Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v6-3-3-v3-mkmlizer
Waiting for job on cycy233-misllm-v6-3-3-v3-mkmlizer to finish
cycy233-misllm-v6-3-3-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v6-3-3-v3-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v6-3-3-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v6-3-3-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v6-3-3-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v6-3-3-v3-mkmlizer: ║ /___/ ║
cycy233-misllm-v6-3-3-v3-mkmlizer: ║ ║
cycy233-misllm-v6-3-3-v3-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v6-3-3-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v6-3-3-v3-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v6-3-3-v3-mkmlizer: ║ ║
cycy233-misllm-v6-3-3-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v6-3-3-v3-mkmlizer: ║ belonging to: ║
cycy233-misllm-v6-3-3-v3-mkmlizer: ║ ║
cycy233-misllm-v6-3-3-v3-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v6-3-3-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v6-3-3-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v6-3-3-v3-mkmlizer: ║ ║
cycy233-misllm-v6-3-3-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v6-3-3-v3-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-v6-3-3-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v6-3-3-v3-mkmlizer: Downloaded to shared memory in 15.583s
cycy233-misllm-v6-3-3-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v6-3-3-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v6-3-3-v3-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 96.00it/s]
Loading 0: 70%|███████ | 204/291 [00:01<00:00, 107.64it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 85.97it/s]
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v6-3-3-v3-mkmlizer: quantized model in 14.895s
cycy233-misllm-v6-3-3-v3-mkmlizer: Processed model cycy233/misllm_v6.3.3 in 32.739s
cycy233-misllm-v6-3-3-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v6-3-3-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v6-3-3-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v6-3-3-v3
cycy233-misllm-v6-3-3-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v6-3-3-v3/config.json
cycy233-misllm-v6-3-3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v6-3-3-v3/tokenizer.model
cycy233-misllm-v6-3-3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v6-3-3-v3/tokenizer_config.json
cycy233-misllm-v6-3-3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v6-3-3-v3/tokenizer.json
cycy233-misllm-v6-3-3-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v6-3-3-v3/special_tokens_map.json
cycy233-misllm-v6-3-3-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v6-3-3-v3/flywheel_model.0.safetensors
cycy233-misllm-v6-3-3-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v6-3-3-v3-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-v6-3-3-v3-mkmlizer: warnings.warn(
cycy233-misllm-v6-3-3-v3-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-v6-3-3-v3-mkmlizer: warnings.warn(
cycy233-misllm-v6-3-3-v3-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-v6-3-3-v3-mkmlizer: warnings.warn(
cycy233-misllm-v6-3-3-v3-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-v6-3-3-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v6-3-3-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v6-3-3-v3-mkmlizer: Saving duration: 0.403s
cycy233-misllm-v6-3-3-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.267s
cycy233-misllm-v6-3-3-v3-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v6-3-3-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v6-3-3-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v6-3-3-v3_reward
cycy233-misllm-v6-3-3-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v6-3-3-v3_reward/config.json
cycy233-misllm-v6-3-3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v6-3-3-v3_reward/tokenizer_config.json
cycy233-misllm-v6-3-3-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v6-3-3-v3_reward/special_tokens_map.json
cycy233-misllm-v6-3-3-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v6-3-3-v3_reward/vocab.json
cycy233-misllm-v6-3-3-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v6-3-3-v3_reward/merges.txt
cycy233-misllm-v6-3-3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v6-3-3-v3_reward/tokenizer.json
cycy233-misllm-v6-3-3-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v6-3-3-v3_reward/reward.tensors
Job cycy233-misllm-v6-3-3-v3-mkmlizer completed after 52.89s with status: succeeded
Stopping job with name cycy233-misllm-v6-3-3-v3-mkmlizer
Pipeline stage MKMLizer completed in 53.22s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v6-3-3-v3
Waiting for inference service cycy233-misllm-v6-3-3-v3 to be ready
Inference service cycy233-misllm-v6-3-3-v3 ready after 100.6059513092041s
Pipeline stage ISVCDeployer completed in 106.21s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8988990783691406s
Received healthy response to inference request in 0.9887773990631104s
Received healthy response to inference request in 1.090824842453003s
Received healthy response to inference request in 1.084111213684082s
Received healthy response to inference request in 0.9645893573760986s
5 requests
0 failed requests
5th percentile: 0.969426965713501
10th percentile: 0.9742645740509033
20th percentile: 0.983939790725708
30th percentile: 1.0078441619873046
40th percentile: 1.0459776878356934
50th percentile: 1.084111213684082
60th percentile: 1.0867966651916503
70th percentile: 1.0894821166992188
80th percentile: 1.2524396896362306
90th percentile: 1.5756693840026856
95th percentile: 1.737284231185913
99th percentile: 1.866576108932495
mean time: 1.205440378189087
Pipeline stage StressChecker completed in 6.67s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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-v6-3-3_v3 status is now deployed due to DeploymentManager action
cycy233-misllm-v6-3-3_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v6-3-3_v3
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v6-3-3-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.98s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v6-3-3-v3/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-3-3-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-3-3-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-3-3-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-3-3-v3/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-3-3-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v6-3-3-v3_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-3-3-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-3-3-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-3-3-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-3-3-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-3-3-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-3-3-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.51s
cycy233-misllm-v6-3-3_v3 status is now torndown due to DeploymentManager action