submission_id: hastagaras-esekembrew-8b_9149_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Esekembrew-8B-L3-MK.VI
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 0.95, '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': "<|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: 2024-06-09T21:32:50+00:00
model_name: hastagaras-esekembrew-8b_9149_v2
model_eval_status: success
model_group: Hastagaras/Esekembrew-8B
num_battles: 11923
num_wins: 6622
celo_rating: 1217.91
safety_score: 0.95
propriety_score: 0.6834755624515128
propriety_total_count: 1289.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-esekembrew-8b_9149_v2
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Esekembrew-8B-L3-MK.VI
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-09
win_ratio: 0.5553971315943974
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-esekembrew-8b-9149-v2-mkmlizer
Waiting for job on hastagaras-esekembrew-8b-9149-v2-mkmlizer to finish
Stopping job with name hastagaras-esekembrew-8b-9149-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-esekembrew-8b-9149-v2-mkmlizer
Waiting for job on hastagaras-esekembrew-8b-9149-v2-mkmlizer to finish
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ║ /___/ ║
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ║ ║
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ║ ║
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ║ belonging to: ║
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ║ ║
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ║ ║
hastagaras-esekembrew-8b-9149-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-esekembrew-8b-9149-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.
hastagaras-esekembrew-8b-9149-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-esekembrew-8b-9149-v2-mkmlizer: Downloaded to shared memory in 31.896s
hastagaras-esekembrew-8b-9149-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-esekembrew-8b-9149-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-esekembrew-8b-9149-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 6%|▌ | 18/291 [00:00<00:01, 179.86it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:01, 193.72it/s] Loading 0: 20%|██ | 59/291 [00:00<00:01, 184.75it/s] Loading 0: 28%|██▊ | 82/291 [00:00<00:01, 201.70it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:02, 93.48it/s] Loading 0: 43%|████▎ | 124/291 [00:00<00:01, 115.09it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 136.59it/s] Loading 0: 57%|█████▋ | 166/291 [00:01<00:00, 147.83it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 96.98it/s] Loading 0: 70%|██████▉ | 203/291 [00:01<00:00, 106.89it/s] Loading 0: 78%|███████▊ | 228/291 [00:01<00:00, 133.08it/s] Loading 0: 85%|████████▌ | 248/291 [00:01<00:00, 145.38it/s] Loading 0: 94%|█████████▍| 273/291 [00:01<00:00, 167.93it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-esekembrew-8b-9149-v2-mkmlizer: quantized model in 17.364s
hastagaras-esekembrew-8b-9149-v2-mkmlizer: Processed model Hastagaras/Esekembrew-8B-L3-MK.VI in 50.258s
hastagaras-esekembrew-8b-9149-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-esekembrew-8b-9149-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-esekembrew-8b-9149-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-esekembrew-8b-9149-v2
hastagaras-esekembrew-8b-9149-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-esekembrew-8b-9149-v2/special_tokens_map.json
hastagaras-esekembrew-8b-9149-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-esekembrew-8b-9149-v2/config.json
hastagaras-esekembrew-8b-9149-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-esekembrew-8b-9149-v2/tokenizer_config.json
hastagaras-esekembrew-8b-9149-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-esekembrew-8b-9149-v2/tokenizer.json
hastagaras-esekembrew-8b-9149-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-esekembrew-8b-9149-v2/flywheel_model.0.safetensors
hastagaras-esekembrew-8b-9149-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-esekembrew-8b-9149-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.
hastagaras-esekembrew-8b-9149-v2-mkmlizer: warnings.warn(
hastagaras-esekembrew-8b-9149-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.
hastagaras-esekembrew-8b-9149-v2-mkmlizer: warnings.warn(
hastagaras-esekembrew-8b-9149-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.
hastagaras-esekembrew-8b-9149-v2-mkmlizer: warnings.warn(
hastagaras-esekembrew-8b-9149-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()
hastagaras-esekembrew-8b-9149-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-esekembrew-8b-9149-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-esekembrew-8b-9149-v2-mkmlizer: Saving duration: 0.220s
hastagaras-esekembrew-8b-9149-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.461s
hastagaras-esekembrew-8b-9149-v2-mkmlizer: creating bucket guanaco-reward-models
Job hastagaras-esekembrew-8b-9149-v2-mkmlizer completed after 73.52s with status: succeeded
Stopping job with name hastagaras-esekembrew-8b-9149-v2-mkmlizer
Pipeline stage MKMLizer completed in 76.87s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-esekembrew-8b-9149-v2
Failed to get response for submission neversleep-noromaid-v0-_8068_v66: ('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))
Waiting for inference service hastagaras-esekembrew-8b-9149-v2 to be ready
Failed to get response for submission neversleep-noromaid-v0-_8068_v66: ('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))
Failed to get response for submission neversleep-noromaid-v0-_8068_v66: ('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))
Tearing down inference service hastagaras-esekembrew-8b-9149-v2
%s, retrying in %s seconds...
Creating inference service hastagaras-esekembrew-8b-9149-v2
Waiting for inference service hastagaras-esekembrew-8b-9149-v2 to be ready
Inference service hastagaras-esekembrew-8b-9149-v2 ready after 191.06346368789673s
Pipeline stage ISVCDeployer completed in 806.98s
Running pipeline stage StressChecker
Received healthy response to inference request in 14.141249418258667s
Received healthy response to inference request in 1.3312647342681885s
Received healthy response to inference request in 1.3505358695983887s
Received healthy response to inference request in 1.307253122329712s
Received healthy response to inference request in 1.2529165744781494s
5 requests
0 failed requests
5th percentile: 1.2637838840484619
10th percentile: 1.2746511936187743
20th percentile: 1.2963858127593995
30th percentile: 1.3120554447174073
40th percentile: 1.321660089492798
50th percentile: 1.3312647342681885
60th percentile: 1.3389731884002685
70th percentile: 1.3466816425323487
80th percentile: 3.908678579330447
90th percentile: 9.024963998794558
95th percentile: 11.583106708526609
99th percentile: 13.629620876312256
mean time: 3.876643943786621
Pipeline stage StressChecker completed in 19.97s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-esekembrew-8b_9149_v2 status is now deployed due to DeploymentManager action
hastagaras-esekembrew-8b_9149_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics