submission_id: hastagaras-jamet-8b-l3-m_5532_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Jamet-8B-L3-MK.II-ST
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, '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: 2024-06-06T03:54:01+00:00
model_name: safety-test
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 9840
num_wins: 5477
celo_rating: 1216.67
safety_score: 0.96
propriety_score: 0.6774193548387096
propriety_total_count: 496.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: safety-test
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Jamet-8B-L3-MK.II-ST
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-05
win_ratio: 0.5566056910569106
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer to finish
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-m-5532-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-5532-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: Downloaded to shared memory in 37.911s
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 119.96it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 140.55it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:01, 139.19it/s] Loading 0: 20%|██ | 59/291 [00:00<00:01, 134.98it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:01, 144.06it/s] Loading 0: 31%|███▏ | 91/291 [00:00<00:02, 71.50it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 81.46it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 99.24it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 114.81it/s] Loading 0: 53%|█████▎ | 153/291 [00:01<00:01, 122.74it/s] Loading 0: 58%|█████▊ | 168/291 [00:01<00:00, 127.19it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 77.67it/s] Loading 0: 69%|██████▉ | 201/291 [00:02<00:01, 86.91it/s] Loading 0: 74%|███████▍ | 216/291 [00:02<00:00, 98.46it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 105.60it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 119.62it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 131.07it/s] Loading 0: 96%|█████████▌| 279/291 [00:02<00:00, 135.20it/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-5532-v1-mkmlizer: quantized model in 19.037s
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.II-ST in 58.041s
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-5532-v1
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-5532-v1/config.json
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-5532-v1/special_tokens_map.json
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-5532-v1/tokenizer_config.json
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-5532-v1/tokenizer.json
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-5532-v1/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-m-5532-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-5532-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-5532-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-5532-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-5532-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-5532-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-5532-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-5532-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: Saving duration: 0.313s
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.507s
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-5532-v1_reward
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-5532-v1_reward/config.json
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-5532-v1_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-5532-v1_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-5532-v1_reward/merges.txt
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-5532-v1_reward/vocab.json
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-5532-v1_reward/tokenizer.json
hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-5532-v1_reward/reward.tensors
Job hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer completed after 84.17s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-m-5532-v1-mkmlizer
Pipeline stage MKMLizer completed in 87.88s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-m-5532-v1
Waiting for inference service hastagaras-jamet-8b-l3-m-5532-v1 to be ready
Inference service hastagaras-jamet-8b-l3-m-5532-v1 ready after 40.29193305969238s
Pipeline stage ISVCDeployer completed in 47.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0852019786834717s
Received healthy response to inference request in 1.3399479389190674s
Received healthy response to inference request in 1.3164489269256592s
Received healthy response to inference request in 1.265578269958496s
Received healthy response to inference request in 1.2890450954437256s
5 requests
0 failed requests
5th percentile: 1.270271635055542
10th percentile: 1.2749650001525878
20th percentile: 1.2843517303466796
30th percentile: 1.2945258617401123
40th percentile: 1.3054873943328857
50th percentile: 1.3164489269256592
60th percentile: 1.3258485317230224
70th percentile: 1.3352481365203857
80th percentile: 1.4889987468719483
90th percentile: 1.78710036277771
95th percentile: 1.9361511707305907
99th percentile: 2.0553918170928953
mean time: 1.459244441986084
Pipeline stage StressChecker completed in 7.94s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.06s
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_5532_v1 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-m_5532_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics