Running pipeline stage MKMLizer
Starting job with name thetsar1209-llama3-carp-v0-4-v3-mkmlizer
Waiting for job on thetsar1209-llama3-carp-v0-4-v3-mkmlizer to finish
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: ║ _____ __ __ ║
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: ║ /___/ ║
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: ║ Version: 0.8.10 ║
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: ║ The license key for the current software has been verified as ║
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: ║ belonging to: ║
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: ║ Chai Research Corp. ║
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thetsar1209-llama3-carp-v0-4-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.
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: Downloaded to shared memory in 13.994s
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: quantizing model to /dev/shm/model_cache
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
thetsar1209-llama3-carp-v0-4-v3-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 38%|███▊ | 111/291 [00:01<00:01, 109.61it/s]
Loading 0: 76%|███████▌ | 221/291 [00:02<00:00, 109.44it/s]
Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 26.25it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: quantized model in 20.693s
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: Processed model TheTsar1209/llama3-carp-v0.4 in 36.050s
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: creating bucket guanaco-mkml-models
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v3
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v3/special_tokens_map.json
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v3/tokenizer_config.json
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v3/config.json
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v3/tokenizer.json
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v3/flywheel_model.0.safetensors
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thetsar1209-llama3-carp-v0-4-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.
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-4-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.
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-4-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.
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: Saving duration: 0.258s
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.507s
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: creating bucket guanaco-reward-models
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v3_reward
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v3_reward/config.json
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v3_reward/tokenizer_config.json
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v3_reward/special_tokens_map.json
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v3_reward/merges.txt
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v3_reward/vocab.json
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v3_reward/tokenizer.json
thetsar1209-llama3-carp-v0-4-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v3_reward/reward.tensors
Job thetsar1209-llama3-carp-v0-4-v3-mkmlizer completed after 62.82s with status: succeeded
Stopping job with name thetsar1209-llama3-carp-v0-4-v3-mkmlizer
Pipeline stage MKMLizer completed in 63.86s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service thetsar1209-llama3-carp-v0-4-v3
Waiting for inference service thetsar1209-llama3-carp-v0-4-v3 to be ready
Inference service thetsar1209-llama3-carp-v0-4-v3 ready after 30.19269299507141s
Pipeline stage ISVCDeployer completed in 36.05s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1126132011413574s
Received healthy response to inference request in 1.2712054252624512s
Received healthy response to inference request in 1.2979891300201416s
Received healthy response to inference request in 1.2782940864562988s
Received healthy response to inference request in 1.3013179302215576s
5 requests
0 failed requests
5th percentile: 1.2726231575012208
10th percentile: 1.2740408897399902
20th percentile: 1.2768763542175292
30th percentile: 1.2822330951690675
40th percentile: 1.2901111125946045
50th percentile: 1.2979891300201416
60th percentile: 1.299320650100708
70th percentile: 1.3006521701812743
80th percentile: 1.4635769844055178
90th percentile: 1.7880950927734376
95th percentile: 1.9503541469573973
99th percentile: 2.0801613903045655
mean time: 1.4522839546203614
Pipeline stage StressChecker completed in 7.96s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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
thetsar1209-llama3-carp-v0-4_v3 status is now deployed due to DeploymentManager action
thetsar1209-llama3-carp-v0-4_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of thetsar1209-llama3-carp-v0-4_v3
Running pipeline stage ISVCDeleter
Checking if service thetsar1209-llama3-carp-v0-4-v3 is running
Tearing down inference service thetsar1209-llama3-carp-v0-4-v3
Toredown service thetsar1209-llama3-carp-v0-4-v3
Pipeline stage ISVCDeleter completed in 7.73s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key thetsar1209-llama3-carp-v0-4-v3/config.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-v0-4-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-v0-4-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-v0-4-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-v0-4-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key thetsar1209-llama3-carp-v0-4-v3_reward/config.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-4-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-4-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-4-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-4-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-4-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-4-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.69s
thetsar1209-llama3-carp-v0-4_v3 status is now torndown due to DeploymentManager action