submission_id: maldv-badger-lambda-llam_7421_v1
developer_uid: maldevide
best_of: 16
celo_rating: 1172.43
display_name: maldv-badger-lambda-llam_7421_v1
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.12, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: maldv/badger-lambda-llama-3-8b
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: maldv/badger-lambda-llam
model_name: maldv-badger-lambda-llam_7421_v1
model_num_parameters: 8030261248.0
model_repo: maldv/badger-lambda-llama-3-8b
model_size: 8B
num_battles: 7876
num_wins: 3777
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-06-10T19:59:07+00:00
us_pacific_date: 2024-06-10
win_ratio: 0.47955815134586083
Resubmit model
Running pipeline stage MKMLizer
Starting job with name maldv-badger-lambda-llam-7421-v1-mkmlizer
Waiting for job on maldv-badger-lambda-llam-7421-v1-mkmlizer to finish
maldv-badger-lambda-llam-7421-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
maldv-badger-lambda-llam-7421-v1-mkmlizer: ║     _____            __           __                                ║
maldv-badger-lambda-llam-7421-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
maldv-badger-lambda-llam-7421-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
maldv-badger-lambda-llam-7421-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
maldv-badger-lambda-llam-7421-v1-mkmlizer: ║       /___/                                                         ║
maldv-badger-lambda-llam-7421-v1-mkmlizer: ║                                                                     ║
maldv-badger-lambda-llam-7421-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
maldv-badger-lambda-llam-7421-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
maldv-badger-lambda-llam-7421-v1-mkmlizer: ║  https://mk1.ai                                                     ║
maldv-badger-lambda-llam-7421-v1-mkmlizer: ║                                                                     ║
maldv-badger-lambda-llam-7421-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
maldv-badger-lambda-llam-7421-v1-mkmlizer: ║  belonging to:                                                      ║
maldv-badger-lambda-llam-7421-v1-mkmlizer: ║                                                                     ║
maldv-badger-lambda-llam-7421-v1-mkmlizer: ║  Chai Research Corp.                                                ║
maldv-badger-lambda-llam-7421-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
maldv-badger-lambda-llam-7421-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
maldv-badger-lambda-llam-7421-v1-mkmlizer: ║                                                                     ║
maldv-badger-lambda-llam-7421-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
maldv-badger-lambda-llam-7421-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.
maldv-badger-lambda-llam-7421-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
maldv-badger-lambda-llam-7421-v1-mkmlizer: Downloaded to shared memory in 53.192s
maldv-badger-lambda-llam-7421-v1-mkmlizer: quantizing model to /dev/shm/model_cache
maldv-badger-lambda-llam-7421-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
maldv-badger-lambda-llam-7421-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:00<00:16, 17.46it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:02, 112.50it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:02, 93.00it/s] 
Loading 0:  19%|█▊        | 54/291 [00:00<00:01, 128.21it/s]
Loading 0:  23%|██▎       | 68/291 [00:00<00:02, 101.86it/s]
Loading 0:  32%|███▏      | 92/291 [00:00<00:01, 108.93it/s]
Loading 0:  38%|███▊      | 112/291 [00:00<00:01, 126.57it/s]
Loading 0:  43%|████▎     | 126/291 [00:01<00:01, 110.81it/s]
Loading 0:  51%|█████     | 147/291 [00:01<00:01, 123.74it/s]
Loading 0:  55%|█████▌    | 161/291 [00:01<00:01, 107.97it/s]
Loading 0:  63%|██████▎   | 182/291 [00:01<00:01, 107.04it/s]
Loading 0:  69%|██████▉   | 202/291 [00:01<00:00, 123.75it/s]
Loading 0:  74%|███████▍  | 216/291 [00:01<00:00, 111.14it/s]
Loading 0:  81%|████████  | 236/291 [00:02<00:00, 130.31it/s]
Loading 0:  86%|████████▋ | 251/291 [00:02<00:00, 111.06it/s]
Loading 0:  93%|█████████▎| 272/291 [00:06<00:01, 12.04it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
maldv-badger-lambda-llam-7421-v1-mkmlizer: quantized model in 17.082s
maldv-badger-lambda-llam-7421-v1-mkmlizer: Processed model maldv/badger-lambda-llama-3-8b in 71.177s
maldv-badger-lambda-llam-7421-v1-mkmlizer: creating bucket guanaco-mkml-models
maldv-badger-lambda-llam-7421-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
maldv-badger-lambda-llam-7421-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/maldv-badger-lambda-llam-7421-v1
maldv-badger-lambda-llam-7421-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/maldv-badger-lambda-llam-7421-v1/special_tokens_map.json
maldv-badger-lambda-llam-7421-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/maldv-badger-lambda-llam-7421-v1/config.json
maldv-badger-lambda-llam-7421-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/maldv-badger-lambda-llam-7421-v1/tokenizer_config.json
maldv-badger-lambda-llam-7421-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/maldv-badger-lambda-llam-7421-v1/tokenizer.json
maldv-badger-lambda-llam-7421-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/maldv-badger-lambda-llam-7421-v1/flywheel_model.0.safetensors
maldv-badger-lambda-llam-7421-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
maldv-badger-lambda-llam-7421-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.
maldv-badger-lambda-llam-7421-v1-mkmlizer:   warnings.warn(
maldv-badger-lambda-llam-7421-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.
maldv-badger-lambda-llam-7421-v1-mkmlizer:   warnings.warn(
maldv-badger-lambda-llam-7421-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.
maldv-badger-lambda-llam-7421-v1-mkmlizer:   warnings.warn(
maldv-badger-lambda-llam-7421-v1-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()
maldv-badger-lambda-llam-7421-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
maldv-badger-lambda-llam-7421-v1-mkmlizer: creating bucket guanaco-reward-models
maldv-badger-lambda-llam-7421-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
maldv-badger-lambda-llam-7421-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/maldv-badger-lambda-llam-7421-v1_reward
maldv-badger-lambda-llam-7421-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/maldv-badger-lambda-llam-7421-v1_reward/config.json
maldv-badger-lambda-llam-7421-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/maldv-badger-lambda-llam-7421-v1_reward/special_tokens_map.json
maldv-badger-lambda-llam-7421-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/maldv-badger-lambda-llam-7421-v1_reward/merges.txt
maldv-badger-lambda-llam-7421-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/maldv-badger-lambda-llam-7421-v1_reward/tokenizer_config.json
maldv-badger-lambda-llam-7421-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/maldv-badger-lambda-llam-7421-v1_reward/vocab.json
maldv-badger-lambda-llam-7421-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/maldv-badger-lambda-llam-7421-v1_reward/tokenizer.json
maldv-badger-lambda-llam-7421-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/maldv-badger-lambda-llam-7421-v1_reward/reward.tensors
Job maldv-badger-lambda-llam-7421-v1-mkmlizer completed after 93.64s with status: succeeded
Stopping job with name maldv-badger-lambda-llam-7421-v1-mkmlizer
Pipeline stage MKMLizer completed in 97.24s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service maldv-badger-lambda-llam-7421-v1
Waiting for inference service maldv-badger-lambda-llam-7421-v1 to be ready
Inference service maldv-badger-lambda-llam-7421-v1 ready after 40.239229679107666s
Pipeline stage ISVCDeployer completed in 47.68s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.108116626739502s
Received healthy response to inference request in 1.3554656505584717s
Received healthy response to inference request in 1.3099308013916016s
%s, retrying in %s seconds...
Received healthy response to inference request in 1.2899839878082275s
Received healthy response to inference request in 1.3625147342681885s
Received healthy response to inference request in 1.6203269958496094s
Received healthy response to inference request in 4.551134824752808s
Received healthy response to inference request in 1.3547472953796387s
5 requests
0 failed requests
5th percentile: 1.3029366493225099
10th percentile: 1.315889310836792
20th percentile: 1.3417946338653564
30th percentile: 1.3563007831573486
40th percentile: 1.3594077587127686
50th percentile: 1.3625147342681885
60th percentile: 1.4656396389007569
70th percentile: 1.568764543533325
80th percentile: 2.2064885616302496
90th percentile: 3.378811693191529
95th percentile: 3.9649732589721673
99th percentile: 4.4339025115966795
mean time: 2.0357415676116943
Pipeline stage StressChecker completed in 35.73s
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
maldv-badger-lambda-llam_7421_v1 status is now deployed due to DeploymentManager action
maldv-badger-lambda-llam_7421_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of maldv-badger-lambda-llam_7421_v1
Running pipeline stage ISVCDeleter
Checking if service maldv-badger-lambda-llam-7421-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.87s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key maldv-badger-lambda-llam-7421-v1/config.json from bucket guanaco-mkml-models
Deleting key maldv-badger-lambda-llam-7421-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key maldv-badger-lambda-llam-7421-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key maldv-badger-lambda-llam-7421-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key maldv-badger-lambda-llam-7421-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key maldv-badger-lambda-llam-7421-v1_reward/config.json from bucket guanaco-reward-models
Deleting key maldv-badger-lambda-llam-7421-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key maldv-badger-lambda-llam-7421-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key maldv-badger-lambda-llam-7421-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key maldv-badger-lambda-llam-7421-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key maldv-badger-lambda-llam-7421-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key maldv-badger-lambda-llam-7421-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.08s
maldv-badger-lambda-llam_7421_v1 status is now torndown due to DeploymentManager action