Running pipeline stage MKMLizer
Starting job with name chaser-cz-share-qlora-out-v2-mkmlizer
Waiting for job on chaser-cz-share-qlora-out-v2-mkmlizer to finish
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
chaser-cz-share-qlora-out-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaser-cz-share-qlora-out-v2-mkmlizer: ║ _____ __ __ ║
chaser-cz-share-qlora-out-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaser-cz-share-qlora-out-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaser-cz-share-qlora-out-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaser-cz-share-qlora-out-v2-mkmlizer: ║ /___/ ║
chaser-cz-share-qlora-out-v2-mkmlizer: ║ ║
chaser-cz-share-qlora-out-v2-mkmlizer: ║ Version: 0.8.14 ║
chaser-cz-share-qlora-out-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaser-cz-share-qlora-out-v2-mkmlizer: ║ https://mk1.ai ║
chaser-cz-share-qlora-out-v2-mkmlizer: ║ ║
chaser-cz-share-qlora-out-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaser-cz-share-qlora-out-v2-mkmlizer: ║ belonging to: ║
chaser-cz-share-qlora-out-v2-mkmlizer: ║ ║
chaser-cz-share-qlora-out-v2-mkmlizer: ║ Chai Research Corp. ║
chaser-cz-share-qlora-out-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaser-cz-share-qlora-out-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaser-cz-share-qlora-out-v2-mkmlizer: ║ ║
chaser-cz-share-qlora-out-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaser-cz-share-qlora-out-v2-mkmlizer: Downloaded to shared memory in 41.012s
chaser-cz-share-qlora-out-v2-mkmlizer: quantizing model to /dev/shm/model_cache
chaser-cz-share-qlora-out-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
chaser-cz-share-qlora-out-v2-mkmlizer: quantized model in 14.707s
chaser-cz-share-qlora-out-v2-mkmlizer: Processed model Chaser-cz/share-qlora-out in 55.719s
chaser-cz-share-qlora-out-v2-mkmlizer: creating bucket guanaco-mkml-models
chaser-cz-share-qlora-out-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaser-cz-share-qlora-out-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaser-cz-share-qlora-out-v2
chaser-cz-share-qlora-out-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaser-cz-share-qlora-out-v2/config.json
chaser-cz-share-qlora-out-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaser-cz-share-qlora-out-v2/tokenizer_config.json
chaser-cz-share-qlora-out-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaser-cz-share-qlora-out-v2/special_tokens_map.json
chaser-cz-share-qlora-out-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaser-cz-share-qlora-out-v2/tokenizer.json
chaser-cz-share-qlora-out-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaser-cz-share-qlora-out-v2/tokenizer.model
chaser-cz-share-qlora-out-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaser-cz-share-qlora-out-v2/flywheel_model.0.safetensors
chaser-cz-share-qlora-out-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
chaser-cz-share-qlora-out-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 34%|███▎ | 98/291 [00:00<00:01, 100.08it/s]
Loading 0: 70%|███████ | 204/291 [00:01<00:00, 108.93it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 85.72it/s]
/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.
chaser-cz-share-qlora-out-v2-mkmlizer: warnings.warn(
chaser-cz-share-qlora-out-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`.
chaser-cz-share-qlora-out-v2-mkmlizer: warnings.warn(
chaser-cz-share-qlora-out-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.
chaser-cz-share-qlora-out-v2-mkmlizer: warnings.warn(
chaser-cz-share-qlora-out-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.
chaser-cz-share-qlora-out-v2-mkmlizer: warnings.warn(
chaser-cz-share-qlora-out-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()
chaser-cz-share-qlora-out-v2-mkmlizer: return self.fget.__get__(instance, owner)()
chaser-cz-share-qlora-out-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaser-cz-share-qlora-out-v2-mkmlizer: Saving duration: 1.910s
chaser-cz-share-qlora-out-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 9.591s
chaser-cz-share-qlora-out-v2-mkmlizer: creating bucket guanaco-reward-models
chaser-cz-share-qlora-out-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaser-cz-share-qlora-out-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaser-cz-share-qlora-out-v2_reward
chaser-cz-share-qlora-out-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaser-cz-share-qlora-out-v2_reward/config.json
chaser-cz-share-qlora-out-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaser-cz-share-qlora-out-v2_reward/special_tokens_map.json
chaser-cz-share-qlora-out-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaser-cz-share-qlora-out-v2_reward/tokenizer_config.json
chaser-cz-share-qlora-out-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaser-cz-share-qlora-out-v2_reward/vocab.json
chaser-cz-share-qlora-out-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaser-cz-share-qlora-out-v2_reward/merges.txt
chaser-cz-share-qlora-out-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaser-cz-share-qlora-out-v2_reward/tokenizer.json
chaser-cz-share-qlora-out-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaser-cz-share-qlora-out-v2_reward/reward.tensors
Job chaser-cz-share-qlora-out-v2-mkmlizer completed after 157.36s with status: succeeded
Stopping job with name chaser-cz-share-qlora-out-v2-mkmlizer
Pipeline stage MKMLizer completed in 158.39s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service chaser-cz-share-qlora-out-v2
Waiting for inference service chaser-cz-share-qlora-out-v2 to be ready
Inference service chaser-cz-share-qlora-out-v2 ready after 40.205403327941895s
Pipeline stage ISVCDeployer completed in 47.27s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4377853870391846s
Received healthy response to inference request in 1.0662424564361572s
Received healthy response to inference request in 3.733755350112915s
Received healthy response to inference request in 1.1832661628723145s
Received healthy response to inference request in 1.1753740310668945s
5 requests
0 failed requests
5th percentile: 1.0880687713623047
10th percentile: 1.1098950862884522
20th percentile: 1.153547716140747
30th percentile: 1.1769524574279786
40th percentile: 1.1801093101501465
50th percentile: 1.1832661628723145
60th percentile: 1.6850738525390625
70th percentile: 2.1868815422058105
80th percentile: 2.6969793796539308
90th percentile: 3.215367364883423
95th percentile: 3.474561357498169
99th percentile: 3.681916551589966
mean time: 1.9192846775054933
Pipeline stage StressChecker completed in 10.41s
chaser-cz-share-qlora-out_v2 status is now deployed due to DeploymentManager action
chaser-cz-share-qlora-out_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaser-cz-share-qlora-out_v2
Running pipeline stage ISVCDeleter
Checking if service chaser-cz-share-qlora-out-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.14s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaser-cz-share-qlora-out-v2/config.json from bucket guanaco-mkml-models
Deleting key chaser-cz-share-qlora-out-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaser-cz-share-qlora-out-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaser-cz-share-qlora-out-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaser-cz-share-qlora-out-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key chaser-cz-share-qlora-out-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaser-cz-share-qlora-out-v2_reward/config.json from bucket guanaco-reward-models
Deleting key chaser-cz-share-qlora-out-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaser-cz-share-qlora-out-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaser-cz-share-qlora-out-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaser-cz-share-qlora-out-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaser-cz-share-qlora-out-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaser-cz-share-qlora-out-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.48s
chaser-cz-share-qlora-out_v2 status is now torndown due to DeploymentManager action