submission_id: chaiml-llamademo_v3
developer_uid: Selenee
status: inactive
model_repo: ChaiML/llamademo
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 100.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 5, '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': 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: 2024-06-20T00:04:22+00:00
model_name: testBot
model_group: ChaiML/llamademo
num_battles: 13783
num_wins: 3644
celo_rating: 814.76
propriety_score: 0.6556943423952976
propriety_total_count: 6805.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 6738415616.0
best_of: 5
max_input_tokens: 512
max_output_tokens: 64
display_name: testBot
ineligible_reason: None
language_model: ChaiML/llamademo
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-19
win_ratio: 0.26438366103170574
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-llamademo-v3-mkmlizer
Waiting for job on chaiml-llamademo-v3-mkmlizer to finish
Stopping job with name chaiml-llamademo-v3-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-llamademo-v3-mkmlizer
Waiting for job on chaiml-llamademo-v3-mkmlizer to finish
chaiml-llamademo-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llamademo-v3-mkmlizer: ║ _____ __ __ ║
chaiml-llamademo-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-llamademo-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-llamademo-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-llamademo-v3-mkmlizer: ║ /___/ ║
chaiml-llamademo-v3-mkmlizer: ║ ║
chaiml-llamademo-v3-mkmlizer: ║ Version: 0.8.14 ║
chaiml-llamademo-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-llamademo-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-llamademo-v3-mkmlizer: ║ ║
chaiml-llamademo-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llamademo-v3-mkmlizer: ║ belonging to: ║
chaiml-llamademo-v3-mkmlizer: ║ ║
chaiml-llamademo-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-llamademo-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llamademo-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
chaiml-llamademo-v3-mkmlizer: ║ ║
chaiml-llamademo-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llamademo-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.
chaiml-llamademo-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
chaiml-llamademo-v3-mkmlizer: Downloaded to shared memory in 23.600s
chaiml-llamademo-v3-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-llamademo-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llamademo-v3-mkmlizer: quantized model in 15.219s
chaiml-llamademo-v3-mkmlizer: Processed model ChaiML/llamademo in 41.288s
chaiml-llamademo-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llamademo-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llamademo-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llamademo-v3
chaiml-llamademo-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llamademo-v3/config.json
chaiml-llamademo-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llamademo-v3/special_tokens_map.json
chaiml-llamademo-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-llamademo-v3/tokenizer.model
chaiml-llamademo-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llamademo-v3/tokenizer.json
chaiml-llamademo-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llamademo-v3/tokenizer_config.json
chaiml-llamademo-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llamademo-v3/flywheel_model.0.safetensors
chaiml-llamademo-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
chaiml-llamademo-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 73%|███████▎ | 213/291 [00:01<00:00, 162.41it/s] Loading 0: 100%|██████████| 291/291 [00:02<00:00, 94.89it/s] /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.
chaiml-llamademo-v3-mkmlizer: warnings.warn(
chaiml-llamademo-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.
chaiml-llamademo-v3-mkmlizer: warnings.warn(
chaiml-llamademo-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.
chaiml-llamademo-v3-mkmlizer: warnings.warn(
chaiml-llamademo-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()
chaiml-llamademo-v3-mkmlizer: return self.fget.__get__(instance, owner)()
chaiml-llamademo-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-llamademo-v3-mkmlizer: Saving duration: 0.411s
chaiml-llamademo-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.338s
chaiml-llamademo-v3-mkmlizer: creating bucket guanaco-reward-models
chaiml-llamademo-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-llamademo-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-llamademo-v3_reward
chaiml-llamademo-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-llamademo-v3_reward/special_tokens_map.json
chaiml-llamademo-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-llamademo-v3_reward/merges.txt
chaiml-llamademo-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-llamademo-v3_reward/vocab.json
chaiml-llamademo-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-llamademo-v3_reward/tokenizer_config.json
chaiml-llamademo-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-llamademo-v3_reward/config.json
chaiml-llamademo-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-llamademo-v3_reward/tokenizer.json
chaiml-llamademo-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-llamademo-v3_reward/reward.tensors
Job chaiml-llamademo-v3-mkmlizer completed after 96.05s with status: succeeded
Stopping job with name chaiml-llamademo-v3-mkmlizer
Pipeline stage MKMLizer completed in 100.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-llamademo-v3
Waiting for inference service chaiml-llamademo-v3 to be ready
Inference service chaiml-llamademo-v3 ready after 40.32055330276489s
Pipeline stage ISVCDeployer completed in 48.05s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9391682147979736s
Received healthy response to inference request in 1.0051100254058838s
Received healthy response to inference request in 0.853538990020752s
Received healthy response to inference request in 0.993577241897583s
Received healthy response to inference request in 1.0088727474212646s
5 requests
0 failed requests
5th percentile: 0.8815466403961182
10th percentile: 0.9095542907714844
20th percentile: 0.9655695915222168
30th percentile: 0.9958837985992431
40th percentile: 1.0004969120025635
50th percentile: 1.0051100254058838
60th percentile: 1.006615114212036
70th percentile: 1.0081202030181884
80th percentile: 1.1949318408966065
90th percentile: 1.56705002784729
95th percentile: 1.7531091213226317
99th percentile: 1.9019563961029053
mean time: 1.1600534439086914
Pipeline stage StressChecker completed in 6.43s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.05s
chaiml-llamademo_v3 status is now deployed due to DeploymentManager action
chaiml-llamademo_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics