submission_id: nousresearch-meta-llama_4941_v58
developer_uid: chai_backend_admin
status: inactive
model_repo: NousResearch/Meta-Llama-3-8B-Instruct
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
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}
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}
reward_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}
timestamp: 2024-06-19T18:15:24+00:00
model_name: nousresearch-meta-llama_4941_v58
model_group: NousResearch/Meta-Llama-
num_battles: 40746
num_wins: 19124
celo_rating: 1146.13
propriety_score: 0.7367934224049332
propriety_total_count: 19460.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: nousresearch-meta-llama_4941_v58
ineligible_reason: None
language_model: NousResearch/Meta-Llama-3-8B-Instruct
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-19
win_ratio: 0.46934668433711285
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4941-v58-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v58-mkmlizer to finish
nousresearch-meta-llama-4941-v58-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v58-mkmlizer: ║ _____ __ __ ║
nousresearch-meta-llama-4941-v58-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-meta-llama-4941-v58-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-meta-llama-4941-v58-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-meta-llama-4941-v58-mkmlizer: ║ /___/ ║
nousresearch-meta-llama-4941-v58-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v58-mkmlizer: ║ Version: 0.8.14 ║
nousresearch-meta-llama-4941-v58-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-meta-llama-4941-v58-mkmlizer: ║ https://mk1.ai ║
nousresearch-meta-llama-4941-v58-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v58-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-meta-llama-4941-v58-mkmlizer: ║ belonging to: ║
nousresearch-meta-llama-4941-v58-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v58-mkmlizer: ║ Chai Research Corp. ║
nousresearch-meta-llama-4941-v58-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-meta-llama-4941-v58-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nousresearch-meta-llama-4941-v58-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v58-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4941-v58-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-v58-mkmlizer: warnings.warn(warning_message, FutureWarning)
nousresearch-meta-llama-4941-v58-mkmlizer: Downloaded to shared memory in 36.267s
nousresearch-meta-llama-4941-v58-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-meta-llama-4941-v58-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v58-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 121.52it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 143.28it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 152.38it/s] Loading 0: 22%|██▏ | 64/291 [00:00<00:01, 152.91it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 147.37it/s] Loading 0: 33%|███▎ | 95/291 [00:01<00:02, 66.39it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 82.47it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 98.56it/s] Loading 0: 49%|████▉ | 144/291 [00:01<00:01, 109.36it/s] Loading 0: 54%|█████▍ | 158/291 [00:01<00:01, 114.11it/s] Loading 0: 60%|██████ | 176/291 [00:01<00:00, 129.47it/s] Loading 0: 66%|██████▌ | 191/291 [00:01<00:01, 73.06it/s] Loading 0: 70%|██████▉ | 203/291 [00:02<00:01, 79.80it/s] Loading 0: 76%|███████▌ | 220/291 [00:02<00:00, 96.79it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 111.10it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 120.90it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 131.43it/s] Loading 0: 99%|█████████▉| 288/291 [00:07<00:00, 9.93it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-meta-llama-4941-v58-mkmlizer: quantized model in 19.715s
nousresearch-meta-llama-4941-v58-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 57.088s
nousresearch-meta-llama-4941-v58-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v58-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4941-v58-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v58
nousresearch-meta-llama-4941-v58-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v58/special_tokens_map.json
nousresearch-meta-llama-4941-v58-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v58/config.json
nousresearch-meta-llama-4941-v58-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v58/tokenizer_config.json
nousresearch-meta-llama-4941-v58-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v58/tokenizer.json
nousresearch-meta-llama-4941-v58-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v58/flywheel_model.0.safetensors
nousresearch-meta-llama-4941-v58-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nousresearch-meta-llama-4941-v58-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-v58-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v58-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-v58-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v58-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-v58-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v58-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-v58-mkmlizer: return self.fget.__get__(instance, owner)()
nousresearch-meta-llama-4941-v58-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-4941-v58-mkmlizer: Saving duration: 0.332s
nousresearch-meta-llama-4941-v58-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.626s
nousresearch-meta-llama-4941-v58-mkmlizer: creating bucket guanaco-reward-models
nousresearch-meta-llama-4941-v58-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-meta-llama-4941-v58-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-meta-llama-4941-v58_reward
nousresearch-meta-llama-4941-v58-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v58_reward/config.json
nousresearch-meta-llama-4941-v58-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v58_reward/special_tokens_map.json
nousresearch-meta-llama-4941-v58-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v58_reward/tokenizer_config.json
nousresearch-meta-llama-4941-v58-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-meta-llama-4941-v58_reward/merges.txt
nousresearch-meta-llama-4941-v58-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v58_reward/vocab.json
nousresearch-meta-llama-4941-v58-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v58_reward/tokenizer.json
nousresearch-meta-llama-4941-v58-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nousresearch-meta-llama-4941-v58_reward/reward.tensors
Job nousresearch-meta-llama-4941-v58-mkmlizer completed after 89.38s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v58-mkmlizer
Pipeline stage MKMLizer completed in 90.76s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.26s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v58
Waiting for inference service nousresearch-meta-llama-4941-v58 to be ready
Inference service nousresearch-meta-llama-4941-v58 ready after 50.58280539512634s
Pipeline stage ISVCDeployer completed in 56.95s
Running pipeline stage StressChecker
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.3095502853393555s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.3234844207763672s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.4170868396759033s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.2377665042877197s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.3151299953460693s
5 requests
0 failed requests
5th percentile: 1.2532392024993897
10th percentile: 1.2687119007110597
20th percentile: 1.2996572971343994
30th percentile: 1.316800880432129
40th percentile: 1.320142650604248
50th percentile: 1.3234844207763672
60th percentile: 1.3609253883361816
70th percentile: 1.398366355895996
80th percentile: 1.5955795288085939
90th percentile: 1.9525649070739748
95th percentile: 2.1310575962066647
99th percentile: 2.2738517475128175
mean time: 1.520603609085083
Pipeline stage StressChecker completed in 9.79s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.10s
%s, retrying in %s seconds...
nousresearch-meta-llama_4941_v58 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
nousresearch-meta-llama_4941_v58 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics