Running pipeline stage MKMLizer
Starting job with name fredithefish-biscuitrp-8x7b-v2-mkmlizer
Waiting for job on fredithefish-biscuitrp-8x7b-v2-mkmlizer to finish
fredithefish-biscuitrp-8x7b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
fredithefish-biscuitrp-8x7b-v2-mkmlizer: ║ _____ __ __ ║
fredithefish-biscuitrp-8x7b-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
fredithefish-biscuitrp-8x7b-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
fredithefish-biscuitrp-8x7b-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
fredithefish-biscuitrp-8x7b-v2-mkmlizer: ║ /___/ ║
fredithefish-biscuitrp-8x7b-v2-mkmlizer: ║ ║
fredithefish-biscuitrp-8x7b-v2-mkmlizer: ║ Version: 0.8.6 ║
fredithefish-biscuitrp-8x7b-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
fredithefish-biscuitrp-8x7b-v2-mkmlizer: ║ ║
fredithefish-biscuitrp-8x7b-v2-mkmlizer: ║ The license key for the current software has been verified as ║
fredithefish-biscuitrp-8x7b-v2-mkmlizer: ║ belonging to: ║
fredithefish-biscuitrp-8x7b-v2-mkmlizer: ║ ║
fredithefish-biscuitrp-8x7b-v2-mkmlizer: ║ Chai Research Corp. ║
fredithefish-biscuitrp-8x7b-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
fredithefish-biscuitrp-8x7b-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
fredithefish-biscuitrp-8x7b-v2-mkmlizer: ║ ║
fredithefish-biscuitrp-8x7b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
fredithefish-biscuitrp-8x7b-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.
fredithefish-biscuitrp-8x7b-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
fredithefish-biscuitrp-8x7b-v2-mkmlizer: Downloaded to shared memory in 70.956s
fredithefish-biscuitrp-8x7b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
fredithefish-biscuitrp-8x7b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
fredithefish-biscuitrp-8x7b-v2-mkmlizer: quantized model in 49.546s
fredithefish-biscuitrp-8x7b-v2-mkmlizer: Processed model Fredithefish/BiscuitRP-8x7B in 126.140s
fredithefish-biscuitrp-8x7b-v2-mkmlizer: creating bucket guanaco-mkml-models
fredithefish-biscuitrp-8x7b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
fredithefish-biscuitrp-8x7b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v2
fredithefish-biscuitrp-8x7b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v2/config.json
fredithefish-biscuitrp-8x7b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v2/tokenizer.model
fredithefish-biscuitrp-8x7b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v2/special_tokens_map.json
fredithefish-biscuitrp-8x7b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v2/tokenizer_config.json
fredithefish-biscuitrp-8x7b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v2/tokenizer.json
fredithefish-biscuitrp-8x7b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v2/flywheel_model.3.safetensors
fredithefish-biscuitrp-8x7b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v2/flywheel_model.2.safetensors
fredithefish-biscuitrp-8x7b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v2/flywheel_model.0.safetensors
fredithefish-biscuitrp-8x7b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v2/flywheel_model.1.safetensors
fredithefish-biscuitrp-8x7b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
fredithefish-biscuitrp-8x7b-v2-mkmlizer:
Loading 0: 0%| | 0/995 [00:00<?, ?it/s]
Loading 0: 1%| | 9/995 [00:00<00:11, 84.61it/s]
Loading 0: 2%|▏ | 18/995 [00:00<00:12, 79.55it/s]
Loading 0: 3%|▎ | 31/995 [00:00<00:09, 100.22it/s]
Loading 0: 4%|▍ | 42/995 [00:00<00:10, 93.53it/s]
Loading 0: 5%|▌ | 52/995 [00:00<00:10, 89.56it/s]
Loading 0: 7%|▋ | 67/995 [00:00<00:08, 105.96it/s]
Loading 0: 8%|▊ | 78/995 [00:00<00:09, 95.99it/s]
Loading 0: 9%|▉ | 88/995 [00:00<00:09, 93.65it/s]
Loading 0: 10%|█ | 102/995 [00:01<00:08, 105.90it/s]
Loading 0: 11%|█▏ | 113/995 [00:01<00:20, 42.11it/s]
Loading 0: 12%|█▏ | 122/995 [00:01<00:18, 48.14it/s]
Loading 0: 14%|█▍ | 137/995 [00:01<00:13, 63.87it/s]
Loading 0: 15%|█▍ | 147/995 [00:02<00:12, 69.14it/s]
Loading 0: 16%|█▌ | 157/995 [00:02<00:11, 73.96it/s]
Loading 0: 17%|█▋ | 173/995 [00:02<00:08, 91.43it/s]
Loading 0: 19%|█▊ | 185/995 [00:02<00:09, 86.81it/s]
Loading 0: 20%|██ | 201/995 [00:02<00:07, 101.48it/s]
Loading 0: 21%|██▏ | 213/995 [00:03<00:16, 46.51it/s]
Loading 0: 23%|██▎ | 225/995 [00:03<00:13, 55.88it/s]
Loading 0: 24%|██▎ | 235/995 [00:03<00:13, 58.40it/s]
Loading 0: 25%|██▌ | 250/995 [00:03<00:10, 73.85it/s]
Loading 0: 26%|██▌ | 261/995 [00:03<00:09, 77.24it/s]
Loading 0: 27%|██▋ | 271/995 [00:03<00:08, 80.79it/s]
Loading 0: 29%|██▊ | 285/995 [00:12<02:42, 4.37it/s]
Loading 0: 30%|██▉ | 294/995 [00:12<02:04, 5.65it/s]
Loading 0: 30%|███ | 303/995 [00:12<01:33, 7.42it/s]
Loading 0: 32%|███▏ | 319/995 [00:13<00:57, 11.82it/s]
Loading 0: 33%|███▎ | 329/995 [00:13<00:53, 12.38it/s]
Loading 0: 34%|███▍ | 338/995 [00:13<00:41, 15.76it/s]
Loading 0: 35%|███▍ | 347/995 [00:13<00:32, 20.14it/s]
Loading 0: 36%|███▋ | 362/995 [00:14<00:21, 29.95it/s]
Loading 0: 37%|███▋ | 372/995 [00:14<00:17, 36.18it/s]
Loading 0: 39%|███▉ | 388/995 [00:14<00:11, 50.91it/s]
Loading 0: 40%|████ | 400/995 [00:14<00:10, 58.07it/s]
Loading 0: 42%|████▏ | 414/995 [00:14<00:08, 70.64it/s]
Loading 0: 43%|████▎ | 426/995 [00:14<00:07, 73.21it/s]
Loading 0: 44%|████▍ | 437/995 [00:15<00:13, 40.39it/s]
Loading 0: 45%|████▌ | 448/995 [00:15<00:11, 48.93it/s]
Loading 0: 46%|████▌ | 457/995 [00:15<00:09, 54.04it/s]
Loading 0: 47%|████▋ | 466/995 [00:15<00:08, 59.27it/s]
Loading 0: 48%|████▊ | 481/995 [00:15<00:06, 76.61it/s]
Loading 0: 49%|████▉ | 492/995 [00:15<00:06, 79.54it/s]
Loading 0: 51%|█████ | 508/995 [00:15<00:05, 96.09it/s]
Loading 0: 52%|█████▏ | 520/995 [00:16<00:05, 92.02it/s]
Loading 0: 53%|█████▎ | 531/995 [00:16<00:05, 92.38it/s]
Loading 0: 54%|█████▍ | 542/995 [00:16<00:09, 45.32it/s]
Loading 0: 55%|█████▌ | 552/995 [00:16<00:08, 52.51it/s]
Loading 0: 56%|█████▋ | 561/995 [00:26<02:04, 3.49it/s]
Loading 0: 58%|█████▊ | 576/995 [00:26<01:15, 5.54it/s]
Loading 0: 59%|█████▉ | 586/995 [00:26<00:55, 7.37it/s]
Loading 0: 61%|██████ | 602/995 [00:26<00:34, 11.47it/s]
Loading 0: 62%|██████▏ | 613/995 [00:26<00:25, 15.01it/s]
Loading 0: 63%|██████▎ | 623/995 [00:27<00:19, 19.25it/s]
Loading 0: 64%|██████▍ | 638/995 [00:27<00:12, 27.82it/s]
Loading 0: 65%|██████▌ | 650/995 [00:27<00:13, 24.94it/s]
Loading 0: 66%|██████▋ | 661/995 [00:27<00:10, 31.63it/s]
Loading 0: 67%|██████▋ | 671/995 [00:27<00:08, 37.62it/s]
Loading 0: 68%|██████▊ | 680/995 [00:28<00:07, 40.61it/s]
Loading 0: 69%|██████▉ | 688/995 [00:28<00:06, 45.85it/s]
Loading 0: 70%|███████ | 699/995 [00:28<00:05, 56.27it/s]
Loading 0: 71%|███████ | 708/995 [00:28<00:04, 61.53it/s]
Loading 0: 73%|███████▎ | 723/995 [00:28<00:03, 78.60it/s]
Loading 0: 74%|███████▍ | 734/995 [00:28<00:03, 81.14it/s]
Loading 0: 75%|███████▍ | 746/995 [00:28<00:02, 90.18it/s]
Loading 0: 76%|███████▌ | 757/995 [00:30<00:12, 19.12it/s]
Loading 0: 77%|███████▋ | 767/995 [00:30<00:09, 24.46it/s]
Loading 0: 78%|███████▊ | 777/995 [00:30<00:07, 30.83it/s]
Loading 0: 80%|███████▉ | 793/995 [00:30<00:04, 44.85it/s]
Loading 0: 81%|████████ | 804/995 [00:30<00:03, 51.63it/s]
Loading 0: 82%|████████▏ | 820/995 [00:31<00:02, 68.12it/s]
Loading 0: 84%|████████▎ | 832/995 [00:31<00:02, 73.87it/s]
Loading 0: 85%|████████▍ | 843/995 [00:40<00:36, 4.21it/s]
Loading 0: 86%|████████▌ | 854/995 [00:41<00:26, 5.38it/s]
Loading 0: 87%|████████▋ | 864/995 [00:41<00:18, 7.17it/s]
Loading 0: 88%|████████▊ | 876/995 [00:41<00:11, 10.13it/s]
Loading 0: 89%|████████▉ | 885/995 [00:41<00:08, 12.98it/s]
Loading 0: 90%|████████▉ | 894/995 [00:41<00:06, 16.76it/s]
Loading 0: 91%|█████████▏| 910/995 [00:41<00:03, 25.96it/s]
Loading 0: 93%|█████████▎| 921/995 [00:41<00:02, 32.45it/s]
Loading 0: 94%|█████████▍| 935/995 [00:41<00:01, 43.77it/s]
Loading 0: 95%|█████████▌| 946/995 [00:41<00:00, 51.15it/s]
Loading 0: 96%|█████████▋| 959/995 [00:42<00:00, 36.87it/s]
Loading 0: 98%|█████████▊| 972/995 [00:42<00:00, 47.49it/s]
Loading 0: 99%|█████████▉| 983/995 [00:42<00:00, 55.83it/s]
Loading 0: 100%|█████████▉| 993/995 [00:42<00:00, 61.11it/s]
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1096: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
fredithefish-biscuitrp-8x7b-v2-mkmlizer: warnings.warn(
fredithefish-biscuitrp-8x7b-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:720: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
fredithefish-biscuitrp-8x7b-v2-mkmlizer: warnings.warn(
fredithefish-biscuitrp-8x7b-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:466: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
fredithefish-biscuitrp-8x7b-v2-mkmlizer: warnings.warn(
fredithefish-biscuitrp-8x7b-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()
fredithefish-biscuitrp-8x7b-v2-mkmlizer: return self.fget.__get__(instance, owner)()
fredithefish-biscuitrp-8x7b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
fredithefish-biscuitrp-8x7b-v2-mkmlizer: Saving duration: 0.252s
fredithefish-biscuitrp-8x7b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.231s
fredithefish-biscuitrp-8x7b-v2-mkmlizer: creating bucket guanaco-reward-models
fredithefish-biscuitrp-8x7b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
fredithefish-biscuitrp-8x7b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/fredithefish-biscuitrp-8x7b-v2_reward
fredithefish-biscuitrp-8x7b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/fredithefish-biscuitrp-8x7b-v2_reward/config.json
fredithefish-biscuitrp-8x7b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/fredithefish-biscuitrp-8x7b-v2_reward/special_tokens_map.json
fredithefish-biscuitrp-8x7b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/fredithefish-biscuitrp-8x7b-v2_reward/tokenizer_config.json
fredithefish-biscuitrp-8x7b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/fredithefish-biscuitrp-8x7b-v2_reward/merges.txt
fredithefish-biscuitrp-8x7b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/fredithefish-biscuitrp-8x7b-v2_reward/vocab.json
fredithefish-biscuitrp-8x7b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/fredithefish-biscuitrp-8x7b-v2_reward/tokenizer.json
Job fredithefish-biscuitrp-8x7b-v2-mkmlizer completed after 167.73s with status: succeeded
Stopping job with name fredithefish-biscuitrp-8x7b-v2-mkmlizer
Pipeline stage MKMLizer completed in 174.92s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service fredithefish-biscuitrp-8x7b-v2
Waiting for inference service fredithefish-biscuitrp-8x7b-v2 to be ready
Inference service fredithefish-biscuitrp-8x7b-v2 ready after 60.328922510147095s
Pipeline stage ISVCDeployer completed in 68.10s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.5801429748535156s
Received healthy response to inference request in 2.735982894897461s
Received healthy response to inference request in 2.6427409648895264s
Received healthy response to inference request in 2.4655191898345947s
Received healthy response to inference request in 2.521317958831787s
5 requests
0 failed requests
5th percentile: 2.4766789436340333
10th percentile: 2.487838697433472
20th percentile: 2.5101582050323485
30th percentile: 2.545602560043335
40th percentile: 2.5941717624664307
50th percentile: 2.6427409648895264
60th percentile: 2.6800377368927
70th percentile: 2.717334508895874
80th percentile: 2.904814910888672
90th percentile: 3.242478942871094
95th percentile: 3.4113109588623045
99th percentile: 3.5463765716552733
mean time: 2.789140796661377
Pipeline stage StressChecker completed in 14.61s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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 0.08s
fredithefish-biscuitrp-8x7b_v2 status is now deployed due to DeploymentManager action
fredithefish-biscuitrp-8x7b_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of fredithefish-biscuitrp-8x7b_v2
Deleting key dreamgen-opus-v1-2-llama-3-8b-v8_reward/tokenizer_config.json from bucket guanaco-reward-models
Running pipeline stage ISVCDeleter
Deleting key dreamgen-opus-v1-2-llama-3-8b-v8_reward/vocab.json from bucket guanaco-reward-models
Deleting key envoid-fish-8x7b-v1/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Checking if service fredithefish-biscuitrp-8x7b-v2 is running
Pipeline stage MKMLModelDeleter completed in 3.90s
dreamgen-opus-v1-2-llama-3-8b_v8 status is now torndown due to DeploymentManager action
Deleting key envoid-fish-8x7b-v1/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key envoid-fish-8x7b-v1/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key envoid-fish-8x7b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Tearing down inference service fredithefish-biscuitrp-8x7b-v2
Deleting key envoid-fish-8x7b-v1/tokenizer.json from bucket guanaco-mkml-models
Toredown service fredithefish-biscuitrp-8x7b-v2
Deleting key envoid-fish-8x7b-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key envoid-fish-8x7b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Pipeline stage ISVCDeleter completed in 4.50s
Cleaning model data from model cache
Running pipeline stage MKMLModelDeleter
Deleting key envoid-fish-8x7b-v1_reward/config.json from bucket guanaco-reward-models
Cleaning model data from S3
Deleting key envoid-fish-8x7b-v1_reward/merges.txt from bucket guanaco-reward-models
Cleaning model data from model cache
Deleting key envoid-fish-8x7b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key fredithefish-biscuitrp-8x7b-v2/config.json from bucket guanaco-mkml-models
Deleting key envoid-fish-8x7b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key fredithefish-biscuitrp-8x7b-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key envoid-fish-8x7b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key envoid-fish-8x7b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key envoid-fish-8x7b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 7.90s
envoid-fish-8x7b_v1 status is now torndown due to DeploymentManager action
Deleting key fredithefish-biscuitrp-8x7b-v2/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key fredithefish-biscuitrp-8x7b-v2/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key fredithefish-biscuitrp-8x7b-v2/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key fredithefish-biscuitrp-8x7b-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key fredithefish-biscuitrp-8x7b-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key fredithefish-biscuitrp-8x7b-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key fredithefish-biscuitrp-8x7b-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key fredithefish-biscuitrp-8x7b-v2_reward/config.json from bucket guanaco-reward-models
Deleting key fredithefish-biscuitrp-8x7b-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key fredithefish-biscuitrp-8x7b-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key fredithefish-biscuitrp-8x7b-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key fredithefish-biscuitrp-8x7b-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key fredithefish-biscuitrp-8x7b-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key fredithefish-biscuitrp-8x7b-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.05s
fredithefish-biscuitrp-8x7b_v2 status is now torndown due to DeploymentManager action