submission_id: nitral-ai-pp-1-4-phase1_v3
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': 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: 2024-06-02T01:24:07+00:00
model_name: nitral-ai-pp-1-4-phase1_v3
model_eval_status: success
model_group: Nitral-AI/Pp-1.4-Phase1
num_battles: 6916
num_wins: 3684
celo_rating: 1203.48
propriety_score: 0.6720430107526881
propriety_total_count: 186.0
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_v3
ineligible_reason: propriety_total_count < 800
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: 0.5326778484673221
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-pp-1-4-phase1-v3-mkmlizer
Waiting for job on nitral-ai-pp-1-4-phase1-v3-mkmlizer to finish
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ║ _____ __ __ ║
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ║ /___/ ║
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ║ https://mk1.ai ║
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ║ belonging to: ║
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-pp-1-4-phase1-v3-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-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-pp-1-4-phase1-v3-mkmlizer: Downloaded to shared memory in 17.765s
nitral-ai-pp-1-4-phase1-v3-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-pp-1-4-phase1-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-pp-1-4-phase1-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:05, 2.30s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:03, 4.32it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.49it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 20.66it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:09, 24.38it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 32.70it/s] Loading 0: 33%|███▎ | 95/291 [00:05<00:04, 46.62it/s] Loading 0: 38%|███▊ | 112/291 [00:05<00:02, 62.12it/s] Loading 0: 45%|████▍ | 130/291 [00:05<00:02, 78.43it/s] Loading 0: 51%|█████ | 148/291 [00:05<00:01, 94.04it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 70.26it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 85.48it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 100.09it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 112.55it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 124.09it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 133.80it/s] Loading 0: 93%|█████████▎| 272/291 [00:07<00:00, 84.44it/s] Loading 0: 98%|█████████▊| 286/291 [00:07<00:00, 93.94it/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-v3-mkmlizer: quantized model in 23.667s
nitral-ai-pp-1-4-phase1-v3-mkmlizer: Processed model Nitral-AI/Pp-1.4-Phase1 in 44.145s
nitral-ai-pp-1-4-phase1-v3-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-pp-1-4-phase1-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-pp-1-4-phase1-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v3
nitral-ai-pp-1-4-phase1-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v3/config.json
nitral-ai-pp-1-4-phase1-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v3/special_tokens_map.json
nitral-ai-pp-1-4-phase1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v3/tokenizer_config.json
nitral-ai-pp-1-4-phase1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v3/tokenizer.json
nitral-ai-pp-1-4-phase1-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v3/flywheel_model.0.safetensors
nitral-ai-pp-1-4-phase1-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-pp-1-4-phase1-v3-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-v3-mkmlizer: warnings.warn(
nitral-ai-pp-1-4-phase1-v3-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-v3-mkmlizer: warnings.warn(
nitral-ai-pp-1-4-phase1-v3-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-v3-mkmlizer: warnings.warn(
nitral-ai-pp-1-4-phase1-v3-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-v3-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-pp-1-4-phase1-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-pp-1-4-phase1-v3-mkmlizer: Saving duration: 0.446s
nitral-ai-pp-1-4-phase1-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.161s
nitral-ai-pp-1-4-phase1-v3-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-pp-1-4-phase1-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-pp-1-4-phase1-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v3_reward
nitral-ai-pp-1-4-phase1-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v3_reward/config.json
nitral-ai-pp-1-4-phase1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v3_reward/tokenizer_config.json
nitral-ai-pp-1-4-phase1-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v3_reward/special_tokens_map.json
nitral-ai-pp-1-4-phase1-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v3_reward/merges.txt
nitral-ai-pp-1-4-phase1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v3_reward/tokenizer.json
nitral-ai-pp-1-4-phase1-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v3_reward/vocab.json
nitral-ai-pp-1-4-phase1-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v3_reward/reward.tensors
Job nitral-ai-pp-1-4-phase1-v3-mkmlizer completed after 73.31s with status: succeeded
Stopping job with name nitral-ai-pp-1-4-phase1-v3-mkmlizer
Pipeline stage MKMLizer completed in 74.17s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-pp-1-4-phase1-v3
Waiting for inference service nitral-ai-pp-1-4-phase1-v3 to be ready
Inference service nitral-ai-pp-1-4-phase1-v3 ready after 100.80332827568054s
Pipeline stage ISVCDeployer completed in 106.74s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1414759159088135s
Received healthy response to inference request in 1.3356821537017822s
Received healthy response to inference request in 1.3085622787475586s
Received healthy response to inference request in 1.2980365753173828s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Received healthy response to inference request in 1.2418980598449707s
5 requests
0 failed requests
5th percentile: 1.2531257629394532
10th percentile: 1.2643534660339355
20th percentile: 1.2868088722229003
30th percentile: 1.3001417160034179
40th percentile: 1.3043519973754882
50th percentile: 1.3085622787475586
60th percentile: 1.319410228729248
70th percentile: 1.3302581787109375
80th percentile: 1.4968409061431887
90th percentile: 1.819158411026001
95th percentile: 1.980317163467407
99th percentile: 2.1092441654205323
mean time: 1.4651309967041015
Pipeline stage StressChecker completed in 7.88s
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_v3 status is now deployed due to DeploymentManager action
nitral-ai-pp-1-4-phase1_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics