Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-st-5210-v10-mkmlizer
Waiting for job on cgato-l3-thespice-8b-st-5210-v10-mkmlizer to finish
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ║ ║
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ║ ║
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ║ ║
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ║ ║
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-st-5210-v10-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.
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: Downloaded to shared memory in 21.864s
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-st-5210-v10-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 84.76it/s]
Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 99.53it/s]
Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 142.42it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: quantized model in 18.959s
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: Processed model cgato/L3-TheSpice-8b-Stoic-Silence-4 in 41.838s
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-st-5210-v10
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-st-5210-v10/config.json
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-st-5210-v10/special_tokens_map.json
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-st-5210-v10/tokenizer_config.json
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-st-5210-v10/tokenizer.json
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-st-5210-v10/flywheel_model.0.safetensors
cgato-l3-thespice-8b-st-5210-v10-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.
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-st-5210-v10-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.
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-st-5210-v10-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.
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-st-5210-v10-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()
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-st-5210-v10_reward
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-st-5210-v10_reward/config.json
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-st-5210-v10_reward/special_tokens_map.json
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-st-5210-v10_reward/tokenizer_config.json
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-st-5210-v10_reward/merges.txt
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-st-5210-v10_reward/vocab.json
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-st-5210-v10_reward/tokenizer.json
cgato-l3-thespice-8b-st-5210-v10-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-st-5210-v10_reward/reward.tensors
Job cgato-l3-thespice-8b-st-5210-v10-mkmlizer completed after 73.86s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-st-5210-v10-mkmlizer
Pipeline stage MKMLizer completed in 77.81s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-st-5210-v10
Waiting for inference service cgato-l3-thespice-8b-st-5210-v10 to be ready
Inference service cgato-l3-thespice-8b-st-5210-v10 ready after 40.27493762969971s
Pipeline stage ISVCDeployer completed in 47.68s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0449626445770264s
Received healthy response to inference request in 1.150482177734375s
Received healthy response to inference request in 1.1399590969085693s
Received healthy response to inference request in 1.166196584701538s
Received healthy response to inference request in 1.1416130065917969s
5 requests
0 failed requests
5th percentile: 1.140289878845215
10th percentile: 1.1406206607818603
20th percentile: 1.1412822246551513
30th percentile: 1.1433868408203125
40th percentile: 1.1469345092773438
50th percentile: 1.150482177734375
60th percentile: 1.1567679405212403
70th percentile: 1.1630537033081054
80th percentile: 1.3419497966766358
90th percentile: 1.693456220626831
95th percentile: 1.8692094326019286
99th percentile: 2.0098120021820067
mean time: 1.3286427021026612
Pipeline stage StressChecker completed in 7.25s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-st_5210_v10 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-st_5210_v10 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-st_5210_v10
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-st-5210-v10 is running
Tearing down inference service cgato-l3-thespice-8b-st-5210-v10
Toredown service cgato-l3-thespice-8b-st-5210-v10
Pipeline stage ISVCDeleter completed in 4.46s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-st-5210-v10/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-st-5210-v10/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-st-5210-v10/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-st-5210-v10/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-st-5210-v10/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-st-5210-v10_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-st-5210-v10_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-st-5210-v10_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-st-5210-v10_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-st-5210-v10_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-st-5210-v10_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-st-5210-v10_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.73s
cgato-l3-thespice-8b-st_5210_v10 status is now torndown due to DeploymentManager action