nitral-ai-pp-0-72xra

developer_uid: Nitral-AI

submission_id: nitral-ai-pp-0-72xra_v1

model_name: nitral-ai-pp-0-72xra_v1

model_group: Nitral-AI/Pp-0.72xra

status: torndown

timestamp: 2024-06-01T23:21:35+00:00

num_battles: 6860

num_wins: 3383

celo_rating: 1172.63

family_friendly_score: 0.0

submission_type: basic

model_repo: Nitral-AI/Pp-0.72xra

model_architecture: LlamaForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 8030261248.0

best_of: 4

max_input_tokens: 512

max_output_tokens: 64

display_name: nitral-ai-pp-0-72xra_v1

is_internal_developer: False

language_model: Nitral-AI/Pp-0.72xra

model_size: 8B

ranking_group: single

us_pacific_date: 2024-06-01

win_ratio: 0.49314868804664724

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': 4, '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}

model_eval_status: success

reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name nitral-ai-pp-0-72xra-v1-mkmlizer
Waiting for job on nitral-ai-pp-0-72xra-v1-mkmlizer to finish
nitral-ai-pp-0-72xra-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-pp-0-72xra-v1-mkmlizer: ║     _____            __           __                                ║
nitral-ai-pp-0-72xra-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nitral-ai-pp-0-72xra-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nitral-ai-pp-0-72xra-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nitral-ai-pp-0-72xra-v1-mkmlizer: ║       /___/                                                         ║
nitral-ai-pp-0-72xra-v1-mkmlizer: ║                                                                     ║
nitral-ai-pp-0-72xra-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
nitral-ai-pp-0-72xra-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nitral-ai-pp-0-72xra-v1-mkmlizer: ║  https://mk1.ai                                                     ║
nitral-ai-pp-0-72xra-v1-mkmlizer: ║                                                                     ║
nitral-ai-pp-0-72xra-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
nitral-ai-pp-0-72xra-v1-mkmlizer: ║  belonging to:                                                      ║
nitral-ai-pp-0-72xra-v1-mkmlizer: ║                                                                     ║
nitral-ai-pp-0-72xra-v1-mkmlizer: ║  Chai Research Corp.                                                ║
nitral-ai-pp-0-72xra-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nitral-ai-pp-0-72xra-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
nitral-ai-pp-0-72xra-v1-mkmlizer: ║                                                                     ║
nitral-ai-pp-0-72xra-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-pp-0-72xra-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-pp-0-72xra-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
nitral-ai-pp-0-72xra-v1-mkmlizer: Downloaded to shared memory in 38.031s
nitral-ai-pp-0-72xra-v1-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-pp-0-72xra-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-pp-0-72xra-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:56,  2.27s/it]
Loading 0:   5%|▌         | 15/291 [00:04<01:02,  4.39it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:22, 11.67it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 21.01it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:08, 25.46it/s]
Loading 0:  27%|██▋       | 79/291 [00:05<00:06, 34.90it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:04, 48.68it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 64.92it/s]
Loading 0:  45%|████▌     | 132/291 [00:05<00:01, 81.13it/s]
Loading 0:  52%|█████▏    | 150/291 [00:05<00:01, 97.49it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 75.75it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 91.50it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 106.71it/s]
Loading 0:  75%|███████▍  | 217/291 [00:06<00:00, 113.45it/s]
Loading 0:  80%|███████▉  | 232/291 [00:06<00:00, 121.73it/s]
Loading 0:  86%|████████▌ | 249/291 [00:06<00:00, 131.23it/s]
Loading 0:  91%|█████████▏| 266/291 [00:06<00:00, 89.28it/s] 
Loading 0:  98%|█████████▊| 284/291 [00:07<00:00, 104.44it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-pp-0-72xra-v1-mkmlizer: quantized model in 23.226s
nitral-ai-pp-0-72xra-v1-mkmlizer: Processed model Nitral-AI/Pp-0.72xra in 63.764s
nitral-ai-pp-0-72xra-v1-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-pp-0-72xra-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-pp-0-72xra-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-pp-0-72xra-v1
nitral-ai-pp-0-72xra-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-pp-0-72xra-v1/config.json
nitral-ai-pp-0-72xra-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-pp-0-72xra-v1/special_tokens_map.json
nitral-ai-pp-0-72xra-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-pp-0-72xra-v1/tokenizer_config.json
nitral-ai-pp-0-72xra-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-pp-0-72xra-v1/tokenizer.json
nitral-ai-pp-0-72xra-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-pp-0-72xra-v1/flywheel_model.0.safetensors
nitral-ai-pp-0-72xra-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-pp-0-72xra-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-pp-0-72xra-v1-mkmlizer:   warnings.warn(
nitral-ai-pp-0-72xra-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-pp-0-72xra-v1-mkmlizer:   warnings.warn(
nitral-ai-pp-0-72xra-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-pp-0-72xra-v1-mkmlizer:   warnings.warn(
nitral-ai-pp-0-72xra-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-pp-0-72xra-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
nitral-ai-pp-0-72xra-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-pp-0-72xra-v1-mkmlizer: Saving duration: 0.401s
nitral-ai-pp-0-72xra-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.213s
nitral-ai-pp-0-72xra-v1-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-pp-0-72xra-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-pp-0-72xra-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-pp-0-72xra-v1_reward
nitral-ai-pp-0-72xra-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-pp-0-72xra-v1_reward/config.json
nitral-ai-pp-0-72xra-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-pp-0-72xra-v1_reward/special_tokens_map.json
nitral-ai-pp-0-72xra-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-pp-0-72xra-v1_reward/tokenizer_config.json
nitral-ai-pp-0-72xra-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-pp-0-72xra-v1_reward/merges.txt
nitral-ai-pp-0-72xra-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-pp-0-72xra-v1_reward/vocab.json
nitral-ai-pp-0-72xra-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-pp-0-72xra-v1_reward/tokenizer.json
nitral-ai-pp-0-72xra-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-pp-0-72xra-v1_reward/reward.tensors
Job nitral-ai-pp-0-72xra-v1-mkmlizer completed after 83.47s with status: succeeded
Stopping job with name nitral-ai-pp-0-72xra-v1-mkmlizer
Pipeline stage MKMLizer completed in 87.54s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-pp-0-72xra-v1
Waiting for inference service nitral-ai-pp-0-72xra-v1 to be ready
Inference service nitral-ai-pp-0-72xra-v1 ready after 100.58909153938293s
Pipeline stage ISVCDeployer completed in 108.02s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.142394781112671s
Received healthy response to inference request in 1.1275105476379395s
Received healthy response to inference request in 1.135822057723999s
Received healthy response to inference request in 1.1312777996063232s
Received healthy response to inference request in 1.1043553352355957s
5 requests
0 failed requests
5th percentile: 1.1089863777160645
10th percentile: 1.1136174201965332
20th percentile: 1.1228795051574707
30th percentile: 1.1282639980316163
40th percentile: 1.1297708988189696
50th percentile: 1.1312777996063232
60th percentile: 1.1330955028533936
70th percentile: 1.1349132061004639
80th percentile: 1.3371366024017335
90th percentile: 1.7397656917572022
95th percentile: 1.9410802364349364
99th percentile: 2.102131872177124
mean time: 1.3282721042633057
Pipeline stage StressChecker completed in 7.25s
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-0-72xra_v1 status is now deployed due to DeploymentManager action
nitral-ai-pp-0-72xra_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-pp-0-72xra_v1
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-pp-0-72xra-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.35s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-pp-0-72xra-v1/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-pp-0-72xra-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-pp-0-72xra-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-pp-0-72xra-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-pp-0-72xra-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-pp-0-72xra-v1_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-72xra-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-72xra-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-72xra-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-72xra-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-72xra-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-72xra-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.98s
nitral-ai-pp-0-72xra_v1 status is now torndown due to DeploymentManager action