submission_id: hastagaras-bu8bl3-rp_v4
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Bu8bl3-RP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], '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: 2024-06-15T20:56:05+00:00
model_name: bubble
model_eval_status: success
model_group: Hastagaras/Bu8bl3-RP
num_battles: 12745
num_wins: 7020
celo_rating: 1207.93
propriety_score: 0.7165354330708661
propriety_total_count: 5842.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: bubble
ineligible_reason: None
language_model: Hastagaras/Bu8bl3-RP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-15
win_ratio: 0.5508042369556689
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-bu8bl3-rp-v4-mkmlizer
Waiting for job on hastagaras-bu8bl3-rp-v4-mkmlizer to finish
hastagaras-bu8bl3-rp-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-bu8bl3-rp-v4-mkmlizer: ║ _____ __ __ ║
hastagaras-bu8bl3-rp-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-bu8bl3-rp-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-bu8bl3-rp-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-bu8bl3-rp-v4-mkmlizer: ║ /___/ ║
hastagaras-bu8bl3-rp-v4-mkmlizer: ║ ║
hastagaras-bu8bl3-rp-v4-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-bu8bl3-rp-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-bu8bl3-rp-v4-mkmlizer: ║ https://mk1.ai ║
hastagaras-bu8bl3-rp-v4-mkmlizer: ║ ║
hastagaras-bu8bl3-rp-v4-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-bu8bl3-rp-v4-mkmlizer: ║ belonging to: ║
hastagaras-bu8bl3-rp-v4-mkmlizer: ║ ║
hastagaras-bu8bl3-rp-v4-mkmlizer: ║ Chai Research Corp. ║
hastagaras-bu8bl3-rp-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-bu8bl3-rp-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-bu8bl3-rp-v4-mkmlizer: ║ ║
hastagaras-bu8bl3-rp-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-bu8bl3-rp-v4-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-bu8bl3-rp-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-bu8bl3-rp-v4-mkmlizer: Downloaded to shared memory in 182.084s
hastagaras-bu8bl3-rp-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-bu8bl3-rp-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-bu8bl3-rp-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 111.17it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:02, 108.26it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 122.97it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:01, 119.61it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 124.74it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:01, 120.47it/s] Loading 0: 32%|███▏ | 92/291 [00:01<00:02, 66.87it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 73.72it/s] Loading 0: 40%|████ | 117/291 [00:01<00:02, 86.81it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 94.57it/s] Loading 0: 49%|████▉ | 144/291 [00:01<00:01, 104.57it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:01, 107.88it/s] Loading 0: 58%|█████▊ | 170/291 [00:01<00:01, 113.49it/s] Loading 0: 63%|██████▎ | 184/291 [00:01<00:00, 119.04it/s] Loading 0: 68%|██████▊ | 197/291 [00:02<00:01, 71.06it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:00, 81.66it/s] Loading 0: 77%|███████▋ | 225/291 [00:02<00:00, 92.83it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 98.33it/s] Loading 0: 86%|████████▋ | 251/291 [00:02<00:00, 105.41it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 111.43it/s] Loading 0: 95%|█████████▌| 277/291 [00:02<00:00, 111.28it/s] Loading 0: 99%|█████████▉| 289/291 [00:08<00:00, 7.16it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-bu8bl3-rp-v4-mkmlizer: quantized model in 24.103s
hastagaras-bu8bl3-rp-v4-mkmlizer: Processed model Hastagaras/Bu8bl3-RP in 208.772s
hastagaras-bu8bl3-rp-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-bu8bl3-rp-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-bu8bl3-rp-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-bu8bl3-rp-v4
hastagaras-bu8bl3-rp-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-bu8bl3-rp-v4/special_tokens_map.json
hastagaras-bu8bl3-rp-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-bu8bl3-rp-v4/config.json
hastagaras-bu8bl3-rp-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-bu8bl3-rp-v4/tokenizer_config.json
hastagaras-bu8bl3-rp-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-bu8bl3-rp-v4/tokenizer.json
hastagaras-bu8bl3-rp-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-bu8bl3-rp-v4/flywheel_model.0.safetensors
hastagaras-bu8bl3-rp-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-bu8bl3-rp-v4-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-bu8bl3-rp-v4-mkmlizer: warnings.warn(
hastagaras-bu8bl3-rp-v4-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-bu8bl3-rp-v4-mkmlizer: warnings.warn(
hastagaras-bu8bl3-rp-v4-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-bu8bl3-rp-v4-mkmlizer: warnings.warn(
hastagaras-bu8bl3-rp-v4-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-bu8bl3-rp-v4-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-bu8bl3-rp-v4-mkmlizer: Saving duration: 0.413s
hastagaras-bu8bl3-rp-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 23.322s
hastagaras-bu8bl3-rp-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-bu8bl3-rp-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-bu8bl3-rp-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-bu8bl3-rp-v4_reward
hastagaras-bu8bl3-rp-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-bu8bl3-rp-v4_reward/special_tokens_map.json
hastagaras-bu8bl3-rp-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-bu8bl3-rp-v4_reward/tokenizer_config.json
hastagaras-bu8bl3-rp-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-bu8bl3-rp-v4_reward/merges.txt
hastagaras-bu8bl3-rp-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-bu8bl3-rp-v4_reward/config.json
hastagaras-bu8bl3-rp-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-bu8bl3-rp-v4_reward/vocab.json
hastagaras-bu8bl3-rp-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-bu8bl3-rp-v4_reward/tokenizer.json
hastagaras-bu8bl3-rp-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-bu8bl3-rp-v4_reward/reward.tensors
Job hastagaras-bu8bl3-rp-v4-mkmlizer completed after 256.35s with status: succeeded
Stopping job with name hastagaras-bu8bl3-rp-v4-mkmlizer
Pipeline stage MKMLizer completed in 259.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-bu8bl3-rp-v4
Waiting for inference service hastagaras-bu8bl3-rp-v4 to be ready
Inference service hastagaras-bu8bl3-rp-v4 ready after 30.191981077194214s
Pipeline stage ISVCDeployer completed in 37.50s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1560423374176025s
Received healthy response to inference request in 1.3565678596496582s
Received healthy response to inference request in 1.2926733493804932s
Received healthy response to inference request in 1.2778146266937256s
Received healthy response to inference request in 1.3507444858551025s
5 requests
0 failed requests
5th percentile: 1.2807863712310792
10th percentile: 1.2837581157684326
20th percentile: 1.2897016048431396
30th percentile: 1.304287576675415
40th percentile: 1.3275160312652587
50th percentile: 1.3507444858551025
60th percentile: 1.3530738353729248
70th percentile: 1.355403184890747
80th percentile: 1.5164627552032472
90th percentile: 1.836252546310425
95th percentile: 1.9961474418640135
99th percentile: 2.1240633583068846
mean time: 1.4867685317993165
Pipeline stage StressChecker completed in 8.11s
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
hastagaras-bu8bl3-rp_v4 status is now deployed due to DeploymentManager action
hastagaras-bu8bl3-rp_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics