Running pipeline stage MKMLizer
Starting job with name hastagaras-sychomet-8b-l-1038-v1-mkmlizer
Waiting for job on hastagaras-sychomet-8b-l-1038-v1-mkmlizer to finish
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ║ /___/ ║
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ║ ║
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ║ ║
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ║ belonging to: ║
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ║ ║
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ║ ║
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-sychomet-8b-l-1038-v1-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-sychomet-8b-l-1038-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: Downloaded to shared memory in 32.526s
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-sychomet-8b-l-1038-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:02, 126.06it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:01, 143.86it/s]
Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 154.17it/s]
Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 156.36it/s]
Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 80.89it/s]
Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 87.86it/s]
Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 105.08it/s]
Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 118.94it/s]
Loading 0: 51%|█████ | 148/291 [00:01<00:01, 131.30it/s]
Loading 0: 57%|█████▋ | 166/291 [00:01<00:00, 140.27it/s]
Loading 0: 63%|██████▎ | 184/291 [00:01<00:00, 150.00it/s]
Loading 0: 69%|██████▉ | 201/291 [00:01<00:01, 89.94it/s]
Loading 0: 75%|███████▌ | 219/291 [00:01<00:00, 104.46it/s]
Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 116.32it/s]
Loading 0: 88%|████████▊ | 255/291 [00:02<00:00, 127.22it/s]
Loading 0: 93%|█████████▎| 270/291 [00:02<00:00, 131.92it/s]
Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 9.77it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: quantized model in 23.026s
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: Processed model Hastagaras/Sychomet-8B-L3-MK.I-TEST-2 in 58.189s
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-sychomet-8b-l-1038-v1
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-sychomet-8b-l-1038-v1/tokenizer_config.json
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-sychomet-8b-l-1038-v1/config.json
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-sychomet-8b-l-1038-v1/tokenizer.json
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-sychomet-8b-l-1038-v1/special_tokens_map.json
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-sychomet-8b-l-1038-v1/flywheel_model.0.safetensors
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-sychomet-8b-l-1038-v1-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-sychomet-8b-l-1038-v1-mkmlizer: warnings.warn(
hastagaras-sychomet-8b-l-1038-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.
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: warnings.warn(
hastagaras-sychomet-8b-l-1038-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()
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: Saving duration: 0.424s
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.450s
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-sychomet-8b-l-1038-v1_reward
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-sychomet-8b-l-1038-v1_reward/config.json
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-sychomet-8b-l-1038-v1_reward/tokenizer_config.json
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-sychomet-8b-l-1038-v1_reward/special_tokens_map.json
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-sychomet-8b-l-1038-v1_reward/vocab.json
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-sychomet-8b-l-1038-v1_reward/merges.txt
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-sychomet-8b-l-1038-v1_reward/tokenizer.json
hastagaras-sychomet-8b-l-1038-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-sychomet-8b-l-1038-v1_reward/reward.tensors
Job hastagaras-sychomet-8b-l-1038-v1-mkmlizer completed after 82.83s with status: succeeded
Stopping job with name hastagaras-sychomet-8b-l-1038-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-sychomet-8b-l-1038-v1
Waiting for inference service hastagaras-sychomet-8b-l-1038-v1 to be ready
Inference service hastagaras-sychomet-8b-l-1038-v1 ready after 50.25419545173645s
Pipeline stage ISVCDeployer completed in 57.47s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2166993618011475s
Received healthy response to inference request in 6.559335231781006s
Received healthy response to inference request in 1.3389804363250732s
Received healthy response to inference request in 1.2757141590118408s
Received healthy response to inference request in 1.232994556427002s
5 requests
0 failed requests
5th percentile: 1.2415384769439697
10th percentile: 1.2500823974609374
20th percentile: 1.267170238494873
30th percentile: 1.2883674144744872
40th percentile: 1.3136739253997802
50th percentile: 1.3389804363250732
60th percentile: 1.690068006515503
70th percentile: 2.0411555767059326
80th percentile: 3.08522653579712
90th percentile: 4.8222808837890625
95th percentile: 5.690808057785033
99th percentile: 6.385629796981811
mean time: 2.524744749069214
Pipeline stage StressChecker completed in 13.19s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-sychomet-8b-l_1038_v1 status is now deployed due to DeploymentManager action
hastagaras-sychomet-8b-l_1038_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-sychomet-8b-l_1038_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-sychomet-8b-l-1038-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.24s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-sychomet-8b-l-1038-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-sychomet-8b-l-1038-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-sychomet-8b-l-1038-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-sychomet-8b-l-1038-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-sychomet-8b-l-1038-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-sychomet-8b-l-1038-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-sychomet-8b-l-1038-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-sychomet-8b-l-1038-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-sychomet-8b-l-1038-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-sychomet-8b-l-1038-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-sychomet-8b-l-1038-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-sychomet-8b-l-1038-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.22s
hastagaras-sychomet-8b-l_1038_v1 status is now torndown due to DeploymentManager action