submission_id: hastagaras-jamet-8b-l3-m_8630_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Jamet-8B-L3-MK.V-Blackroot
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.05, '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: 2024-06-07T02:34:40+00:00
model_name: turu
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 7129
num_wins: 3902
celo_rating: 1225.14
safety_score: 0.94
propriety_score: 0.6653306613226453
propriety_total_count: 499.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: turu
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Jamet-8B-L3-MK.V-Blackroot
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-06
win_ratio: 0.547341843175761
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer to finish
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-m-8630-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-8630-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: Downloaded to shared memory in 17.612s
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 126.71it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 149.30it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 158.04it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 164.83it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 90.27it/s] Loading 0: 35%|███▌ | 102/291 [00:00<00:01, 108.70it/s] Loading 0: 41%|████ | 120/291 [00:00<00:01, 123.67it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 135.67it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 145.96it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 150.71it/s] Loading 0: 65%|██████▌ | 190/291 [00:01<00:01, 96.16it/s] Loading 0: 71%|███████ | 207/291 [00:01<00:00, 110.02it/s] Loading 0: 77%|███████▋ | 225/291 [00:01<00:00, 124.42it/s] Loading 0: 84%|████████▎ | 243/291 [00:01<00:00, 136.43it/s] Loading 0: 90%|████████▉ | 261/291 [00:02<00:00, 146.85it/s] Loading 0: 96%|█████████▌| 279/291 [00:02<00:00, 155.37it/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-8630-v2-mkmlizer: quantized model in 22.434s
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.V-Blackroot in 42.482s
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v2
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v2/tokenizer_config.json
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v2/config.json
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v2/special_tokens_map.json
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v2/tokenizer.json
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v2/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-m-8630-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-8630-v2-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-8630-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-8630-v2-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-8630-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-8630-v2-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-8630-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-8630-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: Saving duration: 0.383s
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.106s
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v2_reward
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v2_reward/config.json
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v2_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v2_reward/merges.txt
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v2_reward/vocab.json
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v2_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v2_reward/tokenizer.json
hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v2_reward/reward.tensors
Job hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer completed after 72.99s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-m-8630-v2-mkmlizer
Pipeline stage MKMLizer completed in 77.76s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-m-8630-v2
Waiting for inference service hastagaras-jamet-8b-l3-m-8630-v2 to be ready
Inference service hastagaras-jamet-8b-l3-m-8630-v2 ready after 40.23855257034302s
Pipeline stage ISVCDeployer completed in 48.05s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.074235677719116s
Received healthy response to inference request in 1.3537745475769043s
Received healthy response to inference request in 1.3346822261810303s
Received healthy response to inference request in 1.327016830444336s
Received healthy response to inference request in 1.2570559978485107s
5 requests
0 failed requests
5th percentile: 1.2710481643676759
10th percentile: 1.2850403308868408
20th percentile: 1.3130246639251708
30th percentile: 1.3285499095916748
40th percentile: 1.3316160678863525
50th percentile: 1.3346822261810303
60th percentile: 1.3423191547393798
70th percentile: 1.3499560832977295
80th percentile: 1.4978667736053468
90th percentile: 1.7860512256622316
95th percentile: 1.9301434516906737
99th percentile: 2.0454172325134277
mean time: 1.4693530559539796
Pipeline stage StressChecker completed in 8.01s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-jamet-8b-l3-m_8630_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-jamet-8b-l3-m_8630_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics