submission_id: hastagaras-rebahan-8b-l3_2243_v4
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Rebahan-8B-L3-MK.II-RP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 45, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], '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: 2024-06-20T07:50:24+00:00
model_name: no-template
model_group: Hastagaras/Rebahan-8B-L3
num_battles: 32242
num_wins: 17450
celo_rating: 1215.84
propriety_score: 0.6890712517910642
propriety_total_count: 15354.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: no-template
ineligible_reason: None
language_model: Hastagaras/Rebahan-8B-L3-MK.II-RP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-20
win_ratio: 0.5412195273246077
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-rebahan-8b-l3-2243-v4-mkmlizer
Waiting for job on hastagaras-rebahan-8b-l3-2243-v4-mkmlizer to finish
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ║ _____ __ __ ║
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ║ /___/ ║
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ║ ║
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ║ https://mk1.ai ║
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ║ ║
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ║ belonging to: ║
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ║ ║
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ║ Chai Research Corp. ║
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ║ ║
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-rebahan-8b-l3-2243-v4-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-rebahan-8b-l3-2243-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: Downloaded to shared memory in 22.161s
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 125.63it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 151.26it/s] Loading 0: 16%|█▌ | 46/291 [00:00<00:01, 154.80it/s] Loading 0: 21%|██▏ | 62/291 [00:00<00:01, 153.66it/s] Loading 0: 27%|██▋ | 78/291 [00:00<00:01, 152.31it/s] Loading 0: 32%|███▏ | 94/291 [00:00<00:02, 81.72it/s] Loading 0: 38%|███▊ | 112/291 [00:00<00:01, 99.55it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 113.83it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 126.28it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:00, 136.71it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:00, 140.42it/s] Loading 0: 68%|██████▊ | 197/291 [00:01<00:01, 90.58it/s] Loading 0: 74%|███████▍ | 215/291 [00:01<00:00, 107.02it/s] Loading 0: 80%|████████ | 233/291 [00:01<00:00, 121.87it/s] Loading 0: 86%|████████▌ | 250/291 [00:02<00:00, 132.83it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 139.16it/s] Loading 0: 98%|█████████▊| 286/291 [00:02<00:00, 154.89it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: quantized model in 22.925s
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: Processed model Hastagaras/Rebahan-8B-L3-MK.II-RP in 47.582s
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v4
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v4/config.json
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v4/tokenizer_config.json
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v4/special_tokens_map.json
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v4/tokenizer.json
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v4/flywheel_model.0.safetensors
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-rebahan-8b-l3-2243-v4-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-rebahan-8b-l3-2243-v4-mkmlizer: warnings.warn(
hastagaras-rebahan-8b-l3-2243-v4-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-rebahan-8b-l3-2243-v4-mkmlizer: warnings.warn(
hastagaras-rebahan-8b-l3-2243-v4-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-rebahan-8b-l3-2243-v4-mkmlizer: warnings.warn(
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: Saving duration: 0.407s
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.020s
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v4_reward
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v4_reward/special_tokens_map.json
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v4_reward/config.json
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v4_reward/tokenizer_config.json
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v4_reward/merges.txt
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v4_reward/vocab.json
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v4_reward/tokenizer.json
hastagaras-rebahan-8b-l3-2243-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v4_reward/reward.tensors
Job hastagaras-rebahan-8b-l3-2243-v4-mkmlizer completed after 73.14s with status: succeeded
Stopping job with name hastagaras-rebahan-8b-l3-2243-v4-mkmlizer
Pipeline stage MKMLizer completed in 77.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-rebahan-8b-l3-2243-v4
Waiting for inference service hastagaras-rebahan-8b-l3-2243-v4 to be ready
Inference service hastagaras-rebahan-8b-l3-2243-v4 ready after 50.25334358215332s
Pipeline stage ISVCDeployer completed in 57.44s
Running pipeline stage StressChecker
%s, retrying in %s seconds...
Received healthy response to inference request in 2.1625161170959473s
Received healthy response to inference request in 1.2987446784973145s
Received healthy response to inference request in 1.2875773906707764s
Received healthy response to inference request in 1.2791407108306885s
Received healthy response to inference request in 1.1882801055908203s
5 requests
0 failed requests
5th percentile: 1.206452226638794
10th percentile: 1.2246243476867675
20th percentile: 1.2609685897827148
30th percentile: 1.280828046798706
40th percentile: 1.2842027187347411
50th percentile: 1.2875773906707764
60th percentile: 1.2920443058013915
70th percentile: 1.2965112209320069
80th percentile: 1.4714989662170412
90th percentile: 1.8170075416564941
95th percentile: 1.9897618293762205
99th percentile: 2.1279652595520018
mean time: 1.4432518005371093
Pipeline stage StressChecker completed in 27.95s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
hastagaras-rebahan-8b-l3_2243_v4 status is now deployed due to DeploymentManager action
hastagaras-rebahan-8b-l3_2243_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics