Running pipeline stage MKMLizer
Starting job with name alkahestry-stheno-l3-8b-v2-mkmlizer
Waiting for job on alkahestry-stheno-l3-8b-v2-mkmlizer to finish
alkahestry-stheno-l3-8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alkahestry-stheno-l3-8b-v2-mkmlizer: ║ _____ __ __ ║
alkahestry-stheno-l3-8b-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alkahestry-stheno-l3-8b-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alkahestry-stheno-l3-8b-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alkahestry-stheno-l3-8b-v2-mkmlizer: ║ /___/ ║
alkahestry-stheno-l3-8b-v2-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v2-mkmlizer: ║ Version: 0.8.14 ║
alkahestry-stheno-l3-8b-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alkahestry-stheno-l3-8b-v2-mkmlizer: ║ https://mk1.ai ║
alkahestry-stheno-l3-8b-v2-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v2-mkmlizer: ║ The license key for the current software has been verified as ║
alkahestry-stheno-l3-8b-v2-mkmlizer: ║ belonging to: ║
alkahestry-stheno-l3-8b-v2-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v2-mkmlizer: ║ Chai Research Corp. ║
alkahestry-stheno-l3-8b-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alkahestry-stheno-l3-8b-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
alkahestry-stheno-l3-8b-v2-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alkahestry-stheno-l3-8b-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.
alkahestry-stheno-l3-8b-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
Retrying (%r) after connection broken by '%r': %s
alkahestry-stheno-l3-8b-v2-mkmlizer: Downloaded to shared memory in 43.351s
alkahestry-stheno-l3-8b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
alkahestry-stheno-l3-8b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alkahestry-stheno-l3-8b-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 2/291 [00:04<11:21, 2.36s/it]
Loading 0: 4%|▍ | 13/291 [00:04<01:16, 3.64it/s]
Loading 0: 8%|▊ | 24/291 [00:04<00:33, 7.86it/s]
Loading 0: 14%|█▎ | 40/291 [00:05<00:15, 15.92it/s]
Loading 0: 17%|█▋ | 50/291 [00:05<00:11, 21.83it/s]
Loading 0: 21%|██ | 60/291 [00:05<00:11, 20.02it/s]
Loading 0: 23%|██▎ | 68/291 [00:05<00:09, 23.02it/s]
Loading 0: 26%|██▌ | 75/291 [00:06<00:08, 26.83it/s]
Loading 0: 28%|██▊ | 81/291 [00:06<00:08, 26.07it/s]
Loading 0: 30%|██▉ | 86/291 [00:06<00:07, 26.42it/s]
Loading 0: 33%|███▎ | 96/291 [00:06<00:05, 36.74it/s]
Loading 0: 38%|███▊ | 112/291 [00:06<00:03, 56.48it/s]
Loading 0: 42%|████▏ | 123/291 [00:06<00:02, 65.20it/s]
Loading 0: 48%|████▊ | 139/291 [00:06<00:01, 82.74it/s]
Loading 0: 52%|█████▏ | 150/291 [00:07<00:01, 85.07it/s]
Loading 0: 57%|█████▋ | 166/291 [00:07<00:02, 58.52it/s]
Loading 0: 61%|██████ | 177/291 [00:07<00:01, 64.71it/s]
Loading 0: 66%|██████▋ | 193/291 [00:07<00:01, 79.73it/s]
Loading 0: 70%|███████ | 204/291 [00:07<00:01, 82.47it/s]
Loading 0: 76%|███████▌ | 220/291 [00:07<00:00, 95.40it/s]
Loading 0: 79%|███████▉ | 231/291 [00:08<00:00, 94.17it/s]
Loading 0: 85%|████████▍ | 247/291 [00:08<00:00, 105.75it/s]
Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 103.77it/s]
Loading 0: 93%|█████████▎| 270/291 [00:08<00:00, 62.40it/s]
Loading 0: 97%|█████████▋| 283/291 [00:08<00:00, 73.39it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
alkahestry-stheno-l3-8b-v2-mkmlizer: quantized model in 24.998s
alkahestry-stheno-l3-8b-v2-mkmlizer: Processed model alkahestry/Stheno-L3-8B in 71.222s
alkahestry-stheno-l3-8b-v2-mkmlizer: creating bucket guanaco-mkml-models
alkahestry-stheno-l3-8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alkahestry-stheno-l3-8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v2
alkahestry-stheno-l3-8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v2/config.json
alkahestry-stheno-l3-8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v2/special_tokens_map.json
alkahestry-stheno-l3-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v2/tokenizer_config.json
alkahestry-stheno-l3-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v2/tokenizer.json
alkahestry-stheno-l3-8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v2/flywheel_model.0.safetensors
alkahestry-stheno-l3-8b-v2-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
alkahestry-stheno-l3-8b-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.
alkahestry-stheno-l3-8b-v2-mkmlizer: warnings.warn(
alkahestry-stheno-l3-8b-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.
alkahestry-stheno-l3-8b-v2-mkmlizer: warnings.warn(
alkahestry-stheno-l3-8b-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.
alkahestry-stheno-l3-8b-v2-mkmlizer: warnings.warn(
alkahestry-stheno-l3-8b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
alkahestry-stheno-l3-8b-v2-mkmlizer: Saving duration: 0.177s
alkahestry-stheno-l3-8b-v2-mkmlizer: Processed model Jellywibble/CHAI_alignment_reward_model in 3.974s
alkahestry-stheno-l3-8b-v2-mkmlizer: creating bucket guanaco-reward-models
alkahestry-stheno-l3-8b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
alkahestry-stheno-l3-8b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v2_reward
alkahestry-stheno-l3-8b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v2_reward/special_tokens_map.json
alkahestry-stheno-l3-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v2_reward/tokenizer_config.json
alkahestry-stheno-l3-8b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v2_reward/config.json
alkahestry-stheno-l3-8b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v2_reward/merges.txt
alkahestry-stheno-l3-8b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v2_reward/vocab.json
alkahestry-stheno-l3-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v2_reward/tokenizer.json
alkahestry-stheno-l3-8b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v2_reward/reward.tensors
Job alkahestry-stheno-l3-8b-v2-mkmlizer completed after 93.15s with status: succeeded
Stopping job with name alkahestry-stheno-l3-8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 96.64s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service alkahestry-stheno-l3-8b-v2
Waiting for inference service alkahestry-stheno-l3-8b-v2 to be ready
Inference service alkahestry-stheno-l3-8b-v2 ready after 40.217589378356934s
Pipeline stage ISVCDeployer completed in 47.59s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8343102931976318s
Received healthy response to inference request in 0.9426977634429932s
Received healthy response to inference request in 0.8635079860687256s
Received healthy response to inference request in 0.7187144756317139s
Received healthy response to inference request in 1.0144693851470947s
5 requests
0 failed requests
5th percentile: 0.7476731777191162
10th percentile: 0.7766318798065186
20th percentile: 0.8345492839813232
30th percentile: 0.8793459415435791
40th percentile: 0.9110218524932862
50th percentile: 0.9426977634429932
60th percentile: 0.9714064121246337
70th percentile: 1.0001150608062743
80th percentile: 1.1784375667572022
90th percentile: 1.506373929977417
95th percentile: 1.6703421115875243
99th percentile: 1.8015166568756102
mean time: 1.0747399806976319
Pipeline stage StressChecker completed in 6.02s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
alkahestry-stheno-l3-8b_v2 status is now deployed due to DeploymentManager action
alkahestry-stheno-l3-8b_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of alkahestry-stheno-l3-8b_v2
Running pipeline stage ISVCDeleter
Checking if service alkahestry-stheno-l3-8b-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.60s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key alkahestry-stheno-l3-8b-v2/config.json from bucket guanaco-mkml-models
Deleting key alkahestry-stheno-l3-8b-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key alkahestry-stheno-l3-8b-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key alkahestry-stheno-l3-8b-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key alkahestry-stheno-l3-8b-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key alkahestry-stheno-l3-8b-v2_reward/config.json from bucket guanaco-reward-models
Deleting key alkahestry-stheno-l3-8b-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key alkahestry-stheno-l3-8b-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key alkahestry-stheno-l3-8b-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key alkahestry-stheno-l3-8b-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key alkahestry-stheno-l3-8b-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key alkahestry-stheno-l3-8b-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.49s
alkahestry-stheno-l3-8b_v2 status is now torndown due to DeploymentManager action