developer_uid: deeppin
submission_id: deeppin-red-paper-v5_v1
model_name: deeppin-red-paper-v5_v1
model_group: deeppin/red-paper-v5
status: torndown
timestamp: 2025-01-22T05:49:28+00:00
num_battles: 11645
num_wins: 5362
celo_rating: 1242.25
family_friendly_score: 0.5964
family_friendly_standard_error: 0.006938400968522935
submission_type: basic
model_repo: deeppin/red-paper-v5
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: deeppin-red-paper-v5_v1
is_internal_developer: False
language_model: deeppin/red-paper-v5
model_size: 8B
ranking_group: single
us_pacific_date: 2025-01-21
win_ratio: 0.46045513095749246
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': ['\n', '<|eot_id|>'], '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{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\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-v5-v1-mkmlizer
Waiting for job on deeppin-red-paper-v5-v1-mkmlizer to finish
deeppin-red-paper-v5-v1-mkmlizer: Downloaded to shared memory in 249.378s
deeppin-red-paper-v5-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnm2zaihf, device:0
deeppin-red-paper-v5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
deeppin-red-paper-v5-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-v5-v1-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
deeppin-red-paper-v5-v1-mkmlizer: quantized model in 26.085s
deeppin-red-paper-v5-v1-mkmlizer: Processed model deeppin/red-paper-v5 in 275.463s
deeppin-red-paper-v5-v1-mkmlizer: creating bucket guanaco-mkml-models
deeppin-red-paper-v5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
deeppin-red-paper-v5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/deeppin-red-paper-v5-v1
deeppin-red-paper-v5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/deeppin-red-paper-v5-v1/config.json
deeppin-red-paper-v5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/deeppin-red-paper-v5-v1/special_tokens_map.json
deeppin-red-paper-v5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/deeppin-red-paper-v5-v1/tokenizer_config.json
deeppin-red-paper-v5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/deeppin-red-paper-v5-v1/tokenizer.json
deeppin-red-paper-v5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/deeppin-red-paper-v5-v1/flywheel_model.0.safetensors
deeppin-red-paper-v5-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 36.15it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 66.01it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 78.13it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 93.12it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:02, 90.43it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 87.64it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 94.14it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:08, 25.48it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:06, 32.22it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 43.58it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 51.25it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 62.14it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:02, 66.47it/s]
Loading 0:  55%|█████▍    | 160/291 [00:02<00:01, 69.58it/s]
Loading 0:  58%|█████▊    | 169/291 [00:02<00:01, 70.72it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 71.99it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:04, 22.12it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 32.18it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:01, 39.76it/s]
Loading 0:  77%|███████▋  | 224/291 [00:04<00:01, 47.00it/s]
Loading 0:  82%|████████▏ | 238/291 [00:04<00:00, 57.72it/s]
Loading 0:  86%|████████▌ | 250/291 [00:04<00:00, 64.50it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 74.25it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 77.01it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 79.67it/s]
                                                            

Job deeppin-red-paper-v5-v1-mkmlizer completed after 297.08s with status: succeeded
Stopping job with name deeppin-red-paper-v5-v1-mkmlizer
Pipeline stage MKMLizer completed in 297.52s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service deeppin-red-paper-v5-v1
Waiting for inference service deeppin-red-paper-v5-v1 to be ready
Inference service deeppin-red-paper-v5-v1 ready after 130.49469470977783s
Pipeline stage MKMLDeployer completed in 130.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7368435859680176s
Received healthy response to inference request in 1.3156180381774902s
Received healthy response to inference request in 1.3115403652191162s
Received healthy response to inference request in 1.4164385795593262s
Received healthy response to inference request in 1.4457294940948486s
5 requests
0 failed requests
5th percentile: 1.312355899810791
10th percentile: 1.3131714344024659
20th percentile: 1.3148025035858155
30th percentile: 1.3357821464538575
40th percentile: 1.3761103630065918
50th percentile: 1.4164385795593262
60th percentile: 1.4281549453735352
70th percentile: 1.4398713111877441
80th percentile: 1.5039523124694825
90th percentile: 1.62039794921875
95th percentile: 1.6786207675933837
99th percentile: 1.7251990222930909
mean time: 1.4452340126037597
Pipeline stage StressChecker completed in 8.36s
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 1.00s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Retrying (%r) after connection broken by '%r': %s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.64s
Shutdown handler de-registered
deeppin-red-paper-v5_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 2250.71s
Shutdown handler de-registered
deeppin-red-paper-v5_v1 status is now inactive due to auto deactivation removed underperforming models
deeppin-red-paper-v5_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1