submission_id: nitral-ai-test530_v1
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_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: 2024-05-31T00:39:09+00:00
model_name: nitral-ai-test530_v1
model_eval_status: success
model_group: Nitral-AI/test530
num_battles: 7102
num_wins: 3841
celo_rating: 1217.72
safety_score: 0.94
propriety_score: 0.8
propriety_total_count: 5.0
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_v1
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: 0.5408335680090115
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-test530-v1-mkmlizer
Waiting for job on nitral-ai-test530-v1-mkmlizer to finish
nitral-ai-test530-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-test530-v1-mkmlizer: ║ _____ __ __ ║
nitral-ai-test530-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-test530-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-test530-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-test530-v1-mkmlizer: ║ /___/ ║
nitral-ai-test530-v1-mkmlizer: ║ ║
nitral-ai-test530-v1-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-test530-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-test530-v1-mkmlizer: ║ https://mk1.ai ║
nitral-ai-test530-v1-mkmlizer: ║ ║
nitral-ai-test530-v1-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-test530-v1-mkmlizer: ║ belonging to: ║
nitral-ai-test530-v1-mkmlizer: ║ ║
nitral-ai-test530-v1-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-test530-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-test530-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-test530-v1-mkmlizer: ║ ║
nitral-ai-test530-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-test530-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.
nitral-ai-test530-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-test530-v1-mkmlizer: Downloaded to shared memory in 35.781s
nitral-ai-test530-v1-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-test530-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-test530-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:59, 2.28s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:03, 4.37it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.63it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 20.99it/s] Loading 0: 23%|██▎ | 66/291 [00:05<00:08, 26.11it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 33.63it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 48.63it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 65.20it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 82.27it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 99.09it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 76.46it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 92.95it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 108.46it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 121.89it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 132.33it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 142.44it/s] Loading 0: 94%|█████████▍| 273/291 [00:06<00:00, 94.46it/s] Loading 0: 99%|█████████▉| 288/291 [00:07<00:00, 104.75it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-test530-v1-mkmlizer: quantized model in 22.958s
nitral-ai-test530-v1-mkmlizer: Processed model Nitral-AI/test530 in 61.252s
nitral-ai-test530-v1-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-test530-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-test530-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-test530-v1
nitral-ai-test530-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-test530-v1/special_tokens_map.json
nitral-ai-test530-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-test530-v1/tokenizer_config.json
nitral-ai-test530-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-test530-v1/config.json
nitral-ai-test530-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-test530-v1/tokenizer.json
nitral-ai-test530-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-test530-v1/flywheel_model.0.safetensors
nitral-ai-test530-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-test530-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.
nitral-ai-test530-v1-mkmlizer: warnings.warn(
nitral-ai-test530-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.
nitral-ai-test530-v1-mkmlizer: warnings.warn(
nitral-ai-test530-v1-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-v1-mkmlizer: warnings.warn(
nitral-ai-test530-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()
nitral-ai-test530-v1-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-test530-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-test530-v1-mkmlizer: Saving duration: 0.397s
nitral-ai-test530-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.495s
nitral-ai-test530-v1-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-test530-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-test530-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-test530-v1_reward
nitral-ai-test530-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-test530-v1_reward/config.json
nitral-ai-test530-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-test530-v1_reward/tokenizer_config.json
nitral-ai-test530-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-test530-v1_reward/vocab.json
nitral-ai-test530-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-test530-v1_reward/merges.txt
nitral-ai-test530-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-test530-v1_reward/special_tokens_map.json
nitral-ai-test530-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-test530-v1_reward/tokenizer.json
nitral-ai-test530-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-test530-v1_reward/reward.tensors
Job nitral-ai-test530-v1-mkmlizer completed after 83.16s with status: succeeded
Stopping job with name nitral-ai-test530-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.98s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-test530-v1
Waiting for inference service nitral-ai-test530-v1 to be ready
Inference service nitral-ai-test530-v1 ready after 30.296674728393555s
Pipeline stage ISVCDeployer completed in 36.00s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2018356323242188s
Received healthy response to inference request in 1.3668723106384277s
Received healthy response to inference request in 1.3286383152008057s
Received healthy response to inference request in 1.3187174797058105s
Received healthy response to inference request in 1.3669307231903076s
5 requests
0 failed requests
5th percentile: 1.3207016468048096
10th percentile: 1.3226858139038087
20th percentile: 1.3266541481018066
30th percentile: 1.33628511428833
40th percentile: 1.351578712463379
50th percentile: 1.3668723106384277
60th percentile: 1.3668956756591797
70th percentile: 1.3669190406799316
80th percentile: 1.53391170501709
90th percentile: 1.8678736686706543
95th percentile: 2.0348546504974365
99th percentile: 2.168439435958862
mean time: 1.516598892211914
Pipeline stage StressChecker completed in 8.19s
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_v1 status is now deployed due to DeploymentManager action
nitral-ai-test530_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics