Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bcm-v0-c1-v2-mkmlizer
Waiting for job on cycy233-l3-bcm-v0-c1-v2-mkmlizer to finish
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ║ /___/ ║
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ║ ║
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ║ ║
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ║ ║
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ║ ║
cycy233-l3-bcm-v0-c1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bcm-v0-c1-v2-mkmlizer: Downloaded to shared memory in 17.542s
cycy233-l3-bcm-v0-c1-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bcm-v0-c1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bcm-v0-c1-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 69.73it/s]
Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 84.66it/s]
Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 120.62it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-bcm-v0-c1-v2-mkmlizer: quantized model in 19.323s
cycy233-l3-bcm-v0-c1-v2-mkmlizer: Processed model cycy233/L3-bcm-v0-c1 in 36.866s
cycy233-l3-bcm-v0-c1-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bcm-v0-c1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bcm-v0-c1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c1-v2
cycy233-l3-bcm-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c1-v2/tokenizer_config.json
cycy233-l3-bcm-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c1-v2/special_tokens_map.json
cycy233-l3-bcm-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c1-v2/config.json
cycy233-l3-bcm-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c1-v2/tokenizer.json
cycy233-l3-bcm-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c1-v2/flywheel_model.0.safetensors
cycy233-l3-bcm-v0-c1-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-bcm-v0-c1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-bcm-v0-c1-v2-mkmlizer: warnings.warn(
cycy233-l3-bcm-v0-c1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
cycy233-l3-bcm-v0-c1-v2-mkmlizer: warnings.warn(
cycy233-l3-bcm-v0-c1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-bcm-v0-c1-v2-mkmlizer: warnings.warn(
cycy233-l3-bcm-v0-c1-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-l3-bcm-v0-c1-v2-mkmlizer: warnings.warn(
cycy233-l3-bcm-v0-c1-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-l3-bcm-v0-c1-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-bcm-v0-c1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-bcm-v0-c1-v2-mkmlizer: Saving duration: 0.273s
cycy233-l3-bcm-v0-c1-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.738s
cycy233-l3-bcm-v0-c1-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-bcm-v0-c1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-bcm-v0-c1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-bcm-v0-c1-v2_reward
cycy233-l3-bcm-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c1-v2_reward/tokenizer_config.json
cycy233-l3-bcm-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c1-v2_reward/config.json
cycy233-l3-bcm-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-bcm-v0-c1-v2_reward/merges.txt
cycy233-l3-bcm-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c1-v2_reward/special_tokens_map.json
cycy233-l3-bcm-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c1-v2_reward/tokenizer.json
cycy233-l3-bcm-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c1-v2_reward/vocab.json
cycy233-l3-bcm-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-bcm-v0-c1-v2_reward/reward.tensors
Failed to get response for submission cycy233-l3-bcm-v0-c4_v1: ('http://cycy233-l3-bcm-v0-c4-v1-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:36384->127.0.0.1:8080: read: connection reset by peer\n')
Job cycy233-l3-bcm-v0-c1-v2-mkmlizer completed after 77.99s with status: succeeded
Stopping job with name cycy233-l3-bcm-v0-c1-v2-mkmlizer
Pipeline stage MKMLizer completed in 78.79s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bcm-v0-c1-v2
Waiting for inference service cycy233-l3-bcm-v0-c1-v2 to be ready
Inference service cycy233-l3-bcm-v0-c1-v2 ready after 70.33336234092712s
Pipeline stage ISVCDeployer completed in 77.03s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0209648609161377s
Received healthy response to inference request in 1.2469096183776855s
Received healthy response to inference request in 1.2455565929412842s
Received healthy response to inference request in 1.2668657302856445s
Received healthy response to inference request in 1.258533239364624s
5 requests
0 failed requests
5th percentile: 1.2458271980285645
10th percentile: 1.2460978031158447
20th percentile: 1.2466390132904053
30th percentile: 1.2492343425750732
40th percentile: 1.2538837909698486
50th percentile: 1.258533239364624
60th percentile: 1.2618662357330321
70th percentile: 1.2651992321014405
80th percentile: 1.4176855564117432
90th percentile: 1.7193252086639406
95th percentile: 1.870145034790039
99th percentile: 1.990800895690918
mean time: 1.407766008377075
Pipeline stage StressChecker completed in 7.77s
cycy233-l3-bcm-v0-c1_v2 status is now deployed due to DeploymentManager action
cycy233-l3-bcm-v0-c1_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-bcm-v0-c1_v2
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-bcm-v0-c1-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.88s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-bcm-v0-c1-v2/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bcm-v0-c1-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-bcm-v0-c1-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bcm-v0-c1-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bcm-v0-c1-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-bcm-v0-c1-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bcm-v0-c1-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-bcm-v0-c1-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-bcm-v0-c1-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bcm-v0-c1-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bcm-v0-c1-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bcm-v0-c1-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.23s
cycy233-l3-bcm-v0-c1_v2 status is now torndown due to DeploymentManager action