thetsar1209-llama3-carp-v0-4

submission_id: thetsar1209-llama3-carp-v0-4_v7

developer_uid: TheTsar1209

best_of: 16

celo_rating: 1191.39

display_name: thetsar1209-llama3-carp-v0-4_v1

family_friendly_score: 0.0

formatter: {'memory_template': '<|im_start|>system\nYou are {bot_name}\nDescription : {memory}\n', 'prompt_template': 'Example conversation : {prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', 'truncate_by_message': True}

generation_params: {'temperature': 1.0, 'top_p': 0.9, '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

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-v0-4_v1

model_num_parameters: 8030261248.0

model_repo: TheTsar1209/llama3-carp-v0.4

model_size: 8B

num_battles: 20022

num_wins: 10660

ranking_group: single

reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': True, 'user_template': 'User: {message}\n'}

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

status: torndown

submission_type: basic

timestamp: 2024-05-22T00:25:03+00:00

us_pacific_date: 2024-05-21

win_ratio: 0.5324143442213565

Resubmit model

Running pipeline stage MKMLizer
Starting job with name thetsar1209-llama3-carp-v0-4-v7-mkmlizer
Waiting for job on thetsar1209-llama3-carp-v0-4-v7-mkmlizer to finish
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ║     _____            __           __                                ║
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ║       /___/                                                         ║
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ║                                                                     ║
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ║  Version: 0.8.14                                                    ║
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ║  https://mk1.ai                                                     ║
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ║                                                                     ║
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ║  belonging to:                                                      ║
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ║                                                                     ║
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ║  Chai Research Corp.                                                ║
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ║                                                                     ║
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thetsar1209-llama3-carp-v0-4-v7-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-v0-4-v7-mkmlizer:   warnings.warn(warning_message, FutureWarning)
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: Downloaded to shared memory in 13.609s
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: quantizing model to /dev/shm/model_cache
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:01, 205.89it/s]
Loading 0:  16%|█▌        | 46/291 [00:00<00:01, 224.52it/s]
Loading 0:  24%|██▎       | 69/291 [00:00<00:01, 207.54it/s]
Loading 0:  31%|███       | 90/291 [00:00<00:01, 103.98it/s]
Loading 0:  38%|███▊      | 112/291 [00:00<00:01, 125.11it/s]
Loading 0:  46%|████▌     | 134/291 [00:00<00:01, 146.17it/s]
Loading 0:  54%|█████▍    | 157/291 [00:01<00:00, 162.68it/s]
Loading 0:  62%|██████▏   | 180/291 [00:01<00:00, 175.08it/s]
Loading 0:  69%|██████▊   | 200/291 [00:01<00:00, 106.50it/s]
Loading 0:  75%|███████▌  | 219/291 [00:01<00:00, 119.88it/s]
Loading 0:  82%|████████▏ | 238/291 [00:01<00:00, 131.26it/s]
Loading 0:  88%|████████▊ | 257/291 [00:01<00:00, 143.10it/s]
Loading 0:  97%|█████████▋| 281/291 [00:01<00:00, 163.01it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: quantized model in 18.408s
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: Processed model TheTsar1209/llama3-carp-v0.4 in 33.030s
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: creating bucket guanaco-mkml-models
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v7
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v7/special_tokens_map.json
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v7/tokenizer_config.json
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v7/config.json
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v7/tokenizer.json
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v7/flywheel_model.0.safetensors
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thetsar1209-llama3-carp-v0-4-v7-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-v0-4-v7-mkmlizer:   warnings.warn(
thetsar1209-llama3-carp-v0-4-v7-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-v0-4-v7-mkmlizer:   warnings.warn(
thetsar1209-llama3-carp-v0-4-v7-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-v0-4-v7-mkmlizer:   warnings.warn(
thetsar1209-llama3-carp-v0-4-v7-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-v0-4-v7-mkmlizer:   return self.fget.__get__(instance, owner)()
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: Saving duration: 0.272s
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.637s
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: creating bucket guanaco-reward-models
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v7_reward
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v7_reward/config.json
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v7_reward/special_tokens_map.json
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v7_reward/tokenizer_config.json
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v7_reward/merges.txt
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v7_reward/vocab.json
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v7_reward/tokenizer.json
thetsar1209-llama3-carp-v0-4-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v7_reward/reward.tensors
Job thetsar1209-llama3-carp-v0-4-v7-mkmlizer completed after 62.91s with status: succeeded
Stopping job with name thetsar1209-llama3-carp-v0-4-v7-mkmlizer
Pipeline stage MKMLizer completed in 65.52s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service thetsar1209-llama3-carp-v0-4-v7
Waiting for inference service thetsar1209-llama3-carp-v0-4-v7 to be ready
Inference service thetsar1209-llama3-carp-v0-4-v7 ready after 30.15827441215515s
Pipeline stage ISVCDeployer completed in 37.31s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.077507734298706s
Received healthy response to inference request in 1.278167486190796s
Received healthy response to inference request in 1.2751080989837646s
Received healthy response to inference request in 1.277036190032959s
Received healthy response to inference request in 1.2795140743255615s
5 requests
0 failed requests
5th percentile: 1.2754937171936036
10th percentile: 1.2758793354034423
20th percentile: 1.27665057182312
30th percentile: 1.2772624492645264
40th percentile: 1.2777149677276611
50th percentile: 1.278167486190796
60th percentile: 1.2787061214447022
70th percentile: 1.2792447566986085
80th percentile: 1.4391128063201906
90th percentile: 1.7583102703094484
95th percentile: 1.917909002304077
99th percentile: 2.04558798789978
mean time: 1.4374667167663575
Pipeline stage StressChecker completed in 7.80s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
thetsar1209-llama3-carp-v0-4_v7 status is now deployed due to DeploymentManager action
thetsar1209-llama3-carp-v0-4_v7 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of thetsar1209-llama3-carp-v0-4_v7
Running pipeline stage ISVCDeleter
Checking if service thetsar1209-llama3-carp-v0-4-v7 is running
Tearing down inference service thetsar1209-llama3-carp-v0-4-v7
Toredown service thetsar1209-llama3-carp-v0-4-v7
Pipeline stage ISVCDeleter completed in 3.26s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key thetsar1209-llama3-carp-v0-4-v7/config.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-v0-4-v7/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-v0-4-v7/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-v0-4-v7/tokenizer.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-v0-4-v7/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key thetsar1209-llama3-carp-v0-4-v7_reward/config.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-4-v7_reward/merges.txt from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-4-v7_reward/reward.tensors from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-4-v7_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-4-v7_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-4-v7_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-4-v7_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.96s
thetsar1209-llama3-carp-v0-4_v7 status is now torndown due to DeploymentManager action