submission_id: hastagaras-bnsca8bl3_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/bnsca8bl3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.08, 'top_k': 60, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, '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", '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: 2024-06-13T08:27:22+00:00
model_name: sssffttt
model_eval_status: success
model_group: Hastagaras/bnsca8bl3
num_battles: 12760
num_wins: 6416
celo_rating: 1183.5
propriety_score: 0.7051399304920432
propriety_total_count: 5467.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: sssffttt
ineligible_reason: None
language_model: Hastagaras/bnsca8bl3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-13
win_ratio: 0.5028213166144201
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-bnsca8bl3-v1-mkmlizer
Waiting for job on hastagaras-bnsca8bl3-v1-mkmlizer to finish
hastagaras-bnsca8bl3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-bnsca8bl3-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-bnsca8bl3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-bnsca8bl3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-bnsca8bl3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-bnsca8bl3-v1-mkmlizer: ║ /___/ ║
hastagaras-bnsca8bl3-v1-mkmlizer: ║ ║
hastagaras-bnsca8bl3-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-bnsca8bl3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-bnsca8bl3-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-bnsca8bl3-v1-mkmlizer: ║ ║
hastagaras-bnsca8bl3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-bnsca8bl3-v1-mkmlizer: ║ belonging to: ║
hastagaras-bnsca8bl3-v1-mkmlizer: ║ ║
hastagaras-bnsca8bl3-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-bnsca8bl3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-bnsca8bl3-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-bnsca8bl3-v1-mkmlizer: ║ ║
hastagaras-bnsca8bl3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-bnsca8bl3-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-bnsca8bl3-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-bnsca8bl3-v1-mkmlizer: Downloaded to shared memory in 27.523s
hastagaras-bnsca8bl3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-bnsca8bl3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-bnsca8bl3-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 119.58it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:02, 113.74it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:01, 126.46it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:01, 122.21it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 127.36it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:01, 123.24it/s] Loading 0: 32%|███▏ | 92/291 [00:01<00:03, 51.20it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:03, 59.54it/s] Loading 0: 41%|████ | 118/291 [00:01<00:02, 75.50it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 84.04it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 99.57it/s] Loading 0: 55%|█████▍ | 160/291 [00:01<00:01, 105.89it/s] Loading 0: 60%|██████ | 175/291 [00:01<00:00, 116.89it/s] Loading 0: 65%|██████▍ | 189/291 [00:02<00:01, 59.33it/s] Loading 0: 69%|██████▉ | 202/291 [00:02<00:01, 69.85it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 85.55it/s] Loading 0: 80%|███████▉ | 232/291 [00:02<00:00, 94.08it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 104.44it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 117.05it/s] Loading 0: 96%|█████████▌| 278/291 [00:02<00:00, 120.94it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-bnsca8bl3-v1-mkmlizer: quantized model in 21.547s
hastagaras-bnsca8bl3-v1-mkmlizer: Processed model Hastagaras/bnsca8bl3 in 50.446s
hastagaras-bnsca8bl3-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-bnsca8bl3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-bnsca8bl3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-bnsca8bl3-v1
hastagaras-bnsca8bl3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-bnsca8bl3-v1/config.json
hastagaras-bnsca8bl3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-bnsca8bl3-v1/special_tokens_map.json
hastagaras-bnsca8bl3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-bnsca8bl3-v1/tokenizer_config.json
hastagaras-bnsca8bl3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-bnsca8bl3-v1/tokenizer.json
hastagaras-bnsca8bl3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-bnsca8bl3-v1/flywheel_model.0.safetensors
hastagaras-bnsca8bl3-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-bnsca8bl3-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-bnsca8bl3-v1-mkmlizer: warnings.warn(
hastagaras-bnsca8bl3-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-bnsca8bl3-v1-mkmlizer: warnings.warn(
hastagaras-bnsca8bl3-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-bnsca8bl3-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-bnsca8bl3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-bnsca8bl3-v1-mkmlizer: Saving duration: 0.252s
hastagaras-bnsca8bl3-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.062s
hastagaras-bnsca8bl3-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-bnsca8bl3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-bnsca8bl3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-bnsca8bl3-v1_reward
hastagaras-bnsca8bl3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-bnsca8bl3-v1_reward/config.json
hastagaras-bnsca8bl3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-bnsca8bl3-v1_reward/special_tokens_map.json
hastagaras-bnsca8bl3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-bnsca8bl3-v1_reward/tokenizer_config.json
hastagaras-bnsca8bl3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-bnsca8bl3-v1_reward/vocab.json
hastagaras-bnsca8bl3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-bnsca8bl3-v1_reward/merges.txt
hastagaras-bnsca8bl3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-bnsca8bl3-v1_reward/tokenizer.json
hastagaras-bnsca8bl3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-bnsca8bl3-v1_reward/reward.tensors
Job hastagaras-bnsca8bl3-v1-mkmlizer completed after 73.05s with status: succeeded
Stopping job with name hastagaras-bnsca8bl3-v1-mkmlizer
Pipeline stage MKMLizer completed in 77.81s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-bnsca8bl3-v1
Waiting for inference service hastagaras-bnsca8bl3-v1 to be ready
Inference service hastagaras-bnsca8bl3-v1 ready after 50.27465510368347s
Pipeline stage ISVCDeployer completed in 58.30s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.05908465385437s
Received healthy response to inference request in 1.1707594394683838s
Received healthy response to inference request in 1.15632963180542s
Received healthy response to inference request in 1.143007516860962s
Received healthy response to inference request in 1.1635322570800781s
5 requests
0 failed requests
5th percentile: 1.1456719398498536
10th percentile: 1.148336362838745
20th percentile: 1.1536652088165282
30th percentile: 1.1577701568603516
40th percentile: 1.1606512069702148
50th percentile: 1.1635322570800781
60th percentile: 1.1664231300354004
70th percentile: 1.1693140029907227
80th percentile: 1.3484244823455813
90th percentile: 1.7037545680999757
95th percentile: 1.8814196109771726
99th percentile: 2.0235516452789306
mean time: 1.3385426998138428
Pipeline stage StressChecker completed in 7.30s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-bnsca8bl3_v1 status is now deployed due to DeploymentManager action
hastagaras-bnsca8bl3_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics