Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer to finish
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-m-1215-v2-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-anjir-8b-l3-m-1215-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: Downloaded to shared memory in 20.427s
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 2/291 [00:04<10:56, 2.27s/it]
Loading 0: 5%|▌ | 15/291 [00:04<01:02, 4.39it/s]
Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.65it/s]
Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 20.94it/s]
Loading 0: 22%|██▏ | 65/291 [00:05<00:09, 24.76it/s]
Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 33.15it/s]
Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 47.75it/s]
Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 63.78it/s]
Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 80.23it/s]
Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 96.25it/s]
Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 72.55it/s]
Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 88.29it/s]
Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 103.62it/s]
Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 116.85it/s]
Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 127.96it/s]
Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 137.20it/s]
Loading 0: 93%|█████████▎| 272/291 [00:07<00:00, 89.44it/s]
Loading 0: 99%|█████████▉| 289/291 [00:07<00:00, 103.45it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: quantized model in 23.121s
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: Processed model Hastagaras/Anjir-8B-L3-M-Aelah in 46.173s
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-1215-v2
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-1215-v2/tokenizer_config.json
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-1215-v2/config.json
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-1215-v2/special_tokens_map.json
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-1215-v2/tokenizer.json
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-1215-v2/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-m-1215-v2-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-anjir-8b-l3-m-1215-v2-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-1215-v2-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.
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-1215-v2-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-anjir-8b-l3-m-1215-v2-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-1215-v2-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-anjir-8b-l3-m-1215-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: Saving duration: 0.427s
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.924s
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-1215-v2_reward
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-1215-v2_reward/config.json
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-1215-v2_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-1215-v2_reward/merges.txt
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-1215-v2_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-1215-v2_reward/vocab.json
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-1215-v2_reward/tokenizer.json
hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-1215-v2_reward/reward.tensors
Job hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer completed after 73.04s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-m-1215-v2-mkmlizer
Pipeline stage MKMLizer completed in 76.24s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-m-1215-v2
Waiting for inference service hastagaras-anjir-8b-l3-m-1215-v2 to be ready
Inference service hastagaras-anjir-8b-l3-m-1215-v2 ready after 50.333011865615845s
Pipeline stage ISVCDeployer completed in 57.41s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.163132905960083s
Received healthy response to inference request in 1.3294975757598877s
Received healthy response to inference request in 1.2934939861297607s
Received healthy response to inference request in 1.285339117050171s
Received healthy response to inference request in 1.3351809978485107s
5 requests
0 failed requests
5th percentile: 1.2869700908660888
10th percentile: 1.2886010646820067
20th percentile: 1.2918630123138428
30th percentile: 1.3006947040557861
40th percentile: 1.315096139907837
50th percentile: 1.3294975757598877
60th percentile: 1.331770944595337
70th percentile: 1.3340443134307862
80th percentile: 1.5007713794708253
90th percentile: 1.8319521427154541
95th percentile: 1.9975425243377685
99th percentile: 2.1300148296356203
mean time: 1.4813289165496826
Pipeline stage StressChecker completed in 8.02s
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-anjir-8b-l3-m_1215_v2 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3-m_1215_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-anjir-8b-l3-m_1215_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-anjir-8b-l3-m-1215-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.99s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-anjir-8b-l3-m-1215-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-m-1215-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-m-1215-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-m-1215-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-m-1215-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-anjir-8b-l3-m-1215-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-m-1215-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-m-1215-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-m-1215-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-m-1215-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-m-1215-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-m-1215-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.65s
hastagaras-anjir-8b-l3-m_1215_v2 status is now torndown due to DeploymentManager action
admin requested tearing down of hastagaras-anjir-8b-l3-m_1215_v2
Deleting key hastagaras-dirtybu8bl3-r-1180-v1_reward/vocab.json from bucket guanaco-reward-models
Running pipeline stage ISVCDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLModelDeleter completed in 10.83s
Pipeline stage ISVCDeleter completed in 1.18s
Running pipeline stage MKMLModelDeleter
hastagaras-dirtybu8bl3-r_1180_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 0.66s
hastagaras-anjir-8b-l3-m_1215_v2 status is now torndown due to DeploymentManager action