developer_uid: deeppin
submission_id: deeppin-red-paper-v16-740_v1
model_name: deeppin-red-paper-v16-740_v1
model_group: deeppin/red-paper-v16-74
status: torndown
timestamp: 2025-02-14T04:16:32+00:00
num_battles: 5402
num_wins: 2471
celo_rating: 1235.09
family_friendly_score: 0.567
family_friendly_standard_error: 0.007007296197535822
submission_type: basic
model_repo: deeppin/red-paper-v16-740
model_architecture: LlamaForCausalLM
model_num_parameters: 8030269440.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: deeppin-red-paper-v16-740_v1
is_internal_developer: False
language_model: deeppin/red-paper-v16-740
model_size: 8B
ranking_group: single
us_pacific_date: 2025-02-13
win_ratio: 0.4574231766012588
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>'], 'max_input_tokens': 1024, 'best_of': 8, '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}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name deeppin-red-paper-v16-740-v1-mkmlizer
Waiting for job on deeppin-red-paper-v16-740-v1-mkmlizer to finish
deeppin-red-paper-v16-740-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
deeppin-red-paper-v16-740-v1-mkmlizer: ║ _____ __ __ ║
deeppin-red-paper-v16-740-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
deeppin-red-paper-v16-740-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
deeppin-red-paper-v16-740-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
deeppin-red-paper-v16-740-v1-mkmlizer: ║ /___/ ║
deeppin-red-paper-v16-740-v1-mkmlizer: ║ ║
deeppin-red-paper-v16-740-v1-mkmlizer: ║ Version: 0.12.8 ║
deeppin-red-paper-v16-740-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
deeppin-red-paper-v16-740-v1-mkmlizer: ║ https://mk1.ai ║
deeppin-red-paper-v16-740-v1-mkmlizer: ║ ║
deeppin-red-paper-v16-740-v1-mkmlizer: ║ The license key for the current software has been verified as ║
deeppin-red-paper-v16-740-v1-mkmlizer: ║ belonging to: ║
deeppin-red-paper-v16-740-v1-mkmlizer: ║ ║
deeppin-red-paper-v16-740-v1-mkmlizer: ║ Chai Research Corp. ║
deeppin-red-paper-v16-740-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
deeppin-red-paper-v16-740-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
deeppin-red-paper-v16-740-v1-mkmlizer: ║ ║
deeppin-red-paper-v16-740-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
deeppin-red-paper-v16-740-v1-mkmlizer: Downloaded to shared memory in 29.842s
deeppin-red-paper-v16-740-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0kdh9sfa, device:0
deeppin-red-paper-v16-740-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
deeppin-red-paper-v16-740-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/mk1/flywheel/functional/loader.py:55: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
deeppin-red-paper-v16-740-v1-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
deeppin-red-paper-v16-740-v1-mkmlizer: quantized model in 25.707s
deeppin-red-paper-v16-740-v1-mkmlizer: Processed model deeppin/red-paper-v16-740 in 55.549s
deeppin-red-paper-v16-740-v1-mkmlizer: creating bucket guanaco-mkml-models
deeppin-red-paper-v16-740-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
deeppin-red-paper-v16-740-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/deeppin-red-paper-v16-740-v1
deeppin-red-paper-v16-740-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/deeppin-red-paper-v16-740-v1/config.json
deeppin-red-paper-v16-740-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/deeppin-red-paper-v16-740-v1/special_tokens_map.json
deeppin-red-paper-v16-740-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/deeppin-red-paper-v16-740-v1/tokenizer_config.json
deeppin-red-paper-v16-740-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/deeppin-red-paper-v16-740-v1/tokenizer.json
deeppin-red-paper-v16-740-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/deeppin-red-paper-v16-740-v1/flywheel_model.0.safetensors
deeppin-red-paper-v16-740-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:07, 37.30it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 65.14it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:03, 73.37it/s] Loading 0: 11%|█ | 31/291 [00:00<00:03, 73.73it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:03, 77.88it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:02, 80.96it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 80.79it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 80.72it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:02, 80.97it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:09, 21.75it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:07, 28.10it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:05, 34.19it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 40.71it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 48.16it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:02, 54.48it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 60.84it/s] Loading 0: 52%|█████▏ | 151/291 [00:02<00:02, 67.51it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:01, 79.09it/s] Loading 0: 60%|██████ | 175/291 [00:03<00:01, 80.92it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:03, 26.16it/s] Loading 0: 68%|██████▊ | 197/291 [00:04<00:02, 32.82it/s] Loading 0: 71%|███████ | 206/291 [00:04<00:02, 39.43it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 50.79it/s] Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 55.91it/s] Loading 0: 82%|████████▏ | 238/291 [00:04<00:00, 56.58it/s] Loading 0: 85%|████████▍ | 247/291 [00:04<00:00, 59.97it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 65.06it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 69.17it/s] Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 72.29it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 74.22it/s] Loading 0: 100%|██████████| 291/291 [00:10<00:00, 5.22it/s]
Job deeppin-red-paper-v16-740-v1-mkmlizer completed after 83.69s with status: succeeded
Stopping job with name deeppin-red-paper-v16-740-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.14s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service deeppin-red-paper-v16-740-v1
Waiting for inference service deeppin-red-paper-v16-740-v1 to be ready
Inference service deeppin-red-paper-v16-740-v1 ready after 190.88527703285217s
Pipeline stage MKMLDeployer completed in 191.44s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8759331703186035s
Received healthy response to inference request in 1.2173192501068115s
Received healthy response to inference request in 1.2913737297058105s
Received healthy response to inference request in 1.139988899230957s
Received healthy response to inference request in 1.1484599113464355s
5 requests
0 failed requests
5th percentile: 1.1416831016540527
10th percentile: 1.1433773040771484
20th percentile: 1.1467657089233398
30th percentile: 1.1622317790985108
40th percentile: 1.1897755146026612
50th percentile: 1.2173192501068115
60th percentile: 1.246941041946411
70th percentile: 1.2765628337860107
80th percentile: 1.4082856178283691
90th percentile: 1.6421093940734863
95th percentile: 1.759021282196045
99th percentile: 1.8525507926940918
mean time: 1.3346149921417236
Pipeline stage StressChecker completed in 7.81s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.89s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.60s
Shutdown handler de-registered
deeppin-red-paper-v16-740_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2379.14s
Shutdown handler de-registered
deeppin-red-paper-v16-740_v1 status is now inactive due to auto deactivation removed underperforming models
deeppin-red-paper-v16-740_v1 status is now torndown due to DeploymentManager action
deeppin-red-paper-v16-740_v1 status is now torndown due to DeploymentManager action
deeppin-red-paper-v16-740_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1