developer_uid: deeppin
submission_id: deeppin-red-paper-v3_v1
model_name: deeppin-red-paper-v3_v1
model_group: deeppin/red-paper-v3
status: torndown
timestamp: 2025-01-16T12:37:23+00:00
num_battles: 14019
num_wins: 6616
celo_rating: 1242.81
family_friendly_score: 0.5962000000000001
family_friendly_standard_error: 0.006938956117457438
submission_type: basic
model_repo: deeppin/red-paper-v3
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: deeppin-red-paper-v3_v1
is_internal_developer: False
language_model: deeppin/red-paper-v3
model_size: 8B
ranking_group: single
us_pacific_date: 2025-01-16
win_ratio: 0.4719309508524146
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\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-v3-v1-mkmlizer
Waiting for job on deeppin-red-paper-v3-v1-mkmlizer to finish
deeppin-red-paper-v3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
deeppin-red-paper-v3-v1-mkmlizer: ║ _____ __ __ ║
deeppin-red-paper-v3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
deeppin-red-paper-v3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
deeppin-red-paper-v3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
deeppin-red-paper-v3-v1-mkmlizer: ║ /___/ ║
deeppin-red-paper-v3-v1-mkmlizer: ║ ║
deeppin-red-paper-v3-v1-mkmlizer: ║ Version: 0.11.12 ║
deeppin-red-paper-v3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
deeppin-red-paper-v3-v1-mkmlizer: ║ https://mk1.ai ║
deeppin-red-paper-v3-v1-mkmlizer: ║ ║
deeppin-red-paper-v3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
deeppin-red-paper-v3-v1-mkmlizer: ║ belonging to: ║
deeppin-red-paper-v3-v1-mkmlizer: ║ ║
deeppin-red-paper-v3-v1-mkmlizer: ║ Chai Research Corp. ║
deeppin-red-paper-v3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
deeppin-red-paper-v3-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
deeppin-red-paper-v3-v1-mkmlizer: ║ ║
deeppin-red-paper-v3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
deeppin-red-paper-v3-v1-mkmlizer: Downloaded to shared memory in 33.015s
deeppin-red-paper-v3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpy0vx9y5s, device:0
deeppin-red-paper-v3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
deeppin-red-paper-v3-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-v3-v1-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
deeppin-red-paper-v3-v1-mkmlizer: quantized model in 28.162s
deeppin-red-paper-v3-v1-mkmlizer: Processed model deeppin/red-paper-v3 in 61.178s
deeppin-red-paper-v3-v1-mkmlizer: creating bucket guanaco-mkml-models
deeppin-red-paper-v3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
deeppin-red-paper-v3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/deeppin-red-paper-v3-v1
deeppin-red-paper-v3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/deeppin-red-paper-v3-v1/tokenizer_config.json
deeppin-red-paper-v3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/deeppin-red-paper-v3-v1/tokenizer.json
deeppin-red-paper-v3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/deeppin-red-paper-v3-v1/flywheel_model.0.safetensors
deeppin-red-paper-v3-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:08, 35.00it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:05, 52.06it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:04, 56.63it/s] Loading 0: 11%|█ | 31/291 [00:00<00:04, 60.53it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:03, 65.45it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:03, 67.82it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:03, 66.17it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:03, 63.53it/s] Loading 0: 26%|██▌ | 76/291 [00:01<00:03, 61.93it/s] Loading 0: 29%|██▊ | 83/291 [00:02<00:12, 16.43it/s] Loading 0: 30%|███ | 88/291 [00:02<00:11, 18.23it/s] Loading 0: 33%|███▎ | 97/291 [00:02<00:07, 24.42it/s] Loading 0: 36%|███▋ | 106/291 [00:02<00:06, 30.45it/s] Loading 0: 40%|███▉ | 115/291 [00:03<00:04, 37.78it/s] Loading 0: 43%|████▎ | 124/291 [00:03<00:03, 44.83it/s] Loading 0: 46%|████▌ | 133/291 [00:03<00:03, 50.78it/s] Loading 0: 49%|████▉ | 142/291 [00:03<00:02, 55.11it/s] Loading 0: 52%|█████▏ | 151/291 [00:03<00:02, 60.95it/s] Loading 0: 55%|█████▍ | 160/291 [00:03<00:02, 63.00it/s] Loading 0: 58%|█████▊ | 169/291 [00:03<00:01, 62.80it/s] Loading 0: 61%|██████ | 178/291 [00:04<00:01, 65.99it/s] Loading 0: 64%|██████▍ | 187/291 [00:05<00:05, 19.53it/s] Loading 0: 67%|██████▋ | 196/291 [00:05<00:03, 24.82it/s] Loading 0: 70%|███████ | 205/291 [00:05<00:02, 30.29it/s] Loading 0: 74%|███████▎ | 214/291 [00:05<00:02, 35.89it/s] Loading 0: 77%|███████▋ | 223/291 [00:05<00:01, 42.49it/s] Loading 0: 80%|███████▉ | 232/291 [00:05<00:01, 48.81it/s] Loading 0: 83%|████████▎ | 241/291 [00:06<00:00, 53.08it/s] Loading 0: 86%|████████▌ | 250/291 [00:06<00:00, 57.90it/s] Loading 0: 89%|████████▉ | 259/291 [00:06<00:00, 61.97it/s] Loading 0: 92%|█████████▏| 268/291 [00:06<00:00, 64.20it/s] Loading 0: 95%|█████████▌| 277/291 [00:06<00:00, 63.65it/s] Loading 0: 98%|█████████▊| 286/291 [00:06<00:00, 62.57it/s]
Job deeppin-red-paper-v3-v1-mkmlizer completed after 83.73s with status: succeeded
Stopping job with name deeppin-red-paper-v3-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.20s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service deeppin-red-paper-v3-v1
Waiting for inference service deeppin-red-paper-v3-v1 to be ready
Inference service deeppin-red-paper-v3-v1 ready after 130.65307569503784s
Pipeline stage MKMLDeployer completed in 131.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9047439098358154s
Received healthy response to inference request in 1.4633595943450928s
Received healthy response to inference request in 1.537421464920044s
Received healthy response to inference request in 1.2569537162780762s
Received healthy response to inference request in 1.2765579223632812s
5 requests
0 failed requests
5th percentile: 1.2608745574951172
10th percentile: 1.2647953987121583
20th percentile: 1.2726370811462402
30th percentile: 1.3139182567596435
40th percentile: 1.3886389255523681
50th percentile: 1.4633595943450928
60th percentile: 1.4929843425750733
70th percentile: 1.5226090908050538
80th percentile: 1.6108859539031983
90th percentile: 1.7578149318695069
95th percentile: 1.831279420852661
99th percentile: 1.8900510120391845
mean time: 1.487807321548462
Pipeline stage StressChecker completed in 8.70s
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 0.66s
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 0.76s
Shutdown handler de-registered
deeppin-red-paper-v3_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 3838.92s
Shutdown handler de-registered
deeppin-red-paper-v3_v1 status is now inactive due to auto deactivation removed underperforming models
deeppin-red-paper-v3_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1