submission_id: nitral-ai-pp-1-4-phase1_v4
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': 1.1, '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': "<|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: 2024-06-02T01:27:43+00:00
model_name: nitral-ai-pp-1-4-phase1_v4
model_eval_status: success
model_group: Nitral-AI/Pp-1.4-Phase1
num_battles: 6836
num_wins: 3658
celo_rating: 1204.58
safety_score: 0.95
propriety_score: 0.6993464052287581
propriety_total_count: 153.0
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_v4
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: 0.5351082504388531
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-pp-1-4-phase1-v4-mkmlizer
Waiting for job on nitral-ai-pp-1-4-phase1-v4-mkmlizer to finish
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ║ _____ __ __ ║
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ║ /___/ ║
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ║ https://mk1.ai ║
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ║ belonging to: ║
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-pp-1-4-phase1-v4-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-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-pp-1-4-phase1-v4-mkmlizer: Downloaded to shared memory in 16.863s
nitral-ai-pp-1-4-phase1-v4-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-pp-1-4-phase1-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-pp-1-4-phase1-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:03, 2.29s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:03, 4.33it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.51it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 20.70it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:09, 24.42it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 32.78it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 47.11it/s] Loading 0: 39%|███▉ | 113/291 [00:05<00:02, 62.48it/s] Loading 0: 45%|████▌ | 131/291 [00:05<00:02, 78.79it/s] Loading 0: 51%|█████ | 149/291 [00:05<00:01, 94.52it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 71.13it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 86.15it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 100.53it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 114.02it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 124.06it/s] Loading 0: 87%|████████▋ | 253/291 [00:06<00:00, 129.50it/s] Loading 0: 92%|█████████▏| 268/291 [00:07<00:00, 80.52it/s] Loading 0: 98%|█████████▊| 284/291 [00:07<00:00, 94.17it/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-v4-mkmlizer: quantized model in 23.681s
nitral-ai-pp-1-4-phase1-v4-mkmlizer: Processed model Nitral-AI/Pp-1.4-Phase1 in 43.235s
nitral-ai-pp-1-4-phase1-v4-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-pp-1-4-phase1-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-pp-1-4-phase1-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v4
nitral-ai-pp-1-4-phase1-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v4/config.json
nitral-ai-pp-1-4-phase1-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v4/special_tokens_map.json
nitral-ai-pp-1-4-phase1-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v4/tokenizer_config.json
nitral-ai-pp-1-4-phase1-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v4/tokenizer.json
nitral-ai-pp-1-4-phase1-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v4/flywheel_model.0.safetensors
nitral-ai-pp-1-4-phase1-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-pp-1-4-phase1-v4-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-v4-mkmlizer: warnings.warn(
nitral-ai-pp-1-4-phase1-v4-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-v4-mkmlizer: warnings.warn(
nitral-ai-pp-1-4-phase1-v4-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-v4-mkmlizer: warnings.warn(
nitral-ai-pp-1-4-phase1-v4-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-v4-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-pp-1-4-phase1-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-pp-1-4-phase1-v4-mkmlizer: Saving duration: 0.449s
nitral-ai-pp-1-4-phase1-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.787s
nitral-ai-pp-1-4-phase1-v4-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-pp-1-4-phase1-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-pp-1-4-phase1-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v4_reward
nitral-ai-pp-1-4-phase1-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v4_reward/config.json
nitral-ai-pp-1-4-phase1-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v4_reward/special_tokens_map.json
nitral-ai-pp-1-4-phase1-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v4_reward/vocab.json
nitral-ai-pp-1-4-phase1-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v4_reward/merges.txt
nitral-ai-pp-1-4-phase1-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v4_reward/tokenizer_config.json
nitral-ai-pp-1-4-phase1-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v4_reward/tokenizer.json
nitral-ai-pp-1-4-phase1-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v4_reward/reward.tensors
Job nitral-ai-pp-1-4-phase1-v4-mkmlizer completed after 62.98s with status: succeeded
Stopping job with name nitral-ai-pp-1-4-phase1-v4-mkmlizer
Pipeline stage MKMLizer completed in 65.94s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-pp-1-4-phase1-v4
Waiting for inference service nitral-ai-pp-1-4-phase1-v4 to be ready
Inference service nitral-ai-pp-1-4-phase1-v4 ready after 30.17919087409973s
Pipeline stage ISVCDeployer completed in 37.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2139134407043457s
Received healthy response to inference request in 1.3546180725097656s
Received healthy response to inference request in 1.3164851665496826s
Received healthy response to inference request in 1.3173887729644775s
Received healthy response to inference request in 1.2548511028289795s
5 requests
0 failed requests
5th percentile: 1.2671779155731202
10th percentile: 1.2795047283172607
20th percentile: 1.304158353805542
30th percentile: 1.3166658878326416
40th percentile: 1.3170273303985596
50th percentile: 1.3173887729644775
60th percentile: 1.3322804927825929
70th percentile: 1.347172212600708
80th percentile: 1.526477146148682
90th percentile: 1.8701952934265138
95th percentile: 2.0420543670654294
99th percentile: 2.1795416259765625
mean time: 1.4914513111114502
Pipeline stage StressChecker completed in 8.10s
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_v4 status is now deployed due to DeploymentManager action
nitral-ai-pp-1-4-phase1_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics