thedrummer-moist-miqu-70_4900

submission_id: thedrummer-moist-miqu-70_4900_v1
developer_uid: Meliodia
best_of: 4
celo_rating: 1164.56
display_name: steelskull-l3-ms-astoria-70b_v2
family_friendly_score: 0.0
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
is_internal_developer: True
language_model: TheDrummer/Moist-Miqu-70B-v1.1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: TheDrummer/Moist-Miqu-70
model_name: steelskull-l3-ms-astoria-70b_v2
model_num_parameters: 68976648192.0
model_repo: TheDrummer/Moist-Miqu-70B-v1.1
model_size: 69B
num_battles: 16021
num_wins: 7586
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-06-09T03:46:00+00:00
us_pacific_date: 2024-06-08
win_ratio: 0.4735035266213095
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thedrummer-moist-miqu-70-4900-v1-mkmlizer
Waiting for job on thedrummer-moist-miqu-70-4900-v1-mkmlizer to finish
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ║     _____            __           __                                ║
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ║       /___/                                                         ║
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ║                                                                     ║
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ║  https://mk1.ai                                                     ║
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ║                                                                     ║
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ║  belonging to:                                                      ║
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ║                                                                     ║
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ║  Chai Research Corp.                                                ║
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ║                                                                     ║
thedrummer-moist-miqu-70-4900-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thedrummer-moist-miqu-70-4900-v1-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.
thedrummer-moist-miqu-70-4900-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v42: ('http://mistralai-mixtral-8x7b-3473-v42-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:33130->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission hastagaras-anjir-8b-l3-m_4330_v1: ('http://hastagaras-anjir-8b-l3-m-4330-v1-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
thedrummer-moist-miqu-70-4900-v1-mkmlizer: Downloaded to shared memory in 332.919s
thedrummer-moist-miqu-70-4900-v1-mkmlizer: quantizing model to /dev/shm/model_cache
thedrummer-moist-miqu-70-4900-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
thedrummer-moist-miqu-70-4900-v1-mkmlizer: quantized model in 84.173s
thedrummer-moist-miqu-70-4900-v1-mkmlizer: Processed model TheDrummer/Moist-Miqu-70B-v1.1 in 425.714s
thedrummer-moist-miqu-70-4900-v1-mkmlizer: creating bucket guanaco-mkml-models
thedrummer-moist-miqu-70-4900-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thedrummer-moist-miqu-70-4900-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thedrummer-moist-miqu-70-4900-v1
thedrummer-moist-miqu-70-4900-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thedrummer-moist-miqu-70-4900-v1/config.json
thedrummer-moist-miqu-70-4900-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thedrummer-moist-miqu-70-4900-v1/tokenizer_config.json
thedrummer-moist-miqu-70-4900-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thedrummer-moist-miqu-70-4900-v1/special_tokens_map.json
thedrummer-moist-miqu-70-4900-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/thedrummer-moist-miqu-70-4900-v1/tokenizer.model
thedrummer-moist-miqu-70-4900-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thedrummer-moist-miqu-70-4900-v1/tokenizer.json
thedrummer-moist-miqu-70-4900-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.5.safetensors s3://guanaco-mkml-models/thedrummer-moist-miqu-70-4900-v1/flywheel_model.5.safetensors
thedrummer-moist-miqu-70-4900-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/thedrummer-moist-miqu-70-4900-v1/flywheel_model.1.safetensors
thedrummer-moist-miqu-70-4900-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/thedrummer-moist-miqu-70-4900-v1/flywheel_model.2.safetensors
thedrummer-moist-miqu-70-4900-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/thedrummer-moist-miqu-70-4900-v1/flywheel_model.4.safetensors
thedrummer-moist-miqu-70-4900-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/thedrummer-moist-miqu-70-4900-v1/flywheel_model.3.safetensors
thedrummer-moist-miqu-70-4900-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/thedrummer-moist-miqu-70-4900-v1/flywheel_model.0.safetensors
thedrummer-moist-miqu-70-4900-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thedrummer-moist-miqu-70-4900-v1-mkmlizer: 
Loading 0:   0%|          | 0/723 [00:00<?, ?it/s]
Loading 0:   0%|          | 2/723 [00:02<13:05,  1.09s/it]
Loading 0:   1%|          | 5/723 [00:02<04:27,  2.68it/s]
Loading 0:   2%|▏         | 13/723 [00:02<01:22,  8.62it/s]
Loading 0:   2%|▏         | 17/723 [00:02<01:00, 11.71it/s]
Loading 0:   3%|▎         | 23/723 [00:02<00:56, 12.46it/s]
Loading 0:   4%|▍         | 31/723 [00:03<00:35, 19.46it/s]
Loading 0:   5%|▍         | 36/723 [00:03<00:29, 23.17it/s]
Loading 0:   6%|▌         | 41/723 [00:03<00:25, 27.10it/s]
Loading 0:   7%|▋         | 49/723 [00:03<00:27, 24.09it/s]
Loading 0:   7%|▋         | 53/723 [00:03<00:25, 26.15it/s]
Loading 0:   8%|▊         | 59/723 [00:03<00:21, 30.96it/s]
Loading 0:   9%|▉         | 67/723 [00:04<00:17, 38.32it/s]
Loading 0:  10%|▉         | 72/723 [00:04<00:16, 39.33it/s]
Loading 0:  11%|█         | 77/723 [00:04<00:25, 25.58it/s]
Loading 0:  12%|█▏        | 85/723 [00:04<00:19, 33.12it/s]
Loading 0:  12%|█▏        | 90/723 [00:04<00:18, 34.86it/s]
Loading 0:  13%|█▎        | 95/723 [00:04<00:16, 37.36it/s]
Loading 0:  14%|█▍        | 100/723 [00:05<00:24, 25.59it/s]
Loading 0:  14%|█▍        | 104/723 [00:05<00:22, 27.88it/s]
Loading 0:  15%|█▌        | 112/723 [00:05<00:17, 35.59it/s]
Loading 0:  16%|█▌        | 117/723 [00:05<00:16, 37.09it/s]
Loading 0:  17%|█▋        | 122/723 [00:05<00:15, 39.39it/s]
Loading 0:  18%|█▊        | 127/723 [00:06<00:21, 27.14it/s]
Loading 0:  18%|█▊        | 132/723 [00:16<06:07,  1.61it/s]
Loading 0:  19%|█▉        | 140/723 [00:16<03:42,  2.63it/s]
Loading 0:  20%|██        | 148/723 [00:16<02:23,  4.02it/s]
Loading 0:  21%|██▏       | 154/723 [00:17<01:53,  5.00it/s]
Loading 0:  22%|██▏       | 159/723 [00:17<01:28,  6.36it/s]
Loading 0:  23%|██▎       | 167/723 [00:17<00:58,  9.45it/s]
Loading 0:  24%|██▍       | 175/723 [00:17<00:48, 11.38it/s]
Loading 0:  25%|██▍       | 179/723 [00:17<00:41, 13.21it/s]
Loading 0:  26%|██▌       | 185/723 [00:18<00:31, 16.92it/s]
Loading 0:  27%|██▋       | 193/723 [00:18<00:22, 23.11it/s]
Loading 0:  27%|██▋       | 198/723 [00:18<00:19, 26.34it/s]
Loading 0:  28%|██▊       | 203/723 [00:18<00:24, 20.89it/s]
Loading 0:  29%|██▉       | 211/723 [00:18<00:18, 27.99it/s]
Loading 0:  30%|██▉       | 216/723 [00:18<00:16, 30.83it/s]
Loading 0:  31%|███       | 221/723 [00:18<00:14, 34.00it/s]
Loading 0:  31%|███▏      | 226/723 [00:19<00:20, 24.39it/s]
Loading 0:  32%|███▏      | 231/723 [00:19<00:18, 26.82it/s]
Loading 0:  33%|███▎      | 239/723 [00:19<00:13, 34.77it/s]
Loading 0:  34%|███▍      | 247/723 [00:19<00:11, 41.86it/s]
Loading 0:  35%|███▍      | 253/723 [00:20<00:16, 28.06it/s]
Loading 0:  36%|███▌      | 258/723 [00:20<00:15, 29.71it/s]
Loading 0:  37%|███▋      | 266/723 [00:20<00:12, 36.90it/s]
Loading 0:  37%|███▋      | 271/723 [00:30<00:12, 36.90it/s]
Loading 0:  38%|███▊      | 272/723 [00:30<03:51,  1.95it/s]
Loading 0:  38%|███▊      | 275/723 [00:31<03:22,  2.21it/s]
Loading 0:  39%|███▉      | 283/723 [00:31<02:04,  3.53it/s]
Loading 0:  40%|███▉      | 288/723 [00:31<01:33,  4.63it/s]
Loading 0:  41%|████      | 293/723 [00:31<01:10,  6.11it/s]
Loading 0:  42%|████▏     | 301/723 [00:32<00:51,  8.26it/s]
Loading 0:  42%|████▏     | 306/723 [00:32<00:40, 10.41it/s]
Loading 0:  43%|████▎     | 311/723 [00:32<00:31, 13.15it/s]
Loading 0:  44%|████▍     | 319/723 [00:32<00:21, 18.84it/s]
Loading 0:  45%|████▍     | 324/723 [00:32<00:18, 22.00it/s]
Loading 0:  46%|████▌     | 329/723 [00:33<00:21, 18.30it/s]
Loading 0:  47%|████▋     | 337/723 [00:33<00:15, 24.93it/s]
Loading 0:  47%|████▋     | 342/723 [00:33<00:13, 27.97it/s]
Loading 0:  48%|████▊     | 347/723 [00:33<00:12, 31.24it/s]
Loading 0:  49%|████▊     | 352/723 [00:33<00:16, 23.16it/s]
Loading 0:  49%|████▉     | 357/723 [00:33<00:14, 25.59it/s]
Loading 0:  50%|█████     | 365/723 [00:34<00:10, 33.24it/s]
Loading 0:  52%|█████▏    | 373/723 [00:34<00:08, 40.47it/s]
Loading 0:  52%|█████▏    | 379/723 [00:34<00:12, 27.55it/s]
Loading 0:  53%|█████▎    | 384/723 [00:34<00:11, 29.33it/s]
Loading 0:  54%|█████▍    | 392/723 [00:34<00:09, 36.59it/s]
Loading 0:  55%|█████▌    | 400/723 [00:34<00:07, 42.76it/s]
Loading 0:  56%|█████▌    | 406/723 [00:35<00:10, 29.25it/s]
Loading 0:  57%|█████▋    | 411/723 [00:46<02:54,  1.79it/s]
Loading 0:  58%|█████▊    | 419/723 [00:46<01:51,  2.73it/s]
Loading 0:  59%|█████▉    | 427/723 [00:46<01:17,  3.81it/s]
Loading 0:  60%|█████▉    | 431/723 [00:47<01:03,  4.62it/s]
Loading 0:  60%|██████    | 437/723 [00:47<00:45,  6.31it/s]
Loading 0:  62%|██████▏   | 445/723 [00:47<00:29,  9.33it/s]
Loading 0:  62%|██████▏   | 450/723 [00:47<00:23, 11.55it/s]
Loading 0:  63%|██████▎   | 455/723 [00:47<00:22, 11.69it/s]
Loading 0:  64%|██████▍   | 463/723 [00:47<00:15, 16.81it/s]
Loading 0:  65%|██████▍   | 468/723 [00:48<00:12, 19.80it/s]
Loading 0:  65%|██████▌   | 473/723 [00:48<00:10, 23.44it/s]
Loading 0:  66%|██████▌   | 478/723 [00:48<00:12, 19.82it/s]
Loading 0:  67%|██████▋   | 483/723 [00:48<00:10, 22.50it/s]
Loading 0:  68%|██████▊   | 491/723 [00:48<00:07, 30.14it/s]
Loading 0:  69%|██████▉   | 499/723 [00:48<00:06, 37.21it/s]
Loading 0:  70%|██████▉   | 505/723 [00:49<00:08, 26.72it/s]
Loading 0:  71%|███████   | 510/723 [00:49<00:07, 28.36it/s]
Loading 0:  72%|███████▏  | 518/723 [00:49<00:05, 35.72it/s]
Loading 0:  73%|███████▎  | 526/723 [00:49<00:04, 42.31it/s]
Loading 0:  74%|███████▎  | 532/723 [00:50<00:06, 28.25it/s]
Loading 0:  74%|███████▍  | 537/723 [00:50<00:06, 29.85it/s]
Loading 0:  75%|███████▌  | 545/723 [00:50<00:04, 36.89it/s]
Loading 0:  75%|███████▌  | 545/723 [01:01<00:04, 36.89it/s]
Loading 0:  76%|███████▌  | 546/723 [01:01<02:02,  1.44it/s]
Loading 0:  76%|███████▋  | 553/723 [01:02<01:20,  2.10it/s]
Loading 0:  77%|███████▋  | 557/723 [01:02<01:01,  2.70it/s]
Loading 0:  78%|███████▊  | 563/723 [01:02<00:40,  3.95it/s]
Loading 0:  79%|███████▉  | 571/723 [01:02<00:24,  6.21it/s]
Loading 0:  80%|███████▉  | 576/723 [01:02<00:18,  7.97it/s]
Loading 0:  80%|████████  | 581/723 [01:03<00:18,  7.72it/s]
Loading 0:  81%|████████▏ | 589/723 [01:03<00:11, 11.63it/s]
Loading 0:  82%|████████▏ | 594/723 [01:03<00:09, 14.32it/s]
Loading 0:  83%|████████▎ | 599/723 [01:03<00:07, 17.60it/s]
Loading 0:  84%|████████▎ | 604/723 [01:04<00:07, 16.60it/s]
Loading 0:  84%|████████▍ | 609/723 [01:04<00:05, 19.44it/s]
Loading 0:  85%|████████▌ | 617/723 [01:04<00:03, 26.89it/s]
Loading 0:  86%|████████▋ | 625/723 [01:04<00:02, 34.17it/s]
Loading 0:  87%|████████▋ | 631/723 [01:04<00:03, 25.97it/s]
Loading 0:  88%|████████▊ | 636/723 [01:05<00:03, 27.73it/s]
Loading 0:  89%|████████▉ | 644/723 [01:05<00:02, 34.81it/s]
Loading 0:  90%|█████████ | 652/723 [01:05<00:01, 41.09it/s]
Loading 0:  91%|█████████ | 658/723 [01:05<00:02, 28.51it/s]
Loading 0:  92%|█████████▏| 663/723 [01:05<00:01, 30.00it/s]
Loading 0:  93%|█████████▎| 671/723 [01:05<00:01, 37.08it/s]
Loading 0:  94%|█████████▍| 679/723 [01:06<00:01, 28.98it/s]
Loading 0:  95%|█████████▍| 684/723 [01:06<00:01, 31.65it/s]
Loading 0:  95%|█████████▌| 689/723 [01:17<00:19,  1.74it/s]
Loading 0:  96%|█████████▋| 697/723 [01:17<00:09,  2.69it/s]
Loading 0:  97%|█████████▋| 702/723 [01:17<00:06,  3.49it/s]
Loading 0:  98%|█████████▊| 707/723 [01:18<00:03,  4.24it/s]
Loading 0:  99%|█████████▉| 715/723 [01:18<00:01,  6.50it/s]
Loading 0: 100%|█████████▉| 720/723 [01:18<00:00,  8.26it/s]
                                                            
/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.
thedrummer-moist-miqu-70-4900-v1-mkmlizer:   warnings.warn(
thedrummer-moist-miqu-70-4900-v1-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.
thedrummer-moist-miqu-70-4900-v1-mkmlizer:   warnings.warn(
thedrummer-moist-miqu-70-4900-v1-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.
thedrummer-moist-miqu-70-4900-v1-mkmlizer:   warnings.warn(
thedrummer-moist-miqu-70-4900-v1-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()
thedrummer-moist-miqu-70-4900-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
thedrummer-moist-miqu-70-4900-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thedrummer-moist-miqu-70-4900-v1-mkmlizer: Saving duration: 0.276s
thedrummer-moist-miqu-70-4900-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 9.809s
thedrummer-moist-miqu-70-4900-v1-mkmlizer: creating bucket guanaco-reward-models
thedrummer-moist-miqu-70-4900-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thedrummer-moist-miqu-70-4900-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thedrummer-moist-miqu-70-4900-v1_reward
thedrummer-moist-miqu-70-4900-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thedrummer-moist-miqu-70-4900-v1_reward/special_tokens_map.json
thedrummer-moist-miqu-70-4900-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thedrummer-moist-miqu-70-4900-v1_reward/config.json
thedrummer-moist-miqu-70-4900-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thedrummer-moist-miqu-70-4900-v1_reward/tokenizer_config.json
thedrummer-moist-miqu-70-4900-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thedrummer-moist-miqu-70-4900-v1_reward/merges.txt
thedrummer-moist-miqu-70-4900-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thedrummer-moist-miqu-70-4900-v1_reward/vocab.json
thedrummer-moist-miqu-70-4900-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thedrummer-moist-miqu-70-4900-v1_reward/tokenizer.json
thedrummer-moist-miqu-70-4900-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thedrummer-moist-miqu-70-4900-v1_reward/reward.tensors
Job thedrummer-moist-miqu-70-4900-v1-mkmlizer completed after 484.42s with status: succeeded
Stopping job with name thedrummer-moist-miqu-70-4900-v1-mkmlizer
Pipeline stage MKMLizer completed in 487.32s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service thedrummer-moist-miqu-70-4900-v1
Waiting for inference service thedrummer-moist-miqu-70-4900-v1 to be ready
Inference service thedrummer-moist-miqu-70-4900-v1 ready after 90.438303232193s
Pipeline stage ISVCDeployer completed in 97.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.511373043060303s
Received healthy response to inference request in 4.171605587005615s
Received healthy response to inference request in 2.1895792484283447s
Received healthy response to inference request in 1.8640823364257812s
Received healthy response to inference request in 2.304457664489746s
5 requests
0 failed requests
5th percentile: 1.9291817188262939
10th percentile: 1.9942811012268067
20th percentile: 2.124479866027832
30th percentile: 2.212554931640625
40th percentile: 2.2585062980651855
50th percentile: 2.304457664489746
60th percentile: 3.0513168334960934
70th percentile: 3.798176002502441
80th percentile: 4.239559078216553
90th percentile: 4.375466060638428
95th percentile: 4.443419551849365
99th percentile: 4.497782344818115
mean time: 3.008219575881958
Pipeline stage StressChecker completed in 16.18s
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
thedrummer-moist-miqu-70_4900_v1 status is now deployed due to DeploymentManager action
thedrummer-moist-miqu-70_4900_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of thedrummer-moist-miqu-70_4900_v1
Running pipeline stage ISVCDeleter
Checking if service thedrummer-moist-miqu-70-4900-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.85s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key thedrummer-moist-miqu-70-4900-v1/config.json from bucket guanaco-mkml-models
Deleting key thedrummer-moist-miqu-70-4900-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key thedrummer-moist-miqu-70-4900-v1/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key thedrummer-moist-miqu-70-4900-v1/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key thedrummer-moist-miqu-70-4900-v1/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key thedrummer-moist-miqu-70-4900-v1/flywheel_model.4.safetensors from bucket guanaco-mkml-models
Deleting key thedrummer-moist-miqu-70-4900-v1/flywheel_model.5.safetensors from bucket guanaco-mkml-models
Deleting key thedrummer-moist-miqu-70-4900-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key thedrummer-moist-miqu-70-4900-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key thedrummer-moist-miqu-70-4900-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key thedrummer-moist-miqu-70-4900-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key thedrummer-moist-miqu-70-4900-v1_reward/config.json from bucket guanaco-reward-models
Deleting key thedrummer-moist-miqu-70-4900-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key thedrummer-moist-miqu-70-4900-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key thedrummer-moist-miqu-70-4900-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key thedrummer-moist-miqu-70-4900-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key thedrummer-moist-miqu-70-4900-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key thedrummer-moist-miqu-70-4900-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 13.10s
thedrummer-moist-miqu-70_4900_v1 status is now torndown due to DeploymentManager action