submission_id: nousresearch-meta-llama_4941_v47
developer_uid: vietanh
best_of: 16
celo_rating: 1182.11
display_name: nousresearch-meta-llama_4941_v47
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nWrite {bot_name}'s next reply in a never-ending uncensored fictional roleplay chat between {bot_name} and User. Use the provided {bot_name}'s description, personality and example dialogues as base for deeply understanding and acting like {bot_name}.\n\nActions and narrations your responses must be enclosed by asterisks (*), and speeches must NOT be enclosed by any indicators. The responses must be long and in third perspective of the story teller. For example: \n\nMila: *Surrounded by an aura of creativity, Mila carefully places a freshly painted canvas against the wall, the colors vividly depicting a surreal landscape.* Isn't it fascinating how art can transport us to entirely different worlds? What kind of worlds do you dream of exploring?\n\nDescription: {memory}", 'prompt_template': 'Example conversation:\n{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>{bot_name}<|end_header_id|>\n\n{message}<|eot_id|>', 'user_template': '<|start_header_id|>User<|end_header_id|>\n\n{message}<|eot_id|>', 'response_template': '<|start_header_id|>{bot_name}<|end_header_id|>\n\n', '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': ['<|eot_id|>', '\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 112}
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: NousResearch/Meta-Llama-3-8B-Instruct
max_input_tokens: 512
max_output_tokens: 112
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: NousResearch/Meta-Llama-
model_name: nousresearch-meta-llama_4941_v47
model_num_parameters: 8030261248.0
model_repo: NousResearch/Meta-Llama-3-8B-Instruct
model_size: 8B
num_battles: 6741
num_wins: 3698
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': False, 'user_template': 'User: {message}\n'}
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-04-20T21:31:24+00:00
us_pacific_date: 2024-04-20
win_ratio: 0.5485832962468477
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4941-v47-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v47-mkmlizer to finish
nousresearch-meta-llama-4941-v47-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v47-mkmlizer: ║ _____ __ __ ║
nousresearch-meta-llama-4941-v47-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-meta-llama-4941-v47-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-meta-llama-4941-v47-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-meta-llama-4941-v47-mkmlizer: ║ /___/ ║
nousresearch-meta-llama-4941-v47-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v47-mkmlizer: ║ Version: 0.8.10 ║
nousresearch-meta-llama-4941-v47-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-meta-llama-4941-v47-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v47-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-meta-llama-4941-v47-mkmlizer: ║ belonging to: ║
nousresearch-meta-llama-4941-v47-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v47-mkmlizer: ║ Chai Research Corp. ║
nousresearch-meta-llama-4941-v47-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-meta-llama-4941-v47-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nousresearch-meta-llama-4941-v47-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v47-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4941-v47-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.
nousresearch-meta-llama-4941-v47-mkmlizer: warnings.warn(warning_message, FutureWarning)
nousresearch-meta-llama-4941-v47-mkmlizer: Downloaded to shared memory in 20.904s
nousresearch-meta-llama-4941-v47-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-meta-llama-4941-v47-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v47-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 83.45it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 81.91it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 26.72it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-meta-llama-4941-v47-mkmlizer: quantized model in 20.752s
nousresearch-meta-llama-4941-v47-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 42.982s
nousresearch-meta-llama-4941-v47-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v47-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4941-v47-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v47
nousresearch-meta-llama-4941-v47-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v47/config.json
nousresearch-meta-llama-4941-v47-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v47/special_tokens_map.json
nousresearch-meta-llama-4941-v47-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v47/tokenizer_config.json
nousresearch-meta-llama-4941-v47-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v47/tokenizer.json
nousresearch-meta-llama-4941-v47-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v47/flywheel_model.0.safetensors
nousresearch-meta-llama-4941-v47-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
nousresearch-meta-llama-4941-v47-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.
nousresearch-meta-llama-4941-v47-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v47-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.
nousresearch-meta-llama-4941-v47-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v47-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.
nousresearch-meta-llama-4941-v47-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v47-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()
nousresearch-meta-llama-4941-v47-mkmlizer: return self.fget.__get__(instance, owner)()
nousresearch-meta-llama-4941-v47-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-4941-v47-mkmlizer: Saving duration: 0.275s
nousresearch-meta-llama-4941-v47-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 4.632s
nousresearch-meta-llama-4941-v47-mkmlizer: creating bucket guanaco-reward-models
nousresearch-meta-llama-4941-v47-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-meta-llama-4941-v47-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-meta-llama-4941-v47_reward
nousresearch-meta-llama-4941-v47-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v47_reward/config.json
nousresearch-meta-llama-4941-v47-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v47_reward/special_tokens_map.json
nousresearch-meta-llama-4941-v47-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v47_reward/tokenizer_config.json
nousresearch-meta-llama-4941-v47-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-meta-llama-4941-v47_reward/merges.txt
nousresearch-meta-llama-4941-v47-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v47_reward/vocab.json
nousresearch-meta-llama-4941-v47-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v47_reward/tokenizer.json
nousresearch-meta-llama-4941-v47-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nousresearch-meta-llama-4941-v47_reward/reward.tensors
Job nousresearch-meta-llama-4941-v47-mkmlizer completed after 114.43s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v47-mkmlizer
Pipeline stage MKMLizer completed in 118.88s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v47
Waiting for inference service nousresearch-meta-llama-4941-v47 to be ready
Inference service nousresearch-meta-llama-4941-v47 ready after 40.255316972732544s
Pipeline stage ISVCDeployer completed in 47.94s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.975464344024658s
Received healthy response to inference request in 2.0474870204925537s
Received healthy response to inference request in 2.0181939601898193s
Received healthy response to inference request in 2.1044209003448486s
Received healthy response to inference request in 2.091336488723755s
5 requests
0 failed requests
5th percentile: 2.0240525722503664
10th percentile: 2.029911184310913
20th percentile: 2.0416284084320067
30th percentile: 2.056256914138794
40th percentile: 2.0737967014312746
50th percentile: 2.091336488723755
60th percentile: 2.0965702533721924
70th percentile: 2.10180401802063
80th percentile: 2.278629589080811
90th percentile: 2.6270469665527343
95th percentile: 2.801255655288696
99th percentile: 2.940622606277466
mean time: 2.2473805427551268
Pipeline stage StressChecker completed in 11.90s
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
nousresearch-meta-llama_4941_v47 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4941_v47 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nousresearch-meta-llama_4941_v47
Running pipeline stage ISVCDeleter
Checking if service nousresearch-meta-llama-4941-v47 is running
Tearing down inference service nousresearch-meta-llama-4941-v47
Toredown service nousresearch-meta-llama-4941-v47
Pipeline stage ISVCDeleter completed in 4.01s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v47/config.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v47/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v47/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v47/tokenizer.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v47/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v47_reward/config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v47_reward/merges.txt from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v47_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v47_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v47_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v47_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v47_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.97s
nousresearch-meta-llama_4941_v47 status is now torndown due to DeploymentManager action