submission_id: hastagaras-esekembrew-0-3_v1
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': 0.0, '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: 2024-05-17T16:37:36+00:00
model_name: mwehehe
model_eval_status: success
model_group: Hastagaras/Esekembrew-0.
num_battles: 16399
num_wins: 8776
celo_rating: 1198.33
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: mwehehe
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: 0.5351545825964998
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-esekembrew-0-3-v1-mkmlizer
Waiting for job on hastagaras-esekembrew-0-3-v1-mkmlizer to finish
hastagaras-esekembrew-0-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-esekembrew-0-3-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-esekembrew-0-3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-esekembrew-0-3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-esekembrew-0-3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-esekembrew-0-3-v1-mkmlizer: ║ /___/ ║
hastagaras-esekembrew-0-3-v1-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-esekembrew-0-3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-esekembrew-0-3-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-esekembrew-0-3-v1-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-esekembrew-0-3-v1-mkmlizer: ║ belonging to: ║
hastagaras-esekembrew-0-3-v1-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-esekembrew-0-3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-esekembrew-0-3-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-esekembrew-0-3-v1-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-esekembrew-0-3-v1-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-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-esekembrew-0-3-v1-mkmlizer: Downloaded to shared memory in 30.078s
hastagaras-esekembrew-0-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-esekembrew-0-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-esekembrew-0-3-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:01, 205.53it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:01, 218.18it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 215.17it/s] Loading 0: 31%|███ | 89/291 [00:00<00:01, 106.87it/s] Loading 0: 38%|███▊ | 112/291 [00:00<00:01, 130.63it/s] Loading 0: 45%|████▌ | 131/291 [00:00<00:01, 142.69it/s] Loading 0: 54%|█████▎ | 156/291 [00:00<00:00, 166.56it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 179.70it/s] Loading 0: 69%|██████▊ | 200/291 [00:01<00:00, 110.03it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 123.96it/s] Loading 0: 83%|████████▎ | 241/291 [00:01<00:00, 141.33it/s] Loading 0: 91%|█████████ | 264/291 [00:01<00:00, 157.46it/s] Loading 0: 97%|█████████▋| 283/291 [00:01<00:00, 164.30it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-esekembrew-0-3-v1-mkmlizer: quantized model in 17.078s
hastagaras-esekembrew-0-3-v1-mkmlizer: Processed model Hastagaras/Esekembrew-0.3 in 48.097s
hastagaras-esekembrew-0-3-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-esekembrew-0-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-esekembrew-0-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v1
hastagaras-esekembrew-0-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v1/config.json
hastagaras-esekembrew-0-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v1/tokenizer_config.json
hastagaras-esekembrew-0-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v1/special_tokens_map.json
hastagaras-esekembrew-0-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v1/tokenizer.json
hastagaras-esekembrew-0-3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v1/flywheel_model.0.safetensors
hastagaras-esekembrew-0-3-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-esekembrew-0-3-v1-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-v1-mkmlizer: warnings.warn(
hastagaras-esekembrew-0-3-v1-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-v1-mkmlizer: warnings.warn(
hastagaras-esekembrew-0-3-v1-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-v1-mkmlizer: warnings.warn(
hastagaras-esekembrew-0-3-v1-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-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-esekembrew-0-3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-esekembrew-0-3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v1_reward
hastagaras-esekembrew-0-3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v1_reward/config.json
hastagaras-esekembrew-0-3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v1_reward/special_tokens_map.json
hastagaras-esekembrew-0-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v1_reward/tokenizer_config.json
hastagaras-esekembrew-0-3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v1_reward/merges.txt
hastagaras-esekembrew-0-3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v1_reward/vocab.json
hastagaras-esekembrew-0-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v1_reward/tokenizer.json
hastagaras-esekembrew-0-3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v1_reward/reward.tensors
Job hastagaras-esekembrew-0-3-v1-mkmlizer completed after 73.89s with status: succeeded
Stopping job with name hastagaras-esekembrew-0-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 77.65s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-esekembrew-0-3-v1
Waiting for inference service hastagaras-esekembrew-0-3-v1 to be ready
Inference service hastagaras-esekembrew-0-3-v1 ready after 100.59076428413391s
Pipeline stage ISVCDeployer completed in 107.73s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1856465339660645s
Received healthy response to inference request in 1.2509989738464355s
Received healthy response to inference request in 1.3013100624084473s
Received healthy response to inference request in 1.3094167709350586s
Received healthy response to inference request in 1.2454369068145752s
5 requests
0 failed requests
5th percentile: 1.2465493202209472
10th percentile: 1.2476617336273192
20th percentile: 1.2498865604400635
30th percentile: 1.261061191558838
40th percentile: 1.2811856269836426
50th percentile: 1.3013100624084473
60th percentile: 1.3045527458190918
70th percentile: 1.3077954292297362
80th percentile: 1.48466272354126
90th percentile: 1.8351546287536622
95th percentile: 2.010400581359863
99th percentile: 2.150597343444824
mean time: 1.4585618495941162
Pipeline stage StressChecker completed in 7.91s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.09s
hastagaras-esekembrew-0-3_v1 status is now deployed due to DeploymentManager action
hastagaras-esekembrew-0-3_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics