Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v6-8-2-5-v2-mkmlizer
Waiting for job on cycy233-misllm-v6-8-2-5-v2-mkmlizer to finish
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ║ /___/ ║
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ║ ║
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ║ ║
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ║ belonging to: ║
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ║ ║
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ║ ║
cycy233-misllm-v6-8-2-5-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v6-8-2-5-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-v6-8-2-5-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v6-8-2-5-v2-mkmlizer: Downloaded to shared memory in 18.368s
cycy233-misllm-v6-8-2-5-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v6-8-2-5-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v6-8-2-5-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 95.47it/s]
Loading 0: 70%|███████ | 204/291 [00:01<00:00, 107.87it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 85.88it/s]
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v6-8-2-5-v2-mkmlizer: quantized model in 14.753s
cycy233-misllm-v6-8-2-5-v2-mkmlizer: Processed model cycy233/misllm_v6.8.2.5 in 35.475s
cycy233-misllm-v6-8-2-5-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v6-8-2-5-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v6-8-2-5-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v6-8-2-5-v2
cycy233-misllm-v6-8-2-5-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v6-8-2-5-v2/config.json
cycy233-misllm-v6-8-2-5-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v6-8-2-5-v2/special_tokens_map.json
cycy233-misllm-v6-8-2-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v6-8-2-5-v2/tokenizer.model
cycy233-misllm-v6-8-2-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v6-8-2-5-v2/tokenizer_config.json
cycy233-misllm-v6-8-2-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v6-8-2-5-v2/tokenizer.json
cycy233-misllm-v6-8-2-5-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v6-8-2-5-v2/flywheel_model.0.safetensors
cycy233-misllm-v6-8-2-5-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v6-8-2-5-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-v6-8-2-5-v2-mkmlizer: warnings.warn(
cycy233-misllm-v6-8-2-5-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-v6-8-2-5-v2-mkmlizer: warnings.warn(
cycy233-misllm-v6-8-2-5-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-v6-8-2-5-v2-mkmlizer: warnings.warn(
cycy233-misllm-v6-8-2-5-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-v6-8-2-5-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v6-8-2-5-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v6-8-2-5-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v6-8-2-5-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v6-8-2-5-v2_reward
cycy233-misllm-v6-8-2-5-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v6-8-2-5-v2_reward/special_tokens_map.json
cycy233-misllm-v6-8-2-5-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v6-8-2-5-v2_reward/config.json
cycy233-misllm-v6-8-2-5-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v6-8-2-5-v2_reward/tokenizer_config.json
cycy233-misllm-v6-8-2-5-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v6-8-2-5-v2_reward/vocab.json
cycy233-misllm-v6-8-2-5-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v6-8-2-5-v2_reward/merges.txt
cycy233-misllm-v6-8-2-5-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v6-8-2-5-v2_reward/tokenizer.json
cycy233-misllm-v6-8-2-5-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v6-8-2-5-v2_reward/reward.tensors
Job cycy233-misllm-v6-8-2-5-v2-mkmlizer completed after 62.89s with status: succeeded
Stopping job with name cycy233-misllm-v6-8-2-5-v2-mkmlizer
Pipeline stage MKMLizer completed in 66.60s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v6-8-2-5-v2
Waiting for inference service cycy233-misllm-v6-8-2-5-v2 to be ready
Inference service cycy233-misllm-v6-8-2-5-v2 ready after 30.172035932540894s
Pipeline stage ISVCDeployer completed in 38.58s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0575993061065674s
Received healthy response to inference request in 1.0644590854644775s
Received healthy response to inference request in 1.1724576950073242s
Received healthy response to inference request in 1.1637916564941406s
Received healthy response to inference request in 1.1680564880371094s
5 requests
0 failed requests
5th percentile: 1.0843255996704102
10th percentile: 1.1041921138763429
20th percentile: 1.143925142288208
30th percentile: 1.1646446228027343
40th percentile: 1.1663505554199218
50th percentile: 1.1680564880371094
60th percentile: 1.1698169708251953
70th percentile: 1.1715774536132812
80th percentile: 1.349486017227173
90th percentile: 1.7035426616668703
95th percentile: 1.8805709838867186
99th percentile: 2.0221936416625974
mean time: 1.3252728462219239
Pipeline stage StressChecker completed in 7.21s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
cycy233-misllm-v6-8-2-5_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cycy233-misllm-v6-8-2-5_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v6-8-2-5_v2
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v6-8-2-5-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.17s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v6-8-2-5-v2/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-8-2-5-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-8-2-5-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-8-2-5-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-8-2-5-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-8-2-5-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v6-8-2-5-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-8-2-5-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-8-2-5-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-8-2-5-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-8-2-5-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-8-2-5-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-8-2-5-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.19s
cycy233-misllm-v6-8-2-5_v2 status is now torndown due to DeploymentManager action