submission_id: nitral-ai-test530_v2
developer_uid: Nitral-AI
status: inactive
model_repo: Nitral-AI/test530
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.03, 'top_k': 40, '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: 2024-05-31T01:01:32+00:00
model_name: nitral-ai-test530_v2
model_eval_status: success
model_group: Nitral-AI/test530
num_battles: 5611
num_wins: 3001
celo_rating: 1215.64
safety_score: 0.95
propriety_score: 0.0
propriety_total_count: 1.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: nitral-ai-test530_v2
ineligible_reason: propriety_total_count < 5000
language_model: Nitral-AI/test530
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-30
win_ratio: 0.5348422741044377
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-test530-v2-mkmlizer
Waiting for job on nitral-ai-test530-v2-mkmlizer to finish
nitral-ai-test530-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-test530-v2-mkmlizer: ║ _____ __ __ ║
nitral-ai-test530-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-test530-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-test530-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-test530-v2-mkmlizer: ║ /___/ ║
nitral-ai-test530-v2-mkmlizer: ║ ║
nitral-ai-test530-v2-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-test530-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-test530-v2-mkmlizer: ║ https://mk1.ai ║
nitral-ai-test530-v2-mkmlizer: ║ ║
nitral-ai-test530-v2-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-test530-v2-mkmlizer: ║ belonging to: ║
nitral-ai-test530-v2-mkmlizer: ║ ║
nitral-ai-test530-v2-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-test530-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-test530-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-test530-v2-mkmlizer: ║ ║
nitral-ai-test530-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-test530-v2-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.
nitral-ai-test530-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-test530-v2-mkmlizer: Downloaded to shared memory in 16.572s
nitral-ai-test530-v2-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-test530-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-test530-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<12:38, 2.62s/it] Loading 0: 4%|▍ | 13/291 [00:05<01:24, 3.28it/s] Loading 0: 8%|▊ | 23/291 [00:05<00:39, 6.74it/s] Loading 0: 11%|█▏ | 33/291 [00:05<00:23, 11.20it/s] Loading 0: 17%|█▋ | 50/291 [00:05<00:11, 21.36it/s] Loading 0: 21%|██ | 61/291 [00:06<00:10, 22.61it/s] Loading 0: 25%|██▌ | 73/291 [00:06<00:07, 31.01it/s] Loading 0: 30%|██▉ | 87/291 [00:06<00:04, 42.35it/s] Loading 0: 36%|███▌ | 104/291 [00:06<00:03, 58.57it/s] Loading 0: 42%|████▏ | 121/291 [00:06<00:02, 74.96it/s] Loading 0: 46%|████▌ | 134/291 [00:06<00:01, 84.77it/s] Loading 0: 51%|█████ | 149/291 [00:06<00:01, 96.55it/s] Loading 0: 57%|█████▋ | 166/291 [00:07<00:01, 65.33it/s] Loading 0: 61%|██████ | 178/291 [00:07<00:01, 73.88it/s] Loading 0: 67%|██████▋ | 194/291 [00:07<00:01, 87.84it/s] Loading 0: 73%|███████▎ | 211/291 [00:07<00:00, 102.10it/s] Loading 0: 77%|███████▋ | 224/291 [00:07<00:00, 108.12it/s] Loading 0: 82%|████████▏ | 238/291 [00:07<00:00, 115.62it/s] Loading 0: 87%|████████▋ | 252/291 [00:07<00:00, 107.96it/s] Loading 0: 91%|█████████ | 265/291 [00:08<00:00, 106.98it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 58.40it/s] Loading 0: 99%|█████████▉| 288/291 [00:08<00:00, 66.02it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-test530-v2-mkmlizer: quantized model in 20.170s
nitral-ai-test530-v2-mkmlizer: Processed model Nitral-AI/test530 in 37.904s
nitral-ai-test530-v2-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-test530-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-test530-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-test530-v2
nitral-ai-test530-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-test530-v2/config.json
nitral-ai-test530-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-test530-v2/special_tokens_map.json
nitral-ai-test530-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-test530-v2/tokenizer_config.json
nitral-ai-test530-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-test530-v2/tokenizer.json
nitral-ai-test530-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-test530-v2/flywheel_model.0.safetensors
nitral-ai-test530-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-test530-v2-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.
nitral-ai-test530-v2-mkmlizer: warnings.warn(
nitral-ai-test530-v2-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.
nitral-ai-test530-v2-mkmlizer: warnings.warn(
nitral-ai-test530-v2-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.
nitral-ai-test530-v2-mkmlizer: warnings.warn(
nitral-ai-test530-v2-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()
nitral-ai-test530-v2-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-test530-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-test530-v2-mkmlizer: Saving duration: 0.261s
nitral-ai-test530-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.630s
nitral-ai-test530-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-test530-v2_reward/reward.tensors
Job nitral-ai-test530-v2-mkmlizer completed after 62.51s with status: succeeded
Stopping job with name nitral-ai-test530-v2-mkmlizer
Pipeline stage MKMLizer completed in 63.29s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-test530-v2
Waiting for inference service nitral-ai-test530-v2 to be ready
Inference service nitral-ai-test530-v2 ready after 40.22256398200989s
Pipeline stage ISVCDeployer completed in 46.27s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1491525173187256s
Received healthy response to inference request in 1.3285634517669678s
Received healthy response to inference request in 1.3039493560791016s
Received healthy response to inference request in 1.2922308444976807s
Received healthy response to inference request in 1.2428600788116455s
5 requests
0 failed requests
5th percentile: 1.2527342319488526
10th percentile: 1.2626083850860597
20th percentile: 1.2823566913604736
30th percentile: 1.2945745468139649
40th percentile: 1.2992619514465331
50th percentile: 1.3039493560791016
60th percentile: 1.313794994354248
70th percentile: 1.3236406326293946
80th percentile: 1.4926812648773196
90th percentile: 1.8209168910980225
95th percentile: 1.9850347042083738
99th percentile: 2.1163289546966553
mean time: 1.4633512496948242
Pipeline stage StressChecker completed in 7.89s
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
nitral-ai-test530_v2 status is now deployed due to DeploymentManager action
nitral-ai-test530_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics