submission_id: hastagaras-rebahan-8b-l3_2243_v3
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': 1.05, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 80, '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: 2024-06-20T06:09:52+00:00
model_name: 3
model_group: Hastagaras/Rebahan-8B-L3
num_battles: 28152
num_wins: 15928
celo_rating: 1223.47
propriety_score: 0.6984752316334719
propriety_total_count: 13707.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: 3
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: 2024-06-19
win_ratio: 0.5657857345836885
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-rebahan-8b-l3-2243-v3-mkmlizer
Waiting for job on hastagaras-rebahan-8b-l3-2243-v3-mkmlizer to finish
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ║ /___/ ║
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ║ ║
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ║ ║
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ║ belonging to: ║
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ║ ║
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ║ ║
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-rebahan-8b-l3-2243-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-rebahan-8b-l3-2243-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: Downloaded to shared memory in 20.612s
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 119.44it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 143.66it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:01, 143.65it/s] Loading 0: 21%|██ | 60/291 [00:00<00:01, 141.99it/s] Loading 0: 26%|██▋ | 77/291 [00:00<00:01, 144.88it/s] Loading 0: 32%|███▏ | 92/291 [00:00<00:02, 79.72it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 87.68it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 104.75it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 118.64it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:01, 130.19it/s] Loading 0: 60%|██████ | 175/291 [00:01<00:00, 142.84it/s] Loading 0: 66%|██████▌ | 191/291 [00:01<00:01, 87.19it/s] Loading 0: 71%|███████ | 206/291 [00:01<00:00, 98.29it/s] Loading 0: 76%|███████▌ | 221/291 [00:01<00:00, 108.84it/s] Loading 0: 82%|████████▏ | 239/291 [00:02<00:00, 123.27it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 134.59it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 143.01it/s] Loading 0: 100%|██████████| 291/291 [00:07<00:00, 9.77it/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-v3-mkmlizer: quantized model in 23.357s
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: Processed model Hastagaras/Rebahan-8B-L3-MK.II-RP in 46.584s
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v3
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v3/config.json
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v3/special_tokens_map.json
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v3/tokenizer_config.json
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v3/tokenizer.json
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-rebahan-8b-l3-2243-v3/flywheel_model.0.safetensors
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-rebahan-8b-l3-2243-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-rebahan-8b-l3-2243-v3-mkmlizer: warnings.warn(
hastagaras-rebahan-8b-l3-2243-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-rebahan-8b-l3-2243-v3-mkmlizer: warnings.warn(
hastagaras-rebahan-8b-l3-2243-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-rebahan-8b-l3-2243-v3-mkmlizer: warnings.warn(
hastagaras-rebahan-8b-l3-2243-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-rebahan-8b-l3-2243-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: Saving duration: 0.399s
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.230s
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v3_reward
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v3_reward/config.json
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v3_reward/special_tokens_map.json
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v3_reward/tokenizer_config.json
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v3_reward/merges.txt
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v3_reward/vocab.json
hastagaras-rebahan-8b-l3-2243-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-rebahan-8b-l3-2243-v3_reward/tokenizer.json
Job hastagaras-rebahan-8b-l3-2243-v3-mkmlizer completed after 76.01s with status: succeeded
Stopping job with name hastagaras-rebahan-8b-l3-2243-v3-mkmlizer
Pipeline stage MKMLizer completed in 76.86s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-rebahan-8b-l3-2243-v3
Waiting for inference service hastagaras-rebahan-8b-l3-2243-v3 to be ready
Inference service hastagaras-rebahan-8b-l3-2243-v3 ready after 40.2084538936615s
Pipeline stage ISVCDeployer completed in 46.10s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2456135749816895s
Received healthy response to inference request in 1.2990338802337646s
Received healthy response to inference request in 1.2977426052093506s
Received healthy response to inference request in 1.2597968578338623s
Received healthy response to inference request in 4.6344287395477295s
5 requests
0 failed requests
5th percentile: 1.26738600730896
10th percentile: 1.2749751567840577
20th percentile: 1.2901534557342529
30th percentile: 1.2980008602142334
40th percentile: 1.298517370223999
50th percentile: 1.2990338802337646
60th percentile: 1.6776657581329344
70th percentile: 2.056297636032104
80th percentile: 2.723376607894898
90th percentile: 3.6789026737213137
95th percentile: 4.156665706634521
99th percentile: 4.538876132965088
mean time: 2.1473231315612793
Pipeline stage StressChecker completed in 11.42s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
hastagaras-rebahan-8b-l3_2243_v3 status is now deployed due to DeploymentManager action
hastagaras-rebahan-8b-l3_2243_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics