submission_id: yuyuclimb-yxyllama2_v2
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': 8, '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: 2024-05-07T11:52:15+00:00
model_name: yxyllama2-2
model_eval_status: success
double_thumbs_up: 96
thumbs_up: 192
thumbs_down: 88
num_battles: 10716
num_wins: 4852
celo_rating: 1114.37
entertaining: 6.68
stay_in_character: 7.65
user_preference: 7.02
safety_score: 0.6
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 6738415616.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: yxyllama2-2
double_thumbs_up_ratio: 0.2553191489361702
feedback_count: 376
ineligible_reason: None
language_model: yuyuclimb/yxyllama2
model_score: 7.116666666666667
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.5106382978723404
thumbs_down_ratio: 0.23404255319148937
thumbs_up_ratio: 0.7659574468085106
us_pacific_date: 2024-05-07
win_ratio: 0.45278088839119074
Resubmit model
Running pipeline stage MKMLizer
Starting job with name yuyuclimb-yxyllama2-v2-mkmlizer
Waiting for job on yuyuclimb-yxyllama2-v2-mkmlizer to finish
yuyuclimb-yxyllama2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
yuyuclimb-yxyllama2-v2-mkmlizer: ║ _____ __ __ ║
yuyuclimb-yxyllama2-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
yuyuclimb-yxyllama2-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
yuyuclimb-yxyllama2-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
yuyuclimb-yxyllama2-v2-mkmlizer: ║ /___/ ║
yuyuclimb-yxyllama2-v2-mkmlizer: ║ ║
yuyuclimb-yxyllama2-v2-mkmlizer: ║ Version: 0.8.10 ║
yuyuclimb-yxyllama2-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
yuyuclimb-yxyllama2-v2-mkmlizer: ║ ║
yuyuclimb-yxyllama2-v2-mkmlizer: ║ The license key for the current software has been verified as ║
yuyuclimb-yxyllama2-v2-mkmlizer: ║ belonging to: ║
yuyuclimb-yxyllama2-v2-mkmlizer: ║ ║
yuyuclimb-yxyllama2-v2-mkmlizer: ║ Chai Research Corp. ║
yuyuclimb-yxyllama2-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
yuyuclimb-yxyllama2-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
yuyuclimb-yxyllama2-v2-mkmlizer: ║ ║
yuyuclimb-yxyllama2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
yuyuclimb-yxyllama2-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.
yuyuclimb-yxyllama2-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
yuyuclimb-yxyllama2-v2-mkmlizer: Downloaded to shared memory in 22.165s
yuyuclimb-yxyllama2-v2-mkmlizer: quantizing model to /dev/shm/model_cache
yuyuclimb-yxyllama2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
yuyuclimb-yxyllama2-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 74%|███████▍ | 215/291 [00:01<00:00, 144.69it/s] Loading 0: 100%|██████████| 291/291 [00:02<00:00, 103.17it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
yuyuclimb-yxyllama2-v2-mkmlizer: quantized model in 9.495s
yuyuclimb-yxyllama2-v2-mkmlizer: Processed model yuyuclimb/yxyllama2 in 32.425s
yuyuclimb-yxyllama2-v2-mkmlizer: creating bucket guanaco-mkml-models
yuyuclimb-yxyllama2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
yuyuclimb-yxyllama2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v2
yuyuclimb-yxyllama2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v2/config.json
yuyuclimb-yxyllama2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v2/tokenizer_config.json
yuyuclimb-yxyllama2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v2/tokenizer.model
yuyuclimb-yxyllama2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v2/special_tokens_map.json
yuyuclimb-yxyllama2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v2/tokenizer.json
yuyuclimb-yxyllama2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v2/flywheel_model.0.safetensors
yuyuclimb-yxyllama2-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
yuyuclimb-yxyllama2-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.
yuyuclimb-yxyllama2-v2-mkmlizer: warnings.warn(
yuyuclimb-yxyllama2-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.
yuyuclimb-yxyllama2-v2-mkmlizer: warnings.warn(
yuyuclimb-yxyllama2-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()
yuyuclimb-yxyllama2-v2-mkmlizer: return self.fget.__get__(instance, owner)()
yuyuclimb-yxyllama2-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
yuyuclimb-yxyllama2-v2-mkmlizer: Saving duration: 0.219s
yuyuclimb-yxyllama2-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.374s
yuyuclimb-yxyllama2-v2-mkmlizer: creating bucket guanaco-reward-models
yuyuclimb-yxyllama2-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
yuyuclimb-yxyllama2-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/yuyuclimb-yxyllama2-v2_reward
yuyuclimb-yxyllama2-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/yuyuclimb-yxyllama2-v2_reward/special_tokens_map.json
yuyuclimb-yxyllama2-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/yuyuclimb-yxyllama2-v2_reward/config.json
yuyuclimb-yxyllama2-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/yuyuclimb-yxyllama2-v2_reward/merges.txt
yuyuclimb-yxyllama2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/yuyuclimb-yxyllama2-v2_reward/tokenizer_config.json
yuyuclimb-yxyllama2-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/yuyuclimb-yxyllama2-v2_reward/vocab.json
yuyuclimb-yxyllama2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/yuyuclimb-yxyllama2-v2_reward/tokenizer.json
yuyuclimb-yxyllama2-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/yuyuclimb-yxyllama2-v2_reward/reward.tensors
Job yuyuclimb-yxyllama2-v2-mkmlizer completed after 53.95s with status: succeeded
Stopping job with name yuyuclimb-yxyllama2-v2-mkmlizer
Pipeline stage MKMLizer completed in 58.79s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service yuyuclimb-yxyllama2-v2
Waiting for inference service yuyuclimb-yxyllama2-v2 to be ready
Inference service yuyuclimb-yxyllama2-v2 ready after 40.28666353225708s
Pipeline stage ISVCDeployer completed in 48.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.985478162765503s
Received healthy response to inference request in 1.0735080242156982s
Received healthy response to inference request in 1.0683388710021973s
Received healthy response to inference request in 1.0667665004730225s
Received healthy response to inference request in 0.8531715869903564s
5 requests
0 failed requests
5th percentile: 0.8958905696868896
10th percentile: 0.9386095523834228
20th percentile: 1.0240475177764892
30th percentile: 1.0670809745788574
40th percentile: 1.0677099227905273
50th percentile: 1.0683388710021973
60th percentile: 1.0704065322875977
70th percentile: 1.072474193572998
80th percentile: 1.2559020519256594
90th percentile: 1.620690107345581
95th percentile: 1.8030841350555418
99th percentile: 1.9489993572235107
mean time: 1.2094526290893555
Pipeline stage StressChecker completed in 6.66s
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
yuyuclimb-yxyllama2_v2 status is now deployed due to DeploymentManager action
yuyuclimb-yxyllama2_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics