Running pipeline stage MKMLizer
Starting job with name kaoeiri-perpicon-experim-5756-v4-mkmlizer
Waiting for job on kaoeiri-perpicon-experim-5756-v4-mkmlizer to finish
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ║ _____ __ __ ║
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ║ /___/ ║
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ║ ║
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ║ Version: 0.8.14 ║
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ║ https://mk1.ai ║
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ║ ║
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ║ The license key for the current software has been verified as ║
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ║ belonging to: ║
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ║ ║
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ║ Chai Research Corp. ║
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ║ ║
kaoeiri-perpicon-experim-5756-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
kaoeiri-perpicon-experim-5756-v4-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.
kaoeiri-perpicon-experim-5756-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
kaoeiri-perpicon-experim-5756-v4-mkmlizer: Downloaded to shared memory in 32.964s
kaoeiri-perpicon-experim-5756-v4-mkmlizer: quantizing model to /dev/shm/model_cache
kaoeiri-perpicon-experim-5756-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
kaoeiri-perpicon-experim-5756-v4-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 2/291 [00:04<11:25, 2.37s/it]
Loading 0: 5%|▍ | 14/291 [00:04<01:11, 3.90it/s]
Loading 0: 9%|▉ | 27/291 [00:04<00:29, 8.92it/s]
Loading 0: 14%|█▍ | 41/291 [00:05<00:15, 15.82it/s]
Loading 0: 19%|█▊ | 54/291 [00:05<00:09, 23.91it/s]
Loading 0: 23%|██▎ | 68/291 [00:05<00:06, 34.02it/s]
Loading 0: 28%|██▊ | 81/291 [00:05<00:04, 44.90it/s]
Loading 0: 32%|███▏ | 94/291 [00:05<00:03, 56.81it/s]
Loading 0: 37%|███▋ | 107/291 [00:05<00:02, 67.28it/s]
Loading 0: 42%|████▏ | 121/291 [00:05<00:02, 80.20it/s]
Loading 0: 46%|████▌ | 134/291 [00:06<00:03, 48.89it/s]
Loading 0: 51%|█████ | 148/291 [00:06<00:02, 61.17it/s]
Loading 0: 55%|█████▍ | 159/291 [00:06<00:01, 67.98it/s]
Loading 0: 60%|██████ | 175/291 [00:06<00:01, 84.26it/s]
Loading 0: 64%|██████▍ | 187/291 [00:06<00:01, 89.84it/s]
Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 103.24it/s]
Loading 0: 74%|███████▍ | 215/291 [00:06<00:00, 106.90it/s]
Loading 0: 79%|███████▊ | 229/291 [00:06<00:00, 115.06it/s]
Loading 0: 83%|████████▎ | 242/291 [00:07<00:00, 116.06it/s]
Loading 0: 88%|████████▊ | 256/291 [00:07<00:00, 121.03it/s]
Loading 0: 92%|█████████▏| 269/291 [00:07<00:00, 119.68it/s]
Loading 0: 98%|█████████▊| 284/291 [00:07<00:00, 122.17it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
kaoeiri-perpicon-experim-5756-v4-mkmlizer: quantized model in 23.520s
kaoeiri-perpicon-experim-5756-v4-mkmlizer: Processed model Kaoeiri/Perpicon-Experimental-4 in 59.055s
kaoeiri-perpicon-experim-5756-v4-mkmlizer: creating bucket guanaco-mkml-models
kaoeiri-perpicon-experim-5756-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
kaoeiri-perpicon-experim-5756-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/kaoeiri-perpicon-experim-5756-v4
kaoeiri-perpicon-experim-5756-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/kaoeiri-perpicon-experim-5756-v4/config.json
kaoeiri-perpicon-experim-5756-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/kaoeiri-perpicon-experim-5756-v4/tokenizer_config.json
kaoeiri-perpicon-experim-5756-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/kaoeiri-perpicon-experim-5756-v4/tokenizer.json
kaoeiri-perpicon-experim-5756-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/kaoeiri-perpicon-experim-5756-v4/special_tokens_map.json
kaoeiri-perpicon-experim-5756-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/kaoeiri-perpicon-experim-5756-v4/flywheel_model.0.safetensors
kaoeiri-perpicon-experim-5756-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
kaoeiri-perpicon-experim-5756-v4-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.
kaoeiri-perpicon-experim-5756-v4-mkmlizer: warnings.warn(
kaoeiri-perpicon-experim-5756-v4-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.
kaoeiri-perpicon-experim-5756-v4-mkmlizer: warnings.warn(
kaoeiri-perpicon-experim-5756-v4-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.
kaoeiri-perpicon-experim-5756-v4-mkmlizer: warnings.warn(
kaoeiri-perpicon-experim-5756-v4-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()
kaoeiri-perpicon-experim-5756-v4-mkmlizer: return self.fget.__get__(instance, owner)()
kaoeiri-perpicon-experim-5756-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
kaoeiri-perpicon-experim-5756-v4-mkmlizer: Saving duration: 0.383s
kaoeiri-perpicon-experim-5756-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.265s
kaoeiri-perpicon-experim-5756-v4-mkmlizer: creating bucket guanaco-reward-models
kaoeiri-perpicon-experim-5756-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
kaoeiri-perpicon-experim-5756-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v4_reward
kaoeiri-perpicon-experim-5756-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v4_reward/config.json
kaoeiri-perpicon-experim-5756-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v4_reward/tokenizer_config.json
kaoeiri-perpicon-experim-5756-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v4_reward/special_tokens_map.json
kaoeiri-perpicon-experim-5756-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v4_reward/merges.txt
kaoeiri-perpicon-experim-5756-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v4_reward/vocab.json
kaoeiri-perpicon-experim-5756-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v4_reward/tokenizer.json
kaoeiri-perpicon-experim-5756-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v4_reward/reward.tensors
Job kaoeiri-perpicon-experim-5756-v4-mkmlizer completed after 93.24s with status: succeeded
Stopping job with name kaoeiri-perpicon-experim-5756-v4-mkmlizer
Pipeline stage MKMLizer completed in 94.11s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service kaoeiri-perpicon-experim-5756-v4
Waiting for inference service kaoeiri-perpicon-experim-5756-v4 to be ready
Inference service kaoeiri-perpicon-experim-5756-v4 ready after 30.17080044746399s
Pipeline stage ISVCDeployer completed in 35.97s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.157498598098755s
Received healthy response to inference request in 1.2961721420288086s
Received healthy response to inference request in 1.2403948307037354s
Received healthy response to inference request in 1.2393760681152344s
Received healthy response to inference request in 1.222306251525879s
5 requests
0 failed requests
5th percentile: 1.22572021484375
10th percentile: 1.2291341781616212
20th percentile: 1.2359621047973632
30th percentile: 1.2395798206329345
40th percentile: 1.239987325668335
50th percentile: 1.2403948307037354
60th percentile: 1.2627057552337646
70th percentile: 1.2850166797637939
80th percentile: 1.468437433242798
90th percentile: 1.8129680156707764
95th percentile: 1.9852333068847654
99th percentile: 2.123045539855957
mean time: 1.4311495780944825
Pipeline stage StressChecker completed in 7.79s
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
kaoeiri-perpicon-experim_5756_v4 status is now deployed due to DeploymentManager action
kaoeiri-perpicon-experim_5756_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of kaoeiri-perpicon-experim_5756_v4
Running pipeline stage ISVCDeleter
Checking if service kaoeiri-perpicon-experim-5756-v4 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.40s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key kaoeiri-perpicon-experim-5756-v4/config.json from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-experim-5756-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-experim-5756-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-experim-5756-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-experim-5756-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key kaoeiri-perpicon-experim-5756-v4_reward/config.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-5756-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-5756-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-5756-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-5756-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-5756-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-5756-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.41s
kaoeiri-perpicon-experim_5756_v4 status is now torndown due to DeploymentManager action