developer_uid: deeppin
submission_id: deeppin-red-paper-v14-3530_v1
model_name: deeppin-red-paper-v14-3530_v1
model_group: deeppin/red-paper-v14-35
status: torndown
timestamp: 2025-02-07T15:21:16+00:00
num_battles: 6629
num_wins: 2965
celo_rating: 1230.9
family_friendly_score: 0.5456
family_friendly_standard_error: 0.007041599818223129
submission_type: basic
model_repo: deeppin/red-paper-v14-3530
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-v14-3530_v1
is_internal_developer: False
language_model: deeppin/red-paper-v14-3530
model_size: 8B
ranking_group: single
us_pacific_date: 2025-02-07
win_ratio: 0.447277115703726
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', '<|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-v14-3530-v1-mkmlizer
Waiting for job on deeppin-red-paper-v14-3530-v1-mkmlizer to finish
deeppin-red-paper-v14-3530-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
deeppin-red-paper-v14-3530-v1-mkmlizer: ║ _____ __ __ ║
deeppin-red-paper-v14-3530-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
deeppin-red-paper-v14-3530-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
deeppin-red-paper-v14-3530-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
deeppin-red-paper-v14-3530-v1-mkmlizer: ║ /___/ ║
deeppin-red-paper-v14-3530-v1-mkmlizer: ║ ║
deeppin-red-paper-v14-3530-v1-mkmlizer: ║ Version: 0.11.12 ║
deeppin-red-paper-v14-3530-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
deeppin-red-paper-v14-3530-v1-mkmlizer: ║ https://mk1.ai ║
deeppin-red-paper-v14-3530-v1-mkmlizer: ║ ║
deeppin-red-paper-v14-3530-v1-mkmlizer: ║ The license key for the current software has been verified as ║
deeppin-red-paper-v14-3530-v1-mkmlizer: ║ belonging to: ║
deeppin-red-paper-v14-3530-v1-mkmlizer: ║ ║
deeppin-red-paper-v14-3530-v1-mkmlizer: ║ Chai Research Corp. ║
deeppin-red-paper-v14-3530-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
deeppin-red-paper-v14-3530-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
deeppin-red-paper-v14-3530-v1-mkmlizer: ║ ║
deeppin-red-paper-v14-3530-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
deeppin-red-paper-v14-3530-v1-mkmlizer: Downloaded to shared memory in 35.089s
deeppin-red-paper-v14-3530-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnpxmf5cb, device:0
deeppin-red-paper-v14-3530-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
deeppin-red-paper-v14-3530-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-v14-3530-v1-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
deeppin-red-paper-v14-3530-v1-mkmlizer: quantized model in 25.197s
deeppin-red-paper-v14-3530-v1-mkmlizer: Processed model deeppin/red-paper-v14-3530 in 60.287s
deeppin-red-paper-v14-3530-v1-mkmlizer: creating bucket guanaco-mkml-models
deeppin-red-paper-v14-3530-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/deeppin-red-paper-v14-3530-v1/config.json
deeppin-red-paper-v14-3530-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/deeppin-red-paper-v14-3530-v1/special_tokens_map.json
deeppin-red-paper-v14-3530-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/deeppin-red-paper-v14-3530-v1/tokenizer_config.json
deeppin-red-paper-v14-3530-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/deeppin-red-paper-v14-3530-v1/tokenizer.json
deeppin-red-paper-v14-3530-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/deeppin-red-paper-v14-3530-v1/flywheel_model.0.safetensors
deeppin-red-paper-v14-3530-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:07, 37.96it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:03, 69.20it/s] Loading 0: 11%|█ | 31/291 [00:00<00:02, 90.54it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:02, 90.88it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 96.27it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 94.28it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:07, 28.93it/s] Loading 0: 31%|███ | 90/291 [00:01<00:06, 32.21it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:04, 41.80it/s] Loading 0: 40%|███▉ | 115/291 [00:02<00:03, 50.42it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:02, 63.11it/s] Loading 0: 48%|████▊ | 141/291 [00:02<00:02, 71.44it/s] Loading 0: 52%|█████▏ | 151/291 [00:02<00:02, 68.41it/s] Loading 0: 55%|█████▍ | 160/291 [00:02<00:01, 71.66it/s] Loading 0: 58%|█████▊ | 170/291 [00:02<00:01, 77.85it/s] Loading 0: 63%|██████▎ | 184/291 [00:02<00:01, 85.04it/s] Loading 0: 67%|██████▋ | 194/291 [00:04<00:03, 25.03it/s] Loading 0: 70%|███████ | 205/291 [00:04<00:02, 31.62it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 42.98it/s] Loading 0: 79%|███████▉ | 230/291 [00:04<00:01, 50.42it/s] Loading 0: 83%|████████▎ | 241/291 [00:04<00:00, 56.62it/s] Loading 0: 88%|████████▊ | 256/291 [00:04<00:00, 68.90it/s] Loading 0: 92%|█████████▏| 268/291 [00:04<00:00, 71.27it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 74.07it/s] Loading 0: 99%|█████████▊| 287/291 [00:05<00:00, 46.17it/s]
Job deeppin-red-paper-v14-3530-v1-mkmlizer completed after 206.57s with status: succeeded
Stopping job with name deeppin-red-paper-v14-3530-v1-mkmlizer
Pipeline stage MKMLizer completed in 207.04s
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-v14-3530-v1
Waiting for inference service deeppin-red-paper-v14-3530-v1 to be ready
Inference service deeppin-red-paper-v14-3530-v1 ready after 180.59648156166077s
Pipeline stage MKMLDeployer completed in 181.10s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6980361938476562s
Received healthy response to inference request in 1.2553443908691406s
Received healthy response to inference request in 1.4000225067138672s
Received healthy response to inference request in 1.3435027599334717s
Received healthy response to inference request in 1.2711498737335205s
5 requests
0 failed requests
5th percentile: 1.2585054874420165
10th percentile: 1.2616665840148926
20th percentile: 1.2679887771606446
30th percentile: 1.2856204509735107
40th percentile: 1.3145616054534912
50th percentile: 1.3435027599334717
60th percentile: 1.36611065864563
70th percentile: 1.388718557357788
80th percentile: 1.459625244140625
90th percentile: 1.5788307189941406
95th percentile: 1.6384334564208984
99th percentile: 1.6861156463623046
mean time: 1.3936111450195312
Pipeline stage StressChecker completed in 8.20s
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 0.69s
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-v14-3530_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...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service deeppin-red-paper-v14-3530-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.21s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service deeppin-red-paper-v14-3530-v1-profiler
Waiting for inference service deeppin-red-paper-v14-3530-v1-profiler to be ready
Inference service deeppin-red-paper-v14-3530-v1-profiler ready after 100.40201473236084s
Pipeline stage MKMLProfilerDeployer completed in 100.70s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/deeppin-red-paper-v1bd37c139832efbac2d1b02796b05fee6-deplombfmx:/code/chaiverse_profiler_1738942463 --namespace tenant-chaiml-guanaco
kubectl exec -it deeppin-red-paper-v1bd37c139832efbac2d1b02796b05fee6-deplombfmx --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1738942463 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1738942463/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/deeppin-red-paper-v1bd37c139832efbac2d1b02796b05fee6-deplombfmx:/code/chaiverse_profiler_1738942468 --namespace tenant-chaiml-guanaco
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 1965.95s
Shutdown handler de-registered
deeppin-red-paper-v14-3530_v1 status is now inactive due to auto deactivation removed underperforming models
deeppin-red-paper-v14-3530_v1 status is now torndown due to DeploymentManager action