submission_id: hastagaras-bu8bl3-x-x_v7
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/bu8bl3-x_x
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, '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: 2024-06-14T14:57:50+00:00
model_name: x__X
model_eval_status: success
model_group: Hastagaras/bu8bl3-x_x
num_battles: 41419
num_wins: 22544
celo_rating: 1213.97
propriety_score: 0.6935559613879467
propriety_total_count: 19165.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: x__X
ineligible_reason: None
language_model: Hastagaras/bu8bl3-x_x
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-14
win_ratio: 0.5442912672927883
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-bu8bl3-x-x-v7-mkmlizer
Waiting for job on hastagaras-bu8bl3-x-x-v7-mkmlizer to finish
hastagaras-bu8bl3-x-x-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-bu8bl3-x-x-v7-mkmlizer: ║ _____ __ __ ║
hastagaras-bu8bl3-x-x-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-bu8bl3-x-x-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-bu8bl3-x-x-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-bu8bl3-x-x-v7-mkmlizer: ║ /___/ ║
hastagaras-bu8bl3-x-x-v7-mkmlizer: ║ ║
hastagaras-bu8bl3-x-x-v7-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-bu8bl3-x-x-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-bu8bl3-x-x-v7-mkmlizer: ║ https://mk1.ai ║
hastagaras-bu8bl3-x-x-v7-mkmlizer: ║ ║
hastagaras-bu8bl3-x-x-v7-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-bu8bl3-x-x-v7-mkmlizer: ║ belonging to: ║
hastagaras-bu8bl3-x-x-v7-mkmlizer: ║ ║
hastagaras-bu8bl3-x-x-v7-mkmlizer: ║ Chai Research Corp. ║
hastagaras-bu8bl3-x-x-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-bu8bl3-x-x-v7-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-bu8bl3-x-x-v7-mkmlizer: ║ ║
hastagaras-bu8bl3-x-x-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-bu8bl3-x-x-v7-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-bu8bl3-x-x-v7-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-bu8bl3-x-x-v7-mkmlizer: Downloaded to shared memory in 18.310s
hastagaras-bu8bl3-x-x-v7-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-bu8bl3-x-x-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-bu8bl3-x-x-v7-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:11, 2.32s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:04, 4.29it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.40it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 20.50it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:09, 24.70it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 33.12it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 47.69it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 63.70it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 79.65it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 94.82it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 74.28it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 90.11it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 105.06it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 118.04it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 128.09it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 137.66it/s] Loading 0: 93%|█████████▎| 272/291 [00:07<00:00, 90.11it/s] Loading 0: 98%|█████████▊| 285/291 [00:07<00:00, 95.89it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-bu8bl3-x-x-v7-mkmlizer: quantized model in 23.266s
hastagaras-bu8bl3-x-x-v7-mkmlizer: Processed model Hastagaras/bu8bl3-x_x in 44.079s
hastagaras-bu8bl3-x-x-v7-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-bu8bl3-x-x-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-bu8bl3-x-x-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v7
hastagaras-bu8bl3-x-x-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v7/tokenizer_config.json
hastagaras-bu8bl3-x-x-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v7/config.json
hastagaras-bu8bl3-x-x-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v7/special_tokens_map.json
hastagaras-bu8bl3-x-x-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v7/flywheel_model.0.safetensors
hastagaras-bu8bl3-x-x-v7-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-bu8bl3-x-x-v7-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-bu8bl3-x-x-v7-mkmlizer: warnings.warn(
hastagaras-bu8bl3-x-x-v7-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-bu8bl3-x-x-v7-mkmlizer: warnings.warn(
hastagaras-bu8bl3-x-x-v7-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-bu8bl3-x-x-v7-mkmlizer: warnings.warn(
hastagaras-bu8bl3-x-x-v7-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-bu8bl3-x-x-v7-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-bu8bl3-x-x-v7-mkmlizer: creating bucket guanaco-reward-models
hastagaras-bu8bl3-x-x-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-bu8bl3-x-x-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v7_reward
hastagaras-bu8bl3-x-x-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v7_reward/special_tokens_map.json
hastagaras-bu8bl3-x-x-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v7_reward/tokenizer_config.json
hastagaras-bu8bl3-x-x-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v7_reward/config.json
hastagaras-bu8bl3-x-x-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v7_reward/merges.txt
hastagaras-bu8bl3-x-x-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v7_reward/vocab.json
hastagaras-bu8bl3-x-x-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v7_reward/tokenizer.json
hastagaras-bu8bl3-x-x-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v7_reward/reward.tensors
Job hastagaras-bu8bl3-x-x-v7-mkmlizer completed after 73.67s with status: succeeded
Stopping job with name hastagaras-bu8bl3-x-x-v7-mkmlizer
Pipeline stage MKMLizer completed in 77.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-bu8bl3-x-x-v7
Waiting for inference service hastagaras-bu8bl3-x-x-v7 to be ready
Inference service hastagaras-bu8bl3-x-x-v7 ready after 91.82958936691284s
Pipeline stage ISVCDeployer completed in 99.18s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.300278902053833s
Received healthy response to inference request in 1.3710758686065674s
Received healthy response to inference request in 1.3322365283966064s
Received healthy response to inference request in 1.7184569835662842s
Received healthy response to inference request in 1.383333683013916s
5 requests
0 failed requests
5th percentile: 1.3400043964385986
10th percentile: 1.3477722644805907
20th percentile: 1.3633080005645752
30th percentile: 1.373527431488037
40th percentile: 1.3784305572509765
50th percentile: 1.383333683013916
60th percentile: 1.5173830032348632
70th percentile: 1.6514323234558106
80th percentile: 1.834821367263794
90th percentile: 2.0675501346588137
95th percentile: 2.1839145183563233
99th percentile: 2.277006025314331
mean time: 1.6210763931274415
Pipeline stage StressChecker completed in 8.70s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
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-bu8bl3-x-x_v7 status is now deployed due to DeploymentManager action
hastagaras-bu8bl3-x-x_v7 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics