developer_uid: deeppin
submission_id: deeppin-red-paper-nemo-754_v1
model_name: deeppin-red-paper-nemo-754_v1
model_group: deeppin/red-paper-nemo-7
status: torndown
timestamp: 2025-02-24T12:39:45+00:00
num_battles: 7658
num_wins: 3406
celo_rating: 1238.71
family_friendly_score: 0.5532
family_friendly_standard_error: 0.0070309282459715084
submission_type: basic
model_repo: deeppin/red-paper-nemo-754
model_architecture: MistralForCausalLM
model_num_parameters: 12772090880.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6030047616815114, 'latency_mean': 1.6582654559612273, 'latency_p50': 1.6765720844268799, 'latency_p90': 1.812847661972046}, {'batch_size': 3, 'throughput': 1.0850706350416854, 'latency_mean': 2.753106219768524, 'latency_p50': 2.759542942047119, 'latency_p90': 3.0063737630844116}, {'batch_size': 5, 'throughput': 1.3074657198661683, 'latency_mean': 3.8048457300662992, 'latency_p50': 3.819043517112732, 'latency_p90': 4.26286211013794}, {'batch_size': 6, 'throughput': 1.3756042407526439, 'latency_mean': 4.341457366943359, 'latency_p50': 4.3414846658706665, 'latency_p90': 4.8446836233139035}, {'batch_size': 8, 'throughput': 1.4330918080111323, 'latency_mean': 5.543267594575882, 'latency_p50': 5.557647466659546, 'latency_p90': 6.351798796653748}, {'batch_size': 10, 'throughput': 1.4647650463299822, 'latency_mean': 6.767463043928147, 'latency_p50': 6.77388072013855, 'latency_p90': 7.704865097999573}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: deeppin-red-paper-nemo-754_v1
is_internal_developer: False
language_model: deeppin/red-paper-nemo-754
model_size: 13B
ranking_group: single
throughput_3p7s: 1.3
us_pacific_date: 2025-02-24
win_ratio: 0.444763645860538
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': 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-nemo-754-v1-mkmlizer
Waiting for job on deeppin-red-paper-nemo-754-v1-mkmlizer to finish
deeppin-red-paper-nemo-754-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
deeppin-red-paper-nemo-754-v1-mkmlizer: ║     _____            __           __                                ║
deeppin-red-paper-nemo-754-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
deeppin-red-paper-nemo-754-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
deeppin-red-paper-nemo-754-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
deeppin-red-paper-nemo-754-v1-mkmlizer: ║       /___/                                                         ║
deeppin-red-paper-nemo-754-v1-mkmlizer: ║                                                                     ║
deeppin-red-paper-nemo-754-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
deeppin-red-paper-nemo-754-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
deeppin-red-paper-nemo-754-v1-mkmlizer: ║  https://mk1.ai                                                     ║
deeppin-red-paper-nemo-754-v1-mkmlizer: ║                                                                     ║
deeppin-red-paper-nemo-754-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
deeppin-red-paper-nemo-754-v1-mkmlizer: ║  belonging to:                                                      ║
deeppin-red-paper-nemo-754-v1-mkmlizer: ║                                                                     ║
deeppin-red-paper-nemo-754-v1-mkmlizer: ║  Chai Research Corp.                                                ║
deeppin-red-paper-nemo-754-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
deeppin-red-paper-nemo-754-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
deeppin-red-paper-nemo-754-v1-mkmlizer: ║                                                                     ║
deeppin-red-paper-nemo-754-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
deeppin-red-paper-nemo-754-v1-mkmlizer: Downloaded to shared memory in 45.296s
deeppin-red-paper-nemo-754-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5bf2qw1d, device:0
deeppin-red-paper-nemo-754-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
deeppin-red-paper-nemo-754-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-nemo-754-v1-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
Failed to get response for submission nischaydnk-mistral24b-s_29097_v2: HTTPConnectionPool(host='nischaydnk-mistral24b-s-29097-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
deeppin-red-paper-nemo-754-v1-mkmlizer: quantized model in 36.277s
deeppin-red-paper-nemo-754-v1-mkmlizer: Processed model deeppin/red-paper-nemo-754 in 81.574s
deeppin-red-paper-nemo-754-v1-mkmlizer: creating bucket guanaco-mkml-models
deeppin-red-paper-nemo-754-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
deeppin-red-paper-nemo-754-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/deeppin-red-paper-nemo-754-v1
deeppin-red-paper-nemo-754-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/deeppin-red-paper-nemo-754-v1/config.json
deeppin-red-paper-nemo-754-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/deeppin-red-paper-nemo-754-v1/special_tokens_map.json
deeppin-red-paper-nemo-754-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/deeppin-red-paper-nemo-754-v1/tokenizer_config.json
deeppin-red-paper-nemo-754-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/deeppin-red-paper-nemo-754-v1/flywheel_model.0.safetensors
deeppin-red-paper-nemo-754-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 34.15it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:05, 64.15it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:04, 83.49it/s]
Loading 0:   9%|▉         | 34/363 [00:00<00:04, 76.76it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:03, 86.85it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:13, 22.97it/s]
Loading 0:  19%|█▉        | 70/363 [00:01<00:10, 28.84it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:07, 36.72it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:06, 41.74it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:05, 51.10it/s]
Loading 0:  29%|██▉       | 107/363 [00:02<00:04, 57.79it/s]
Loading 0:  32%|███▏      | 116/363 [00:02<00:03, 63.60it/s]
Loading 0:  36%|███▌      | 130/363 [00:02<00:03, 73.18it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:09, 23.65it/s]
Loading 0:  42%|████▏     | 151/363 [00:03<00:07, 28.97it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 35.36it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:03, 47.73it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 54.76it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:02, 60.42it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 72.11it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:05, 25.51it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:04, 30.69it/s]
Loading 0:  66%|██████▋   | 241/363 [00:05<00:03, 36.86it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 49.09it/s]
Loading 0:  74%|███████▍  | 268/363 [00:06<00:01, 56.42it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 63.66it/s]
Loading 0:  79%|███████▉  | 287/363 [00:06<00:01, 67.55it/s]
Loading 0:  83%|████████▎ | 301/363 [00:06<00:00, 75.74it/s]
Loading 0:  86%|████████▌ | 311/363 [00:07<00:02, 25.79it/s]
Loading 0:  88%|████████▊ | 321/363 [00:07<00:01, 32.44it/s]
Loading 0:  91%|█████████ | 331/363 [00:07<00:00, 38.47it/s]
Loading 0:  95%|█████████▌| 346/363 [00:08<00:00, 50.93it/s]
Loading 0:  99%|█████████▊| 358/363 [00:08<00:00, 57.96it/s]
                                                            

Job deeppin-red-paper-nemo-754-v1-mkmlizer completed after 104.21s with status: succeeded
Stopping job with name deeppin-red-paper-nemo-754-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.72s
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-nemo-754-v1
Waiting for inference service deeppin-red-paper-nemo-754-v1 to be ready
Failed to get response for submission nischaydnk-mistral24b-s_29097_v1: HTTPConnectionPool(host='nischaydnk-mistral24b-s-29097-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-mistral24b-s_29097_v1: HTTPConnectionPool(host='nischaydnk-mistral24b-s-29097-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-mistral24b-s_27493_v1: HTTPConnectionPool(host='nischaydnk-mistral24b-s-27493-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-mistral24b-s_29097_v2: HTTPConnectionPool(host='nischaydnk-mistral24b-s-29097-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service deeppin-red-paper-nemo-754-v1 ready after 240.8158884048462s
Pipeline stage MKMLDeployer completed in 241.34s
run pipeline stage %s
Running pipeline stage StressChecker
Failed to get response for submission nischaydnk-mistral24b-s_29097_v2: HTTPConnectionPool(host='nischaydnk-mistral24b-s-29097-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-mistral24b-s_84547_v1: HTTPConnectionPool(host='nischaydnk-mistral24b-s-84547-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 2.446246385574341s
Received healthy response to inference request in 1.7154145240783691s
Received healthy response to inference request in 1.5494978427886963s
Received healthy response to inference request in 1.8455731868743896s
Received healthy response to inference request in 1.8814637660980225s
5 requests
0 failed requests
5th percentile: 1.5826811790466309
10th percentile: 1.6158645153045654
20th percentile: 1.6822311878204346
30th percentile: 1.7414462566375732
40th percentile: 1.7935097217559814
50th percentile: 1.8455731868743896
60th percentile: 1.8599294185638429
70th percentile: 1.8742856502532959
80th percentile: 1.9944202899932861
90th percentile: 2.2203333377838135
95th percentile: 2.333289861679077
99th percentile: 2.423655080795288
mean time: 1.8876391410827638
Pipeline stage StressChecker completed in 10.71s
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 0.68s
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 0.66s
Shutdown handler de-registered
deeppin-red-paper-nemo-754_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 4649.08s
Shutdown handler de-registered
deeppin-red-paper-nemo-754_v1 status is now inactive due to auto deactivation removed underperforming models
deeppin-red-paper-nemo-754_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1