submission_id: hastagaras-esekembrew-ll_1360_v3
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/esekembrew-llama3-8b
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, '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': True}
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': True}
timestamp: 2024-05-17T08:45:39+00:00
model_name: mweheh3
model_eval_status: success
model_group: Hastagaras/esekembrew-ll
num_battles: 9470
num_wins: 4973
celo_rating: 1196.25
safety_score: 0.98
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: mweheh3
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/esekembrew-llama3-8b
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-17
win_ratio: 0.5251319957761351
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-esekembrew-ll-1360-v3-mkmlizer
Waiting for job on hastagaras-esekembrew-ll-1360-v3-mkmlizer to finish
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ║ /___/ ║
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ║ ║
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ║ ║
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ║ belonging to: ║
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ║ ║
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ║ ║
hastagaras-esekembrew-ll-1360-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-esekembrew-ll-1360-v3-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.
hastagaras-esekembrew-ll-1360-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-esekembrew-ll-1360-v3-mkmlizer: Downloaded to shared memory in 21.738s
hastagaras-esekembrew-ll-1360-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-esekembrew-ll-1360-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-esekembrew-ll-1360-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 117.84it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:02, 117.44it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:01, 126.32it/s] Loading 0: 18%|█▊ | 53/291 [00:00<00:01, 122.92it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 120.74it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 115.95it/s] Loading 0: 32%|███▏ | 92/291 [00:01<00:03, 55.23it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 64.13it/s] Loading 0: 40%|████ | 117/291 [00:01<00:02, 78.26it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 85.87it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 88.35it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 104.21it/s] Loading 0: 58%|█████▊ | 168/291 [00:01<00:01, 102.20it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:01, 105.07it/s] Loading 0: 66%|██████▋ | 193/291 [00:02<00:01, 58.05it/s] Loading 0: 70%|██████▉ | 203/291 [00:02<00:01, 64.78it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 81.44it/s] Loading 0: 80%|████████ | 233/291 [00:02<00:00, 93.26it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 101.18it/s] Loading 0: 90%|████████▉ | 261/291 [00:02<00:00, 110.18it/s] Loading 0: 94%|█████████▍| 274/291 [00:03<00:00, 107.47it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 7.54it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-esekembrew-ll-1360-v3-mkmlizer: quantized model in 20.821s
hastagaras-esekembrew-ll-1360-v3-mkmlizer: Processed model Hastagaras/esekembrew-llama3-8b in 43.749s
hastagaras-esekembrew-ll-1360-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-esekembrew-ll-1360-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-esekembrew-ll-1360-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v3
hastagaras-esekembrew-ll-1360-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v3/config.json
hastagaras-esekembrew-ll-1360-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v3/tokenizer_config.json
hastagaras-esekembrew-ll-1360-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v3/special_tokens_map.json
hastagaras-esekembrew-ll-1360-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v3/tokenizer.json
hastagaras-esekembrew-ll-1360-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v3/flywheel_model.0.safetensors
hastagaras-esekembrew-ll-1360-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-esekembrew-ll-1360-v3-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.
hastagaras-esekembrew-ll-1360-v3-mkmlizer: warnings.warn(
hastagaras-esekembrew-ll-1360-v3-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.
hastagaras-esekembrew-ll-1360-v3-mkmlizer: warnings.warn(
hastagaras-esekembrew-ll-1360-v3-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.
hastagaras-esekembrew-ll-1360-v3-mkmlizer: warnings.warn(
hastagaras-esekembrew-ll-1360-v3-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()
hastagaras-esekembrew-ll-1360-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-esekembrew-ll-1360-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-esekembrew-ll-1360-v3-mkmlizer: Saving duration: 0.283s
hastagaras-esekembrew-ll-1360-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.774s
hastagaras-esekembrew-ll-1360-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-esekembrew-ll-1360-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-esekembrew-ll-1360-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v3_reward
hastagaras-esekembrew-ll-1360-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v3_reward/config.json
hastagaras-esekembrew-ll-1360-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v3_reward/merges.txt
hastagaras-esekembrew-ll-1360-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v3_reward/tokenizer_config.json
hastagaras-esekembrew-ll-1360-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v3_reward/special_tokens_map.json
hastagaras-esekembrew-ll-1360-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v3_reward/vocab.json
hastagaras-esekembrew-ll-1360-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v3_reward/tokenizer.json
hastagaras-esekembrew-ll-1360-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v3_reward/reward.tensors
Job hastagaras-esekembrew-ll-1360-v3-mkmlizer completed after 73.38s with status: succeeded
Stopping job with name hastagaras-esekembrew-ll-1360-v3-mkmlizer
Pipeline stage MKMLizer completed in 77.70s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-esekembrew-ll-1360-v3
Waiting for inference service hastagaras-esekembrew-ll-1360-v3 to be ready
Inference service hastagaras-esekembrew-ll-1360-v3 ready after 100.53691124916077s
Pipeline stage ISVCDeployer completed in 108.08s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1697747707366943s
Received healthy response to inference request in 1.2697992324829102s
Received healthy response to inference request in 1.2820971012115479s
Received healthy response to inference request in 1.286055326461792s
Received healthy response to inference request in 1.261915683746338s
5 requests
0 failed requests
5th percentile: 1.2634923934936524
10th percentile: 1.2650691032409669
20th percentile: 1.2682225227355957
30th percentile: 1.2722588062286377
40th percentile: 1.2771779537200927
50th percentile: 1.2820971012115479
60th percentile: 1.2836803913116455
70th percentile: 1.285263681411743
80th percentile: 1.4627992153167726
90th percentile: 1.8162869930267336
95th percentile: 1.9930308818817137
99th percentile: 2.1344259929656983
mean time: 1.4539284229278564
Pipeline stage StressChecker completed in 7.90s
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 0.07s
hastagaras-esekembrew-ll_1360_v3 status is now deployed due to DeploymentManager action
hastagaras-esekembrew-ll_1360_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics