submission_id: hastagaras-esekembrew-8b_3407_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Esekembrew-8B-L3-REVERSE
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, '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': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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: 2024-06-10T11:04:58+00:00
model_name: prop-test-1
model_eval_status: success
model_group: Hastagaras/Esekembrew-8B
num_battles: 19660
num_wins: 10690
celo_rating: 1211.49
propriety_score: 0.6877076411960132
propriety_total_count: 1505.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: prop-test-1
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Esekembrew-8B-L3-REVERSE
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-10
win_ratio: 0.5437436419125127
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-esekembrew-8b-3407-v1-mkmlizer
Waiting for job on hastagaras-esekembrew-8b-3407-v1-mkmlizer to finish
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ║ /___/ ║
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ║ ║
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ║ ║
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ║ belonging to: ║
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ║ ║
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ║ ║
hastagaras-esekembrew-8b-3407-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-esekembrew-8b-3407-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.
hastagaras-esekembrew-8b-3407-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-esekembrew-8b-3407-v1-mkmlizer: Downloaded to shared memory in 58.900s
hastagaras-esekembrew-8b-3407-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-esekembrew-8b-3407-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-esekembrew-8b-3407-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 111.43it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:02, 109.71it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 124.56it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:01, 120.83it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 126.43it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:01, 122.57it/s] Loading 0: 32%|███▏ | 92/291 [00:01<00:02, 68.86it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 75.53it/s] Loading 0: 40%|████ | 117/291 [00:01<00:01, 88.56it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 95.71it/s] Loading 0: 49%|████▉ | 143/291 [00:01<00:01, 103.54it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:01, 107.77it/s] Loading 0: 59%|█████▉ | 171/291 [00:01<00:01, 114.98it/s] Loading 0: 64%|██████▎ | 185/291 [00:01<00:00, 120.12it/s] Loading 0: 68%|██████▊ | 198/291 [00:02<00:01, 71.61it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:01, 79.76it/s] Loading 0: 76%|███████▋ | 222/291 [00:02<00:00, 82.13it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 96.06it/s] Loading 0: 86%|████████▌ | 249/291 [00:02<00:00, 99.26it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 110.68it/s] Loading 0: 95%|█████████▌| 277/291 [00:02<00:00, 112.15it/s] Loading 0: 99%|█████████▉| 289/291 [00:08<00:00, 7.42it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-esekembrew-8b-3407-v1-mkmlizer: quantized model in 23.417s
hastagaras-esekembrew-8b-3407-v1-mkmlizer: Processed model Hastagaras/Esekembrew-8B-L3-REVERSE in 84.842s
hastagaras-esekembrew-8b-3407-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-esekembrew-8b-3407-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-esekembrew-8b-3407-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-esekembrew-8b-3407-v1
hastagaras-esekembrew-8b-3407-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-esekembrew-8b-3407-v1/config.json
hastagaras-esekembrew-8b-3407-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-esekembrew-8b-3407-v1/tokenizer_config.json
hastagaras-esekembrew-8b-3407-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-esekembrew-8b-3407-v1/tokenizer.json
hastagaras-esekembrew-8b-3407-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-esekembrew-8b-3407-v1/special_tokens_map.json
hastagaras-esekembrew-8b-3407-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-esekembrew-8b-3407-v1-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-8b-3407-v1-mkmlizer: warnings.warn(
hastagaras-esekembrew-8b-3407-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.
hastagaras-esekembrew-8b-3407-v1-mkmlizer: warnings.warn(
hastagaras-esekembrew-8b-3407-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.
hastagaras-esekembrew-8b-3407-v1-mkmlizer: warnings.warn(
hastagaras-esekembrew-8b-3407-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()
hastagaras-esekembrew-8b-3407-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-esekembrew-8b-3407-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-esekembrew-8b-3407-v1-mkmlizer: Saving duration: 0.380s
hastagaras-esekembrew-8b-3407-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 22.493s
hastagaras-esekembrew-8b-3407-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-esekembrew-8b-3407-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-esekembrew-8b-3407-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-esekembrew-8b-3407-v1_reward
hastagaras-esekembrew-8b-3407-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-esekembrew-8b-3407-v1_reward/special_tokens_map.json
hastagaras-esekembrew-8b-3407-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-esekembrew-8b-3407-v1_reward/vocab.json
hastagaras-esekembrew-8b-3407-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-esekembrew-8b-3407-v1_reward/merges.txt
hastagaras-esekembrew-8b-3407-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-esekembrew-8b-3407-v1_reward/tokenizer_config.json
hastagaras-esekembrew-8b-3407-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-esekembrew-8b-3407-v1_reward/config.json
hastagaras-esekembrew-8b-3407-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-esekembrew-8b-3407-v1_reward/tokenizer.json
hastagaras-esekembrew-8b-3407-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-esekembrew-8b-3407-v1_reward/reward.tensors
Job hastagaras-esekembrew-8b-3407-v1-mkmlizer completed after 123.81s with status: succeeded
Stopping job with name hastagaras-esekembrew-8b-3407-v1-mkmlizer
Pipeline stage MKMLizer completed in 128.79s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-esekembrew-8b-3407-v1
Waiting for inference service hastagaras-esekembrew-8b-3407-v1 to be ready
Inference service hastagaras-esekembrew-8b-3407-v1 ready after 50.26754665374756s
Pipeline stage ISVCDeployer completed in 57.69s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2039923667907715s
Received healthy response to inference request in 1.3867168426513672s
Received healthy response to inference request in 19.96714973449707s
Received healthy response to inference request in 1.3097131252288818s
Received healthy response to inference request in 1.35610032081604s
5 requests
0 failed requests
5th percentile: 1.3189905643463136
10th percentile: 1.328268003463745
20th percentile: 1.3468228816986083
30th percentile: 1.3622236251831055
40th percentile: 1.3744702339172363
50th percentile: 1.3867168426513672
60th percentile: 1.7136270523071289
70th percentile: 2.0405372619628905
80th percentile: 5.7566238403320344
90th percentile: 12.861886787414551
95th percentile: 16.41451826095581
99th percentile: 19.256623439788818
mean time: 5.244734477996826
Pipeline stage StressChecker completed in 26.82s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-esekembrew-8b_3407_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-esekembrew-8b_3407_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics