submission_id: hastagaras-jamet-8b-l3-m_2070_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Jamet-8B-L3-MK.II-LV
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 80, '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: 2024-06-05T06:04:00+00:00
model_name: less-violence
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 9118
num_wins: 5205
celo_rating: 1221.93
safety_score: 0.97
propriety_score: 0.6619718309859155
propriety_total_count: 284.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: less-violence
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Jamet-8B-L3-MK.II-LV
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-04
win_ratio: 0.5708488703663084
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer to finish
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-m-2070-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-jamet-8b-l3-m-2070-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: Downloaded to shared memory in 29.990s
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 127.36it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 150.22it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 158.85it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 162.58it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 87.72it/s] Loading 0: 35%|███▌ | 102/291 [00:00<00:01, 105.76it/s] Loading 0: 41%|████ | 120/291 [00:00<00:01, 121.21it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 133.38it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 142.94it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 148.11it/s] Loading 0: 65%|██████▌ | 190/291 [00:01<00:01, 95.09it/s] Loading 0: 71%|███████ | 206/291 [00:01<00:00, 107.26it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 113.03it/s] Loading 0: 81%|████████▏ | 237/291 [00:01<00:00, 124.28it/s] Loading 0: 88%|████████▊ | 255/291 [00:02<00:00, 136.13it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 142.90it/s] Loading 0: 99%|█████████▉| 289/291 [00:07<00:00, 9.78it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: quantized model in 22.826s
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.II-LV in 55.315s
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v1
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v1/tokenizer.json
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v1/special_tokens_map.json
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v1/tokenizer_config.json
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v1/config.json
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v1/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-m-2070-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-jamet-8b-l3-m-2070-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-2070-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-jamet-8b-l3-m-2070-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-2070-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-jamet-8b-l3-m-2070-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-2070-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-jamet-8b-l3-m-2070-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: Saving duration: 0.388s
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.144s
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v1_reward
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v1_reward/config.json
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v1_reward/merges.txt
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v1_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v1_reward/vocab.json
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v1_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v1_reward/tokenizer.json
hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v1_reward/reward.tensors
Job hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer completed after 82.82s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-m-2070-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.67s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-m-2070-v1
Waiting for inference service hastagaras-jamet-8b-l3-m-2070-v1 to be ready
Inference service hastagaras-jamet-8b-l3-m-2070-v1 ready after 30.154001235961914s
Pipeline stage ISVCDeployer completed in 36.10s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0581393241882324s
Received healthy response to inference request in 1.3491339683532715s
Received healthy response to inference request in 1.2917790412902832s
Received healthy response to inference request in 1.301123857498169s
Received healthy response to inference request in 1.2456693649291992s
5 requests
0 failed requests
5th percentile: 1.254891300201416
10th percentile: 1.2641132354736329
20th percentile: 1.2825571060180665
30th percentile: 1.2936480045318604
40th percentile: 1.2973859310150146
50th percentile: 1.301123857498169
60th percentile: 1.3203279018402099
70th percentile: 1.339531946182251
80th percentile: 1.4909350395202638
90th percentile: 1.7745371818542481
95th percentile: 1.91633825302124
99th percentile: 2.029779109954834
mean time: 1.449169111251831
Pipeline stage StressChecker completed in 7.93s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-jamet-8b-l3-m_2070_v1 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-m_2070_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics