submission_id: thetsar1209-llama3-carp-_2297_v2
developer_uid: TheTsar1209
best_of: 16
celo_rating: 1175.47
display_name: thetsar1209-llama3-carp_2297_v1
family_friendly_score: 0.0
formatter: {'memory_template': '<|im_start|>system\\You are {bot_name}\\Description : {memory}\\', 'prompt_template': 'Example conversation:\\{prompt}<|im_end|>\\', 'bot_template': '<|im_start|>assistantshort\\{message}<|im_end|>\\', 'user_template': '<|im_start|>user\\{message}<|im_end|>\\', 'response_template': '<|im_start|>assistantshort\\', 'truncate_by_message': False}
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': ['<|im_end|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: TheTsar1209/llama3-carp-v0.4.1A
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: TheTsar1209/llama3-carp-
model_name: thetsar1209-llama3-carp_2297_v1
model_num_parameters: 8030261248.0
model_repo: TheTsar1209/llama3-carp-v0.4.1A
model_size: 8B
num_battles: 11018
num_wins: 5583
ranking_group: single
reward_formatter: {'bot_template': 'Bot: {message}\\', 'memory_template': 'Memory: {memory}\\', 'prompt_template': '{prompt}\\', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\\'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-15T01:38:31+00:00
us_pacific_date: 2024-05-14
win_ratio: 0.506716282446905
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thetsar1209-llama3-carp-2297-v2-mkmlizer
Waiting for job on thetsar1209-llama3-carp-2297-v2-mkmlizer to finish
thetsar1209-llama3-carp-2297-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thetsar1209-llama3-carp-2297-v2-mkmlizer: ║     _____            __           __                                ║
thetsar1209-llama3-carp-2297-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
thetsar1209-llama3-carp-2297-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
thetsar1209-llama3-carp-2297-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
thetsar1209-llama3-carp-2297-v2-mkmlizer: ║       /___/                                                         ║
thetsar1209-llama3-carp-2297-v2-mkmlizer: ║                                                                     ║
thetsar1209-llama3-carp-2297-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
thetsar1209-llama3-carp-2297-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
thetsar1209-llama3-carp-2297-v2-mkmlizer: ║  https://mk1.ai                                                     ║
thetsar1209-llama3-carp-2297-v2-mkmlizer: ║                                                                     ║
thetsar1209-llama3-carp-2297-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
thetsar1209-llama3-carp-2297-v2-mkmlizer: ║  belonging to:                                                      ║
thetsar1209-llama3-carp-2297-v2-mkmlizer: ║                                                                     ║
thetsar1209-llama3-carp-2297-v2-mkmlizer: ║  Chai Research Corp.                                                ║
thetsar1209-llama3-carp-2297-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
thetsar1209-llama3-carp-2297-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
thetsar1209-llama3-carp-2297-v2-mkmlizer: ║                                                                     ║
thetsar1209-llama3-carp-2297-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thetsar1209-llama3-carp-2297-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.
thetsar1209-llama3-carp-2297-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
thetsar1209-llama3-carp-2297-v2-mkmlizer: Downloaded to shared memory in 17.555s
thetsar1209-llama3-carp-2297-v2-mkmlizer: quantizing model to /dev/shm/model_cache
thetsar1209-llama3-carp-2297-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
thetsar1209-llama3-carp-2297-v2-mkmlizer: Processed model TheTsar1209/llama3-carp-v0.4.1A in 35.598s
thetsar1209-llama3-carp-2297-v2-mkmlizer: creating bucket guanaco-mkml-models
thetsar1209-llama3-carp-2297-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thetsar1209-llama3-carp-2297-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thetsar1209-llama3-carp-2297-v2
thetsar1209-llama3-carp-2297-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-2297-v2/config.json
thetsar1209-llama3-carp-2297-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-2297-v2/special_tokens_map.json
thetsar1209-llama3-carp-2297-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-2297-v2/tokenizer_config.json
thetsar1209-llama3-carp-2297-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-2297-v2/tokenizer.json
thetsar1209-llama3-carp-2297-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/thetsar1209-llama3-carp-2297-v2/flywheel_model.0.safetensors
thetsar1209-llama3-carp-2297-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thetsar1209-llama3-carp-2297-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.
thetsar1209-llama3-carp-2297-v2-mkmlizer:   warnings.warn(
thetsar1209-llama3-carp-2297-v2-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.
thetsar1209-llama3-carp-2297-v2-mkmlizer:   warnings.warn(
thetsar1209-llama3-carp-2297-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.
thetsar1209-llama3-carp-2297-v2-mkmlizer:   warnings.warn(
thetsar1209-llama3-carp-2297-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()
thetsar1209-llama3-carp-2297-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
thetsar1209-llama3-carp-2297-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thetsar1209-llama3-carp-2297-v2-mkmlizer: Saving duration: 0.237s
thetsar1209-llama3-carp-2297-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.241s
Job thetsar1209-llama3-carp-2297-v2-mkmlizer completed after 62.58s with status: succeeded
Stopping job with name thetsar1209-llama3-carp-2297-v2-mkmlizer
Pipeline stage MKMLizer completed in 67.73s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service thetsar1209-llama3-carp-2297-v2
Waiting for inference service thetsar1209-llama3-carp-2297-v2 to be ready
Inference service thetsar1209-llama3-carp-2297-v2 ready after 30.21163249015808s
Pipeline stage ISVCDeployer completed in 38.27s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.221771478652954s
Received healthy response to inference request in 1.3281528949737549s
Received healthy response to inference request in 1.277158260345459s
Received healthy response to inference request in 1.280454397201538s
Received healthy response to inference request in 1.3077187538146973s
5 requests
0 failed requests
5th percentile: 1.2778174877166748
10th percentile: 1.2784767150878906
20th percentile: 1.2797951698303223
30th percentile: 1.28590726852417
40th percentile: 1.2968130111694336
50th percentile: 1.3077187538146973
60th percentile: 1.3158924102783203
70th percentile: 1.3240660667419433
80th percentile: 1.5068766117095949
90th percentile: 1.8643240451812746
95th percentile: 2.043047761917114
99th percentile: 2.186026735305786
mean time: 1.4830511569976808
Pipeline stage StressChecker completed in 8.01s
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
thetsar1209-llama3-carp-_2297_v2 status is now deployed due to DeploymentManager action
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
thetsar1209-llama3-carp-_2297_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of thetsar1209-llama3-carp-_2297_v2
Running pipeline stage ISVCDeleter
Checking if service thetsar1209-llama3-carp-2297-v2 is running
Tearing down inference service thetsar1209-llama3-carp-2297-v2
Toredown service thetsar1209-llama3-carp-2297-v2
Pipeline stage ISVCDeleter completed in 6.14s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key thetsar1209-llama3-carp-2297-v2/config.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-2297-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-2297-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-2297-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-2297-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key thetsar1209-llama3-carp-2297-v2_reward/config.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-2297-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-2297-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-2297-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-2297-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-2297-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-2297-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.82s
thetsar1209-llama3-carp-_2297_v2 status is now torndown due to DeploymentManager action