Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bcm-v0-c4-v1-mkmlizer
Waiting for job on cycy233-l3-bcm-v0-c4-v1-mkmlizer to finish
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v61: ('http://mistralai-mixtral-8x7b-3473-v61-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: connection timeout')
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ║ /___/ ║
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-bcm-v0-c4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bcm-v0-c4-v1-mkmlizer: Downloaded to shared memory in 32.310s
cycy233-l3-bcm-v0-c4-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bcm-v0-c4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bcm-v0-c4-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 60.06it/s]
Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 69.61it/s]
Loading 0: 99%|█████████▊| 287/291 [00:03<00:00, 99.43it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-bcm-v0-c4-v1-mkmlizer: quantized model in 30.626s
cycy233-l3-bcm-v0-c4-v1-mkmlizer: Processed model cycy233/L3-bcm-v0-c4 in 62.936s
cycy233-l3-bcm-v0-c4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bcm-v0-c4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bcm-v0-c4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c4-v1
cycy233-l3-bcm-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c4-v1/special_tokens_map.json
cycy233-l3-bcm-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c4-v1/tokenizer_config.json
cycy233-l3-bcm-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c4-v1/config.json
cycy233-l3-bcm-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c4-v1/tokenizer.json
cycy233-l3-bcm-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c4-v1/flywheel_model.0.safetensors
cycy233-l3-bcm-v0-c4-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-bcm-v0-c4-v1-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-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-bcm-v0-c4-v1-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-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-bcm-v0-c4-v1-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-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-bcm-v0-c4-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-l3-bcm-v0-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-bcm-v0-c4-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-l3-bcm-v0-c4-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-bcm-v0-c4-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-bcm-v0-c4-v1-mkmlizer: Saving duration: 0.564s
cycy233-l3-bcm-v0-c4-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.679s
cycy233-l3-bcm-v0-c4-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-bcm-v0-c4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-bcm-v0-c4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-bcm-v0-c4-v1_reward
cycy233-l3-bcm-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c4-v1_reward/config.json
cycy233-l3-bcm-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-bcm-v0-c4-v1_reward/merges.txt
cycy233-l3-bcm-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c4-v1_reward/tokenizer_config.json
cycy233-l3-bcm-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c4-v1_reward/special_tokens_map.json
cycy233-l3-bcm-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c4-v1_reward/vocab.json
cycy233-l3-bcm-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c4-v1_reward/tokenizer.json
cycy233-l3-bcm-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-bcm-v0-c4-v1_reward/reward.tensors
Job cycy233-l3-bcm-v0-c4-v1-mkmlizer completed after 94.17s with status: succeeded
Stopping job with name cycy233-l3-bcm-v0-c4-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bcm-v0-c4-v1
Waiting for inference service cycy233-l3-bcm-v0-c4-v1 to be ready
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
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service cycy233-l3-bcm-v0-c4-v1 ready after 40.39239311218262s
Pipeline stage ISVCDeployer completed in 47.33s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2464301586151123s
Received healthy response to inference request in 1.2650866508483887s
Received healthy response to inference request in 1.2817754745483398s
Received healthy response to inference request in 1.2558424472808838s
Received healthy response to inference request in 1.2604281902313232s
5 requests
0 failed requests
5th percentile: 1.2567595958709716
10th percentile: 1.2576767444610595
20th percentile: 1.2595110416412354
30th percentile: 1.2613598823547363
40th percentile: 1.2632232666015626
50th percentile: 1.2650866508483887
60th percentile: 1.2717621803283692
70th percentile: 1.2784377098083497
80th percentile: 1.4747064113616946
90th percentile: 1.8605682849884033
95th percentile: 2.053499221801758
99th percentile: 2.2078439712524416
mean time: 1.4619125843048095
Pipeline stage StressChecker completed in 8.08s
cycy233-l3-bcm-v0-c4_v1 status is now deployed due to DeploymentManager action
cycy233-l3-bcm-v0-c4_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-bcm-v0-c4_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-bcm-v0-c4-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.98s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-bcm-v0-c4-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bcm-v0-c4-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-bcm-v0-c4-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bcm-v0-c4-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bcm-v0-c4-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-bcm-v0-c4-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bcm-v0-c4-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-bcm-v0-c4-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-bcm-v0-c4-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bcm-v0-c4-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bcm-v0-c4-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bcm-v0-c4-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.47s
cycy233-l3-bcm-v0-c4_v1 status is now torndown due to DeploymentManager action