submission_id: hastagaras-jamet-8b-l3-m_2070_v2
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: 2024-06-05T07:39:50+00:00
model_name: less-violence2
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 15558
num_wins: 8668
celo_rating: 1217.56
safety_score: 0.97
propriety_score: 0.6379310344827587
propriety_total_count: 522.0
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-violence2
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: 2024-06-05
win_ratio: 0.5571410206967476
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer to finish
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-m-2070-v2-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-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: Downloaded to shared memory in 16.455s
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:01, 194.34it/s] Loading 0: 14%|█▍ | 41/291 [00:00<00:01, 188.88it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 210.94it/s] Loading 0: 30%|███ | 88/291 [00:00<00:01, 104.81it/s] Loading 0: 38%|███▊ | 111/291 [00:00<00:01, 130.69it/s] Loading 0: 45%|████▌ | 131/291 [00:00<00:01, 145.02it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 170.44it/s] Loading 0: 62%|██████▏ | 180/291 [00:01<00:00, 183.91it/s] Loading 0: 69%|██████▉ | 201/291 [00:01<00:00, 115.47it/s] Loading 0: 76%|███████▌ | 221/291 [00:01<00:00, 130.20it/s] Loading 0: 85%|████████▍ | 246/291 [00:01<00:00, 154.77it/s] Loading 0: 91%|█████████▏| 266/291 [00:01<00:00, 163.78it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 11.61it/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-v2-mkmlizer: quantized model in 21.357s
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.II-LV in 38.761s
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v2
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v2/special_tokens_map.json
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v2/config.json
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v2/tokenizer_config.json
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v2/tokenizer.json
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-2070-v2/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-m-2070-v2-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-v2-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-2070-v2-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-v2-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-2070-v2-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-v2-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-2070-v2-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-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: Saving duration: 0.209s
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.213s
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v2_reward
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v2_reward/config.json
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v2_reward/merges.txt
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v2_reward/vocab.json
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v2_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v2_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v2_reward/tokenizer.json
hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-2070-v2_reward/reward.tensors
Job hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer completed after 63.21s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-m-2070-v2-mkmlizer
Pipeline stage MKMLizer completed in 64.17s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-m-2070-v2
Waiting for inference service hastagaras-jamet-8b-l3-m-2070-v2 to be ready
Inference service hastagaras-jamet-8b-l3-m-2070-v2 ready after 40.20561742782593s
Pipeline stage ISVCDeployer completed in 46.43s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1545872688293457s
Received healthy response to inference request in 1.3331003189086914s
Received healthy response to inference request in 1.3205382823944092s
Received healthy response to inference request in 1.288550853729248s
Received healthy response to inference request in 1.265507698059082s
5 requests
0 failed requests
5th percentile: 1.2701163291931152
10th percentile: 1.2747249603271484
20th percentile: 1.2839422225952148
30th percentile: 1.2949483394622803
40th percentile: 1.3077433109283447
50th percentile: 1.3205382823944092
60th percentile: 1.325563097000122
70th percentile: 1.330587911605835
80th percentile: 1.4973977088928225
90th percentile: 1.8259924888610841
95th percentile: 1.9902898788452146
99th percentile: 2.1217277908325194
mean time: 1.4724568843841552
Pipeline stage StressChecker completed in 8.02s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-jamet-8b-l3-m_2070_v2 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-m_2070_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics