Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v6-5-3-v2-mkmlizer
Waiting for job on cycy233-misllm-v6-5-3-v2-mkmlizer to finish
cycy233-misllm-v6-5-3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v6-5-3-v2-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v6-5-3-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v6-5-3-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v6-5-3-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v6-5-3-v2-mkmlizer: ║ /___/ ║
cycy233-misllm-v6-5-3-v2-mkmlizer: ║ ║
cycy233-misllm-v6-5-3-v2-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v6-5-3-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v6-5-3-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v6-5-3-v2-mkmlizer: ║ ║
cycy233-misllm-v6-5-3-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v6-5-3-v2-mkmlizer: ║ belonging to: ║
cycy233-misllm-v6-5-3-v2-mkmlizer: ║ ║
cycy233-misllm-v6-5-3-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v6-5-3-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v6-5-3-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v6-5-3-v2-mkmlizer: ║ ║
cycy233-misllm-v6-5-3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v6-5-3-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-v6-5-3-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v6-5-3-v2-mkmlizer: Downloaded to shared memory in 32.355s
cycy233-misllm-v6-5-3-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v6-5-3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v6-5-3-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 34%|███▎ | 98/291 [00:01<00:01, 97.00it/s]
Loading 0: 70%|███████ | 204/291 [00:01<00:00, 108.99it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 90.56it/s]
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v6-5-3-v2-mkmlizer: quantized model in 11.207s
cycy233-misllm-v6-5-3-v2-mkmlizer: Processed model cycy233/misllm_v6.5.3 in 44.445s
cycy233-misllm-v6-5-3-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v6-5-3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v6-5-3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v6-5-3-v2
cycy233-misllm-v6-5-3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v6-5-3-v2/config.json
cycy233-misllm-v6-5-3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v6-5-3-v2/special_tokens_map.json
cycy233-misllm-v6-5-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v6-5-3-v2/tokenizer_config.json
cycy233-misllm-v6-5-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v6-5-3-v2/tokenizer.model
cycy233-misllm-v6-5-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v6-5-3-v2/tokenizer.json
cycy233-misllm-v6-5-3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v6-5-3-v2/flywheel_model.0.safetensors
cycy233-misllm-v6-5-3-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v6-5-3-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-v6-5-3-v2-mkmlizer: warnings.warn(
cycy233-misllm-v6-5-3-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-v6-5-3-v2-mkmlizer: warnings.warn(
cycy233-misllm-v6-5-3-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-v6-5-3-v2-mkmlizer: warnings.warn(
cycy233-misllm-v6-5-3-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-v6-5-3-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v6-5-3-v2-mkmlizer: Saving duration: 0.290s
cycy233-misllm-v6-5-3-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.208s
cycy233-misllm-v6-5-3-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v6-5-3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v6-5-3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v6-5-3-v2_reward
cycy233-misllm-v6-5-3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v6-5-3-v2_reward/config.json
cycy233-misllm-v6-5-3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v6-5-3-v2_reward/special_tokens_map.json
cycy233-misllm-v6-5-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v6-5-3-v2_reward/tokenizer_config.json
cycy233-misllm-v6-5-3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v6-5-3-v2_reward/merges.txt
cycy233-misllm-v6-5-3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v6-5-3-v2_reward/vocab.json
cycy233-misllm-v6-5-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v6-5-3-v2_reward/tokenizer.json
cycy233-misllm-v6-5-3-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v6-5-3-v2_reward/reward.tensors
Job cycy233-misllm-v6-5-3-v2-mkmlizer completed after 74.41s with status: succeeded
Stopping job with name cycy233-misllm-v6-5-3-v2-mkmlizer
Pipeline stage MKMLizer completed in 75.87s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v6-5-3-v2
Waiting for inference service cycy233-misllm-v6-5-3-v2 to be ready
Inference service cycy233-misllm-v6-5-3-v2 ready after 40.249481439590454s
Pipeline stage ISVCDeployer completed in 46.74s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.017329692840576s
Received healthy response to inference request in 1.1727783679962158s
Received healthy response to inference request in 1.1629834175109863s
Received healthy response to inference request in 1.1475811004638672s
Received healthy response to inference request in 1.205467939376831s
5 requests
0 failed requests
5th percentile: 1.150661563873291
10th percentile: 1.1537420272827148
20th percentile: 1.1599029541015624
30th percentile: 1.1649424076080321
40th percentile: 1.168860387802124
50th percentile: 1.1727783679962158
60th percentile: 1.185854196548462
70th percentile: 1.198930025100708
80th percentile: 1.3678402900695803
90th percentile: 1.6925849914550781
95th percentile: 1.854957342147827
99th percentile: 1.9848552227020264
mean time: 1.3412281036376954
Pipeline stage StressChecker completed in 7.35s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.21s
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-v6-5-3_v2 status is now deployed due to DeploymentManager action
cycy233-misllm-v6-5-3_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v6-5-3_v2
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v6-5-3-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.40s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v6-5-3-v2/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-5-3-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-5-3-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-5-3-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-5-3-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-5-3-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v6-5-3-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-5-3-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-5-3-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-5-3-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-5-3-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-5-3-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-5-3-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.78s
cycy233-misllm-v6-5-3_v2 status is now torndown due to DeploymentManager action