submission_id: hastagaras-llama-3-8b-healah_v3
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': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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: 2024-05-20T04:40:48+00:00
model_name: corrected-format
model_eval_status: success
model_group: Hastagaras/Llama-3-8B-He
num_battles: 17775
num_wins: 9652
celo_rating: 1203.32
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: corrected-format
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: 0.5430098452883263
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-healah-v3-mkmlizer
Waiting for job on hastagaras-llama-3-8b-healah-v3-mkmlizer to finish
hastagaras-llama-3-8b-healah-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-healah-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-llama-3-8b-healah-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama-3-8b-healah-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama-3-8b-healah-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama-3-8b-healah-v3-mkmlizer: ║ /___/ ║
hastagaras-llama-3-8b-healah-v3-mkmlizer: ║ ║
hastagaras-llama-3-8b-healah-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-llama-3-8b-healah-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama-3-8b-healah-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-llama-3-8b-healah-v3-mkmlizer: ║ ║
hastagaras-llama-3-8b-healah-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama-3-8b-healah-v3-mkmlizer: ║ belonging to: ║
hastagaras-llama-3-8b-healah-v3-mkmlizer: ║ ║
hastagaras-llama-3-8b-healah-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama-3-8b-healah-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama-3-8b-healah-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama-3-8b-healah-v3-mkmlizer: ║ ║
hastagaras-llama-3-8b-healah-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-healah-v3-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-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-healah-v3-mkmlizer: Downloaded to shared memory in 18.087s
hastagaras-llama-3-8b-healah-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-healah-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-healah-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 127.59it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 152.09it/s] Loading 0: 16%|█▌ | 46/291 [00:00<00:01, 155.08it/s] Loading 0: 21%|██▏ | 62/291 [00:00<00:01, 152.08it/s] Loading 0: 27%|██▋ | 78/291 [00:00<00:01, 149.74it/s] Loading 0: 32%|███▏ | 93/291 [00:00<00:02, 79.65it/s] Loading 0: 37%|███▋ | 109/291 [00:00<00:01, 95.53it/s] Loading 0: 42%|████▏ | 122/291 [00:01<00:01, 102.42it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 117.60it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 130.08it/s] Loading 0: 59%|█████▉ | 171/291 [00:01<00:00, 133.66it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 80.22it/s] Loading 0: 69%|██████▉ | 201/291 [00:01<00:00, 90.02it/s] Loading 0: 74%|███████▍ | 216/291 [00:01<00:00, 102.19it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 109.49it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 122.11it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 132.45it/s] Loading 0: 97%|█████████▋| 283/291 [00:02<00:00, 141.70it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-healah-v3-mkmlizer: quantized model in 18.261s
hastagaras-llama-3-8b-healah-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-healah-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-healah-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v3
hastagaras-llama-3-8b-healah-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v3/config.json
hastagaras-llama-3-8b-healah-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v3/special_tokens_map.json
hastagaras-llama-3-8b-healah-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v3/tokenizer_config.json
hastagaras-llama-3-8b-healah-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v3/tokenizer.json
hastagaras-llama-3-8b-healah-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-healah-v3/flywheel_model.0.safetensors
hastagaras-llama-3-8b-healah-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-healah-v3-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-v3-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-healah-v3-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-v3-mkmlizer: warnings.warn(
hastagaras-llama-3-8b-healah-v3-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.
hastagaras-llama-3-8b-healah-v3-mkmlizer: warnings.warn(
Job hastagaras-llama-3-8b-healah-v3-mkmlizer completed after 82.84s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-healah-v3-mkmlizer
Pipeline stage MKMLizer completed in 85.78s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-healah-v3
Waiting for inference service hastagaras-llama-3-8b-healah-v3 to be ready
Inference service hastagaras-llama-3-8b-healah-v3 ready after 30.300036191940308s
Pipeline stage ISVCDeployer completed in 37.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.125635862350464s
Received healthy response to inference request in 1.3255817890167236s
Received healthy response to inference request in 1.3067479133605957s
Received healthy response to inference request in 1.290813684463501s
Received healthy response to inference request in 1.338327407836914s
5 requests
0 failed requests
5th percentile: 1.2940005302429198
10th percentile: 1.297187376022339
20th percentile: 1.3035610675811768
30th percentile: 1.3105146884918213
40th percentile: 1.3180482387542725
50th percentile: 1.3255817890167236
60th percentile: 1.3306800365447997
70th percentile: 1.335778284072876
80th percentile: 1.495789098739624
90th percentile: 1.810712480545044
95th percentile: 1.9681741714477539
99th percentile: 2.094143524169922
mean time: 1.4774213314056397
Pipeline stage StressChecker completed in 8.00s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama-3-8b-healah_v3 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-healah_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics