submission_id: nitral-ai-pp-1-4-phase1_v5
developer_uid: Nitral-AI
status: inactive
model_repo: Nitral-AI/Pp-1.4-Phase1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 100, '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': "{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}
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: 2024-06-02T02:15:41+00:00
model_name: nitral-ai-pp-1-4-phase1_v5
model_eval_status: success
model_group: Nitral-AI/Pp-1.4-Phase1
num_battles: 8270
num_wins: 4433
celo_rating: 1208.94
safety_score: 0.93
propriety_score: 0.6923076923076923
propriety_total_count: 182.0
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-pp-1-4-phase1_v5
ineligible_reason: propriety_total_count < 5000
language_model: Nitral-AI/Pp-1.4-Phase1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-01
win_ratio: 0.5360338573155985
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-pp-1-4-phase1-v5-mkmlizer
Waiting for job on nitral-ai-pp-1-4-phase1-v5-mkmlizer to finish
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ║ _____ __ __ ║
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ║ /___/ ║
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ║ https://mk1.ai ║
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ║ belonging to: ║
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-pp-1-4-phase1-v5-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-pp-1-4-phase1-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-pp-1-4-phase1-v5-mkmlizer: Downloaded to shared memory in 18.231s
nitral-ai-pp-1-4-phase1-v5-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-pp-1-4-phase1-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-pp-1-4-phase1-v5-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, 4.36it/s] Loading 0: 11%|█ | 32/291 [00:04<00:23, 11.22it/s] Loading 0: 17%|█▋ | 50/291 [00:04<00:11, 20.50it/s] Loading 0: 22%|██▏ | 64/291 [00:05<00:09, 24.04it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 33.13it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 47.41it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 62.83it/s] Loading 0: 45%|████▌ | 131/291 [00:05<00:02, 78.04it/s] Loading 0: 51%|█████ | 148/291 [00:05<00:01, 94.02it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 69.89it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 85.13it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 99.91it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 112.94it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 123.83it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 133.47it/s] Loading 0: 93%|█████████▎| 272/291 [00:07<00:00, 85.18it/s] Loading 0: 98%|█████████▊| 285/291 [00:07<00:00, 92.95it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-pp-1-4-phase1-v5-mkmlizer: quantized model in 23.623s
nitral-ai-pp-1-4-phase1-v5-mkmlizer: Processed model Nitral-AI/Pp-1.4-Phase1 in 44.553s
nitral-ai-pp-1-4-phase1-v5-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-pp-1-4-phase1-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-pp-1-4-phase1-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v5
nitral-ai-pp-1-4-phase1-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v5/config.json
nitral-ai-pp-1-4-phase1-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v5/special_tokens_map.json
nitral-ai-pp-1-4-phase1-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v5/tokenizer_config.json
nitral-ai-pp-1-4-phase1-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v5/tokenizer.json
nitral-ai-pp-1-4-phase1-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v5/flywheel_model.0.safetensors
nitral-ai-pp-1-4-phase1-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-pp-1-4-phase1-v5-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-pp-1-4-phase1-v5-mkmlizer: warnings.warn(
nitral-ai-pp-1-4-phase1-v5-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-pp-1-4-phase1-v5-mkmlizer: warnings.warn(
nitral-ai-pp-1-4-phase1-v5-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-pp-1-4-phase1-v5-mkmlizer: warnings.warn(
nitral-ai-pp-1-4-phase1-v5-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-pp-1-4-phase1-v5-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-pp-1-4-phase1-v5-mkmlizer: Saving duration: 0.466s
nitral-ai-pp-1-4-phase1-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.912s
nitral-ai-pp-1-4-phase1-v5-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-pp-1-4-phase1-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-pp-1-4-phase1-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v5_reward
nitral-ai-pp-1-4-phase1-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v5_reward/special_tokens_map.json
nitral-ai-pp-1-4-phase1-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v5_reward/config.json
nitral-ai-pp-1-4-phase1-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v5_reward/tokenizer_config.json
nitral-ai-pp-1-4-phase1-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v5_reward/merges.txt
nitral-ai-pp-1-4-phase1-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v5_reward/vocab.json
nitral-ai-pp-1-4-phase1-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v5_reward/tokenizer.json
nitral-ai-pp-1-4-phase1-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v5_reward/reward.tensors
Job nitral-ai-pp-1-4-phase1-v5-mkmlizer completed after 73.04s with status: succeeded
Stopping job with name nitral-ai-pp-1-4-phase1-v5-mkmlizer
Pipeline stage MKMLizer completed in 76.12s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-pp-1-4-phase1-v5
Waiting for inference service nitral-ai-pp-1-4-phase1-v5 to be ready
Inference service nitral-ai-pp-1-4-phase1-v5 ready after 40.23503041267395s
Pipeline stage ISVCDeployer completed in 47.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2847845554351807s
Received healthy response to inference request in 1.2666871547698975s
Received healthy response to inference request in 1.2632639408111572s
Received healthy response to inference request in 1.2514994144439697s
Received healthy response to inference request in 1.368072509765625s
5 requests
0 failed requests
5th percentile: 1.2538523197174072
10th percentile: 1.2562052249908446
20th percentile: 1.2609110355377198
30th percentile: 1.2639485836029052
40th percentile: 1.2653178691864013
50th percentile: 1.2666871547698975
60th percentile: 1.3072412967681886
70th percentile: 1.3477954387664794
80th percentile: 1.7514149188995365
90th percentile: 2.5180997371673586
95th percentile: 2.901442146301269
99th percentile: 3.2081160736083985
mean time: 1.686861515045166
Pipeline stage StressChecker completed in 9.07s
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
nitral-ai-pp-1-4-phase1_v5 status is now deployed due to DeploymentManager action
nitral-ai-pp-1-4-phase1_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics