developer_uid: zonemercy
submission_id: nousresearch-meta-llama_4941_v43
model_name: nousresearch-meta-llama-3-8b_v1
model_group: NousResearch/Meta-Llama-
status: torndown
timestamp: 2024-04-20T16:12:55+00:00
num_battles: 6448
num_wins: 3421
celo_rating: 1167.05
family_friendly_score: 0.0
submission_type: basic
model_repo: NousResearch/Meta-Llama-3-8B-Instruct
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: nousresearch-meta-llama-3-8b_v1
is_internal_developer: True
language_model: NousResearch/Meta-Llama-3-8B-Instruct
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-20
win_ratio: 0.5305521091811415
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': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "Bot's name: {bot_name}\nBot's Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
model_eval_status: success
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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4941-v43-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v43-mkmlizer to finish
nousresearch-meta-llama-4941-v43-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v43-mkmlizer: ║     _____            __           __                                ║
nousresearch-meta-llama-4941-v43-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nousresearch-meta-llama-4941-v43-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nousresearch-meta-llama-4941-v43-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nousresearch-meta-llama-4941-v43-mkmlizer: ║       /___/                                                         ║
nousresearch-meta-llama-4941-v43-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v43-mkmlizer: ║  Version: 0.8.10                                                    ║
nousresearch-meta-llama-4941-v43-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nousresearch-meta-llama-4941-v43-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v43-mkmlizer: ║  The license key for the current software has been verified as      ║
nousresearch-meta-llama-4941-v43-mkmlizer: ║  belonging to:                                                      ║
nousresearch-meta-llama-4941-v43-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v43-mkmlizer: ║  Chai Research Corp.                                                ║
nousresearch-meta-llama-4941-v43-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nousresearch-meta-llama-4941-v43-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
nousresearch-meta-llama-4941-v43-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v43-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4941-v43-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-v43-mkmlizer:   warnings.warn(warning_message, FutureWarning)
nousresearch-meta-llama-4941-v43-mkmlizer: Downloaded to shared memory in 18.873s
nousresearch-meta-llama-4941-v43-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-meta-llama-4941-v43-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v43-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:02, 75.20it/s]
Loading 0:  47%|████▋     | 138/291 [00:02<00:02, 67.34it/s]
Loading 0:  66%|██████▋   | 193/291 [00:03<00:01, 60.89it/s]
Loading 0:  99%|█████████▊| 287/291 [00:10<00:00, 21.82it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-meta-llama-4941-v43-mkmlizer: quantized model in 22.612s
nousresearch-meta-llama-4941-v43-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 43.267s
nousresearch-meta-llama-4941-v43-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v43-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4941-v43-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v43
nousresearch-meta-llama-4941-v43-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v43/special_tokens_map.json
nousresearch-meta-llama-4941-v43-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v43/tokenizer_config.json
nousresearch-meta-llama-4941-v43-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v43/config.json
nousresearch-meta-llama-4941-v43-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v43/tokenizer.json
nousresearch-meta-llama-4941-v43-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v43/flywheel_model.0.safetensors
nousresearch-meta-llama-4941-v43-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-v43-mkmlizer:   warnings.warn(
nousresearch-meta-llama-4941-v43-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-v43-mkmlizer:   warnings.warn(
nousresearch-meta-llama-4941-v43-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-v43-mkmlizer:   return self.fget.__get__(instance, owner)()
nousresearch-meta-llama-4941-v43-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-4941-v43-mkmlizer: Saving duration: 0.316s
nousresearch-meta-llama-4941-v43-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.215s
nousresearch-meta-llama-4941-v43-mkmlizer: creating bucket guanaco-reward-models
nousresearch-meta-llama-4941-v43-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-meta-llama-4941-v43-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-meta-llama-4941-v43_reward
nousresearch-meta-llama-4941-v43-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v43_reward/config.json
nousresearch-meta-llama-4941-v43-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v43_reward/special_tokens_map.json
nousresearch-meta-llama-4941-v43-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-meta-llama-4941-v43_reward/merges.txt
nousresearch-meta-llama-4941-v43-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v43_reward/tokenizer_config.json
nousresearch-meta-llama-4941-v43-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v43_reward/vocab.json
nousresearch-meta-llama-4941-v43-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v43_reward/tokenizer.json
nousresearch-meta-llama-4941-v43-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nousresearch-meta-llama-4941-v43_reward/reward.tensors
Job nousresearch-meta-llama-4941-v43-mkmlizer completed after 74.0s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v43-mkmlizer
Pipeline stage MKMLizer completed in 79.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v43
Waiting for inference service nousresearch-meta-llama-4941-v43 to be ready
Inference service nousresearch-meta-llama-4941-v43 ready after 40.26445698738098s
Pipeline stage ISVCDeployer completed in 47.98s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.110407590866089s
Received healthy response to inference request in 1.2931506633758545s
Received healthy response to inference request in 1.28554105758667s
Received healthy response to inference request in 1.2917039394378662s
Received healthy response to inference request in 1.2739436626434326s
5 requests
0 failed requests
5th percentile: 1.27626314163208
10th percentile: 1.2785826206207276
20th percentile: 1.2832215785980225
30th percentile: 1.2867736339569091
40th percentile: 1.2892387866973878
50th percentile: 1.2917039394378662
60th percentile: 1.2922826290130616
70th percentile: 1.292861318588257
80th percentile: 1.4566020488739015
90th percentile: 1.7835048198699952
95th percentile: 1.9469562053680418
99th percentile: 2.0777173137664793
mean time: 1.4509493827819824
Pipeline stage StressChecker completed in 8.12s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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
nousresearch-meta-llama_4941_v43 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4941_v43 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nousresearch-meta-llama_4941_v43
Running pipeline stage ISVCDeleter
Checking if service nousresearch-meta-llama-4941-v43 is running
Tearing down inference service nousresearch-meta-llama-4941-v43
Toredown service nousresearch-meta-llama-4941-v43
Pipeline stage ISVCDeleter completed in 4.54s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v43/config.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v43/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v43/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v43/tokenizer.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v43/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v43_reward/config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v43_reward/merges.txt from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v43_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v43_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v43_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v43_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v43_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.86s
nousresearch-meta-llama_4941_v43 status is now torndown due to DeploymentManager action