submission_id: hastagaras-anjir-8b-l3-m_6262_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Anjir-8B-L3-MK.V-BlackJammer
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.08, '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: 2024-06-11T00:53:48+00:00
model_name: blackjammer
model_eval_status: success
model_group: Hastagaras/Anjir-8B-L3-M
num_battles: 21681
num_wins: 12017
celo_rating: 1218.24
safety_score: 0.94
propriety_score: 0.6721288515406163
propriety_total_count: 7140.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: blackjammer
ineligible_reason: None
language_model: Hastagaras/Anjir-8B-L3-MK.V-BlackJammer
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-10
win_ratio: 0.5542641022093077
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer to finish
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-m-6262-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-anjir-8b-l3-m-6262-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: Downloaded to shared memory in 37.731s
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 122.47it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 149.57it/s] Loading 0: 16%|█▌ | 46/291 [00:00<00:01, 151.24it/s] Loading 0: 21%|██▏ | 62/291 [00:00<00:01, 149.21it/s] Loading 0: 26%|██▋ | 77/291 [00:00<00:01, 145.13it/s] Loading 0: 32%|███▏ | 92/291 [00:00<00:02, 79.03it/s] Loading 0: 36%|███▌ | 104/291 [00:00<00:02, 87.12it/s] Loading 0: 42%|████▏ | 122/291 [00:01<00:01, 104.50it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 119.01it/s] Loading 0: 54%|█████▍ | 158/291 [00:01<00:01, 130.24it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 146.57it/s] Loading 0: 67%|██████▋ | 195/291 [00:01<00:01, 86.69it/s] Loading 0: 73%|███████▎ | 212/291 [00:01<00:00, 99.73it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 113.38it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 125.44it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 134.80it/s] Loading 0: 98%|█████████▊| 284/291 [00:02<00:00, 144.66it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: quantized model in 23.259s
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: Processed model Hastagaras/Anjir-8B-L3-MK.V-BlackJammer in 63.646s
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6262-v1
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6262-v1/special_tokens_map.json
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6262-v1/tokenizer.json
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6262-v1/config.json
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6262-v1/tokenizer_config.json
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6262-v1/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-m-6262-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-anjir-8b-l3-m-6262-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-6262-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-anjir-8b-l3-m-6262-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-6262-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-anjir-8b-l3-m-6262-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-6262-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-anjir-8b-l3-m-6262-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: Saving duration: 0.424s
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.725s
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6262-v1_reward
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6262-v1_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6262-v1_reward/config.json
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6262-v1_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6262-v1_reward/merges.txt
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6262-v1_reward/vocab.json
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6262-v1_reward/tokenizer.json
hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6262-v1_reward/reward.tensors
Job hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer completed after 93.57s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-m-6262-v1-mkmlizer
Pipeline stage MKMLizer completed in 93.95s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-m-6262-v1
Waiting for inference service hastagaras-anjir-8b-l3-m-6262-v1 to be ready
Inference service hastagaras-anjir-8b-l3-m-6262-v1 ready after 30.215938568115234s
Pipeline stage ISVCDeployer completed in 35.95s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2216129302978516s
Received healthy response to inference request in 1.3419442176818848s
%s, retrying in %s seconds...
Received healthy response to inference request in 1.2662248611450195s
Received healthy response to inference request in 1.3507425785064697s
Received healthy response to inference request in 1.5095934867858887s
Received healthy response to inference request in 1.2761919498443604s
Received healthy response to inference request in 1.2581346035003662s
5 requests
0 failed requests
5th percentile: 1.2597526550292968
10th percentile: 1.2613707065582276
20th percentile: 1.264606809616089
30th percentile: 1.2682182788848877
40th percentile: 1.272205114364624
50th percentile: 1.2761919498443604
60th percentile: 1.3060122013092041
70th percentile: 1.335832452774048
80th percentile: 1.3825127601623535
90th percentile: 1.4460531234741212
95th percentile: 1.477823305130005
99th percentile: 1.503239450454712
mean time: 1.332177495956421
Pipeline stage StressChecker completed in 30.98s
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 0.08s
hastagaras-anjir-8b-l3-m_6262_v1 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3-m_6262_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics