submission_id: hastagaras-jamet-8b-l3-m_8630_v3
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': 1.1, '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: 2024-06-07T03:22:47+00:00
model_name: turu
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 13940
num_wins: 7699
celo_rating: 1220.55
propriety_score: 0.6673170731707317
propriety_total_count: 1025.0
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: 0.5522955523672883
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer to finish
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-m-8630-v3-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-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: Downloaded to shared memory in 18.101s
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 128.58it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 148.37it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 154.29it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 157.64it/s] Loading 0: 28%|██▊ | 82/291 [00:00<00:01, 157.38it/s] Loading 0: 34%|███▎ | 98/291 [00:00<00:02, 80.20it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 91.01it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 106.64it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 120.19it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:00, 131.65it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:00, 132.04it/s] Loading 0: 67%|██████▋ | 196/291 [00:01<00:01, 82.95it/s] Loading 0: 73%|███████▎ | 212/291 [00:01<00:00, 96.12it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 109.88it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 121.52it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 131.19it/s] Loading 0: 98%|█████████▊| 284/291 [00:02<00:00, 142.30it/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-v3-mkmlizer: quantized model in 23.335s
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.V-Blackroot in 44.005s
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v3
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v3/special_tokens_map.json
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v3/tokenizer_config.json
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v3/config.json
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v3/tokenizer.json
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8630-v3/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-m-8630-v3-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-v3-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-8630-v3-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-v3-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-8630-v3-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-v3-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-8630-v3-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-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: Saving duration: 0.417s
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.308s
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v3_reward
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v3_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v3_reward/config.json
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v3_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v3_reward/vocab.json
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v3_reward/merges.txt
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v3_reward/tokenizer.json
hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8630-v3_reward/reward.tensors
Job hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer completed after 73.36s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-m-8630-v3-mkmlizer
Pipeline stage MKMLizer completed in 76.83s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-m-8630-v3
Waiting for inference service hastagaras-jamet-8b-l3-m-8630-v3 to be ready
Inference service hastagaras-jamet-8b-l3-m-8630-v3 ready after 40.22366261482239s
Pipeline stage ISVCDeployer completed in 48.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0786190032958984s
Received healthy response to inference request in 1.3567657470703125s
Received healthy response to inference request in 1.3589491844177246s
Received healthy response to inference request in 1.3183925151824951s
Received healthy response to inference request in 1.2489314079284668s
5 requests
0 failed requests
5th percentile: 1.2628236293792725
10th percentile: 1.2767158508300782
20th percentile: 1.3045002937316894
30th percentile: 1.3260671615600585
40th percentile: 1.3414164543151856
50th percentile: 1.3567657470703125
60th percentile: 1.3576391220092774
70th percentile: 1.3585124969482423
80th percentile: 1.5028831481933596
90th percentile: 1.790751075744629
95th percentile: 1.9346850395202635
99th percentile: 2.0498322105407714
mean time: 1.4723315715789795
Pipeline stage StressChecker completed in 8.00s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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_8630_v3 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-m_8630_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics