Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v7-8-2-5-v4-mkmlizer
Waiting for job on cycy233-misllm-v7-8-2-5-v4-mkmlizer to finish
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ║ /___/ ║
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ║ ║
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ║ ║
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ║ belonging to: ║
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ║ ║
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ║ ║
cycy233-misllm-v7-8-2-5-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v7-8-2-5-v4-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.
cycy233-misllm-v7-8-2-5-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v7-8-2-5-v4-mkmlizer: Downloaded to shared memory in 12.451s
cycy233-misllm-v7-8-2-5-v4-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v7-8-2-5-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v7-8-2-5-v4-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 70.15it/s]
Loading 0: 70%|███████ | 204/291 [00:02<00:01, 74.32it/s]
Loading 0: 100%|██████████| 291/291 [00:04<00:00, 69.57it/s]
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v7-8-2-5-v4-mkmlizer: quantized model in 12.157s
cycy233-misllm-v7-8-2-5-v4-mkmlizer: Processed model cycy233/misllm_v7.8.2.5 in 25.819s
cycy233-misllm-v7-8-2-5-v4-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v7-8-2-5-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v7-8-2-5-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v7-8-2-5-v4
cycy233-misllm-v7-8-2-5-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v7-8-2-5-v4/config.json
cycy233-misllm-v7-8-2-5-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v7-8-2-5-v4/tokenizer_config.json
cycy233-misllm-v7-8-2-5-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v7-8-2-5-v4/special_tokens_map.json
cycy233-misllm-v7-8-2-5-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v7-8-2-5-v4/tokenizer.model
cycy233-misllm-v7-8-2-5-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v7-8-2-5-v4/tokenizer.json
cycy233-misllm-v7-8-2-5-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v7-8-2-5-v4/flywheel_model.0.safetensors
cycy233-misllm-v7-8-2-5-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v7-8-2-5-v4-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.
cycy233-misllm-v7-8-2-5-v4-mkmlizer: warnings.warn(
cycy233-misllm-v7-8-2-5-v4-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.
cycy233-misllm-v7-8-2-5-v4-mkmlizer: warnings.warn(
cycy233-misllm-v7-8-2-5-v4-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.
cycy233-misllm-v7-8-2-5-v4-mkmlizer: warnings.warn(
cycy233-misllm-v7-8-2-5-v4-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()
cycy233-misllm-v7-8-2-5-v4-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v7-8-2-5-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v7-8-2-5-v4-mkmlizer: Saving duration: 0.273s
cycy233-misllm-v7-8-2-5-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.775s
cycy233-misllm-v7-8-2-5-v4-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v7-8-2-5-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v7-8-2-5-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v7-8-2-5-v4_reward
cycy233-misllm-v7-8-2-5-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v7-8-2-5-v4_reward/merges.txt
cycy233-misllm-v7-8-2-5-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v7-8-2-5-v4_reward/special_tokens_map.json
cycy233-misllm-v7-8-2-5-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v7-8-2-5-v4_reward/tokenizer.json
cycy233-misllm-v7-8-2-5-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v7-8-2-5-v4_reward/tokenizer_config.json
cycy233-misllm-v7-8-2-5-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v7-8-2-5-v4_reward/vocab.json
cycy233-misllm-v7-8-2-5-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v7-8-2-5-v4_reward/config.json
cycy233-misllm-v7-8-2-5-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v7-8-2-5-v4_reward/reward.tensors
Job cycy233-misllm-v7-8-2-5-v4-mkmlizer completed after 52.45s with status: succeeded
Stopping job with name cycy233-misllm-v7-8-2-5-v4-mkmlizer
Pipeline stage MKMLizer completed in 55.16s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v7-8-2-5-v4
Waiting for inference service cycy233-misllm-v7-8-2-5-v4 to be ready
Inference service cycy233-misllm-v7-8-2-5-v4 ready after 40.24048566818237s
Pipeline stage ISVCDeployer completed in 47.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2307233810424805s
Received healthy response to inference request in 1.1883001327514648s
Received healthy response to inference request in 1.2144739627838135s
Received healthy response to inference request in 1.3695409297943115s
Received healthy response to inference request in 5.389032363891602s
5 requests
0 failed requests
5th percentile: 1.1935348987579346
10th percentile: 1.1987696647644044
20th percentile: 1.2092391967773437
30th percentile: 1.245487356185913
40th percentile: 1.3075141429901123
50th percentile: 1.3695409297943115
60th percentile: 1.714013910293579
70th percentile: 2.0584868907928464
80th percentile: 2.862385177612305
90th percentile: 4.125708770751953
95th percentile: 4.757370567321777
99th percentile: 5.262700004577637
mean time: 2.2784141540527343
Pipeline stage StressChecker completed in 12.03s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
cycy233-misllm-v7-8-2-5_v4 status is now deployed due to DeploymentManager action
cycy233-misllm-v7-8-2-5_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v7-8-2-5_v4
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v7-8-2-5-v4 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.82s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v7-8-2-5-v4/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v7-8-2-5-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v7-8-2-5-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v7-8-2-5-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v7-8-2-5-v4/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v7-8-2-5-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v7-8-2-5-v4_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v7-8-2-5-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v7-8-2-5-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v7-8-2-5-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v7-8-2-5-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v7-8-2-5-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v7-8-2-5-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.13s
cycy233-misllm-v7-8-2-5_v4 status is now torndown due to DeploymentManager action