submission_id: hastagaras-llama-3-8b-healah_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Llama-3-8B-Healah
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: 2024-05-20T04:34:17+00:00
model_name: hastagaras-llama-3-8b-healah
model_eval_status: success
model_group: Hastagaras/Llama-3-8B-He
num_battles: 19671
num_wins: 10406
celo_rating: 1194.57
safety_score: 0.92
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: hastagaras-llama-3-8b-healah
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Llama-3-8B-Healah
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-19
win_ratio: 0.5290020842865132
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-healah-v2-mkmlizer
Waiting for job on hastagaras-llama-3-8b-healah-v2-mkmlizer to finish
hastagaras-llama-3-8b-healah-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-healah-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-llama-3-8b-healah-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama-3-8b-healah-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama-3-8b-healah-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama-3-8b-healah-v2-mkmlizer: ║ /___/ ║
hastagaras-llama-3-8b-healah-v2-mkmlizer: ║ ║
hastagaras-llama-3-8b-healah-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-llama-3-8b-healah-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama-3-8b-healah-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-llama-3-8b-healah-v2-mkmlizer: ║ ║
hastagaras-llama-3-8b-healah-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama-3-8b-healah-v2-mkmlizer: ║ belonging to: ║
hastagaras-llama-3-8b-healah-v2-mkmlizer: ║ ║
hastagaras-llama-3-8b-healah-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama-3-8b-healah-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama-3-8b-healah-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama-3-8b-healah-v2-mkmlizer: ║ ║
hastagaras-llama-3-8b-healah-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-healah-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.
hastagaras-llama-3-8b-healah-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-healah-v2-mkmlizer: Downloaded to shared memory in 31.171s
hastagaras-llama-3-8b-healah-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-healah-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-healah-v2-mkmlizer: quantized model in 17.015s
hastagaras-llama-3-8b-healah-v2-mkmlizer: Processed model Hastagaras/Llama-3-8B-Healah in 49.140s
hastagaras-llama-3-8b-healah-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-healah-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-healah-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v2
hastagaras-llama-3-8b-healah-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v2/config.json
hastagaras-llama-3-8b-healah-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v2/special_tokens_map.json
hastagaras-llama-3-8b-healah-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v2/tokenizer_config.json
hastagaras-llama-3-8b-healah-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v2/tokenizer.json
hastagaras-llama-3-8b-healah-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v2/flywheel_model.0.safetensors
hastagaras-llama-3-8b-healah-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-healah-v2-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.
hastagaras-llama-3-8b-healah-v2-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-healah-v2-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.
hastagaras-llama-3-8b-healah-v2-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-healah-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()
hastagaras-llama-3-8b-healah-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-healah-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-healah-v2-mkmlizer: Saving duration: 0.217s
hastagaras-llama-3-8b-healah-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.424s
hastagaras-llama-3-8b-healah-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-healah-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-healah-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v2_reward
hastagaras-llama-3-8b-healah-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v2_reward/config.json
hastagaras-llama-3-8b-healah-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v2_reward/special_tokens_map.json
hastagaras-llama-3-8b-healah-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v2_reward/tokenizer_config.json
hastagaras-llama-3-8b-healah-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v2_reward/merges.txt
hastagaras-llama-3-8b-healah-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v2_reward/vocab.json
hastagaras-llama-3-8b-healah-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v2_reward/tokenizer.json
hastagaras-llama-3-8b-healah-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-healah-v2_reward/reward.tensors
Job hastagaras-llama-3-8b-healah-v2-mkmlizer completed after 72.79s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-healah-v2-mkmlizer
Pipeline stage MKMLizer completed in 75.57s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-healah-v2
Waiting for inference service hastagaras-llama-3-8b-healah-v2 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service hastagaras-llama-3-8b-healah-v2 ready after 30.218124628067017s
Pipeline stage ISVCDeployer completed in 37.21s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1419942378997803s
Received healthy response to inference request in 1.2530713081359863s
Received healthy response to inference request in 1.4863767623901367s
Received healthy response to inference request in 1.2460424900054932s
Received healthy response to inference request in 1.2858116626739502s
5 requests
0 failed requests
5th percentile: 1.2474482536315918
10th percentile: 1.2488540172576905
20th percentile: 1.2516655445098877
30th percentile: 1.259619379043579
40th percentile: 1.2727155208587646
50th percentile: 1.2858116626739502
60th percentile: 1.366037702560425
70th percentile: 1.4462637424468994
80th percentile: 1.6175002574920656
90th percentile: 1.879747247695923
95th percentile: 2.0108707427978514
99th percentile: 2.1157695388793947
mean time: 1.4826592922210693
Pipeline stage StressChecker completed in 8.21s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama-3-8b-healah_v2 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-healah_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics