submission_id: fredithefish-biscuitrp-8x7b_v4
developer_uid: fredi
status: torndown
model_repo: Fredithefish/BiscuitRP-8x7B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.99, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.9, 'frequency_penalty': 0.3, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
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}
reward_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}
timestamp: 2024-04-08T21:59:06+00:00
model_name: fredithefish-biscuitrp-8x7b_v4
model_eval_status: success
model_group: Fredithefish/BiscuitRP-8
num_battles: 83319
num_wins: 42556
celo_rating: 1169.33
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: MixtralForCausalLM
model_num_parameters: 46702792704.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: fredithefish-biscuitrp-8x7b_v4
ineligible_reason: propriety_total_count < 800
language_model: Fredithefish/BiscuitRP-8x7B
model_size: 47B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-08
win_ratio: 0.5107598506943194
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name fredithefish-biscuitrp-8x7b-v4-mkmlizer
Waiting for job on fredithefish-biscuitrp-8x7b-v4-mkmlizer to finish
fredithefish-biscuitrp-8x7b-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
fredithefish-biscuitrp-8x7b-v4-mkmlizer: ║ _____ __ __ ║
fredithefish-biscuitrp-8x7b-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
fredithefish-biscuitrp-8x7b-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
fredithefish-biscuitrp-8x7b-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
fredithefish-biscuitrp-8x7b-v4-mkmlizer: ║ /___/ ║
fredithefish-biscuitrp-8x7b-v4-mkmlizer: ║ ║
fredithefish-biscuitrp-8x7b-v4-mkmlizer: ║ Version: 0.8.6 ║
fredithefish-biscuitrp-8x7b-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
fredithefish-biscuitrp-8x7b-v4-mkmlizer: ║ ║
fredithefish-biscuitrp-8x7b-v4-mkmlizer: ║ The license key for the current software has been verified as ║
fredithefish-biscuitrp-8x7b-v4-mkmlizer: ║ belonging to: ║
fredithefish-biscuitrp-8x7b-v4-mkmlizer: ║ ║
fredithefish-biscuitrp-8x7b-v4-mkmlizer: ║ Chai Research Corp. ║
fredithefish-biscuitrp-8x7b-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
fredithefish-biscuitrp-8x7b-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
fredithefish-biscuitrp-8x7b-v4-mkmlizer: ║ ║
fredithefish-biscuitrp-8x7b-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
fredithefish-biscuitrp-8x7b-v4-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-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
fredithefish-biscuitrp-8x7b-v4-mkmlizer: Downloaded to shared memory in 55.100s
fredithefish-biscuitrp-8x7b-v4-mkmlizer: quantizing model to /dev/shm/model_cache
fredithefish-biscuitrp-8x7b-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
fredithefish-biscuitrp-8x7b-v4-mkmlizer: quantized model in 48.915s
fredithefish-biscuitrp-8x7b-v4-mkmlizer: Processed model Fredithefish/BiscuitRP-8x7B in 109.560s
fredithefish-biscuitrp-8x7b-v4-mkmlizer: creating bucket guanaco-mkml-models
fredithefish-biscuitrp-8x7b-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
fredithefish-biscuitrp-8x7b-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v4
fredithefish-biscuitrp-8x7b-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v4/special_tokens_map.json
fredithefish-biscuitrp-8x7b-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v4/config.json
fredithefish-biscuitrp-8x7b-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v4/tokenizer_config.json
fredithefish-biscuitrp-8x7b-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v4/tokenizer.json
fredithefish-biscuitrp-8x7b-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v4/tokenizer.model
fredithefish-biscuitrp-8x7b-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v4/flywheel_model.3.safetensors
fredithefish-biscuitrp-8x7b-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v4/flywheel_model.0.safetensors
fredithefish-biscuitrp-8x7b-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v4/flywheel_model.2.safetensors
fredithefish-biscuitrp-8x7b-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/fredithefish-biscuitrp-8x7b-v4/flywheel_model.1.safetensors
fredithefish-biscuitrp-8x7b-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
fredithefish-biscuitrp-8x7b-v4-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 1%| | 10/995 [00:00<00:10, 92.67it/s] Loading 0: 2%|▏ | 20/995 [00:00<00:11, 86.62it/s] Loading 0: 3%|▎ | 34/995 [00:00<00:08, 108.26it/s] Loading 0: 5%|▍ | 45/995 [00:00<00:10, 93.75it/s] Loading 0: 6%|▌ | 55/995 [00:00<00:10, 90.86it/s] Loading 0: 7%|▋ | 70/995 [00:00<00:08, 108.00it/s] Loading 0: 8%|▊ | 82/995 [00:00<00:09, 97.00it/s] Loading 0: 10%|▉ | 97/995 [00:00<00:08, 109.54it/s] Loading 0: 11%|█ | 109/995 [00:01<00:20, 43.84it/s] Loading 0: 12%|█▏ | 119/995 [00:01<00:17, 51.12it/s] Loading 0: 13%|█▎ | 128/995 [00:01<00:15, 57.30it/s] Loading 0: 14%|█▍ | 142/995 [00:01<00:11, 71.95it/s] Loading 0: 15%|█▌ | 153/995 [00:02<00:11, 74.52it/s] Loading 0: 17%|█▋ | 168/995 [00:02<00:09, 89.08it/s] Loading 0: 18%|█▊ | 179/995 [00:02<00:09, 85.10it/s] Loading 0: 19%|█▉ | 189/995 [00:02<00:09, 81.98it/s] Loading 0: 21%|██ | 204/995 [00:02<00:08, 97.91it/s] Loading 0: 22%|██▏ | 215/995 [00:03<00:18, 41.63it/s] Loading 0: 23%|██▎ | 229/995 [00:03<00:14, 53.85it/s] Loading 0: 24%|██▍ | 239/995 [00:03<00:13, 55.55it/s] Loading 0: 25%|██▍ | 248/995 [00:03<00:12, 58.27it/s] Loading 0: 26%|██▌ | 257/995 [00:03<00:12, 60.43it/s] Loading 0: 27%|██▋ | 265/995 [00:03<00:11, 63.95it/s] Loading 0: 28%|██▊ | 279/995 [00:03<00:08, 80.70it/s] Loading 0: 29%|██▉ | 289/995 [00:12<03:01, 3.90it/s] Loading 0: 30%|███ | 299/995 [00:12<02:09, 5.37it/s] Loading 0: 32%|███▏ | 315/995 [00:12<01:18, 8.68it/s] Loading 0: 33%|███▎ | 327/995 [00:13<01:04, 10.42it/s] Loading 0: 34%|███▍ | 336/995 [00:13<00:49, 13.20it/s] Loading 0: 35%|███▍ | 345/995 [00:13<00:38, 16.84it/s] Loading 0: 36%|███▌ | 359/995 [00:13<00:26, 24.46it/s] Loading 0: 37%|███▋ | 369/995 [00:14<00:21, 29.07it/s] Loading 0: 39%|███▊ | 385/995 [00:14<00:14, 41.97it/s] Loading 0: 40%|███▉ | 396/995 [00:14<00:12, 48.77it/s] Loading 0: 41%|████ | 406/995 [00:14<00:10, 54.13it/s] Loading 0: 42%|████▏ | 420/995 [00:14<00:08, 67.52it/s] Loading 0: 43%|████▎ | 431/995 [00:15<00:14, 39.76it/s] Loading 0: 44%|████▍ | 442/995 [00:15<00:11, 48.58it/s] Loading 0: 45%|████▌ | 452/995 [00:15<00:09, 55.50it/s] Loading 0: 46%|████▋ | 461/995 [00:15<00:08, 60.14it/s] Loading 0: 48%|████▊ | 476/995 [00:15<00:06, 77.47it/s] Loading 0: 49%|████▉ | 487/995 [00:15<00:06, 79.96it/s] Loading 0: 50%|████▉ | 497/995 [00:15<00:06, 81.90it/s] Loading 0: 51%|█████▏ | 512/995 [00:15<00:05, 96.07it/s] Loading 0: 53%|█████▎ | 523/995 [00:16<00:05, 91.49it/s] Loading 0: 54%|█████▎ | 534/995 [00:16<00:10, 42.42it/s] Loading 0: 55%|█████▍ | 545/995 [00:16<00:08, 51.47it/s] Loading 0: 56%|█████▌ | 555/995 [00:16<00:07, 58.25it/s] Loading 0: 57%|█████▋ | 564/995 [00:25<01:57, 3.67it/s] Loading 0: 58%|█████▊ | 575/995 [00:25<01:19, 5.25it/s] Loading 0: 59%|█████▊ | 584/995 [00:26<00:58, 7.01it/s] Loading 0: 60%|██████ | 600/995 [00:26<00:34, 11.39it/s] Loading 0: 61%|██████▏ | 610/995 [00:26<00:25, 14.81it/s] Loading 0: 62%|██████▏ | 620/995 [00:26<00:19, 19.22it/s] Loading 0: 64%|██████▍ | 636/995 [00:26<00:12, 28.89it/s] Loading 0: 65%|██████▌ | 647/995 [00:27<00:13, 25.08it/s] Loading 0: 66%|██████▌ | 656/995 [00:27<00:11, 30.31it/s] Loading 0: 67%|██████▋ | 667/995 [00:27<00:08, 38.37it/s] Loading 0: 68%|██████▊ | 676/995 [00:27<00:07, 44.14it/s] Loading 0: 69%|██████▉ | 691/995 [00:27<00:05, 60.34it/s] Loading 0: 71%|███████ | 702/995 [00:27<00:04, 66.36it/s] Loading 0: 72%|███████▏ | 712/995 [00:27<00:04, 69.70it/s] Loading 0: 73%|███████▎ | 727/995 [00:27<00:03, 84.53it/s] Loading 0: 74%|███████▍ | 738/995 [00:28<00:03, 83.52it/s] Loading 0: 75%|███████▌ | 748/995 [00:29<00:13, 18.97it/s] Loading 0: 76%|███████▌ | 758/995 [00:29<00:09, 24.34it/s] Loading 0: 77%|███████▋ | 767/995 [00:29<00:07, 29.84it/s] Loading 0: 78%|███████▊ | 776/995 [00:30<00:06, 36.40it/s] Loading 0: 79%|███████▉ | 791/995 [00:30<00:03, 51.30it/s] Loading 0: 81%|████████ | 801/995 [00:30<00:03, 57.28it/s] Loading 0: 82%|████████▏ | 811/995 [00:30<00:02, 64.89it/s] Loading 0: 83%|████████▎ | 826/995 [00:30<00:02, 81.02it/s] Loading 0: 84%|████████▍ | 837/995 [00:30<00:01, 82.75it/s] Loading 0: 85%|████████▌ | 848/995 [00:39<00:35, 4.19it/s] Loading 0: 86%|████████▌ | 856/995 [00:40<00:28, 4.92it/s] Loading 0: 87%|████████▋ | 863/995 [00:40<00:21, 6.20it/s] Loading 0: 88%|████████▊ | 872/995 [00:40<00:14, 8.50it/s] Loading 0: 89%|████████▊ | 882/995 [00:40<00:09, 11.92it/s] Loading 0: 89%|████████▉ | 890/995 [00:40<00:06, 15.36it/s] Loading 0: 90%|█████████ | 898/995 [00:40<00:04, 19.66it/s] Loading 0: 92%|█████████▏| 914/995 [00:40<00:02, 31.71it/s] Loading 0: 93%|█████████▎| 924/995 [00:40<00:01, 38.74it/s] Loading 0: 94%|█████████▍| 940/995 [00:40<00:01, 54.39it/s] Loading 0: 96%|█████████▌| 951/995 [00:41<00:00, 59.46it/s] Loading 0: 97%|█████████▋| 962/995 [00:41<00:00, 37.04it/s] Loading 0: 98%|█████████▊| 978/995 [00:41<00:00, 51.18it/s] Loading 0: 99%|█████████▉| 988/995 [00:41<00:00, 57.05it/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-v4-mkmlizer: warnings.warn(
fredithefish-biscuitrp-8x7b-v4-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-v4-mkmlizer: warnings.warn(
fredithefish-biscuitrp-8x7b-v4-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-v4-mkmlizer: warnings.warn(
fredithefish-biscuitrp-8x7b-v4-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-v4-mkmlizer: return self.fget.__get__(instance, owner)()
fredithefish-biscuitrp-8x7b-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
fredithefish-biscuitrp-8x7b-v4-mkmlizer: Saving duration: 0.223s
fredithefish-biscuitrp-8x7b-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.571s
fredithefish-biscuitrp-8x7b-v4-mkmlizer: creating bucket guanaco-reward-models
fredithefish-biscuitrp-8x7b-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
fredithefish-biscuitrp-8x7b-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/fredithefish-biscuitrp-8x7b-v4_reward
fredithefish-biscuitrp-8x7b-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/fredithefish-biscuitrp-8x7b-v4_reward/special_tokens_map.json
fredithefish-biscuitrp-8x7b-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/fredithefish-biscuitrp-8x7b-v4_reward/tokenizer_config.json
fredithefish-biscuitrp-8x7b-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/fredithefish-biscuitrp-8x7b-v4_reward/config.json
fredithefish-biscuitrp-8x7b-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/fredithefish-biscuitrp-8x7b-v4_reward/merges.txt
fredithefish-biscuitrp-8x7b-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/fredithefish-biscuitrp-8x7b-v4_reward/vocab.json
fredithefish-biscuitrp-8x7b-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/fredithefish-biscuitrp-8x7b-v4_reward/tokenizer.json
fredithefish-biscuitrp-8x7b-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/fredithefish-biscuitrp-8x7b-v4_reward/reward.tensors
Job fredithefish-biscuitrp-8x7b-v4-mkmlizer completed after 158.55s with status: succeeded
Stopping job with name fredithefish-biscuitrp-8x7b-v4-mkmlizer
Pipeline stage MKMLizer completed in 164.32s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service fredithefish-biscuitrp-8x7b-v4
Waiting for inference service fredithefish-biscuitrp-8x7b-v4 to be ready
Inference service fredithefish-biscuitrp-8x7b-v4 ready after 60.41743350028992s
Pipeline stage ISVCDeployer completed in 68.27s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9119300842285156s
Received healthy response to inference request in 1.389472246170044s
Received healthy response to inference request in 1.9327926635742188s
Received healthy response to inference request in 2.0569064617156982s
Received healthy response to inference request in 2.0333681106567383s
5 requests
0 failed requests
5th percentile: 1.4939638137817384
10th percentile: 1.5984553813934326
20th percentile: 1.8074385166168212
30th percentile: 1.9161026000976562
40th percentile: 1.9244476318359376
50th percentile: 1.9327926635742188
60th percentile: 1.9730228424072265
70th percentile: 2.013253021240234
80th percentile: 2.0380757808685304
90th percentile: 2.047491121292114
95th percentile: 2.052198791503906
99th percentile: 2.05596492767334
mean time: 1.864893913269043
Pipeline stage StressChecker completed in 10.02s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
fredithefish-biscuitrp-8x7b_v4 status is now deployed due to DeploymentManager action
fredithefish-biscuitrp-8x7b_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of fredithefish-biscuitrp-8x7b_v4
Running pipeline stage ISVCDeleter
Checking if service fredithefish-biscuitrp-8x7b-v4 is running
Tearing down inference service fredithefish-biscuitrp-8x7b-v4
Toredown service fredithefish-biscuitrp-8x7b-v4
Pipeline stage ISVCDeleter completed in 3.27s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key fredithefish-biscuitrp-8x7b-v4/config.json from bucket guanaco-mkml-models
Deleting key fredithefish-biscuitrp-8x7b-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key fredithefish-biscuitrp-8x7b-v4/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key fredithefish-biscuitrp-8x7b-v4/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key fredithefish-biscuitrp-8x7b-v4/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key fredithefish-biscuitrp-8x7b-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key fredithefish-biscuitrp-8x7b-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key fredithefish-biscuitrp-8x7b-v4/tokenizer.model from bucket guanaco-mkml-models
Deleting key fredithefish-biscuitrp-8x7b-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key fredithefish-biscuitrp-8x7b-v4_reward/config.json from bucket guanaco-reward-models
Deleting key fredithefish-biscuitrp-8x7b-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key fredithefish-biscuitrp-8x7b-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key fredithefish-biscuitrp-8x7b-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key fredithefish-biscuitrp-8x7b-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key fredithefish-biscuitrp-8x7b-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key fredithefish-biscuitrp-8x7b-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.06s
fredithefish-biscuitrp-8x7b_v4 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics