submission_id: hastagaras-bu8bl3-x-x_v5
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/bu8bl3-x_x
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 100, '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: 2024-06-14T07:40:38+00:00
model_name: x_x4
model_eval_status: success
model_group: Hastagaras/bu8bl3-x_x
num_battles: 29299
num_wins: 15781
celo_rating: 1203.87
propriety_score: 0.6803063118811881
propriety_total_count: 12928.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: x_x4
ineligible_reason: None
language_model: Hastagaras/bu8bl3-x_x
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-14
win_ratio: 0.5386190654971159
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-bu8bl3-x-x-v5-mkmlizer
Waiting for job on hastagaras-bu8bl3-x-x-v5-mkmlizer to finish
hastagaras-bu8bl3-x-x-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-bu8bl3-x-x-v5-mkmlizer: ║ _____ __ __ ║
hastagaras-bu8bl3-x-x-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-bu8bl3-x-x-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-bu8bl3-x-x-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-bu8bl3-x-x-v5-mkmlizer: ║ /___/ ║
hastagaras-bu8bl3-x-x-v5-mkmlizer: ║ ║
hastagaras-bu8bl3-x-x-v5-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-bu8bl3-x-x-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-bu8bl3-x-x-v5-mkmlizer: ║ https://mk1.ai ║
hastagaras-bu8bl3-x-x-v5-mkmlizer: ║ ║
hastagaras-bu8bl3-x-x-v5-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-bu8bl3-x-x-v5-mkmlizer: ║ belonging to: ║
hastagaras-bu8bl3-x-x-v5-mkmlizer: ║ ║
hastagaras-bu8bl3-x-x-v5-mkmlizer: ║ Chai Research Corp. ║
hastagaras-bu8bl3-x-x-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-bu8bl3-x-x-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-bu8bl3-x-x-v5-mkmlizer: ║ ║
hastagaras-bu8bl3-x-x-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-bu8bl3-x-x-v5-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-x-x-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-bu8bl3-x-x-v5-mkmlizer: Downloaded to shared memory in 46.144s
hastagaras-bu8bl3-x-x-v5-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-bu8bl3-x-x-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-bu8bl3-x-x-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 118.75it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:02, 115.29it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:01, 130.63it/s] Loading 0: 18%|█▊ | 53/291 [00:00<00:01, 130.26it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 131.86it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 72.73it/s] Loading 0: 33%|███▎ | 95/291 [00:01<00:02, 79.39it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:01, 95.85it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 109.46it/s] Loading 0: 49%|████▉ | 142/291 [00:01<00:01, 112.98it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:01, 118.64it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 125.30it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 80.05it/s] Loading 0: 68%|██████▊ | 198/291 [00:02<00:01, 85.71it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:00, 94.97it/s] Loading 0: 78%|███████▊ | 228/291 [00:02<00:00, 109.83it/s] Loading 0: 83%|████████▎ | 241/291 [00:02<00:00, 113.54it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 118.54it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 129.00it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 8.52it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-bu8bl3-x-x-v5-mkmlizer: quantized model in 23.520s
hastagaras-bu8bl3-x-x-v5-mkmlizer: Processed model Hastagaras/bu8bl3-x_x in 72.326s
hastagaras-bu8bl3-x-x-v5-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-bu8bl3-x-x-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-bu8bl3-x-x-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v5
hastagaras-bu8bl3-x-x-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v5/flywheel_model.0.safetensors
hastagaras-bu8bl3-x-x-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-bu8bl3-x-x-v5-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-x-x-v5-mkmlizer: warnings.warn(
hastagaras-bu8bl3-x-x-v5-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-x-x-v5-mkmlizer: warnings.warn(
hastagaras-bu8bl3-x-x-v5-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-x-x-v5-mkmlizer: warnings.warn(
hastagaras-bu8bl3-x-x-v5-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-x-x-v5-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-bu8bl3-x-x-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-bu8bl3-x-x-v5-mkmlizer: Saving duration: 0.408s
hastagaras-bu8bl3-x-x-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.274s
hastagaras-bu8bl3-x-x-v5-mkmlizer: creating bucket guanaco-reward-models
hastagaras-bu8bl3-x-x-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-bu8bl3-x-x-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v5_reward
hastagaras-bu8bl3-x-x-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v5_reward/config.json
hastagaras-bu8bl3-x-x-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v5_reward/tokenizer_config.json
hastagaras-bu8bl3-x-x-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v5_reward/special_tokens_map.json
hastagaras-bu8bl3-x-x-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v5_reward/merges.txt
hastagaras-bu8bl3-x-x-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v5_reward/vocab.json
hastagaras-bu8bl3-x-x-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v5_reward/tokenizer.json
hastagaras-bu8bl3-x-x-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v5_reward/reward.tensors
Job hastagaras-bu8bl3-x-x-v5-mkmlizer completed after 113.46s with status: succeeded
Stopping job with name hastagaras-bu8bl3-x-x-v5-mkmlizer
Pipeline stage MKMLizer completed in 114.10s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-bu8bl3-x-x-v5
Waiting for inference service hastagaras-bu8bl3-x-x-v5 to be ready
Inference service hastagaras-bu8bl3-x-x-v5 ready after 100.51389288902283s
Pipeline stage ISVCDeployer completed in 106.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2443721294403076s
Received healthy response to inference request in 1.3445227146148682s
Received healthy response to inference request in 1.3053700923919678s
Received healthy response to inference request in 1.2689552307128906s
Received healthy response to inference request in 1.3374431133270264s
5 requests
0 failed requests
5th percentile: 1.276238203048706
10th percentile: 1.2835211753845215
20th percentile: 1.2980871200561523
30th percentile: 1.3117846965789794
40th percentile: 1.324613904953003
50th percentile: 1.3374431133270264
60th percentile: 1.340274953842163
70th percentile: 1.3431067943572998
80th percentile: 1.5244925975799561
90th percentile: 1.8844323635101319
95th percentile: 2.0644022464752196
99th percentile: 2.20837815284729
mean time: 1.5001326560974122
Pipeline stage StressChecker completed in 8.11s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
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-bu8bl3-x-x_v5 status is now deployed due to DeploymentManager action
hastagaras-bu8bl3-x-x_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics