Running pipeline stage MKMLizer
Starting job with name cycy233-l3-base-v5-e2-0-v3-mkmlizer
Waiting for job on cycy233-l3-base-v5-e2-0-v3-mkmlizer to finish
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ║ _____ __ __ ║
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ║ /___/ ║
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ║ ║
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ║ ║
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ║ belonging to: ║
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ║ ║
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ║ ║
cycy233-l3-base-v5-e2-0-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-base-v5-e2-0-v3-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-l3-base-v5-e2-0-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-l3-base-v5-e2-0-v3-mkmlizer: Downloaded to shared memory in 17.531s
cycy233-l3-base-v5-e2-0-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-base-v5-e2-0-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-base-v5-e2-0-v3-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 66.36it/s]
Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 78.46it/s]
Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 114.29it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-base-v5-e2-0-v3-mkmlizer: quantized model in 23.759s
cycy233-l3-base-v5-e2-0-v3-mkmlizer: Processed model cycy233/L3-base-v5-e2.0 in 43.782s
cycy233-l3-base-v5-e2-0-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-base-v5-e2-0-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-base-v5-e2-0-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-base-v5-e2-0-v3
cycy233-l3-base-v5-e2-0-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-base-v5-e2-0-v3/config.json
cycy233-l3-base-v5-e2-0-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-base-v5-e2-0-v3/tokenizer_config.json
cycy233-l3-base-v5-e2-0-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-base-v5-e2-0-v3/special_tokens_map.json
cycy233-l3-base-v5-e2-0-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-base-v5-e2-0-v3/tokenizer.json
cycy233-l3-base-v5-e2-0-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-base-v5-e2-0-v3/flywheel_model.0.safetensors
cycy233-l3-base-v5-e2-0-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-base-v5-e2-0-v3-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-l3-base-v5-e2-0-v3-mkmlizer: warnings.warn(
cycy233-l3-base-v5-e2-0-v3-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-l3-base-v5-e2-0-v3-mkmlizer: warnings.warn(
cycy233-l3-base-v5-e2-0-v3-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-l3-base-v5-e2-0-v3-mkmlizer: warnings.warn(
cycy233-l3-base-v5-e2-0-v3-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-l3-base-v5-e2-0-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-base-v5-e2-0-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-base-v5-e2-0-v3-mkmlizer: Saving duration: 0.421s
cycy233-l3-base-v5-e2-0-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.399s
cycy233-l3-base-v5-e2-0-v3-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-base-v5-e2-0-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-base-v5-e2-0-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-base-v5-e2-0-v3_reward
cycy233-l3-base-v5-e2-0-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-base-v5-e2-0-v3_reward/config.json
cycy233-l3-base-v5-e2-0-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-base-v5-e2-0-v3_reward/special_tokens_map.json
cycy233-l3-base-v5-e2-0-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-base-v5-e2-0-v3_reward/tokenizer_config.json
cycy233-l3-base-v5-e2-0-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-base-v5-e2-0-v3_reward/vocab.json
cycy233-l3-base-v5-e2-0-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-base-v5-e2-0-v3_reward/merges.txt
cycy233-l3-base-v5-e2-0-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-base-v5-e2-0-v3_reward/tokenizer.json
cycy233-l3-base-v5-e2-0-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-base-v5-e2-0-v3_reward/reward.tensors
Retrying (%r) after connection broken by '%r': %s
Job cycy233-l3-base-v5-e2-0-v3-mkmlizer completed after 73.72s with status: succeeded
Stopping job with name cycy233-l3-base-v5-e2-0-v3-mkmlizer
Pipeline stage MKMLizer completed in 74.15s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-base-v5-e2-0-v3
Connection pool is full, discarding connection: %s
Waiting for inference service cycy233-l3-base-v5-e2-0-v3 to be ready
Inference service cycy233-l3-base-v5-e2-0-v3 ready after 82.86295366287231s
Pipeline stage ISVCDeployer completed in 88.58s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0326015949249268s
Received healthy response to inference request in 1.1118566989898682s
Received healthy response to inference request in 0.815584659576416s
Received healthy response to inference request in 0.8898389339447021s
Received healthy response to inference request in 1.1454339027404785s
5 requests
0 failed requests
5th percentile: 0.8304355144500732
10th percentile: 0.8452863693237305
20th percentile: 0.8749880790710449
30th percentile: 0.9342424869537354
40th percentile: 1.0230495929718018
50th percentile: 1.1118566989898682
60th percentile: 1.1252875804901123
70th percentile: 1.1387184619903565
80th percentile: 1.3228674411773684
90th percentile: 1.6777345180511476
95th percentile: 1.8551680564880368
99th percentile: 1.9971148872375488
mean time: 1.1990631580352784
Pipeline stage StressChecker completed in 6.87s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.09s
cycy233-l3-base-v5-e2-0_v3 status is now deployed due to DeploymentManager action
cycy233-l3-base-v5-e2-0_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-base-v5-e2-0_v3
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-base-v5-e2-0-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.26s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-base-v5-e2-0-v3/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-base-v5-e2-0-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-base-v5-e2-0-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-base-v5-e2-0-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-base-v5-e2-0-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-base-v5-e2-0-v3_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v5-e2-0-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v5-e2-0-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v5-e2-0-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v5-e2-0-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v5-e2-0-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-base-v5-e2-0-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.44s
cycy233-l3-base-v5-e2-0_v3 status is now torndown due to DeploymentManager action