Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v5-0-v1-mkmlizer
Waiting for job on cycy233-misllm-v5-0-v1-mkmlizer to finish
cycy233-misllm-v5-0-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v5-0-v1-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v5-0-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v5-0-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v5-0-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v5-0-v1-mkmlizer: ║ /___/ ║
cycy233-misllm-v5-0-v1-mkmlizer: ║ ║
cycy233-misllm-v5-0-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v5-0-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v5-0-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v5-0-v1-mkmlizer: ║ ║
cycy233-misllm-v5-0-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v5-0-v1-mkmlizer: ║ belonging to: ║
cycy233-misllm-v5-0-v1-mkmlizer: ║ ║
cycy233-misllm-v5-0-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v5-0-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v5-0-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v5-0-v1-mkmlizer: ║ ║
cycy233-misllm-v5-0-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v5-0-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-v5-0-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v5-0-v1-mkmlizer: Downloaded to shared memory in 27.253s
cycy233-misllm-v5-0-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v5-0-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v5-0-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 34%|███▎ | 98/291 [00:00<00:01, 98.66it/s]
Loading 0: 70%|███████ | 204/291 [00:01<00:00, 105.78it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 86.16it/s]
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v5-0-v1-mkmlizer: quantized model in 13.193s
cycy233-misllm-v5-0-v1-mkmlizer: Processed model cycy233/misllm_v5.0 in 41.480s
cycy233-misllm-v5-0-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v5-0-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v5-0-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v5-0-v1
cycy233-misllm-v5-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v5-0-v1/tokenizer_config.json
cycy233-misllm-v5-0-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v5-0-v1/config.json
cycy233-misllm-v5-0-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v5-0-v1/special_tokens_map.json
cycy233-misllm-v5-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v5-0-v1/tokenizer.model
cycy233-misllm-v5-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v5-0-v1/tokenizer.json
cycy233-misllm-v5-0-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v5-0-v1/flywheel_model.0.safetensors
cycy233-misllm-v5-0-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v5-0-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-v5-0-v1-mkmlizer: warnings.warn(
Failed to get response for submission blend_sosin_2024-05-22: ('http://pointwise-ranking-qunil-v2-predictor-default.tenant-chairesearch-test.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
cycy233-misllm-v5-0-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-v5-0-v1-mkmlizer: warnings.warn(
cycy233-misllm-v5-0-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-v5-0-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v5-0-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v5-0-v1-mkmlizer: Saving duration: 0.244s
cycy233-misllm-v5-0-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.889s
cycy233-misllm-v5-0-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v5-0-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v5-0-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v5-0-v1_reward
cycy233-misllm-v5-0-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v5-0-v1_reward/config.json
cycy233-misllm-v5-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v5-0-v1_reward/tokenizer_config.json
cycy233-misllm-v5-0-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v5-0-v1_reward/merges.txt
cycy233-misllm-v5-0-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v5-0-v1_reward/special_tokens_map.json
cycy233-misllm-v5-0-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v5-0-v1_reward/vocab.json
cycy233-misllm-v5-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v5-0-v1_reward/tokenizer.json
cycy233-misllm-v5-0-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v5-0-v1_reward/reward.tensors
Job cycy233-misllm-v5-0-v1-mkmlizer completed after 62.78s with status: succeeded
Stopping job with name cycy233-misllm-v5-0-v1-mkmlizer
Pipeline stage MKMLizer completed in 68.09s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v5-0-v1
Waiting for inference service cycy233-misllm-v5-0-v1 to be ready
Failed to get response for submission blend_fatul_2024-05-22: ('http://pointwise-ranking-qunil-v2-predictor-default.tenant-chairesearch-test.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service cycy233-misllm-v5-0-v1 ready after 30.197879791259766s
Pipeline stage ISVCDeployer completed in 38.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4023792743682861s
Received healthy response to inference request in 0.9275310039520264s
Received healthy response to inference request in 1.149827003479004s
Received healthy response to inference request in 0.8396096229553223s
Received healthy response to inference request in 0.9589405059814453s
5 requests
0 failed requests
5th percentile: 0.857193899154663
10th percentile: 0.8747781753540039
20th percentile: 0.9099467277526856
30th percentile: 0.9338129043579102
40th percentile: 0.9463767051696778
50th percentile: 0.9589405059814453
60th percentile: 1.0352951049804688
70th percentile: 1.1116497039794921
80th percentile: 1.2003374576568604
90th percentile: 1.3013583660125732
95th percentile: 1.3518688201904296
99th percentile: 1.3922771835327148
mean time: 1.0556574821472169
Pipeline stage StressChecker completed in 5.90s
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-v5-0_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cycy233-misllm-v5-0_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v5-0_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v5-0-v1 is running
Tearing down inference service cycy233-misllm-v5-0-v1
Toredown service cycy233-misllm-v5-0-v1
Pipeline stage ISVCDeleter completed in 4.44s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v5-0-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-0-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-0-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-0-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-0-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-0-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v5-0-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-0-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-0-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-0-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-0-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-0-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-0-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.46s
cycy233-misllm-v5-0_v1 status is now torndown due to DeploymentManager action