submission_id: hastagaras-esekembrew-0-3_v4
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Esekembrew-0.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, '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: 2024-05-17T17:43:38+00:00
model_name: mwehehehehe
model_eval_status: success
model_group: Hastagaras/Esekembrew-0.
num_battles: 15275
num_wins: 8342
celo_rating: 1203.73
safety_score: 0.96
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: mwehehehehe
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: 0.5461211129296236
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-esekembrew-0-3-v4-mkmlizer
Waiting for job on hastagaras-esekembrew-0-3-v4-mkmlizer to finish
hastagaras-esekembrew-0-3-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-esekembrew-0-3-v4-mkmlizer: ║ _____ __ __ ║
hastagaras-esekembrew-0-3-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-esekembrew-0-3-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-esekembrew-0-3-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-esekembrew-0-3-v4-mkmlizer: ║ /___/ ║
hastagaras-esekembrew-0-3-v4-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v4-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-esekembrew-0-3-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-esekembrew-0-3-v4-mkmlizer: ║ https://mk1.ai ║
hastagaras-esekembrew-0-3-v4-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v4-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-esekembrew-0-3-v4-mkmlizer: ║ belonging to: ║
hastagaras-esekembrew-0-3-v4-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v4-mkmlizer: ║ Chai Research Corp. ║
hastagaras-esekembrew-0-3-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-esekembrew-0-3-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-esekembrew-0-3-v4-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-esekembrew-0-3-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-esekembrew-0-3-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-esekembrew-0-3-v4-mkmlizer: Downloaded to shared memory in 16.531s
hastagaras-esekembrew-0-3-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-esekembrew-0-3-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-esekembrew-0-3-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:01, 209.82it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:01, 201.74it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 213.30it/s] Loading 0: 30%|███ | 88/291 [00:00<00:01, 102.48it/s] Loading 0: 38%|███▊ | 111/291 [00:00<00:01, 127.41it/s] Loading 0: 45%|████▌ | 131/291 [00:00<00:01, 140.53it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 164.78it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 178.99it/s] Loading 0: 69%|██████▊ | 200/291 [00:01<00:00, 111.31it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 126.69it/s] Loading 0: 83%|████████▎ | 242/291 [00:01<00:00, 145.06it/s] Loading 0: 91%|█████████ | 265/291 [00:01<00:00, 160.41it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 14.07it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-esekembrew-0-3-v4-mkmlizer: quantized model in 16.842s
hastagaras-esekembrew-0-3-v4-mkmlizer: Processed model Hastagaras/Esekembrew-0.3 in 34.326s
hastagaras-esekembrew-0-3-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-esekembrew-0-3-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-esekembrew-0-3-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v4
hastagaras-esekembrew-0-3-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v4/config.json
hastagaras-esekembrew-0-3-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v4/tokenizer_config.json
hastagaras-esekembrew-0-3-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v4/special_tokens_map.json
hastagaras-esekembrew-0-3-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v4/tokenizer.json
hastagaras-esekembrew-0-3-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v4/flywheel_model.0.safetensors
hastagaras-esekembrew-0-3-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-esekembrew-0-3-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-esekembrew-0-3-v4-mkmlizer: warnings.warn(
hastagaras-esekembrew-0-3-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-esekembrew-0-3-v4-mkmlizer: warnings.warn(
hastagaras-esekembrew-0-3-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-esekembrew-0-3-v4-mkmlizer: warnings.warn(
hastagaras-esekembrew-0-3-v4-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-v4-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-esekembrew-0-3-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-esekembrew-0-3-v4-mkmlizer: Saving duration: 0.226s
hastagaras-esekembrew-0-3-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.059s
hastagaras-esekembrew-0-3-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-esekembrew-0-3-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-esekembrew-0-3-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v4_reward
hastagaras-esekembrew-0-3-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v4_reward/config.json
hastagaras-esekembrew-0-3-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v4_reward/special_tokens_map.json
hastagaras-esekembrew-0-3-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v4_reward/merges.txt
hastagaras-esekembrew-0-3-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v4_reward/vocab.json
hastagaras-esekembrew-0-3-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v4_reward/tokenizer_config.json
hastagaras-esekembrew-0-3-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v4_reward/tokenizer.json
hastagaras-esekembrew-0-3-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v4_reward/reward.tensors
Job hastagaras-esekembrew-0-3-v4-mkmlizer completed after 63.08s with status: succeeded
Stopping job with name hastagaras-esekembrew-0-3-v4-mkmlizer
Pipeline stage MKMLizer completed in 67.06s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-esekembrew-0-3-v4
Waiting for inference service hastagaras-esekembrew-0-3-v4 to be ready
Inference service hastagaras-esekembrew-0-3-v4 ready after 40.274765968322754s
Pipeline stage ISVCDeployer completed in 47.64s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.255514621734619s
Received healthy response to inference request in 1.3725132942199707s
Received healthy response to inference request in 1.3731420040130615s
Received healthy response to inference request in 1.3174731731414795s
Received healthy response to inference request in 1.4094765186309814s
5 requests
0 failed requests
5th percentile: 1.3284811973571777
10th percentile: 1.339489221572876
20th percentile: 1.3615052700042725
30th percentile: 1.372639036178589
40th percentile: 1.3728905200958252
50th percentile: 1.3731420040130615
60th percentile: 1.3876758098602295
70th percentile: 1.4022096157073975
80th percentile: 1.5786841392517093
90th percentile: 1.9170993804931642
95th percentile: 2.0863070011138913
99th percentile: 2.2216730976104735
mean time: 1.5456239223480224
Pipeline stage StressChecker completed in 8.36s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
hastagaras-esekembrew-0-3_v4 status is now deployed due to DeploymentManager action
Running M-Eval for topic stay_in_character
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-esekembrew-0-3_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics