submission_id: mylesfriedman30-llama-2-_1165_v1
developer_uid: DDDDDDDDFFFF
best_of: 4
display_name: mylesfriedman30-llama-2-_1165_v1
family_friendly_score: 0.0
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}
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': 4, 'max_output_tokens': 64}
ineligible_reason: model is not deployable
is_internal_developer: False
language_model: mylesfriedman30/llama-2-7b-flirtbot
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: error
model_group: mylesfriedman30/llama-2-
model_name: mylesfriedman30-llama-2-_1165_v1
model_num_parameters: 6738415616.0
model_repo: mylesfriedman30/llama-2-7b-flirtbot
model_size: 7B
num_battles: 132
num_wins: 49
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: rejected
submission_type: basic
timestamp: 2024-06-15T17:46:13+00:00
us_pacific_date: 2024-06-15
win_ratio: 0.3712121212121212
Resubmit model
Running pipeline stage MKMLizer
Starting job with name mylesfriedman30-llama-2-1165-v1-mkmlizer
Waiting for job on mylesfriedman30-llama-2-1165-v1-mkmlizer to finish
Stopping job with name mylesfriedman30-llama-2-1165-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name mylesfriedman30-llama-2-1165-v1-mkmlizer
Waiting for job on mylesfriedman30-llama-2-1165-v1-mkmlizer to finish
mylesfriedman30-llama-2-1165-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mylesfriedman30-llama-2-1165-v1-mkmlizer: ║     _____            __           __                                ║
mylesfriedman30-llama-2-1165-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mylesfriedman30-llama-2-1165-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mylesfriedman30-llama-2-1165-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mylesfriedman30-llama-2-1165-v1-mkmlizer: ║       /___/                                                         ║
mylesfriedman30-llama-2-1165-v1-mkmlizer: ║                                                                     ║
mylesfriedman30-llama-2-1165-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
mylesfriedman30-llama-2-1165-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mylesfriedman30-llama-2-1165-v1-mkmlizer: ║  https://mk1.ai                                                     ║
mylesfriedman30-llama-2-1165-v1-mkmlizer: ║                                                                     ║
mylesfriedman30-llama-2-1165-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
mylesfriedman30-llama-2-1165-v1-mkmlizer: ║  belonging to:                                                      ║
mylesfriedman30-llama-2-1165-v1-mkmlizer: ║                                                                     ║
mylesfriedman30-llama-2-1165-v1-mkmlizer: ║  Chai Research Corp.                                                ║
mylesfriedman30-llama-2-1165-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mylesfriedman30-llama-2-1165-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
mylesfriedman30-llama-2-1165-v1-mkmlizer: ║                                                                     ║
mylesfriedman30-llama-2-1165-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mylesfriedman30-llama-2-1165-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.
mylesfriedman30-llama-2-1165-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
mylesfriedman30-llama-2-1165-v1-mkmlizer: Downloaded to shared memory in 37.779s
mylesfriedman30-llama-2-1165-v1-mkmlizer: quantizing model to /dev/shm/model_cache
mylesfriedman30-llama-2-1165-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mylesfriedman30-llama-2-1165-v1-mkmlizer: quantized model in 14.175s
mylesfriedman30-llama-2-1165-v1-mkmlizer: Processed model mylesfriedman30/llama-2-7b-flirtbot in 54.114s
mylesfriedman30-llama-2-1165-v1-mkmlizer: creating bucket guanaco-mkml-models
mylesfriedman30-llama-2-1165-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mylesfriedman30-llama-2-1165-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mylesfriedman30-llama-2-1165-v1
mylesfriedman30-llama-2-1165-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mylesfriedman30-llama-2-1165-v1/special_tokens_map.json
mylesfriedman30-llama-2-1165-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mylesfriedman30-llama-2-1165-v1/config.json
mylesfriedman30-llama-2-1165-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/mylesfriedman30-llama-2-1165-v1/tokenizer.model
mylesfriedman30-llama-2-1165-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mylesfriedman30-llama-2-1165-v1/tokenizer_config.json
mylesfriedman30-llama-2-1165-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mylesfriedman30-llama-2-1165-v1/tokenizer.json
mylesfriedman30-llama-2-1165-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/mylesfriedman30-llama-2-1165-v1/added_tokens.json
mylesfriedman30-llama-2-1165-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mylesfriedman30-llama-2-1165-v1/flywheel_model.0.safetensors
mylesfriedman30-llama-2-1165-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
mylesfriedman30-llama-2-1165-v1-mkmlizer: 
Loading 0:   0%|          | 0/323 [00:00<?, ?it/s]
Loading 0:  75%|███████▍  | 242/323 [00:01<00:00, 210.80it/s]
Loading 0: 100%|██████████| 323/323 [00:02<00:00, 114.05it/s]
                                                             
/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.
mylesfriedman30-llama-2-1165-v1-mkmlizer:   warnings.warn(
mylesfriedman30-llama-2-1165-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.
mylesfriedman30-llama-2-1165-v1-mkmlizer:   warnings.warn(
mylesfriedman30-llama-2-1165-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.
mylesfriedman30-llama-2-1165-v1-mkmlizer:   warnings.warn(
mylesfriedman30-llama-2-1165-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()
mylesfriedman30-llama-2-1165-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
mylesfriedman30-llama-2-1165-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
mylesfriedman30-llama-2-1165-v1-mkmlizer: Saving duration: 0.464s
mylesfriedman30-llama-2-1165-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 13.105s
mylesfriedman30-llama-2-1165-v1-mkmlizer: creating bucket guanaco-reward-models
mylesfriedman30-llama-2-1165-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
mylesfriedman30-llama-2-1165-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/mylesfriedman30-llama-2-1165-v1_reward
mylesfriedman30-llama-2-1165-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/mylesfriedman30-llama-2-1165-v1_reward/config.json
mylesfriedman30-llama-2-1165-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/mylesfriedman30-llama-2-1165-v1_reward/tokenizer_config.json
mylesfriedman30-llama-2-1165-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/mylesfriedman30-llama-2-1165-v1_reward/special_tokens_map.json
mylesfriedman30-llama-2-1165-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/mylesfriedman30-llama-2-1165-v1_reward/merges.txt
mylesfriedman30-llama-2-1165-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/mylesfriedman30-llama-2-1165-v1_reward/vocab.json
mylesfriedman30-llama-2-1165-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/mylesfriedman30-llama-2-1165-v1_reward/tokenizer.json
mylesfriedman30-llama-2-1165-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/mylesfriedman30-llama-2-1165-v1_reward/reward.tensors
Job mylesfriedman30-llama-2-1165-v1-mkmlizer completed after 93.41s with status: succeeded
Stopping job with name mylesfriedman30-llama-2-1165-v1-mkmlizer
Pipeline stage MKMLizer completed in 98.04s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service mylesfriedman30-llama-2-1165-v1
Waiting for inference service mylesfriedman30-llama-2-1165-v1 to be ready
Inference service mylesfriedman30-llama-2-1165-v1 ready after 50.337995529174805s
Pipeline stage ISVCDeployer completed in 58.31s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4207594394683838s
Received healthy response to inference request in 0.6555991172790527s
Received healthy response to inference request in 0.9989669322967529s
Received healthy response to inference request in 0.6757206916809082s
Received healthy response to inference request in 0.7638766765594482s
5 requests
0 failed requests
5th percentile: 0.6596234321594239
10th percentile: 0.6636477470397949
20th percentile: 0.6716963768005371
30th percentile: 0.6933518886566162
40th percentile: 0.7286142826080322
50th percentile: 0.7638766765594482
60th percentile: 0.8579127788543701
70th percentile: 0.951948881149292
80th percentile: 1.0833254337310791
90th percentile: 1.2520424365997316
95th percentile: 1.3364009380340576
99th percentile: 1.4038877391815185
mean time: 0.9029845714569091
Pipeline stage StressChecker completed in 5.08s
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
mylesfriedman30-llama-2-_1165_v1 status is now deployed due to DeploymentManager action
mylesfriedman30-llama-2-_1165_v1 status is now rejected due to a failure to get M-Eval score. Please try again in five minutes.