grimjim-kukulemon-7b

submission_id: grimjim-kukulemon-7b_v6

developer_uid: grimjim.

best_of: 16

celo_rating: 1188.41

display_name: grimjim-kukulemon-7b_v6

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': 0.02, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

is_internal_developer: False

language_model: grimjim/kukulemon-7B

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_eval_status: success

model_group: grimjim/kukulemon-7B

model_name: grimjim-kukulemon-7b_v6

model_num_parameters: 7241732096.0

model_repo: grimjim/kukulemon-7B

model_size: 7B

num_battles: 11658

num_wins: 6142

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: 2024-06-03T20:25:10+00:00

us_pacific_date: 2024-06-03

win_ratio: 0.5268485160404872

Resubmit model

Running pipeline stage MKMLizer
Starting job with name grimjim-kukulemon-7b-v6-mkmlizer
Waiting for job on grimjim-kukulemon-7b-v6-mkmlizer to finish
grimjim-kukulemon-7b-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
grimjim-kukulemon-7b-v6-mkmlizer: ║     _____            __           __                                ║
grimjim-kukulemon-7b-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
grimjim-kukulemon-7b-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
grimjim-kukulemon-7b-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
grimjim-kukulemon-7b-v6-mkmlizer: ║       /___/                                                         ║
grimjim-kukulemon-7b-v6-mkmlizer: ║                                                                     ║
grimjim-kukulemon-7b-v6-mkmlizer: ║  Version: 0.8.14                                                    ║
grimjim-kukulemon-7b-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
grimjim-kukulemon-7b-v6-mkmlizer: ║  https://mk1.ai                                                     ║
grimjim-kukulemon-7b-v6-mkmlizer: ║                                                                     ║
grimjim-kukulemon-7b-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
grimjim-kukulemon-7b-v6-mkmlizer: ║  belonging to:                                                      ║
grimjim-kukulemon-7b-v6-mkmlizer: ║                                                                     ║
grimjim-kukulemon-7b-v6-mkmlizer: ║  Chai Research Corp.                                                ║
grimjim-kukulemon-7b-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
grimjim-kukulemon-7b-v6-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
grimjim-kukulemon-7b-v6-mkmlizer: ║                                                                     ║
grimjim-kukulemon-7b-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
grimjim-kukulemon-7b-v6-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.
grimjim-kukulemon-7b-v6-mkmlizer:   warnings.warn(warning_message, FutureWarning)
grimjim-kukulemon-7b-v6-mkmlizer: Downloaded to shared memory in 26.864s
grimjim-kukulemon-7b-v6-mkmlizer: quantizing model to /dev/shm/model_cache
grimjim-kukulemon-7b-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
grimjim-kukulemon-7b-v6-mkmlizer: quantized model in 14.017s
grimjim-kukulemon-7b-v6-mkmlizer: Processed model grimjim/kukulemon-7B in 43.135s
grimjim-kukulemon-7b-v6-mkmlizer: creating bucket guanaco-mkml-models
grimjim-kukulemon-7b-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
grimjim-kukulemon-7b-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/grimjim-kukulemon-7b-v6
grimjim-kukulemon-7b-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/grimjim-kukulemon-7b-v6/special_tokens_map.json
grimjim-kukulemon-7b-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/grimjim-kukulemon-7b-v6/config.json
grimjim-kukulemon-7b-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/grimjim-kukulemon-7b-v6/tokenizer_config.json
grimjim-kukulemon-7b-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/grimjim-kukulemon-7b-v6/tokenizer.model
grimjim-kukulemon-7b-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/grimjim-kukulemon-7b-v6/tokenizer.json
grimjim-kukulemon-7b-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/grimjim-kukulemon-7b-v6/flywheel_model.0.safetensors
grimjim-kukulemon-7b-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
grimjim-kukulemon-7b-v6-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:02, 123.93it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:01, 145.47it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:01, 157.11it/s]
Loading 0:  23%|██▎       | 68/291 [00:00<00:01, 163.25it/s]
Loading 0:  30%|██▉       | 86/291 [00:00<00:01, 166.47it/s]
Loading 0:  36%|███▌      | 104/291 [00:00<00:01, 168.29it/s]
Loading 0:  42%|████▏     | 122/291 [00:00<00:00, 170.58it/s]
Loading 0:  48%|████▊     | 140/291 [00:00<00:00, 172.25it/s]
Loading 0:  54%|█████▍    | 158/291 [00:00<00:00, 174.38it/s]
Loading 0:  60%|██████    | 176/291 [00:01<00:00, 174.78it/s]
Loading 0:  67%|██████▋   | 194/291 [00:01<00:00, 173.93it/s]
Loading 0:  73%|███████▎  | 212/291 [00:02<00:02, 28.97it/s] 
Loading 0:  79%|███████▉  | 230/291 [00:03<00:01, 38.78it/s]
Loading 0:  85%|████████▌ | 248/291 [00:03<00:00, 50.66it/s]
Loading 0:  91%|█████████▏| 266/291 [00:03<00:00, 64.47it/s]
Loading 0:  98%|█████████▊| 284/291 [00:03<00:00, 79.51it/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.
grimjim-kukulemon-7b-v6-mkmlizer:   warnings.warn(
grimjim-kukulemon-7b-v6-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.
grimjim-kukulemon-7b-v6-mkmlizer:   warnings.warn(
grimjim-kukulemon-7b-v6-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.
grimjim-kukulemon-7b-v6-mkmlizer:   warnings.warn(
grimjim-kukulemon-7b-v6-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()
grimjim-kukulemon-7b-v6-mkmlizer:   return self.fget.__get__(instance, owner)()
grimjim-kukulemon-7b-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
grimjim-kukulemon-7b-v6-mkmlizer: Saving duration: 0.399s
grimjim-kukulemon-7b-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.812s
grimjim-kukulemon-7b-v6-mkmlizer: creating bucket guanaco-reward-models
grimjim-kukulemon-7b-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
grimjim-kukulemon-7b-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/grimjim-kukulemon-7b-v6_reward
grimjim-kukulemon-7b-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/grimjim-kukulemon-7b-v6_reward/special_tokens_map.json
grimjim-kukulemon-7b-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/grimjim-kukulemon-7b-v6_reward/tokenizer_config.json
grimjim-kukulemon-7b-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/grimjim-kukulemon-7b-v6_reward/merges.txt
grimjim-kukulemon-7b-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/grimjim-kukulemon-7b-v6_reward/vocab.json
grimjim-kukulemon-7b-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/grimjim-kukulemon-7b-v6_reward/config.json
grimjim-kukulemon-7b-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/grimjim-kukulemon-7b-v6_reward/tokenizer.json
grimjim-kukulemon-7b-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/grimjim-kukulemon-7b-v6_reward/reward.tensors
Job grimjim-kukulemon-7b-v6-mkmlizer completed after 73.96s with status: succeeded
Stopping job with name grimjim-kukulemon-7b-v6-mkmlizer
Pipeline stage MKMLizer completed in 79.99s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service grimjim-kukulemon-7b-v6
Waiting for inference service grimjim-kukulemon-7b-v6 to be ready
Inference service grimjim-kukulemon-7b-v6 ready after 30.220219135284424s
Pipeline stage ISVCDeployer completed in 38.34s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9645969867706299s
Received healthy response to inference request in 1.1916251182556152s
Received healthy response to inference request in 1.195418357849121s
Received healthy response to inference request in 1.1979622840881348s
Received healthy response to inference request in 1.1730339527130127s
5 requests
0 failed requests
5th percentile: 1.1767521858215333
10th percentile: 1.1804704189300537
20th percentile: 1.1879068851470946
30th percentile: 1.1923837661743164
40th percentile: 1.1939010620117188
50th percentile: 1.195418357849121
60th percentile: 1.1964359283447266
70th percentile: 1.197453498840332
80th percentile: 1.351289224624634
90th percentile: 1.657943105697632
95th percentile: 1.8112700462341307
99th percentile: 1.93393159866333
mean time: 1.3445273399353028
Pipeline stage StressChecker completed in 7.42s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
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
grimjim-kukulemon-7b_v6 status is now deployed due to DeploymentManager action
grimjim-kukulemon-7b_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of grimjim-kukulemon-7b_v6
Running pipeline stage ISVCDeleter
Checking if service grimjim-kukulemon-7b-v6 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.90s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key grimjim-kukulemon-7b-v6/config.json from bucket guanaco-mkml-models
Deleting key grimjim-kukulemon-7b-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key grimjim-kukulemon-7b-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key grimjim-kukulemon-7b-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key grimjim-kukulemon-7b-v6/tokenizer.model from bucket guanaco-mkml-models
Deleting key grimjim-kukulemon-7b-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key grimjim-kukulemon-7b-v6_reward/config.json from bucket guanaco-reward-models
Deleting key grimjim-kukulemon-7b-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key grimjim-kukulemon-7b-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key grimjim-kukulemon-7b-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key grimjim-kukulemon-7b-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key grimjim-kukulemon-7b-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key grimjim-kukulemon-7b-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.63s
grimjim-kukulemon-7b_v6 status is now torndown due to DeploymentManager action