Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v6-6-3-v2-mkmlizer
Waiting for job on cycy233-misllm-v6-6-3-v2-mkmlizer to finish
cycy233-misllm-v6-6-3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v6-6-3-v2-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v6-6-3-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v6-6-3-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v6-6-3-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v6-6-3-v2-mkmlizer: ║ /___/ ║
cycy233-misllm-v6-6-3-v2-mkmlizer: ║ ║
cycy233-misllm-v6-6-3-v2-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v6-6-3-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v6-6-3-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v6-6-3-v2-mkmlizer: ║ ║
cycy233-misllm-v6-6-3-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v6-6-3-v2-mkmlizer: ║ belonging to: ║
cycy233-misllm-v6-6-3-v2-mkmlizer: ║ ║
cycy233-misllm-v6-6-3-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v6-6-3-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v6-6-3-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v6-6-3-v2-mkmlizer: ║ ║
cycy233-misllm-v6-6-3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v6-6-3-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.
cycy233-misllm-v6-6-3-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v6-6-3-v2-mkmlizer: Downloaded to shared memory in 21.598s
cycy233-misllm-v6-6-3-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v6-6-3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v6-6-3-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 83.42it/s]
Loading 0: 70%|███████ | 204/291 [00:02<00:00, 92.57it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 81.49it/s]
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v6-6-3-v2-mkmlizer: quantized model in 11.141s
cycy233-misllm-v6-6-3-v2-mkmlizer: Processed model cycy233/misllm_v6.6.3 in 33.722s
cycy233-misllm-v6-6-3-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v6-6-3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v6-6-3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v6-6-3-v2
cycy233-misllm-v6-6-3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v6-6-3-v2/config.json
cycy233-misllm-v6-6-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v6-6-3-v2/tokenizer.model
cycy233-misllm-v6-6-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v6-6-3-v2/tokenizer_config.json
cycy233-misllm-v6-6-3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v6-6-3-v2/special_tokens_map.json
cycy233-misllm-v6-6-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v6-6-3-v2/tokenizer.json
cycy233-misllm-v6-6-3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v6-6-3-v2/flywheel_model.0.safetensors
cycy233-misllm-v6-6-3-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v6-6-3-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.
cycy233-misllm-v6-6-3-v2-mkmlizer: warnings.warn(
cycy233-misllm-v6-6-3-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.
cycy233-misllm-v6-6-3-v2-mkmlizer: warnings.warn(
cycy233-misllm-v6-6-3-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.
cycy233-misllm-v6-6-3-v2-mkmlizer: warnings.warn(
cycy233-misllm-v6-6-3-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()
cycy233-misllm-v6-6-3-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v6-6-3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v6-6-3-v2-mkmlizer: Saving duration: 0.253s
cycy233-misllm-v6-6-3-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.469s
cycy233-misllm-v6-6-3-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v6-6-3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v6-6-3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v6-6-3-v2_reward
cycy233-misllm-v6-6-3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v6-6-3-v2_reward/special_tokens_map.json
cycy233-misllm-v6-6-3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v6-6-3-v2_reward/merges.txt
cycy233-misllm-v6-6-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v6-6-3-v2_reward/tokenizer_config.json
cycy233-misllm-v6-6-3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v6-6-3-v2_reward/config.json
cycy233-misllm-v6-6-3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v6-6-3-v2_reward/vocab.json
cycy233-misllm-v6-6-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v6-6-3-v2_reward/tokenizer.json
cycy233-misllm-v6-6-3-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v6-6-3-v2_reward/reward.tensors
Job cycy233-misllm-v6-6-3-v2-mkmlizer completed after 62.53s with status: succeeded
Stopping job with name cycy233-misllm-v6-6-3-v2-mkmlizer
Pipeline stage MKMLizer completed in 66.85s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.29s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v6-6-3-v2
Waiting for inference service cycy233-misllm-v6-6-3-v2 to be ready
Inference service cycy233-misllm-v6-6-3-v2 ready after 40.23123383522034s
Pipeline stage ISVCDeployer completed in 47.59s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.12939453125s
Received healthy response to inference request in 1.1471035480499268s
Received healthy response to inference request in 1.1689212322235107s
Received healthy response to inference request in 1.1933071613311768s
Received healthy response to inference request in 1.190627098083496s
5 requests
0 failed requests
5th percentile: 1.1514670848846436
10th percentile: 1.1558306217193604
20th percentile: 1.164557695388794
30th percentile: 1.1732624053955079
40th percentile: 1.1819447517395019
50th percentile: 1.190627098083496
60th percentile: 1.1916991233825684
70th percentile: 1.1927711486816406
80th percentile: 1.3805246353149416
90th percentile: 1.7549595832824707
95th percentile: 1.9421770572662351
99th percentile: 2.091951036453247
mean time: 1.365870714187622
Pipeline stage StressChecker completed in 7.45s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
cycy233-misllm-v6-6-3_v2 status is now deployed due to DeploymentManager action
cycy233-misllm-v6-6-3_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v6-6-3_v2
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v6-6-3-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.00s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v6-6-3-v2/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-6-3-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-6-3-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-6-3-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-6-3-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-6-3-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v6-6-3-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-6-3-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-6-3-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-6-3-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-6-3-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-6-3-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-6-3-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.33s
cycy233-misllm-v6-6-3_v2 status is now torndown due to DeploymentManager action