submission_id: nitral-ai-pp-1-4-phase1_v2
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': 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: 2024-06-02T00:02:41+00:00
model_name: nitral-ai-pp-1-4-phase1_v2
model_eval_status: success
model_group: Nitral-AI/Pp-1.4-Phase1
num_battles: 6283
num_wins: 3463
celo_rating: 1216.91
safety_score: 0.96
propriety_score: 0.6794871794871795
propriety_total_count: 156.0
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_v2
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: 0.5511698233328028
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-pp-1-4-phase1-v2-mkmlizer
Waiting for job on nitral-ai-pp-1-4-phase1-v2-mkmlizer to finish
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ║ _____ __ __ ║
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ║ /___/ ║
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ║ https://mk1.ai ║
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ║ belonging to: ║
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-pp-1-4-phase1-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-pp-1-4-phase1-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-pp-1-4-phase1-v2-mkmlizer: Downloaded to shared memory in 20.158s
nitral-ai-pp-1-4-phase1-v2-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-pp-1-4-phase1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-pp-1-4-phase1-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:55, 2.27s/it] Loading 0: 5%|▌ | 16/291 [00:04<00:58, 4.70it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.58it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 20.97it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.18it/s] Loading 0: 28%|██▊ | 81/291 [00:05<00:05, 36.14it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 47.51it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 63.99it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 80.93it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 97.07it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 76.33it/s] Loading 0: 62%|██████▏ | 179/291 [00:06<00:01, 83.45it/s] Loading 0: 67%|██████▋ | 195/291 [00:06<00:00, 96.25it/s] Loading 0: 73%|███████▎ | 213/291 [00:06<00:00, 112.59it/s] Loading 0: 79%|███████▉ | 231/291 [00:06<00:00, 126.74it/s] Loading 0: 86%|████████▌ | 249/291 [00:06<00:00, 138.29it/s] Loading 0: 91%|█████████▏| 266/291 [00:06<00:00, 93.62it/s] Loading 0: 98%|█████████▊| 284/291 [00:07<00:00, 108.33it/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-v2-mkmlizer: quantized model in 23.057s
nitral-ai-pp-1-4-phase1-v2-mkmlizer: Processed model Nitral-AI/Pp-1.4-Phase1 in 45.754s
nitral-ai-pp-1-4-phase1-v2-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-pp-1-4-phase1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-pp-1-4-phase1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v2
nitral-ai-pp-1-4-phase1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v2/config.json
nitral-ai-pp-1-4-phase1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v2/special_tokens_map.json
nitral-ai-pp-1-4-phase1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v2/tokenizer_config.json
nitral-ai-pp-1-4-phase1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v2/tokenizer.json
nitral-ai-pp-1-4-phase1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v2/flywheel_model.0.safetensors
nitral-ai-pp-1-4-phase1-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-pp-1-4-phase1-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-pp-1-4-phase1-v2-mkmlizer: warnings.warn(
nitral-ai-pp-1-4-phase1-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-pp-1-4-phase1-v2-mkmlizer: warnings.warn(
nitral-ai-pp-1-4-phase1-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-pp-1-4-phase1-v2-mkmlizer: warnings.warn(
nitral-ai-pp-1-4-phase1-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-pp-1-4-phase1-v2-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-pp-1-4-phase1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-pp-1-4-phase1-v2-mkmlizer: Saving duration: 0.419s
nitral-ai-pp-1-4-phase1-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.303s
nitral-ai-pp-1-4-phase1-v2-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-pp-1-4-phase1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-pp-1-4-phase1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v2_reward
nitral-ai-pp-1-4-phase1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v2_reward/config.json
nitral-ai-pp-1-4-phase1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v2_reward/tokenizer_config.json
nitral-ai-pp-1-4-phase1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v2_reward/special_tokens_map.json
nitral-ai-pp-1-4-phase1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v2_reward/merges.txt
nitral-ai-pp-1-4-phase1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v2_reward/vocab.json
nitral-ai-pp-1-4-phase1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v2_reward/tokenizer.json
nitral-ai-pp-1-4-phase1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v2_reward/reward.tensors
Job nitral-ai-pp-1-4-phase1-v2-mkmlizer completed after 73.03s with status: succeeded
Stopping job with name nitral-ai-pp-1-4-phase1-v2-mkmlizer
Pipeline stage MKMLizer completed in 76.55s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-pp-1-4-phase1-v2
Waiting for inference service nitral-ai-pp-1-4-phase1-v2 to be ready
Inference service nitral-ai-pp-1-4-phase1-v2 ready after 90.59700584411621s
Pipeline stage ISVCDeployer completed in 97.87s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0439999103546143s
Received healthy response to inference request in 1.3290514945983887s
Received healthy response to inference request in 1.3164293766021729s
Received healthy response to inference request in 1.2657229900360107s
Received healthy response to inference request in 1.2584760189056396s
5 requests
0 failed requests
5th percentile: 1.259925413131714
10th percentile: 1.2613748073577882
20th percentile: 1.2642735958099365
30th percentile: 1.275864267349243
40th percentile: 1.296146821975708
50th percentile: 1.3164293766021729
60th percentile: 1.3214782238006593
70th percentile: 1.3265270709991455
80th percentile: 1.4720411777496338
90th percentile: 1.7580205440521242
95th percentile: 1.901010227203369
99th percentile: 2.0154019737243654
mean time: 1.4427359580993653
Pipeline stage StressChecker completed in 7.79s
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-pp-1-4-phase1_v2 status is now deployed due to DeploymentManager action
nitral-ai-pp-1-4-phase1_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics