developer_uid: deeppin
submission_id: deeppin-red-paper-v11-842_v3
model_name: deeppin-red-paper-v11-842_v3
model_group: deeppin/red-paper-v11-84
status: torndown
timestamp: 2025-02-02T14:05:56+00:00
num_battles: 7035
num_wins: 3143
celo_rating: 1230.76
family_friendly_score: 0.5838
family_friendly_standard_error: 0.006971048127792549
submission_type: basic
model_repo: deeppin/red-paper-v11-842
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
display_name: deeppin-red-paper-v11-842_v3
is_internal_developer: False
language_model: deeppin/red-paper-v11-842
model_size: 8B
ranking_group: single
us_pacific_date: 2025-02-02
win_ratio: 0.44676616915422884
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|eot_id|>', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|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': True}
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-v11-842-v3-mkmlizer
Waiting for job on deeppin-red-paper-v11-842-v3-mkmlizer to finish
deeppin-red-paper-v11-842-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
deeppin-red-paper-v11-842-v3-mkmlizer: ║ _____ __ __ ║
deeppin-red-paper-v11-842-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
deeppin-red-paper-v11-842-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
deeppin-red-paper-v11-842-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
deeppin-red-paper-v11-842-v3-mkmlizer: ║ /___/ ║
deeppin-red-paper-v11-842-v3-mkmlizer: ║ ║
deeppin-red-paper-v11-842-v3-mkmlizer: ║ Version: 0.11.12 ║
deeppin-red-paper-v11-842-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
deeppin-red-paper-v11-842-v3-mkmlizer: ║ https://mk1.ai ║
deeppin-red-paper-v11-842-v3-mkmlizer: ║ ║
deeppin-red-paper-v11-842-v3-mkmlizer: ║ The license key for the current software has been verified as ║
deeppin-red-paper-v11-842-v3-mkmlizer: ║ belonging to: ║
deeppin-red-paper-v11-842-v3-mkmlizer: ║ ║
deeppin-red-paper-v11-842-v3-mkmlizer: ║ Chai Research Corp. ║
deeppin-red-paper-v11-842-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
deeppin-red-paper-v11-842-v3-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
deeppin-red-paper-v11-842-v3-mkmlizer: ║ ║
deeppin-red-paper-v11-842-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
deeppin-red-paper-v11-842-v3-mkmlizer: Downloaded to shared memory in 23.659s
deeppin-red-paper-v11-842-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphwqas3gy, device:0
deeppin-red-paper-v11-842-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
deeppin-red-paper-v11-842-v3-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-v11-842-v3-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
deeppin-red-paper-v11-842-v3-mkmlizer: quantized model in 28.392s
deeppin-red-paper-v11-842-v3-mkmlizer: Processed model deeppin/red-paper-v11-842 in 52.052s
deeppin-red-paper-v11-842-v3-mkmlizer: creating bucket guanaco-mkml-models
deeppin-red-paper-v11-842-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/deeppin-red-paper-v11-842-v3/config.json
deeppin-red-paper-v11-842-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/deeppin-red-paper-v11-842-v3/special_tokens_map.json
deeppin-red-paper-v11-842-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/deeppin-red-paper-v11-842-v3/tokenizer_config.json
deeppin-red-paper-v11-842-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/deeppin-red-paper-v11-842-v3/tokenizer.json
deeppin-red-paper-v11-842-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/deeppin-red-paper-v11-842-v3/flywheel_model.0.safetensors
deeppin-red-paper-v11-842-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:08, 32.38it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:06, 43.93it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:05, 47.45it/s] Loading 0: 11%|█ | 31/291 [00:00<00:05, 49.59it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:04, 50.56it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:04, 51.10it/s] Loading 0: 20%|█▉ | 58/291 [00:01<00:04, 52.17it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 51.58it/s] Loading 0: 26%|██▌ | 76/291 [00:01<00:04, 51.43it/s] Loading 0: 29%|██▊ | 83/291 [00:02<00:13, 15.86it/s] Loading 0: 30%|███ | 88/291 [00:03<00:11, 17.52it/s] Loading 0: 33%|███▎ | 97/291 [00:03<00:08, 22.79it/s] Loading 0: 36%|███▋ | 106/291 [00:03<00:06, 27.89it/s] Loading 0: 40%|███▉ | 115/291 [00:03<00:05, 32.70it/s] Loading 0: 43%|████▎ | 124/291 [00:03<00:04, 37.22it/s] Loading 0: 46%|████▌ | 133/291 [00:03<00:04, 39.39it/s] Loading 0: 49%|████▉ | 142/291 [00:04<00:03, 42.20it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:03, 44.39it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:02, 45.82it/s] Loading 0: 58%|█████▊ | 169/291 [00:04<00:02, 47.63it/s] Loading 0: 61%|██████ | 178/291 [00:04<00:02, 48.14it/s] Loading 0: 64%|██████▍ | 187/291 [00:06<00:06, 16.92it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:03, 25.89it/s] Loading 0: 73%|███████▎ | 211/291 [00:06<00:02, 31.70it/s] Loading 0: 77%|███████▋ | 223/291 [00:06<00:01, 39.96it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:01, 52.03it/s] Loading 0: 86%|████████▌ | 250/291 [00:06<00:00, 58.77it/s] Loading 0: 89%|████████▉ | 259/291 [00:06<00:00, 64.08it/s] Loading 0: 92%|█████████▏| 268/291 [00:07<00:00, 68.95it/s] Loading 0: 96%|█████████▌| 278/291 [00:07<00:00, 75.70it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 41.63it/s]
Job deeppin-red-paper-v11-842-v3-mkmlizer completed after 83.57s with status: succeeded
Stopping job with name deeppin-red-paper-v11-842-v3-mkmlizer
Pipeline stage MKMLizer completed in 84.06s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service deeppin-red-paper-v11-842-v3
Waiting for inference service deeppin-red-paper-v11-842-v3 to be ready
Inference service deeppin-red-paper-v11-842-v3 ready after 180.6028175354004s
Pipeline stage MKMLDeployer completed in 181.13s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.939720869064331s
Received healthy response to inference request in 1.5383310317993164s
Received healthy response to inference request in 1.6478400230407715s
Received healthy response to inference request in 1.5783205032348633s
Received healthy response to inference request in 1.5187981128692627s
5 requests
0 failed requests
5th percentile: 1.5227046966552735
10th percentile: 1.5266112804412841
20th percentile: 1.5344244480133056
30th percentile: 1.5463289260864257
40th percentile: 1.5623247146606445
50th percentile: 1.5783205032348633
60th percentile: 1.6061283111572267
70th percentile: 1.6339361190795898
80th percentile: 1.7062161922454835
90th percentile: 1.8229685306549073
95th percentile: 1.881344699859619
99th percentile: 1.9280456352233886
mean time: 1.644602108001709
Pipeline stage StressChecker completed in 9.53s
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 0.71s
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 0.63s
Shutdown handler de-registered
deeppin-red-paper-v11-842_v3 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service deeppin-red-paper-v11-842-v3-profiler
Waiting for inference service deeppin-red-paper-v11-842-v3-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4047.08s
Shutdown handler de-registered
deeppin-red-paper-v11-842_v3 status is now inactive due to auto deactivation removed underperforming models
deeppin-red-paper-v11-842_v3 status is now torndown due to DeploymentManager action