submission_id: hastagaras-esekembrew-0-3_v3
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Esekembrew-0.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 200, '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: 2024-05-17T16:59:55+00:00
model_name: mwehehe2
model_eval_status: success
model_group: Hastagaras/Esekembrew-0.
num_battles: 8216
num_wins: 4479
celo_rating: 1208.16
safety_score: 0.94
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: mwehehe2
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Esekembrew-0.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-17
win_ratio: 0.5451557935735151
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-esekembrew-0-3-v3-mkmlizer
Waiting for job on hastagaras-esekembrew-0-3-v3-mkmlizer to finish
hastagaras-esekembrew-0-3-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-esekembrew-0-3-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-esekembrew-0-3-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-esekembrew-0-3-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-esekembrew-0-3-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-esekembrew-0-3-v3-mkmlizer: ║ /___/ ║
hastagaras-esekembrew-0-3-v3-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-esekembrew-0-3-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-esekembrew-0-3-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-esekembrew-0-3-v3-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-esekembrew-0-3-v3-mkmlizer: ║ belonging to: ║
hastagaras-esekembrew-0-3-v3-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-esekembrew-0-3-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-esekembrew-0-3-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-esekembrew-0-3-v3-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-esekembrew-0-3-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-esekembrew-0-3-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-esekembrew-0-3-v3-mkmlizer: Downloaded to shared memory in 17.184s
hastagaras-esekembrew-0-3-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-esekembrew-0-3-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-esekembrew-0-3-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 6%|▌ | 18/291 [00:00<00:01, 175.41it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:01, 190.74it/s] Loading 0: 20%|██ | 59/291 [00:00<00:01, 180.96it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 190.68it/s] Loading 0: 34%|███▍ | 100/291 [00:00<00:02, 89.85it/s] Loading 0: 41%|████ | 120/291 [00:00<00:01, 110.09it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 126.27it/s] Loading 0: 55%|█████▍ | 160/291 [00:01<00:00, 145.34it/s] Loading 0: 62%|██████▏ | 180/291 [00:01<00:00, 157.89it/s] Loading 0: 68%|██████▊ | 199/291 [00:01<00:00, 96.16it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 115.18it/s] Loading 0: 82%|████████▏ | 239/291 [00:01<00:00, 129.94it/s] Loading 0: 91%|█████████ | 264/291 [00:01<00:00, 153.85it/s] Loading 0: 98%|█████████▊| 284/291 [00:02<00:00, 164.22it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-esekembrew-0-3-v3-mkmlizer: quantized model in 17.555s
hastagaras-esekembrew-0-3-v3-mkmlizer: Processed model Hastagaras/Esekembrew-0.3 in 35.741s
hastagaras-esekembrew-0-3-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-esekembrew-0-3-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-esekembrew-0-3-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v3
hastagaras-esekembrew-0-3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v3/tokenizer.json
hastagaras-esekembrew-0-3-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v3/config.json
hastagaras-esekembrew-0-3-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v3/special_tokens_map.json
hastagaras-esekembrew-0-3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v3/tokenizer_config.json
hastagaras-esekembrew-0-3-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v3/flywheel_model.0.safetensors
hastagaras-esekembrew-0-3-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-esekembrew-0-3-v3-mkmlizer: warnings.warn(
hastagaras-esekembrew-0-3-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-esekembrew-0-3-v3-mkmlizer: warnings.warn(
hastagaras-esekembrew-0-3-v3-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-esekembrew-0-3-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-esekembrew-0-3-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-esekembrew-0-3-v3-mkmlizer: Saving duration: 0.244s
hastagaras-esekembrew-0-3-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.383s
hastagaras-esekembrew-0-3-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-esekembrew-0-3-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-esekembrew-0-3-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v3_reward
hastagaras-esekembrew-0-3-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v3_reward/config.json
hastagaras-esekembrew-0-3-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v3_reward/special_tokens_map.json
hastagaras-esekembrew-0-3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v3_reward/tokenizer_config.json
hastagaras-esekembrew-0-3-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v3_reward/merges.txt
hastagaras-esekembrew-0-3-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v3_reward/vocab.json
hastagaras-esekembrew-0-3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v3_reward/tokenizer.json
hastagaras-esekembrew-0-3-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v3_reward/reward.tensors
Job hastagaras-esekembrew-0-3-v3-mkmlizer completed after 63.1s with status: succeeded
Stopping job with name hastagaras-esekembrew-0-3-v3-mkmlizer
Pipeline stage MKMLizer completed in 67.59s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.16s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-esekembrew-0-3-v3
Waiting for inference service hastagaras-esekembrew-0-3-v3 to be ready
Inference service hastagaras-esekembrew-0-3-v3 ready after 40.52116799354553s
Pipeline stage ISVCDeployer completed in 48.74s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0816080570220947s
Received healthy response to inference request in 1.3339321613311768s
Received healthy response to inference request in 1.3152709007263184s
Received healthy response to inference request in 1.3134441375732422s
Received healthy response to inference request in 1.371192216873169s
5 requests
0 failed requests
5th percentile: 1.3138094902038575
10th percentile: 1.3141748428344726
20th percentile: 1.314905548095703
30th percentile: 1.31900315284729
40th percentile: 1.3264676570892333
50th percentile: 1.3339321613311768
60th percentile: 1.3488361835479736
70th percentile: 1.3637402057647705
80th percentile: 1.5132753849029543
90th percentile: 1.7974417209625244
95th percentile: 1.9395248889923093
99th percentile: 2.0531914234161377
mean time: 1.4830894947052002
Pipeline stage StressChecker completed in 8.12s
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-esekembrew-0-3_v3 status is now deployed due to DeploymentManager action
hastagaras-esekembrew-0-3_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics