it/s]
Loading 0: 27%|██▋ | 265/995 [00:06<00:16, 43.43it/s]
Loading 0: 28%|██▊ | 278/995 [00:15<01:15, 9.55it/s]
Loading 0: 32%|███▏ | 320/995 [00:17<00:53, 12.59it/s]
Loading 0: 37%|███▋ | 368/995 [00:18<00:37, 16.54it/s]
Loading 0: 43%|████▎ | 423/995 [00:19<00:26, 21.73it/s]
Loading 0: 48%|████▊ | 478/995 [00:20<00:19, 26.74it/s]
Loading 0: 53%|█████▎ | 526/995 [00:22<00:16, 29.30it/s]
Loading 0: 57%|█████▋ | 565/995 [00:31<00:39, 11.02it/s]
Loading 0: 58%|█████▊ | 581/995 [00:33<00:37, 11.03it/s]
Loading 0: 64%|██████▍ | 636/995 [00:34<00:22, 15.93it/s]
Loading 0: 69%|██████▉ | 691/995 [00:35<00:14, 20.65it/s]
Loading 0: 74%|███████▍ | 739/995 [00:36<00:10, 24.78it/s]
Loading 0: 80%|███████▉ | 794/995 [00:37<00:06, 29.83it/s]
Loading 0: 85%|████████▌ | 846/995 [00:47<00:12, 12.26it/s]
Loading 0: 90%|█████████ | 897/995 [00:49<00:06, 14.10it/s]
Loading 0: 96%|█████████▌| 952/995 [00:51<00:02, 18.26it/s]
Loading 0: 100%|██████████| 995/995 [00:52<00:00, 20.99it/s]
/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.
neversleep-noromaid-v0-8068-v32-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v32-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.
neversleep-noromaid-v0-8068-v32-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v32-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.
neversleep-noromaid-v0-8068-v32-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v32-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()
neversleep-noromaid-v0-8068-v32-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v32-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v32-mkmlizer: Saving duration: 0.293s
neversleep-noromaid-v0-8068-v32-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 7.094s
neversleep-noromaid-v0-8068-v32-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v32-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v32-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v32_reward
neversleep-noromaid-v0-8068-v32-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v32_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v32-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v32_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v32-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v32_reward/config.json
neversleep-noromaid-v0-8068-v32-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v32_reward/vocab.json
neversleep-noromaid-v0-8068-v32-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v32_reward/merges.txt
neversleep-noromaid-v0-8068-v32-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v32_reward/tokenizer.json
neversleep-noromaid-v0-8068-v32-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v32_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v32-mkmlizer completed after 177.15s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v32-mkmlizer
Pipeline stage MKMLizer completed in 182.90s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.51s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v32
Waiting for inference service neversleep-noromaid-v0-8068-v32 to be ready
Inference service neversleep-noromaid-v0-8068-v32 ready after 50.288368701934814s
Pipeline stage ISVCDeployer completed in 57.83s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0980777740478516s
Received healthy response to inference request in 2.1368350982666016s
Received healthy response to inference request in 2.2145144939422607s
Received healthy response to inference request in 2.1387624740600586s
Received healthy response to inference request in 2.3841845989227295s
5 requests
0 failed requests
5th percentile: 2.137220573425293
10th percentile: 2.1376060485839843
20th percentile: 2.138376998901367
30th percentile: 2.153912878036499
40th percentile: 2.1842136859893797
50th percentile: 2.2145144939422607
60th percentile: 2.282382535934448
70th percentile: 2.350250577926636
80th percentile: 2.526963233947754
90th percentile: 2.8125205039978027
95th percentile: 2.955299139022827
99th percentile: 3.0695220470428466
mean time: 2.3944748878479003
Pipeline stage StressChecker completed in 12.68s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
%s, retrying in %s seconds...
neversleep-noromaid-v0-_8068_v32 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
neversleep-noromaid-v0-_8068_v32 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-noromaid-v0-_8068_v32
Running pipeline stage ISVCDeleter
Checking if service neversleep-noromaid-v0-8068-v32 is running
Tearing down inference service neversleep-noromaid-v0-8068-v32
Toredown service neversleep-noromaid-v0-8068-v32
Pipeline stage ISVCDeleter completed in 5.47s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v32/config.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v32/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v32/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v32/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v32/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v32/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v32/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v32/tokenizer.model from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v32/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v32_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v32_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v32_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v32_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v32_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v32_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v32_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.69s
neversleep-noromaid-v0-_8068_v32 status is now torndown due to DeploymentManager action