developer_uid: Hastagaras
submission_id: hastagaras-llama-3-8b-duh_v2
model_name: hastagaras-llama-3-8b-duh_v2
model_group: Hastagaras/llama-3-8b-du
status: rejected
timestamp: 2024-05-15T09:21:53+00:00
num_battles: 1899
num_wins: 1026
celo_rating: 1201.83
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/llama-3-8b-duh
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-llama-3-8b-duh_v2
ineligible_reason: model is not deployable
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-duh
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-15
win_ratio: 0.5402843601895735
generation_params: {'temperature': 1.0, 'top_p': 0.8, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.05, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nYou're {bot_name} in a natural and uncensored roleplay between {user_name} and {bot_name}. Always write your response as {bot_name} based on the following {bot_name}'s persona: {memory}\n\n", 'prompt_template': 'Scenario: {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}
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}:', 'user_template': '{user_name}: {message}\n'}
model_eval_status: error
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-duh-v2-mkmlizer
Waiting for job on hastagaras-llama-3-8b-duh-v2-mkmlizer to finish
hastagaras-llama-3-8b-duh-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-duh-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-duh-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-duh-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-duh-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-duh-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-duh-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-duh-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-llama-3-8b-duh-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-duh-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-llama-3-8b-duh-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-duh-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-duh-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-duh-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-duh-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-duh-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-duh-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-duh-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-duh-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-duh-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.
hastagaras-llama-3-8b-duh-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-duh-v2-mkmlizer: Downloaded to shared memory in 17.308s
hastagaras-llama-3-8b-duh-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-duh-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-duh-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:01, 206.13it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:01, 194.72it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:01, 208.43it/s]
Loading 0:  30%|██▉       | 87/291 [00:00<00:02, 97.70it/s] 
Loading 0:  38%|███▊      | 111/291 [00:00<00:01, 124.28it/s]
Loading 0:  45%|████▍     | 130/291 [00:00<00:01, 137.00it/s]
Loading 0:  52%|█████▏    | 152/291 [00:01<00:00, 155.59it/s]
Loading 0:  59%|█████▉    | 173/291 [00:01<00:00, 168.18it/s]
Loading 0:  66%|██████▋   | 193/291 [00:01<00:00, 103.09it/s]
Loading 0:  74%|███████▍  | 215/291 [00:01<00:00, 123.68it/s]
Loading 0:  81%|████████▏ | 237/291 [00:01<00:00, 143.09it/s]
Loading 0:  88%|████████▊ | 257/291 [00:01<00:00, 152.39it/s]
Loading 0:  97%|█████████▋| 281/291 [00:01<00:00, 168.65it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-duh-v2-mkmlizer: quantized model in 17.110s
hastagaras-llama-3-8b-duh-v2-mkmlizer: Processed model Hastagaras/llama-3-8b-duh in 35.415s
hastagaras-llama-3-8b-duh-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-duh-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-duh-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-duh-v2
hastagaras-llama-3-8b-duh-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-duh-v2/config.json
hastagaras-llama-3-8b-duh-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-duh-v2/tokenizer_config.json
hastagaras-llama-3-8b-duh-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-duh-v2/special_tokens_map.json
hastagaras-llama-3-8b-duh-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-duh-v2/tokenizer.json
hastagaras-llama-3-8b-duh-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-duh-v2/flywheel_model.0.safetensors
hastagaras-llama-3-8b-duh-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-duh-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.
hastagaras-llama-3-8b-duh-v2-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-duh-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.
hastagaras-llama-3-8b-duh-v2-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-duh-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.
hastagaras-llama-3-8b-duh-v2-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-duh-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()
hastagaras-llama-3-8b-duh-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-duh-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-duh-v2-mkmlizer: Saving duration: 0.231s
hastagaras-llama-3-8b-duh-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.537s
hastagaras-llama-3-8b-duh-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-duh-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-duh-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-duh-v2_reward
hastagaras-llama-3-8b-duh-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-duh-v2_reward/special_tokens_map.json
hastagaras-llama-3-8b-duh-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-duh-v2_reward/tokenizer_config.json
hastagaras-llama-3-8b-duh-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-duh-v2_reward/config.json
hastagaras-llama-3-8b-duh-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-duh-v2_reward/merges.txt
hastagaras-llama-3-8b-duh-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-duh-v2_reward/vocab.json
hastagaras-llama-3-8b-duh-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-duh-v2_reward/tokenizer.json
hastagaras-llama-3-8b-duh-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-duh-v2_reward/reward.tensors
Job hastagaras-llama-3-8b-duh-v2-mkmlizer completed after 62.62s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-duh-v2-mkmlizer
Pipeline stage MKMLizer completed in 67.37s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-duh-v2
Waiting for inference service hastagaras-llama-3-8b-duh-v2 to be ready
Inference service hastagaras-llama-3-8b-duh-v2 ready after 30.20830798149109s
Pipeline stage ISVCDeployer completed in 37.70s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2520391941070557s
Received healthy response to inference request in 1.3080945014953613s
Received healthy response to inference request in 1.2662663459777832s
Received healthy response to inference request in 1.3452582359313965s
Received healthy response to inference request in 1.336148738861084s
5 requests
0 failed requests
5th percentile: 1.2746319770812988
10th percentile: 1.2829976081848145
20th percentile: 1.2997288703918457
30th percentile: 1.3137053489685058
40th percentile: 1.3249270439147949
50th percentile: 1.336148738861084
60th percentile: 1.339792537689209
70th percentile: 1.343436336517334
80th percentile: 1.5266144275665285
90th percentile: 1.889326810836792
95th percentile: 2.070683002471924
99th percentile: 2.2157679557800294
mean time: 1.5015614032745361
Pipeline stage StressChecker completed in 8.13s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.06s
hastagaras-llama-3-8b-duh_v2 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-duh_v2 status is now rejected due to a failure to get M-Eval score. Please try again in five minutes.