pawankrd-pai-001-rp-gpt4_1659

developer_uid: PawanOsman

submission_id: pawankrd-pai-001-rp-gpt4_1659_v1

model_name: pawankrd-pai-001-rp-gpt4_1659_v1

model_group: PawanKrd/pai-001-rp-gpt4

status: torndown

timestamp: 2024-06-11T13:54:19+00:00

num_battles: 15182

num_wins: 6430

celo_rating: 1114.7

family_friendly_score: 0.0

submission_type: basic

model_repo: PawanKrd/pai-001-rp-gpt4-turbo

model_architecture: MistralForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 7241732096.0

best_of: 4

max_input_tokens: 512

max_output_tokens: 64

display_name: pawankrd-pai-001-rp-gpt4_1659_v1

is_internal_developer: False

language_model: PawanKrd/pai-001-rp-gpt4-turbo

model_size: 7B

ranking_group: single

us_pacific_date: 2024-06-11

win_ratio: 0.42352786194177316

generation_params: {'temperature': 0.7, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 1.2, 'frequency_penalty': 1.2, 'stopping_words': ['<', '>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}

reward_formatter: {'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True, 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n'}

model_eval_status: success

Resubmit model

Running pipeline stage MKMLizer
Starting job with name pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer
Waiting for job on pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer to finish
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ║     _____            __           __                                ║
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ║       /___/                                                         ║
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ║                                                                     ║
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ║  https://mk1.ai                                                     ║
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ║                                                                     ║
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ║  belonging to:                                                      ║
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ║                                                                     ║
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ║  Chai Research Corp.                                                ║
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ║                                                                     ║
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-pai-001-rp-gpt4-1659-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.
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: Downloaded to shared memory in 29.045s
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 8/291 [00:00<00:03, 79.92it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:03, 85.31it/s]
Loading 0:  10%|▉         | 28/291 [00:00<00:02, 89.07it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:02, 104.12it/s]
Loading 0:  19%|█▉        | 55/291 [00:00<00:02, 110.49it/s]
Loading 0:  24%|██▎       | 69/291 [00:00<00:01, 117.85it/s]
Loading 0:  28%|██▊       | 82/291 [00:00<00:01, 118.92it/s]
Loading 0:  33%|███▎      | 96/291 [00:00<00:01, 124.66it/s]
Loading 0:  37%|███▋      | 109/291 [00:01<00:03, 49.78it/s]
Loading 0:  41%|████      | 120/291 [00:01<00:03, 56.52it/s]
Loading 0:  45%|████▍     | 130/291 [00:01<00:02, 62.35it/s]
Loading 0:  49%|████▉     | 144/291 [00:01<00:01, 76.42it/s]
Loading 0:  53%|█████▎    | 155/291 [00:01<00:01, 83.13it/s]
Loading 0:  57%|█████▋    | 166/291 [00:02<00:01, 79.45it/s]
Loading 0:  60%|██████    | 176/291 [00:02<00:01, 79.88it/s]
Loading 0:  64%|██████▍   | 187/291 [00:02<00:01, 86.96it/s]
Loading 0:  68%|██████▊   | 199/291 [00:02<00:00, 95.10it/s]
Loading 0:  72%|███████▏  | 210/291 [00:04<00:05, 15.72it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:03, 20.39it/s]
Loading 0:  79%|███████▉  | 230/291 [00:04<00:02, 25.89it/s]
Loading 0:  82%|████████▏ | 240/291 [00:04<00:01, 32.31it/s]
Loading 0:  87%|████████▋ | 252/291 [00:04<00:00, 42.48it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 50.51it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 60.27it/s]
Loading 0:  98%|█████████▊| 285/291 [00:05<00:00, 68.79it/s]
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: quantized model in 12.823s
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: Processed model PawanKrd/pai-001-rp-gpt4-turbo in 43.223s
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-pai-001-rp-gpt4-1659-v1
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-pai-001-rp-gpt4-1659-v1/config.json
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-pai-001-rp-gpt4-1659-v1/tokenizer_config.json
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-pai-001-rp-gpt4-1659-v1/special_tokens_map.json
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/pawankrd-pai-001-rp-gpt4-1659-v1/tokenizer.model
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-pai-001-rp-gpt4-1659-v1/tokenizer.json
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-pai-001-rp-gpt4-1659-v1/flywheel_model.0.safetensors
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-pai-001-rp-gpt4-1659-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.
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer:   warnings.warn(
pawankrd-pai-001-rp-gpt4-1659-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.
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer:   warnings.warn(
pawankrd-pai-001-rp-gpt4-1659-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.
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer:   warnings.warn(
pawankrd-pai-001-rp-gpt4-1659-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()
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: Saving duration: 0.329s
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.881s
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: creating bucket guanaco-reward-models
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-pai-001-rp-gpt4-1659-v1_reward
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-pai-001-rp-gpt4-1659-v1_reward/config.json
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-pai-001-rp-gpt4-1659-v1_reward/special_tokens_map.json
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-pai-001-rp-gpt4-1659-v1_reward/tokenizer_config.json
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-pai-001-rp-gpt4-1659-v1_reward/merges.txt
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-pai-001-rp-gpt4-1659-v1_reward/vocab.json
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-pai-001-rp-gpt4-1659-v1_reward/tokenizer.json
pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-pai-001-rp-gpt4-1659-v1_reward/reward.tensors
Job pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer completed after 73.14s with status: succeeded
Stopping job with name pawankrd-pai-001-rp-gpt4-1659-v1-mkmlizer
Pipeline stage MKMLizer completed in 77.41s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-pai-001-rp-gpt4-1659-v1
Waiting for inference service pawankrd-pai-001-rp-gpt4-1659-v1 to be ready
Inference service pawankrd-pai-001-rp-gpt4-1659-v1 ready after 50.34890174865723s
Pipeline stage ISVCDeployer completed in 57.91s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9478261470794678s
Received healthy response to inference request in 1.1157991886138916s
Received healthy response to inference request in 1.1230862140655518s
Received healthy response to inference request in 1.1385564804077148s
Received healthy response to inference request in 1.1450080871582031s
5 requests
0 failed requests
5th percentile: 1.1172565937042236
10th percentile: 1.1187139987945556
20th percentile: 1.1216288089752198
30th percentile: 1.1261802673339845
40th percentile: 1.1323683738708497
50th percentile: 1.1385564804077148
60th percentile: 1.1411371231079102
70th percentile: 1.1437177658081055
80th percentile: 1.3055716991424562
90th percentile: 1.626698923110962
95th percentile: 1.7872625350952147
99th percentile: 1.915713424682617
mean time: 1.2940552234649658
Pipeline stage StressChecker completed in 7.11s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
pawankrd-pai-001-rp-gpt4_1659_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
pawankrd-pai-001-rp-gpt4_1659_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of pawankrd-pai-001-rp-gpt4_1659_v1
Running pipeline stage ISVCDeleter
Checking if service pawankrd-pai-001-rp-gpt4-1659-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.86s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key pawankrd-pai-001-rp-gpt4-1659-v1/config.json from bucket guanaco-mkml-models
Deleting key pawankrd-pai-001-rp-gpt4-1659-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key pawankrd-pai-001-rp-gpt4-1659-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key pawankrd-pai-001-rp-gpt4-1659-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key pawankrd-pai-001-rp-gpt4-1659-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key pawankrd-pai-001-rp-gpt4-1659-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key pawankrd-pai-001-rp-gpt4-1659-v1_reward/config.json from bucket guanaco-reward-models
Deleting key pawankrd-pai-001-rp-gpt4-1659-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key pawankrd-pai-001-rp-gpt4-1659-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key pawankrd-pai-001-rp-gpt4-1659-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key pawankrd-pai-001-rp-gpt4-1659-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key pawankrd-pai-001-rp-gpt4-1659-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key pawankrd-pai-001-rp-gpt4-1659-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.46s
pawankrd-pai-001-rp-gpt4_1659_v1 status is now torndown due to DeploymentManager action