submission_id: yuyuclimb-yxyllama2_v1
developer_uid: yuyuclimb
status: inactive
model_repo: yuyuclimb/yxyllama2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, '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': 16, '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: 2024-05-07T11:29:01+00:00
model_name: yxyllama2
model_eval_status: success
double_thumbs_up: 186
thumbs_up: 304
thumbs_down: 139
num_battles: 18366
num_wins: 8677
celo_rating: 1128.28
entertaining: 7.04
stay_in_character: 8.02
user_preference: 6.48
safety_score: 0.66
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 6738415616.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: yxyllama2
double_thumbs_up_ratio: 0.2957074721780604
feedback_count: 629
ineligible_reason: None
language_model: yuyuclimb/yxyllama2
model_score: 7.18
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.48330683624801274
thumbs_down_ratio: 0.22098569157392686
thumbs_up_ratio: 0.7790143084260731
us_pacific_date: 2024-05-07
win_ratio: 0.4724490907110966
Resubmit model
Running pipeline stage MKMLizer
Starting job with name yuyuclimb-yxyllama2-v1-mkmlizer
Waiting for job on yuyuclimb-yxyllama2-v1-mkmlizer to finish
yuyuclimb-yxyllama2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
yuyuclimb-yxyllama2-v1-mkmlizer: ║ _____ __ __ ║
yuyuclimb-yxyllama2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
yuyuclimb-yxyllama2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
yuyuclimb-yxyllama2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
yuyuclimb-yxyllama2-v1-mkmlizer: ║ /___/ ║
yuyuclimb-yxyllama2-v1-mkmlizer: ║ ║
yuyuclimb-yxyllama2-v1-mkmlizer: ║ Version: 0.8.10 ║
yuyuclimb-yxyllama2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
yuyuclimb-yxyllama2-v1-mkmlizer: ║ ║
yuyuclimb-yxyllama2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
yuyuclimb-yxyllama2-v1-mkmlizer: ║ belonging to: ║
yuyuclimb-yxyllama2-v1-mkmlizer: ║ ║
yuyuclimb-yxyllama2-v1-mkmlizer: ║ Chai Research Corp. ║
yuyuclimb-yxyllama2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
yuyuclimb-yxyllama2-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
yuyuclimb-yxyllama2-v1-mkmlizer: ║ ║
yuyuclimb-yxyllama2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
yuyuclimb-yxyllama2-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.
yuyuclimb-yxyllama2-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
yuyuclimb-yxyllama2-v1-mkmlizer: Downloaded to shared memory in 25.338s
yuyuclimb-yxyllama2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
yuyuclimb-yxyllama2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
yuyuclimb-yxyllama2-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 74%|███████▍ | 215/291 [00:01<00:00, 140.91it/s] Loading 0: 100%|██████████| 291/291 [00:02<00:00, 100.55it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
yuyuclimb-yxyllama2-v1-mkmlizer: quantized model in 9.387s
Retrying (%r) after connection broken by '%r': %s
yuyuclimb-yxyllama2-v1-mkmlizer: Processed model yuyuclimb/yxyllama2 in 35.584s
yuyuclimb-yxyllama2-v1-mkmlizer: creating bucket guanaco-mkml-models
yuyuclimb-yxyllama2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
yuyuclimb-yxyllama2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v1
yuyuclimb-yxyllama2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v1/tokenizer.model
yuyuclimb-yxyllama2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v1/tokenizer_config.json
yuyuclimb-yxyllama2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v1/special_tokens_map.json
yuyuclimb-yxyllama2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v1/config.json
yuyuclimb-yxyllama2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v1/tokenizer.json
yuyuclimb-yxyllama2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v1/flywheel_model.0.safetensors
yuyuclimb-yxyllama2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
yuyuclimb-yxyllama2-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.
yuyuclimb-yxyllama2-v1-mkmlizer: warnings.warn(
yuyuclimb-yxyllama2-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.
yuyuclimb-yxyllama2-v1-mkmlizer: warnings.warn(
yuyuclimb-yxyllama2-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.
yuyuclimb-yxyllama2-v1-mkmlizer: warnings.warn(
Job yuyuclimb-yxyllama2-v1-mkmlizer completed after 178.58s with status: succeeded
Stopping job with name yuyuclimb-yxyllama2-v1-mkmlizer
Pipeline stage MKMLizer completed in 183.35s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service yuyuclimb-yxyllama2-v1
Waiting for inference service yuyuclimb-yxyllama2-v1 to be ready
Inference service yuyuclimb-yxyllama2-v1 ready after 30.156951904296875s
Pipeline stage ISVCDeployer completed in 37.81s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.217374324798584s
Received healthy response to inference request in 1.1819665431976318s
Received healthy response to inference request in 1.166769027709961s
Received healthy response to inference request in 1.2022058963775635s
Received healthy response to inference request in 1.1461036205291748s
5 requests
0 failed requests
5th percentile: 1.1502367019653321
10th percentile: 1.1543697834014892
20th percentile: 1.1626359462738036
30th percentile: 1.169808530807495
40th percentile: 1.1758875370025634
50th percentile: 1.1819665431976318
60th percentile: 1.1900622844696045
70th percentile: 1.1981580257415771
80th percentile: 1.4052395820617678
90th percentile: 1.8113069534301758
95th percentile: 2.01434063911438
99th percentile: 2.176767587661743
mean time: 1.382883882522583
Pipeline stage StressChecker completed in 7.49s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.06s
yuyuclimb-yxyllama2_v1 status is now deployed due to DeploymentManager action
yuyuclimb-yxyllama2_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics