submission_id: nousresearch-meta-llama-3-8b_v19
developer_uid: end_to_end_test
status: inactive
model_repo: NousResearch/Meta-Llama-3-8B
reward_repo: ChaiML/reward_models_100_170000000_cp_498032
generation_params: {'temperature': 1.0, 'top_p': 0.99, 'min_p': 0.1, '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': 'character: {bot_name} {memory}\n', 'prompt_template': '{prompt}', 'bot_template': '{bot_name}: {message}', 'user_template': '{user_name}: {message}', 'response_template': '{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': 'character: {bot_name} {memory}\n', 'prompt_template': '{prompt}', 'bot_template': '{bot_name}: {message}', 'user_template': '{user_name}: {message}', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-06-18T19:10:24+00:00
model_name: nousresearch-meta-llama-3-8b_v19
model_group: NousResearch/Meta-Llama-
num_battles: 28422
num_wins: 9623
celo_rating: 1080.81
propriety_score: 0.7064777327935222
propriety_total_count: 13338.0
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-3-8b_v19
ineligible_reason: None
language_model: NousResearch/Meta-Llama-3-8B
model_size: 8B
reward_model: ChaiML/reward_models_100_170000000_cp_498032
us_pacific_date: 2024-06-18
win_ratio: 0.3385757511786644
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-3-8b-v19-mkmlizer
Waiting for job on nousresearch-meta-llama-3-8b-v19-mkmlizer to finish
nousresearch-meta-llama-3-8b-v19-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-3-8b-v19-mkmlizer: ║ _____ __ __ ║
nousresearch-meta-llama-3-8b-v19-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-meta-llama-3-8b-v19-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-meta-llama-3-8b-v19-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-meta-llama-3-8b-v19-mkmlizer: ║ /___/ ║
nousresearch-meta-llama-3-8b-v19-mkmlizer: ║ ║
nousresearch-meta-llama-3-8b-v19-mkmlizer: ║ Version: 0.8.14 ║
nousresearch-meta-llama-3-8b-v19-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-meta-llama-3-8b-v19-mkmlizer: ║ https://mk1.ai ║
nousresearch-meta-llama-3-8b-v19-mkmlizer: ║ ║
nousresearch-meta-llama-3-8b-v19-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-meta-llama-3-8b-v19-mkmlizer: ║ belonging to: ║
nousresearch-meta-llama-3-8b-v19-mkmlizer: ║ ║
nousresearch-meta-llama-3-8b-v19-mkmlizer: ║ Chai Research Corp. ║
nousresearch-meta-llama-3-8b-v19-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-meta-llama-3-8b-v19-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nousresearch-meta-llama-3-8b-v19-mkmlizer: ║ ║
nousresearch-meta-llama-3-8b-v19-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-3-8b-v19-mkmlizer: Downloaded to shared memory in 20.503s
nousresearch-meta-llama-3-8b-v19-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-meta-llama-3-8b-v19-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-3-8b-v19-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:01, 159.33it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 156.74it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 163.27it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 163.81it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 89.71it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:01, 107.46it/s] Loading 0: 42%|████▏ | 121/291 [00:00<00:01, 122.54it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 134.95it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:00, 143.75it/s] Loading 0: 60%|██████ | 175/291 [00:01<00:00, 151.98it/s] Loading 0: 66%|██████▌ | 192/291 [00:01<00:01, 95.49it/s] Loading 0: 72%|███████▏ | 210/291 [00:01<00:00, 110.18it/s] Loading 0: 78%|███████▊ | 228/291 [00:01<00:00, 124.01it/s] Loading 0: 85%|████████▍ | 246/291 [00:01<00:00, 135.17it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 143.98it/s] Loading 0: 97%|█████████▋| 281/291 [00:02<00:00, 149.24it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-meta-llama-3-8b-v19-mkmlizer: quantized model in 22.470s
nousresearch-meta-llama-3-8b-v19-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B in 42.973s
nousresearch-meta-llama-3-8b-v19-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-3-8b-v19-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-3-8b-v19-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-3-8b-v19
nousresearch-meta-llama-3-8b-v19-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-3-8b-v19/special_tokens_map.json
nousresearch-meta-llama-3-8b-v19-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-3-8b-v19/config.json
nousresearch-meta-llama-3-8b-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-3-8b-v19/tokenizer_config.json
nousresearch-meta-llama-3-8b-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-3-8b-v19/tokenizer.json
nousresearch-meta-llama-3-8b-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-3-8b-v19/flywheel_model.0.safetensors
nousresearch-meta-llama-3-8b-v19-mkmlizer: loading reward model from ChaiML/reward_models_100_170000000_cp_498032
nousresearch-meta-llama-3-8b-v19-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nousresearch-meta-llama-3-8b-v19-mkmlizer: warnings.warn(
nousresearch-meta-llama-3-8b-v19-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
nousresearch-meta-llama-3-8b-v19-mkmlizer: warnings.warn(
nousresearch-meta-llama-3-8b-v19-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nousresearch-meta-llama-3-8b-v19-mkmlizer: warnings.warn(
nousresearch-meta-llama-3-8b-v19-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-3-8b-v19-mkmlizer: warnings.warn(
nousresearch-meta-llama-3-8b-v19-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-3-8b-v19-mkmlizer: return self.fget.__get__(instance, owner)()
nousresearch-meta-llama-3-8b-v19-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-3-8b-v19-mkmlizer: Saving duration: 0.142s
nousresearch-meta-llama-3-8b-v19-mkmlizer: Processed model ChaiML/reward_models_100_170000000_cp_498032 in 2.552s
nousresearch-meta-llama-3-8b-v19-mkmlizer: creating bucket guanaco-reward-models
nousresearch-meta-llama-3-8b-v19-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-meta-llama-3-8b-v19-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-meta-llama-3-8b-v19_reward
nousresearch-meta-llama-3-8b-v19-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-meta-llama-3-8b-v19_reward/special_tokens_map.json
nousresearch-meta-llama-3-8b-v19-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-meta-llama-3-8b-v19_reward/config.json
nousresearch-meta-llama-3-8b-v19-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-meta-llama-3-8b-v19_reward/tokenizer_config.json
nousresearch-meta-llama-3-8b-v19-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-meta-llama-3-8b-v19_reward/vocab.json
nousresearch-meta-llama-3-8b-v19-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-meta-llama-3-8b-v19_reward/merges.txt
nousresearch-meta-llama-3-8b-v19-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-meta-llama-3-8b-v19_reward/tokenizer.json
nousresearch-meta-llama-3-8b-v19-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nousresearch-meta-llama-3-8b-v19_reward/reward.tensors
Job nousresearch-meta-llama-3-8b-v19-mkmlizer completed after 192.27s with status: succeeded
Stopping job with name nousresearch-meta-llama-3-8b-v19-mkmlizer
Pipeline stage MKMLizer completed in 196.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.42s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-3-8b-v19
Waiting for inference service nousresearch-meta-llama-3-8b-v19 to be ready
Inference service nousresearch-meta-llama-3-8b-v19 ready after 104.0019178390503s
Pipeline stage ISVCDeployer completed in 107.49s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3883211612701416s
Received healthy response to inference request in 1.36130690574646s
Received healthy response to inference request in 1.288748025894165s
Received healthy response to inference request in 1.4122579097747803s
Received healthy response to inference request in 1.3021681308746338s
5 requests
0 failed requests
5th percentile: 1.2914320468902587
10th percentile: 1.2941160678863526
20th percentile: 1.2994841098785401
30th percentile: 1.313995885848999
40th percentile: 1.3376513957977294
50th percentile: 1.36130690574646
60th percentile: 1.381687307357788
70th percentile: 1.4020677089691163
80th percentile: 1.6074705600738528
90th percentile: 1.9978958606719972
95th percentile: 2.193108510971069
99th percentile: 2.349278631210327
mean time: 1.550560426712036
Pipeline stage StressChecker completed in 11.77s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.15s
%s, retrying in %s seconds...
nousresearch-meta-llama-3-8b_v19 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
nousresearch-meta-llama-3-8b_v19 status is now inactive due to auto deactivation removed underperforming models
nousresearch-meta-llama-3-8b_v19 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics