deeppin-red-paper-v9-3396

developer_uid: deeppin

submission_id: deeppin-red-paper-v9-3396_v1

model_name: deeppin-red-paper-v9-3396_v1

model_group: deeppin/red-paper-v9-339

status: torndown

timestamp: 2025-01-26T07:05:39+00:00

num_battles: 9899

num_wins: 4374

celo_rating: 1225.99

family_friendly_score: 0.5868

family_friendly_standard_error: 0.006963702463488802

submission_type: basic

model_repo: deeppin/red-paper-v9-3396

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-v9-3396_v1

is_internal_developer: False

language_model: deeppin/red-paper-v9-3396

model_size: 8B

ranking_group: single

us_pacific_date: 2025-01-25

win_ratio: 0.4418628144256996

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'], '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-v9-3396-v1-mkmlizer
Waiting for job on deeppin-red-paper-v9-3396-v1-mkmlizer to finish
deeppin-red-paper-v9-3396-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
deeppin-red-paper-v9-3396-v1-mkmlizer: ║     _____            __           __                                ║
deeppin-red-paper-v9-3396-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
deeppin-red-paper-v9-3396-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
deeppin-red-paper-v9-3396-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
deeppin-red-paper-v9-3396-v1-mkmlizer: ║       /___/                                                         ║
deeppin-red-paper-v9-3396-v1-mkmlizer: ║                                                                     ║
deeppin-red-paper-v9-3396-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
deeppin-red-paper-v9-3396-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
deeppin-red-paper-v9-3396-v1-mkmlizer: ║  https://mk1.ai                                                     ║
deeppin-red-paper-v9-3396-v1-mkmlizer: ║                                                                     ║
deeppin-red-paper-v9-3396-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
deeppin-red-paper-v9-3396-v1-mkmlizer: ║  belonging to:                                                      ║
deeppin-red-paper-v9-3396-v1-mkmlizer: ║                                                                     ║
deeppin-red-paper-v9-3396-v1-mkmlizer: ║  Chai Research Corp.                                                ║
deeppin-red-paper-v9-3396-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
deeppin-red-paper-v9-3396-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
deeppin-red-paper-v9-3396-v1-mkmlizer: ║                                                                     ║
deeppin-red-paper-v9-3396-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
deeppin-red-paper-v9-3396-v1-mkmlizer: Downloaded to shared memory in 33.037s
deeppin-red-paper-v9-3396-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxgc__20h, device:0
deeppin-red-paper-v9-3396-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
deeppin-red-paper-v9-3396-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-v9-3396-v1-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
deeppin-red-paper-v9-3396-v1-mkmlizer: quantized model in 26.551s
deeppin-red-paper-v9-3396-v1-mkmlizer: Processed model deeppin/red-paper-v9-3396 in 59.588s
deeppin-red-paper-v9-3396-v1-mkmlizer: creating bucket guanaco-mkml-models
deeppin-red-paper-v9-3396-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
deeppin-red-paper-v9-3396-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/deeppin-red-paper-v9-3396-v1
deeppin-red-paper-v9-3396-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/deeppin-red-paper-v9-3396-v1/special_tokens_map.json
deeppin-red-paper-v9-3396-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/deeppin-red-paper-v9-3396-v1/tokenizer_config.json
deeppin-red-paper-v9-3396-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/deeppin-red-paper-v9-3396-v1/tokenizer.json
deeppin-red-paper-v9-3396-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/deeppin-red-paper-v9-3396-v1/flywheel_model.0.safetensors
deeppin-red-paper-v9-3396-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 47.68it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 78.87it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 80.00it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 79.82it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:02, 82.84it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:02, 82.62it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 78.87it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 79.95it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:09, 20.83it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:07, 27.19it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 33.16it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 38.86it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 44.11it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 49.81it/s]
Loading 0:  47%|████▋     | 137/291 [00:02<00:02, 51.63it/s]
Loading 0:  49%|████▉     | 144/291 [00:02<00:02, 55.28it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 65.54it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 70.52it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 74.29it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:04, 21.67it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 27.23it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 34.00it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:01, 41.43it/s]
Loading 0:  77%|███████▋  | 224/291 [00:04<00:01, 50.74it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:00, 61.98it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 67.27it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 71.40it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 74.90it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 76.01it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 75.41it/s]
                                                            
Job deeppin-red-paper-v9-3396-v1-mkmlizer completed after 83.48s with status: succeeded
Stopping job with name deeppin-red-paper-v9-3396-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.93s
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-v9-3396-v1
Waiting for inference service deeppin-red-paper-v9-3396-v1 to be ready
Failed to get response for submission chaiml-llama-8b-multihea_7878_v5: ('http://chaiml-llama-8b-multihea-7878-v5-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:34686->127.0.0.1:8080: read: connection reset by peer\n')
Inference service deeppin-red-paper-v9-3396-v1 ready after 180.89989399909973s
Pipeline stage MKMLDeployer completed in 181.42s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7819468975067139s
Received healthy response to inference request in 1.5357708930969238s
Received healthy response to inference request in 1.3421247005462646s
Received healthy response to inference request in 1.2628967761993408s
Received healthy response to inference request in 1.6769020557403564s
5 requests
0 failed requests
5th percentile: 1.2787423610687256
10th percentile: 1.2945879459381104
20th percentile: 1.3262791156768798
30th percentile: 1.3808539390563965
40th percentile: 1.45831241607666
50th percentile: 1.5357708930969238
60th percentile: 1.5922233581542968
70th percentile: 1.6486758232116698
80th percentile: 1.697911024093628
90th percentile: 1.739928960800171
95th percentile: 1.7609379291534424
99th percentile: 1.7777451038360597
mean time: 1.51992826461792
Pipeline stage StressChecker completed in 8.91s
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 0.65s
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 1.21s
Shutdown handler de-registered
deeppin-red-paper-v9-3396_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3759.04s
Shutdown handler de-registered
deeppin-red-paper-v9-3396_v1 status is now inactive due to auto deactivation removed underperforming models
deeppin-red-paper-v9-3396_v1 status is now torndown due to DeploymentManager action