submission_id: nousresearch-meta-llama-3-8b_v2
developer_uid: Meliodia
status: torndown
model_repo: NousResearch/Meta-Llama-3-8B
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': 16, '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: 2024-04-24T17:20:38+00:00
model_name: nousresearch-meta-llama-3-8b_v2
model_eval_status: success
model_group: NousResearch/Meta-Llama-
num_battles: 7089
num_wins: 3418
celo_rating: 1142.09
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: nousresearch-meta-llama-3-8b_v2
ineligible_reason: propriety_total_count < 800
language_model: NousResearch/Meta-Llama-3-8B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-24
win_ratio: 0.4821554521089011
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-3-8b-v2-mkmlizer
Waiting for job on nousresearch-meta-llama-3-8b-v2-mkmlizer to finish
nousresearch-meta-llama-3-8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-3-8b-v2-mkmlizer: ║ _____ __ __ ║
nousresearch-meta-llama-3-8b-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-meta-llama-3-8b-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-meta-llama-3-8b-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-meta-llama-3-8b-v2-mkmlizer: ║ /___/ ║
nousresearch-meta-llama-3-8b-v2-mkmlizer: ║ ║
nousresearch-meta-llama-3-8b-v2-mkmlizer: ║ Version: 0.8.10 ║
nousresearch-meta-llama-3-8b-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-meta-llama-3-8b-v2-mkmlizer: ║ ║
nousresearch-meta-llama-3-8b-v2-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-meta-llama-3-8b-v2-mkmlizer: ║ belonging to: ║
nousresearch-meta-llama-3-8b-v2-mkmlizer: ║ ║
nousresearch-meta-llama-3-8b-v2-mkmlizer: ║ Chai Research Corp. ║
nousresearch-meta-llama-3-8b-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-meta-llama-3-8b-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nousresearch-meta-llama-3-8b-v2-mkmlizer: ║ ║
nousresearch-meta-llama-3-8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-3-8b-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.
nousresearch-meta-llama-3-8b-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
nousresearch-meta-llama-3-8b-v2-mkmlizer: Downloaded to shared memory in 32.681s
nousresearch-meta-llama-3-8b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-meta-llama-3-8b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-3-8b-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 76.53it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 88.60it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 29.65it/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-v2-mkmlizer: quantized model in 19.531s
nousresearch-meta-llama-3-8b-v2-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B in 53.428s
nousresearch-meta-llama-3-8b-v2-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-3-8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-3-8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-3-8b-v2
nousresearch-meta-llama-3-8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-3-8b-v2/config.json
nousresearch-meta-llama-3-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-3-8b-v2/tokenizer_config.json
nousresearch-meta-llama-3-8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-3-8b-v2/special_tokens_map.json
nousresearch-meta-llama-3-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-3-8b-v2/tokenizer.json
nousresearch-meta-llama-3-8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-3-8b-v2/flywheel_model.0.safetensors
nousresearch-meta-llama-3-8b-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.
nousresearch-meta-llama-3-8b-v2-mkmlizer: warnings.warn(
nousresearch-meta-llama-3-8b-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()
nousresearch-meta-llama-3-8b-v2-mkmlizer: return self.fget.__get__(instance, owner)()
nousresearch-meta-llama-3-8b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-3-8b-v2-mkmlizer: Saving duration: 0.269s
nousresearch-meta-llama-3-8b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.746s
nousresearch-meta-llama-3-8b-v2-mkmlizer: creating bucket guanaco-reward-models
nousresearch-meta-llama-3-8b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-meta-llama-3-8b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-meta-llama-3-8b-v2_reward
nousresearch-meta-llama-3-8b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-meta-llama-3-8b-v2_reward/config.json
nousresearch-meta-llama-3-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-meta-llama-3-8b-v2_reward/tokenizer_config.json
nousresearch-meta-llama-3-8b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-meta-llama-3-8b-v2_reward/special_tokens_map.json
nousresearch-meta-llama-3-8b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-meta-llama-3-8b-v2_reward/merges.txt
nousresearch-meta-llama-3-8b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-meta-llama-3-8b-v2_reward/vocab.json
nousresearch-meta-llama-3-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-meta-llama-3-8b-v2_reward/tokenizer.json
nousresearch-meta-llama-3-8b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nousresearch-meta-llama-3-8b-v2_reward/reward.tensors
Job nousresearch-meta-llama-3-8b-v2-mkmlizer completed after 73.79s with status: succeeded
Stopping job with name nousresearch-meta-llama-3-8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 75.64s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-3-8b-v2
Waiting for inference service nousresearch-meta-llama-3-8b-v2 to be ready
Inference service nousresearch-meta-llama-3-8b-v2 ready after 60.34765863418579s
Pipeline stage ISVCDeployer completed in 68.38s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1244804859161377s
Received healthy response to inference request in 1.2290570735931396s
Received healthy response to inference request in 1.0180230140686035s
Received healthy response to inference request in 2.2127137184143066s
Received healthy response to inference request in 1.1991302967071533s
5 requests
0 failed requests
5th percentile: 1.0542444705963134
10th percentile: 1.0904659271240233
20th percentile: 1.1629088401794434
30th percentile: 1.2051156520843507
40th percentile: 1.2170863628387452
50th percentile: 1.2290570735931396
60th percentile: 1.5872264385223387
70th percentile: 1.945395803451538
80th percentile: 2.1421271324157716
90th percentile: 2.177420425415039
95th percentile: 2.1950670719146728
99th percentile: 2.20918438911438
mean time: 1.5566809177398682
Pipeline stage StressChecker completed in 8.44s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
nousresearch-meta-llama-3-8b_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
nousresearch-meta-llama-3-8b_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nousresearch-meta-llama-3-8b_v2
Running pipeline stage ISVCDeleter
Checking if service nousresearch-meta-llama-3-8b-v2 is running
Tearing down inference service nousresearch-meta-llama-3-8b-v2
Toredown service nousresearch-meta-llama-3-8b-v2
Pipeline stage ISVCDeleter completed in 3.96s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-3-8b-v2/config.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-3-8b-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-3-8b-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-3-8b-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-3-8b-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-3-8b-v2_reward/config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-3-8b-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-3-8b-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-3-8b-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-3-8b-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-3-8b-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-3-8b-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.79s
nousresearch-meta-llama-3-8b_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics