maldv-badger-zeta-l3-4x8b

developer_uid: maldevide

submission_id: maldv-badger-zeta-l3-4x8b_v2

model_name: badger-zeta-l3-4x8b

model_group: maldv/badger-zeta-l3-4x8

status: torndown

timestamp: 2024-05-17T18:22:30+00:00

num_battles: 20836

num_wins: 10103

celo_rating: 1164.97

family_friendly_score: 0.0

submission_type: basic

model_repo: maldv/badger-zeta-l3-4x8b

model_architecture: MixtralForCausalLM

model_num_parameters: 24942219264.0

best_of: 8

max_input_tokens: 512

max_output_tokens: 64

reward_model: default

display_name: badger-zeta-l3-4x8b

is_internal_developer: False

language_model: maldv/badger-zeta-l3-4x8b

model_size: 25B

ranking_group: single

us_pacific_date: 2024-05-17

win_ratio: 0.48488193511230565

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|eot_id|>', '\n'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name}, and are meeting {user_name}.\n\nUse *emotes*\n\nMemory: {memory}', 'prompt_template': "{prompt}. Don't say too much.<|eot_id|>", 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n{bot_name}:', 'truncate_by_message': True}

model_eval_status: success

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

Resubmit model

Running pipeline stage MKMLizer
Starting job with name maldv-badger-zeta-l3-4x8b-v2-mkmlizer
Waiting for job on maldv-badger-zeta-l3-4x8b-v2-mkmlizer to finish
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ║     _____            __           __                                ║
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ║       /___/                                                         ║
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ║                                                                     ║
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ║  https://mk1.ai                                                     ║
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ║                                                                     ║
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ║  belonging to:                                                      ║
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ║                                                                     ║
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ║  Chai Research Corp.                                                ║
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ║                                                                     ║
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
maldv-badger-zeta-l3-4x8b-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.
maldv-badger-zeta-l3-4x8b-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: Downloaded to shared memory in 47.770s
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: 
Loading 0:   0%|          | 0/611 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 10/611 [00:00<00:06, 96.91it/s]
Loading 0:   4%|▍         | 24/611 [00:00<00:04, 120.66it/s]
Loading 0:   6%|▌         | 38/611 [00:00<00:04, 127.29it/s]
Loading 0:   8%|▊         | 51/611 [00:00<00:04, 112.82it/s]
Loading 0:  10%|█         | 63/611 [00:00<00:04, 113.06it/s]
Loading 0:  13%|█▎        | 77/611 [00:00<00:04, 120.87it/s]
Loading 0:  15%|█▍        | 90/611 [00:00<00:04, 113.40it/s]
Loading 0:  17%|█▋        | 102/611 [00:00<00:04, 101.83it/s]
Loading 0:  18%|█▊        | 113/611 [00:01<00:11, 45.04it/s] 
Loading 0:  21%|██        | 127/611 [00:01<00:08, 58.27it/s]
Loading 0:  22%|██▏       | 137/611 [00:01<00:08, 58.06it/s]
Loading 0:  24%|██▍       | 149/611 [00:01<00:06, 68.24it/s]
Loading 0:  27%|██▋       | 163/611 [00:02<00:05, 82.08it/s]
Loading 0:  29%|██▉       | 177/611 [00:02<00:04, 93.53it/s]
Loading 0:  31%|███       | 189/611 [00:02<00:04, 91.26it/s]
Loading 0:  33%|███▎      | 202/611 [00:02<00:04, 98.17it/s]
Loading 0:  35%|███▌      | 216/611 [00:02<00:03, 107.57it/s]
Loading 0:  37%|███▋      | 228/611 [00:02<00:03, 110.50it/s]
Loading 0:  39%|███▉      | 240/611 [00:03<00:08, 45.77it/s] 
Loading 0:  42%|████▏     | 254/611 [00:03<00:06, 57.75it/s]
Loading 0:  43%|████▎     | 264/611 [00:03<00:05, 63.05it/s]
Loading 0:  45%|████▌     | 278/611 [00:03<00:04, 76.83it/s]
Loading 0:  48%|████▊     | 292/611 [00:03<00:03, 89.44it/s]
Loading 0:  50%|████▉     | 304/611 [00:12<01:07,  4.53it/s]
Loading 0:  52%|█████▏    | 315/611 [00:12<00:48,  6.10it/s]
Loading 0:  54%|█████▍    | 329/611 [00:12<00:31,  8.90it/s]
Loading 0:  56%|█████▌    | 341/611 [00:12<00:22, 12.12it/s]
Loading 0:  58%|█████▊    | 353/611 [00:13<00:18, 13.62it/s]
Loading 0:  59%|█████▉    | 362/611 [00:13<00:15, 16.55it/s]
Loading 0:  61%|██████    | 370/611 [00:13<00:11, 20.27it/s]
Loading 0:  63%|██████▎   | 384/611 [00:13<00:07, 29.46it/s]
Loading 0:  65%|██████▍   | 396/611 [00:14<00:05, 38.42it/s]
Loading 0:  67%|██████▋   | 407/611 [00:14<00:04, 46.75it/s]
Loading 0:  69%|██████▉   | 422/611 [00:14<00:03, 61.40it/s]
Loading 0:  71%|███████▏  | 436/611 [00:14<00:02, 75.05it/s]
Loading 0:  73%|███████▎  | 449/611 [00:14<00:01, 84.26it/s]
Loading 0:  75%|███████▌  | 461/611 [00:14<00:01, 89.49it/s]
Loading 0:  77%|███████▋  | 473/611 [00:15<00:03, 42.39it/s]
Loading 0:  79%|███████▉  | 482/611 [00:15<00:02, 47.39it/s]
Loading 0:  81%|████████  | 496/611 [00:15<00:01, 60.54it/s]
Loading 0:  83%|████████▎ | 510/611 [00:15<00:01, 73.84it/s]
Loading 0:  86%|████████▌ | 524/611 [00:15<00:01, 86.75it/s]
Loading 0:  88%|████████▊ | 536/611 [00:15<00:00, 89.95it/s]
Loading 0:  90%|████████▉ | 549/611 [00:15<00:00, 98.84it/s]
Loading 0:  92%|█████████▏| 564/611 [00:16<00:00, 107.31it/s]
Loading 0:  95%|█████████▍| 579/611 [00:21<00:03,  8.75it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: quantized model in 34.092s
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: Processed model maldv/badger-zeta-l3-4x8b in 84.867s
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: creating bucket guanaco-mkml-models
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/maldv-badger-zeta-l3-4x8b-v2
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/maldv-badger-zeta-l3-4x8b-v2/config.json
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/maldv-badger-zeta-l3-4x8b-v2/special_tokens_map.json
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/maldv-badger-zeta-l3-4x8b-v2/tokenizer_config.json
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/maldv-badger-zeta-l3-4x8b-v2/tokenizer.json
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/maldv-badger-zeta-l3-4x8b-v2/flywheel_model.1.safetensors
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/maldv-badger-zeta-l3-4x8b-v2/flywheel_model.0.safetensors
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
maldv-badger-zeta-l3-4x8b-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.
maldv-badger-zeta-l3-4x8b-v2-mkmlizer:   warnings.warn(
maldv-badger-zeta-l3-4x8b-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.
maldv-badger-zeta-l3-4x8b-v2-mkmlizer:   warnings.warn(
maldv-badger-zeta-l3-4x8b-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.
maldv-badger-zeta-l3-4x8b-v2-mkmlizer:   warnings.warn(
maldv-badger-zeta-l3-4x8b-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()
maldv-badger-zeta-l3-4x8b-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: Saving duration: 0.252s
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.665s
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: creating bucket guanaco-reward-models
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/maldv-badger-zeta-l3-4x8b-v2_reward
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/maldv-badger-zeta-l3-4x8b-v2_reward/config.json
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/maldv-badger-zeta-l3-4x8b-v2_reward/special_tokens_map.json
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/maldv-badger-zeta-l3-4x8b-v2_reward/tokenizer_config.json
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/maldv-badger-zeta-l3-4x8b-v2_reward/vocab.json
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/maldv-badger-zeta-l3-4x8b-v2_reward/merges.txt
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/maldv-badger-zeta-l3-4x8b-v2_reward/tokenizer.json
maldv-badger-zeta-l3-4x8b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/maldv-badger-zeta-l3-4x8b-v2_reward/reward.tensors
Job maldv-badger-zeta-l3-4x8b-v2-mkmlizer completed after 114.37s with status: succeeded
Stopping job with name maldv-badger-zeta-l3-4x8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 117.91s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service maldv-badger-zeta-l3-4x8b-v2
Waiting for inference service maldv-badger-zeta-l3-4x8b-v2 to be ready
Inference service maldv-badger-zeta-l3-4x8b-v2 ready after 151.66602301597595s
Pipeline stage ISVCDeployer completed in 158.66s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0595927238464355s
Received healthy response to inference request in 2.1392982006073s
Received healthy response to inference request in 1.1813256740570068s
Received healthy response to inference request in 2.065319776535034s
Received healthy response to inference request in 2.330875873565674s
5 requests
0 failed requests
5th percentile: 1.3581244945526123
10th percentile: 1.5349233150482178
20th percentile: 1.8885209560394287
30th percentile: 2.080115461349487
40th percentile: 2.1097068309783937
50th percentile: 2.1392982006073
60th percentile: 2.2159292697906494
70th percentile: 2.292560338973999
80th percentile: 2.476619243621826
90th percentile: 2.768105983734131
95th percentile: 2.913849353790283
99th percentile: 3.030444049835205
mean time: 2.15528244972229
Pipeline stage StressChecker completed in 11.54s
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
maldv-badger-zeta-l3-4x8b_v2 status is now deployed due to DeploymentManager action
maldv-badger-zeta-l3-4x8b_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of maldv-badger-zeta-l3-4x8b_v2
Running pipeline stage ISVCDeleter
Checking if service maldv-badger-zeta-l3-4x8b-v2 is running
Tearing down inference service maldv-badger-zeta-l3-4x8b-v2
Toredown service maldv-badger-zeta-l3-4x8b-v2
Pipeline stage ISVCDeleter completed in 6.27s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key maldv-badger-zeta-l3-4x8b-v2/config.json from bucket guanaco-mkml-models
Deleting key maldv-badger-zeta-l3-4x8b-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key maldv-badger-zeta-l3-4x8b-v2/flywheel_model.1.safetensors from bucket guanaco-mkml-models
admin requested tearing down of mistralai-mixtral-8x7b-_3473_v36
Deleting key maldv-badger-zeta-l3-4x8b-v2/special_tokens_map.json from bucket guanaco-mkml-models
Running pipeline stage ISVCDeleter
Deleting key maldv-badger-zeta-l3-4x8b-v2/tokenizer.json from bucket guanaco-mkml-models
Checking if service mistralai-mixtral-8x7b-3473-v36 is running
Deleting key maldv-badger-zeta-l3-4x8b-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key maldv-badger-zeta-l3-4x8b-v2_reward/config.json from bucket guanaco-reward-models
Deleting key maldv-badger-zeta-l3-4x8b-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key maldv-badger-zeta-l3-4x8b-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key maldv-badger-zeta-l3-4x8b-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key maldv-badger-zeta-l3-4x8b-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key maldv-badger-zeta-l3-4x8b-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key maldv-badger-zeta-l3-4x8b-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 4.40s
maldv-badger-zeta-l3-4x8b_v2 status is now torndown due to DeploymentManager action