submission_id: sicariussicariistuff-ten_5200_v1
developer_uid: windyheath
alignment_samples: 0
best_of: 4
celo_rating: 1137.64
display_name: sicariussicariistuff-ten_5200_v1
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}
ineligible_reason: propriety_total_count < 800
is_internal_developer: False
language_model: SicariusSicariiStuff/Tenebra_30B_Alpha01_FP16
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: SicariusSicariiStuff/Ten
model_name: sicariussicariistuff-ten_5200_v1
model_num_parameters: 32528943616.0
model_repo: SicariusSicariiStuff/Tenebra_30B_Alpha01_FP16
model_size: 33B
num_battles: 7088
num_wins: 3201
propriety_score: 0.7105263157894737
propriety_total_count: 532.0
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: 2024-06-07T20:32:56+00:00
us_pacific_date: 2024-06-07
win_ratio: 0.45160835214446954
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sicariussicariistuff-ten-5200-v1-mkmlizer
Waiting for job on sicariussicariistuff-ten-5200-v1-mkmlizer to finish
sicariussicariistuff-ten-5200-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sicariussicariistuff-ten-5200-v1-mkmlizer: ║     _____            __           __                                ║
sicariussicariistuff-ten-5200-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sicariussicariistuff-ten-5200-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sicariussicariistuff-ten-5200-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sicariussicariistuff-ten-5200-v1-mkmlizer: ║       /___/                                                         ║
sicariussicariistuff-ten-5200-v1-mkmlizer: ║                                                                     ║
sicariussicariistuff-ten-5200-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
sicariussicariistuff-ten-5200-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sicariussicariistuff-ten-5200-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sicariussicariistuff-ten-5200-v1-mkmlizer: ║                                                                     ║
sicariussicariistuff-ten-5200-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sicariussicariistuff-ten-5200-v1-mkmlizer: ║  belonging to:                                                      ║
sicariussicariistuff-ten-5200-v1-mkmlizer: ║                                                                     ║
sicariussicariistuff-ten-5200-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sicariussicariistuff-ten-5200-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sicariussicariistuff-ten-5200-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
sicariussicariistuff-ten-5200-v1-mkmlizer: ║                                                                     ║
sicariussicariistuff-ten-5200-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sicariussicariistuff-ten-5200-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.
sicariussicariistuff-ten-5200-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
sicariussicariistuff-ten-5200-v1-mkmlizer: Downloaded to shared memory in 115.016s
sicariussicariistuff-ten-5200-v1-mkmlizer: quantizing model to /dev/shm/model_cache
sicariussicariistuff-ten-5200-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sicariussicariistuff-ten-5200-v1-mkmlizer: quantized model in 56.155s
sicariussicariistuff-ten-5200-v1-mkmlizer: Processed model SicariusSicariiStuff/Tenebra_30B_Alpha01_FP16 in 181.343s
sicariussicariistuff-ten-5200-v1-mkmlizer: creating bucket guanaco-mkml-models
sicariussicariistuff-ten-5200-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sicariussicariistuff-ten-5200-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sicariussicariistuff-ten-5200-v1
sicariussicariistuff-ten-5200-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sicariussicariistuff-ten-5200-v1/config.json
sicariussicariistuff-ten-5200-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sicariussicariistuff-ten-5200-v1/tokenizer_config.json
sicariussicariistuff-ten-5200-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sicariussicariistuff-ten-5200-v1/special_tokens_map.json
sicariussicariistuff-ten-5200-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sicariussicariistuff-ten-5200-v1/tokenizer.model
sicariussicariistuff-ten-5200-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sicariussicariistuff-ten-5200-v1/tokenizer.json
sicariussicariistuff-ten-5200-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/sicariussicariistuff-ten-5200-v1/flywheel_model.2.safetensors
sicariussicariistuff-ten-5200-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/sicariussicariistuff-ten-5200-v1/flywheel_model.1.safetensors
sicariussicariistuff-ten-5200-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sicariussicariistuff-ten-5200-v1/flywheel_model.0.safetensors
sicariussicariistuff-ten-5200-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sicariussicariistuff-ten-5200-v1-mkmlizer: 
Loading 0:   0%|          | 0/543 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 7/543 [00:00<00:08, 66.04it/s]
Loading 0:   3%|▎         | 14/543 [00:00<00:08, 60.66it/s]
Loading 0:   4%|▍         | 23/543 [00:00<00:07, 65.43it/s]
Loading 0:   6%|▌         | 32/543 [00:00<00:07, 67.57it/s]
Loading 0:   7%|▋         | 40/543 [00:00<00:07, 71.28it/s]
Loading 0:   9%|▉         | 48/543 [00:00<00:06, 73.76it/s]
Loading 0:  10%|█         | 56/543 [00:00<00:06, 75.41it/s]
Loading 0:  12%|█▏        | 64/543 [00:00<00:06, 70.90it/s]
Loading 0:  13%|█▎        | 72/543 [00:01<00:13, 35.22it/s]
Loading 0:  15%|█▍        | 79/543 [00:01<00:11, 40.27it/s]
Loading 0:  16%|█▌        | 86/543 [00:01<00:10, 43.97it/s]
Loading 0:  17%|█▋        | 94/543 [00:01<00:08, 51.12it/s]
Loading 0:  19%|█▊        | 101/543 [00:01<00:08, 54.98it/s]
Loading 0:  20%|█▉        | 108/543 [00:01<00:07, 54.82it/s]
Loading 0:  22%|██▏       | 117/543 [00:02<00:07, 59.28it/s]
Loading 0:  23%|██▎       | 126/543 [00:02<00:06, 62.54it/s]
Loading 0:  24%|██▍       | 133/543 [00:02<00:11, 36.04it/s]
Loading 0:  26%|██▌       | 139/543 [00:02<00:10, 38.93it/s]
Loading 0:  27%|██▋       | 148/543 [00:02<00:08, 46.16it/s]
Loading 0:  29%|██▊       | 156/543 [00:02<00:07, 52.97it/s]
Loading 0:  30%|███       | 165/543 [00:03<00:06, 57.99it/s]
Loading 0:  32%|███▏      | 173/543 [00:03<00:05, 63.04it/s]
Loading 0:  33%|███▎      | 181/543 [00:03<00:05, 63.21it/s]
Loading 0:  35%|███▍      | 188/543 [00:03<00:05, 63.95it/s]
Loading 0:  36%|███▌      | 195/543 [00:03<00:05, 64.20it/s]
Loading 0:  37%|███▋      | 202/543 [00:03<00:09, 34.14it/s]
Loading 0:  39%|███▊      | 210/543 [00:04<00:08, 41.48it/s]
Loading 0:  40%|███▉      | 217/543 [00:04<00:06, 46.80it/s]
Loading 0:  40%|████      | 218/543 [00:20<00:06, 46.80it/s]
Loading 0:  40%|████      | 219/543 [00:20<04:40,  1.16it/s]
Loading 0:  42%|████▏     | 226/543 [00:20<03:02,  1.74it/s]
Loading 0:  43%|████▎     | 233/543 [00:20<02:01,  2.55it/s]
Loading 0:  44%|████▍     | 240/543 [00:20<01:22,  3.68it/s]
Loading 0:  46%|████▌     | 248/543 [00:20<00:54,  5.43it/s]
Loading 0:  47%|████▋     | 257/543 [00:21<00:35,  8.08it/s]
Loading 0:  49%|████▉     | 266/543 [00:21<00:27, 10.07it/s]
Loading 0:  50%|█████     | 272/543 [00:21<00:21, 12.61it/s]
Loading 0:  51%|█████     | 278/543 [00:21<00:16, 15.77it/s]
Loading 0:  52%|█████▏    | 284/543 [00:21<00:13, 19.58it/s]
Loading 0:  54%|█████▍    | 293/543 [00:21<00:09, 26.65it/s]
Loading 0:  56%|█████▌    | 302/543 [00:22<00:07, 33.90it/s]
Loading 0:  57%|█████▋    | 311/543 [00:22<00:05, 40.78it/s]
Loading 0:  59%|█████▉    | 320/543 [00:22<00:04, 47.18it/s]
Loading 0:  61%|██████    | 329/543 [00:22<00:03, 55.05it/s]
Loading 0:  62%|██████▏   | 337/543 [00:22<00:06, 33.54it/s]
Loading 0:  64%|██████▎   | 345/543 [00:23<00:04, 40.27it/s]
Loading 0:  65%|██████▌   | 354/543 [00:23<00:04, 46.70it/s]
Loading 0:  66%|██████▋   | 361/543 [00:23<00:03, 50.64it/s]
Loading 0:  68%|██████▊   | 368/543 [00:23<00:03, 53.80it/s]
Loading 0:  69%|██████▉   | 375/543 [00:23<00:02, 56.36it/s]
Loading 0:  71%|███████   | 383/543 [00:23<00:02, 58.33it/s]
Loading 0:  72%|███████▏  | 391/543 [00:23<00:02, 63.52it/s]
Loading 0:  73%|███████▎  | 398/543 [00:24<00:04, 35.17it/s]
Loading 0:  74%|███████▍  | 404/543 [00:24<00:03, 38.73it/s]
Loading 0:  76%|███████▌  | 410/543 [00:24<00:03, 42.33it/s]
Loading 0:  77%|███████▋  | 419/543 [00:24<00:02, 49.59it/s]
Loading 0:  79%|███████▉  | 428/543 [00:24<00:02, 55.26it/s]
Loading 0:  80%|████████  | 437/543 [00:24<00:01, 59.44it/s]
Loading 0:  81%|████████  | 438/543 [00:41<00:01, 59.44it/s]
Loading 0:  81%|████████  | 439/543 [00:41<01:22,  1.27it/s]
Loading 0:  82%|████████▏ | 446/543 [00:41<00:52,  1.84it/s]
Loading 0:  84%|████████▍ | 455/543 [00:41<00:30,  2.89it/s]
Loading 0:  86%|████████▌ | 465/543 [00:41<00:18,  4.25it/s]
Loading 0:  87%|████████▋ | 471/543 [00:41<00:13,  5.45it/s]
Loading 0:  88%|████████▊ | 478/543 [00:42<00:08,  7.40it/s]
Loading 0:  89%|████████▉ | 485/543 [00:42<00:05,  9.96it/s]
Loading 0:  90%|█████████ | 491/543 [00:42<00:04, 12.70it/s]
Loading 0:  92%|█████████▏| 500/543 [00:42<00:02, 18.00it/s]
Loading 0:  94%|█████████▎| 509/543 [00:42<00:01, 24.09it/s]
Loading 0:  95%|█████████▌| 518/543 [00:42<00:00, 30.67it/s]
Loading 0:  97%|█████████▋| 526/543 [00:42<00:00, 36.91it/s]
Loading 0:  98%|█████████▊| 533/543 [00:45<00:01,  8.53it/s]
Loading 0:  99%|█████████▉| 540/543 [00:45<00:00, 11.23it/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.
sicariussicariistuff-ten-5200-v1-mkmlizer:   warnings.warn(
sicariussicariistuff-ten-5200-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.
sicariussicariistuff-ten-5200-v1-mkmlizer:   warnings.warn(
sicariussicariistuff-ten-5200-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.
