Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v8-2-3-v1-mkmlizer
Waiting for job on cycy233-misllm-v8-2-3-v1-mkmlizer to finish
cycy233-misllm-v8-2-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v8-2-3-v1-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v8-2-3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v8-2-3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v8-2-3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v8-2-3-v1-mkmlizer: ║ /___/ ║
cycy233-misllm-v8-2-3-v1-mkmlizer: ║ ║
cycy233-misllm-v8-2-3-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v8-2-3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v8-2-3-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v8-2-3-v1-mkmlizer: ║ ║
cycy233-misllm-v8-2-3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v8-2-3-v1-mkmlizer: ║ belonging to: ║
cycy233-misllm-v8-2-3-v1-mkmlizer: ║ ║
cycy233-misllm-v8-2-3-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v8-2-3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v8-2-3-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v8-2-3-v1-mkmlizer: ║ ║
cycy233-misllm-v8-2-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v8-2-3-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.
cycy233-misllm-v8-2-3-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v8-2-3-v1-mkmlizer: Downloaded to shared memory in 28.355s
cycy233-misllm-v8-2-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v8-2-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v8-2-3-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 34%|███▎ | 98/291 [00:00<00:01, 99.68it/s]
Loading 0: 70%|███████ | 204/291 [00:02<00:00, 96.18it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 80.27it/s]
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v8-2-3-v1-mkmlizer: quantized model in 14.751s
cycy233-misllm-v8-2-3-v1-mkmlizer: Processed model cycy233/misllm_v8.2.3 in 45.327s
cycy233-misllm-v8-2-3-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v8-2-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v8-2-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v8-2-3-v1
cycy233-misllm-v8-2-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v8-2-3-v1/special_tokens_map.json
cycy233-misllm-v8-2-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v8-2-3-v1/tokenizer.model
cycy233-misllm-v8-2-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v8-2-3-v1/tokenizer_config.json
cycy233-misllm-v8-2-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v8-2-3-v1/config.json
cycy233-misllm-v8-2-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v8-2-3-v1/tokenizer.json
cycy233-misllm-v8-2-3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v8-2-3-v1/flywheel_model.0.safetensors
cycy233-misllm-v8-2-3-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v8-2-3-v1-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-v8-2-3-v1-mkmlizer: warnings.warn(
cycy233-misllm-v8-2-3-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.
cycy233-misllm-v8-2-3-v1-mkmlizer: warnings.warn(
cycy233-misllm-v8-2-3-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.
cycy233-misllm-v8-2-3-v1-mkmlizer: warnings.warn(
cycy233-misllm-v8-2-3-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()
cycy233-misllm-v8-2-3-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v8-2-3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v8-2-3-v1-mkmlizer: Saving duration: 0.398s
cycy233-misllm-v8-2-3-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.370s
cycy233-misllm-v8-2-3-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v8-2-3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v8-2-3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v8-2-3-v1_reward
cycy233-misllm-v8-2-3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v8-2-3-v1_reward/config.json
cycy233-misllm-v8-2-3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v8-2-3-v1_reward/merges.txt
cycy233-misllm-v8-2-3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v8-2-3-v1_reward/special_tokens_map.json
cycy233-misllm-v8-2-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v8-2-3-v1_reward/tokenizer.json
cycy233-misllm-v8-2-3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v8-2-3-v1_reward/vocab.json
cycy233-misllm-v8-2-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v8-2-3-v1_reward/tokenizer_config.json
cycy233-misllm-v8-2-3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v8-2-3-v1_reward/reward.tensors
Job cycy233-misllm-v8-2-3-v1-mkmlizer completed after 72.87s with status: succeeded
Stopping job with name cycy233-misllm-v8-2-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 75.59s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v8-2-3-v1
Waiting for inference service cycy233-misllm-v8-2-3-v1 to be ready
Inference service cycy233-misllm-v8-2-3-v1 ready after 40.23214507102966s
Pipeline stage ISVCDeployer completed in 47.02s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.999772548675537s
Received healthy response to inference request in 0.9792137145996094s
Received healthy response to inference request in 1.062974214553833s
Received healthy response to inference request in 1.0864336490631104s
Received healthy response to inference request in 1.01511812210083s
5 requests
0 failed requests
5th percentile: 0.9863945960998535
10th percentile: 0.9935754776000977
20th percentile: 1.007937240600586
30th percentile: 1.0246893405914306
40th percentile: 1.0438317775726318
50th percentile: 1.062974214553833
60th percentile: 1.072357988357544
70th percentile: 1.0817417621612548
80th percentile: 1.269101428985596
90th percentile: 1.6344369888305665
95th percentile: 1.8171047687530515
99th percentile: 1.96323899269104
mean time: 1.228702449798584
Pipeline stage StressChecker completed in 6.75s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
cycy233-misllm-v8-2-3_v1 status is now deployed due to DeploymentManager action
cycy233-misllm-v8-2-3_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v8-2-3_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v8-2-3-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.64s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v8-2-3-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v8-2-3-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v8-2-3-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v8-2-3-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v8-2-3-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v8-2-3-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v8-2-3-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v8-2-3-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v8-2-3-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v8-2-3-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v8-2-3-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v8-2-3-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v8-2-3-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.61s
cycy233-misllm-v8-2-3_v1 status is now torndown due to DeploymentManager action