submission_id: hastagaras-rebahan-8b-l3_2243_v5
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Rebahan-8B-L3-MK.II-RP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 45, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|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: 2024-06-22T23:09:57+00:00
model_name: 4
model_group: Hastagaras/Rebahan-8B-L3
num_battles: 14990
num_wins: 8069
celo_rating: 1224.9
propriety_score: 0.7010600706713781
propriety_total_count: 7075.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: 4
ineligible_reason: None
language_model: Hastagaras/Rebahan-8B-L3-MK.II-RP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-22
win_ratio: 0.538292194796531
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-rebahan-8b-l3-2243-v5-mkmlizer
Waiting for job on hastagaras-rebahan-8b-l3-2243-v5-mkmlizer to finish
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ║ _____ __ __ ║
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ║ /___/ ║
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ║ ║
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ║ https://mk1.ai ║
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ║ ║
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ║ belonging to: ║
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ║ ║
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ║ Chai Research Corp. ║
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ║ ║
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-rebahan-8b-l3-2243-v5-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-rebahan-8b-l3-2243-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: Downloaded to shared memory in 30.081s
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 126.00it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 154.80it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 161.22it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 165.46it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 89.93it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:01, 107.95it/s] Loading 0: 42%|████▏ | 121/291 [00:00<00:01, 123.30it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 135.86it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:00, 144.44it/s] Loading 0: 60%|██████ | 176/291 [00:01<00:00, 156.04it/s] Loading 0: 66%|██████▋ | 193/291 [00:01<00:01, 95.44it/s] Loading 0: 73%|███████▎ | 211/291 [00:01<00:00, 110.68it/s] Loading 0: 79%|███████▊ | 229/291 [00:01<00:00, 123.24it/s] Loading 0: 85%|████████▍ | 247/291 [00:01<00:00, 133.01it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 141.24it/s] Loading 0: 97%|█████████▋| 282/291 [00:02<00:00, 146.28it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: quantized model in 22.661s
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: Processed model Hastagaras/Rebahan-8B-L3-MK.II-RP in 55.225s
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v5
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v5/special_tokens_map.json
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v5/config.json
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v5/tokenizer_config.json
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v5/tokenizer.json
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v5/flywheel_model.0.safetensors
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-rebahan-8b-l3-2243-v5-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-rebahan-8b-l3-2243-v5-mkmlizer: warnings.warn(
hastagaras-rebahan-8b-l3-2243-v5-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-rebahan-8b-l3-2243-v5-mkmlizer: warnings.warn(
hastagaras-rebahan-8b-l3-2243-v5-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-rebahan-8b-l3-2243-v5-mkmlizer: warnings.warn(
hastagaras-rebahan-8b-l3-2243-v5-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-rebahan-8b-l3-2243-v5-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: Saving duration: 0.398s
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.671s
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: creating bucket guanaco-reward-models
hastagaras-rebahan-8b-l3-2243-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v5_reward/reward.tensors
Job hastagaras-rebahan-8b-l3-2243-v5-mkmlizer completed after 83.26s with status: succeeded
Stopping job with name hastagaras-rebahan-8b-l3-2243-v5-mkmlizer
Pipeline stage MKMLizer completed in 83.70s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-rebahan-8b-l3-2243-v5
Waiting for inference service hastagaras-rebahan-8b-l3-2243-v5 to be ready
Inference service hastagaras-rebahan-8b-l3-2243-v5 ready after 50.27752923965454s
Pipeline stage ISVCDeployer completed in 56.00s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2373483180999756s
Received healthy response to inference request in 1.392357349395752s
Received healthy response to inference request in 1.3510489463806152s
Received healthy response to inference request in 1.3313748836517334s
Received healthy response to inference request in 1.383591651916504s
5 requests
0 failed requests
5th percentile: 1.3353096961975097
10th percentile: 1.339244508743286
20th percentile: 1.347114133834839
30th percentile: 1.357557487487793
40th percentile: 1.3705745697021485
50th percentile: 1.383591651916504
60th percentile: 1.3870979309082032
70th percentile: 1.3906042098999023
80th percentile: 1.5613555431365969
90th percentile: 1.8993519306182862
95th percentile: 2.0683501243591307
99th percentile: 2.2035486793518064
mean time: 1.539144229888916
Pipeline stage StressChecker completed in 8.47s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
hastagaras-rebahan-8b-l3_2243_v5 status is now deployed due to DeploymentManager action
hastagaras-rebahan-8b-l3_2243_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics