Running pipeline stage MKMLizer
Starting job with name hastagaras-markites-2-v2-mkmlizer
Waiting for job on hastagaras-markites-2-v2-mkmlizer to finish
hastagaras-markites-2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-markites-2-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-markites-2-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-markites-2-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-markites-2-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-markites-2-v2-mkmlizer: ║ /___/ ║
hastagaras-markites-2-v2-mkmlizer: ║ ║
hastagaras-markites-2-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-markites-2-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-markites-2-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-markites-2-v2-mkmlizer: ║ ║
hastagaras-markites-2-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-markites-2-v2-mkmlizer: ║ belonging to: ║
hastagaras-markites-2-v2-mkmlizer: ║ ║
hastagaras-markites-2-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-markites-2-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-markites-2-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-markites-2-v2-mkmlizer: ║ ║
hastagaras-markites-2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-markites-2-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.
hastagaras-markites-2-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-markites-2-v2-mkmlizer: Downloaded to shared memory in 17.168s
hastagaras-markites-2-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-markites-2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-markites-2-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 2/291 [00:03<09:33, 1.98s/it]
Loading 0: 8%|▊ | 22/291 [00:04<00:36, 7.43it/s]
Loading 0: 14%|█▍ | 42/291 [00:04<00:15, 16.46it/s]
Loading 0: 21%|██ | 60/291 [00:04<00:09, 23.16it/s]
Loading 0: 29%|██▉ | 85/291 [00:04<00:05, 39.45it/s]
Loading 0: 36%|███▌ | 104/291 [00:04<00:03, 53.37it/s]
Loading 0: 42%|████▏ | 123/291 [00:04<00:02, 69.40it/s]
Loading 0: 51%|█████ | 148/291 [00:04<00:01, 94.04it/s]
Loading 0: 58%|█████▊ | 168/291 [00:05<00:01, 77.31it/s]
Loading 0: 66%|██████▋ | 193/291 [00:05<00:00, 101.31it/s]
Loading 0: 73%|███████▎ | 213/291 [00:05<00:00, 117.16it/s]
Loading 0: 82%|████████▏ | 238/291 [00:05<00:00, 142.69it/s]
Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 154.26it/s]
Loading 0: 96%|█████████▌| 279/291 [00:06<00:00, 105.18it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-markites-2-v2-mkmlizer: quantized model in 17.192s
hastagaras-markites-2-v2-mkmlizer: Processed model Hastagaras/Markites-2 in 35.273s
hastagaras-markites-2-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-markites-2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-markites-2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-markites-2-v2
hastagaras-markites-2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-markites-2-v2/config.json
hastagaras-markites-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-markites-2-v2/tokenizer.json
hastagaras-markites-2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-markites-2-v2/special_tokens_map.json
hastagaras-markites-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-markites-2-v2/tokenizer_config.json
hastagaras-markites-2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-markites-2-v2/flywheel_model.0.safetensors
hastagaras-markites-2-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-markites-2-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.
hastagaras-markites-2-v2-mkmlizer: warnings.warn(
hastagaras-markites-2-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.
hastagaras-markites-2-v2-mkmlizer: warnings.warn(
hastagaras-markites-2-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.
hastagaras-markites-2-v2-mkmlizer: warnings.warn(
hastagaras-markites-2-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()
hastagaras-markites-2-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-markites-2-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-markites-2-v2-mkmlizer: Saving duration: 0.215s
hastagaras-markites-2-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.219s
hastagaras-markites-2-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-markites-2-v2_reward/reward.tensors
Job hastagaras-markites-2-v2-mkmlizer completed after 62.67s with status: succeeded
Stopping job with name hastagaras-markites-2-v2-mkmlizer
Pipeline stage MKMLizer completed in 66.86s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-markites-2-v2
Waiting for inference service hastagaras-markites-2-v2 to be ready
Inference service hastagaras-markites-2-v2 ready after 40.36242747306824s
Pipeline stage ISVCDeployer completed in 47.32s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.172250747680664s
Received healthy response to inference request in 1.2388739585876465s
Received healthy response to inference request in 1.250666618347168s
Received healthy response to inference request in 1.2386088371276855s
Received healthy response to inference request in 1.139096736907959s
5 requests
0 failed requests
5th percentile: 1.1589991569519043
10th percentile: 1.1789015769958495
20th percentile: 1.2187064170837403
30th percentile: 1.2386618614196778
40th percentile: 1.2387679100036622
50th percentile: 1.2388739585876465
60th percentile: 1.243591022491455
70th percentile: 1.2483080863952636
80th percentile: 1.4349834442138674
90th percentile: 1.8036170959472657
95th percentile: 1.9879339218139647
99th percentile: 2.135387382507324
mean time: 1.4078993797302246
Pipeline stage StressChecker completed in 7.79s
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
hastagaras-markites-2_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-markites-2_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-markites-2_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-markites-2-v2 is running
Tearing down inference service hastagaras-markites-2-v2
Toredown service hastagaras-markites-2-v2
Pipeline stage ISVCDeleter completed in 4.11s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-markites-2-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-markites-2-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-markites-2-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-markites-2-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-markites-2-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-markites-2-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-markites-2-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-markites-2-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-markites-2-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-markites-2-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-markites-2-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-markites-2-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.37s
hastagaras-markites-2_v2 status is now torndown due to DeploymentManager action