Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-v1-3-v3-mkmlizer
Waiting for job on cgato-l3-thespice-8b-v1-3-v3-mkmlizer to finish
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-v1-3-v3-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-v1-3-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: Downloaded to shared memory in 20.387s
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-v1-3-v3-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 34%|███▍ | 99/291 [00:01<00:01, 98.69it/s]
Loading 0: 69%|██████▉ | 201/291 [00:02<00:00, 100.53it/s]
Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 30.39it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: quantized model in 18.278s
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: Processed model cgato/L3-TheSpice-8b-v1.3 in 39.635s
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-v1-3-v3
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v1-3-v3/tokenizer_config.json
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v1-3-v3/config.json
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v1-3-v3/special_tokens_map.json
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v1-3-v3/tokenizer.json
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-v1-3-v3/flywheel_model.0.safetensors
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-v1-3-v3-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-v1-3-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v1-3-v3-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-v1-3-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v1-3-v3-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-v1-3-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v1-3-v3_reward/config.json
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v1-3-v3_reward/tokenizer_config.json
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v1-3-v3_reward/special_tokens_map.json
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v1-3-v3_reward/vocab.json
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-v1-3-v3_reward/merges.txt
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v1-3-v3_reward/tokenizer.json
cgato-l3-thespice-8b-v1-3-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-v1-3-v3_reward/reward.tensors
Job cgato-l3-thespice-8b-v1-3-v3-mkmlizer completed after 63.71s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-v1-3-v3-mkmlizer
Pipeline stage MKMLizer completed in 67.49s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-v1-3-v3
Waiting for inference service cgato-l3-thespice-8b-v1-3-v3 to be ready
Inference service cgato-l3-thespice-8b-v1-3-v3 ready after 30.230079650878906s
Pipeline stage ISVCDeployer completed in 38.04s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1011459827423096s
Received healthy response to inference request in 1.2624330520629883s
Received healthy response to inference request in 1.273592233657837s
Received healthy response to inference request in 1.2920114994049072s
Received healthy response to inference request in 1.2739973068237305s
5 requests
0 failed requests
5th percentile: 1.264664888381958
10th percentile: 1.2668967247009277
20th percentile: 1.2713603973388672
30th percentile: 1.2736732482910156
40th percentile: 1.2738352775573731
50th percentile: 1.2739973068237305
60th percentile: 1.2812029838562011
70th percentile: 1.2884086608886718
80th percentile: 1.453838396072388
90th percentile: 1.7774921894073488
95th percentile: 1.9393190860748288
99th percentile: 2.0687806034088134
mean time: 1.4406360149383546
Pipeline stage StressChecker completed in 7.82s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.06s
cgato-l3-thespice-8b-v1-3_v3 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-v1-3_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-v1-3_v3
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-v1-3-v3 is running
Tearing down inference service cgato-l3-thespice-8b-v1-3-v3
Toredown service cgato-l3-thespice-8b-v1-3-v3
Pipeline stage ISVCDeleter completed in 4.04s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v1-3-v3/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v1-3-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v1-3-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v1-3-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v1-3-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v1-3-v3_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v1-3-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v1-3-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v1-3-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v1-3-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v1-3-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v1-3-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.30s
cgato-l3-thespice-8b-v1-3_v3 status is now torndown due to DeploymentManager action