sicariussicariistuff-ten-5200-v1-mkmlizer:   warnings.warn(
sicariussicariistuff-ten-5200-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()
sicariussicariistuff-ten-5200-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
sicariussicariistuff-ten-5200-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sicariussicariistuff-ten-5200-v1-mkmlizer: Saving duration: 0.409s
sicariussicariistuff-ten-5200-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.236s
sicariussicariistuff-ten-5200-v1-mkmlizer: creating bucket guanaco-reward-models
sicariussicariistuff-ten-5200-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sicariussicariistuff-ten-5200-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sicariussicariistuff-ten-5200-v1_reward
sicariussicariistuff-ten-5200-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sicariussicariistuff-ten-5200-v1_reward/special_tokens_map.json
sicariussicariistuff-ten-5200-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sicariussicariistuff-ten-5200-v1_reward/config.json
sicariussicariistuff-ten-5200-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sicariussicariistuff-ten-5200-v1_reward/vocab.json
sicariussicariistuff-ten-5200-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sicariussicariistuff-ten-5200-v1_reward/merges.txt
sicariussicariistuff-ten-5200-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sicariussicariistuff-ten-5200-v1_reward/tokenizer_config.json
sicariussicariistuff-ten-5200-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sicariussicariistuff-ten-5200-v1_reward/tokenizer.json
sicariussicariistuff-ten-5200-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sicariussicariistuff-ten-5200-v1_reward/reward.tensors
Job sicariussicariistuff-ten-5200-v1-mkmlizer completed after 220.85s with status: succeeded
Stopping job with name sicariussicariistuff-ten-5200-v1-mkmlizer
Pipeline stage MKMLizer completed in 224.58s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service sicariussicariistuff-ten-5200-v1
Waiting for inference service sicariussicariistuff-ten-5200-v1 to be ready
Inference service sicariussicariistuff-ten-5200-v1 ready after 50.2655303478241s
Pipeline stage ISVCDeployer completed in 57.17s
Running pipeline stage StressChecker
%s, retrying in %s seconds...
Received healthy response to inference request in 3.7258729934692383s
Received healthy response to inference request in 3.8739211559295654s
Received healthy response to inference request in 3.3650565147399902s
Received healthy response to inference request in 7.699918985366821s
Received healthy response to inference request in 3.400879383087158s
5 requests
0 failed requests
5th percentile: 3.372221088409424
10th percentile: 3.3793856620788576
20th percentile: 3.3937148094177245
30th percentile: 3.4658781051635743
40th percentile: 3.595875549316406
50th percentile: 3.7258729934692383
60th percentile: 3.785092258453369
70th percentile: 3.8443115234375
80th percentile: 4.639120721817017
90th percentile: 6.169519853591919
95th percentile: 6.93471941947937
99th percentile: 7.546879072189331
mean time: 4.413129806518555
Pipeline stage StressChecker completed in 42.80s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
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
sicariussicariistuff-ten_5200_v1 status is now deployed due to DeploymentManager action
sicariussicariistuff-ten_5200_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sicariussicariistuff-ten_5200_v1
Running pipeline stage ISVCDeleter
Checking if service sicariussicariistuff-ten-5200-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.47s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sicariussicariistuff-ten-5200-v1/config.json from bucket guanaco-mkml-models
Deleting key sicariussicariistuff-ten-5200-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sicariussicariistuff-ten-5200-v1/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key sicariussicariistuff-ten-5200-v1/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key sicariussicariistuff-ten-5200-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sicariussicariistuff-ten-5200-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key sicariussicariistuff-ten-5200-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key sicariussicariistuff-ten-5200-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sicariussicariistuff-ten-5200-v1_reward/config.json from bucket guanaco-reward-models
Deleting key sicariussicariistuff-ten-5200-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key sicariussicariistuff-ten-5200-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sicariussicariistuff-ten-5200-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sicariussicariistuff-ten-5200-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sicariussicariistuff-ten-5200-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sicariussicariistuff-ten-5200-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 9.15s
sicariussicariistuff-ten_5200_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics