developer_uid: deeppin
submission_id: deeppin-red-paper-v8-159_v1
model_name: deeppin-red-paper-v8-159_v1
model_group: deeppin/red-paper-v8-159
status: torndown
timestamp: 2025-01-24T06:48:05+00:00
num_battles: 5702
num_wins: 2466
celo_rating: 1220.47
family_friendly_score: 0.5942000000000001
family_friendly_standard_error: 0.006944441806221721
submission_type: basic
model_repo: deeppin/red-paper-v8-159
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: deeppin-red-paper-v8-159_v1
is_internal_developer: False
language_model: deeppin/red-paper-v8-159
model_size: 8B
ranking_group: single
us_pacific_date: 2025-01-23
win_ratio: 0.43247983163802173
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-v8-159-v1-mkmlizer
Waiting for job on deeppin-red-paper-v8-159-v1-mkmlizer to finish
deeppin-red-paper-v8-159-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
deeppin-red-paper-v8-159-v1-mkmlizer: ║ _____ __ __ ║
deeppin-red-paper-v8-159-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
deeppin-red-paper-v8-159-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
deeppin-red-paper-v8-159-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
deeppin-red-paper-v8-159-v1-mkmlizer: ║ /___/ ║
deeppin-red-paper-v8-159-v1-mkmlizer: ║ ║
deeppin-red-paper-v8-159-v1-mkmlizer: ║ Version: 0.11.12 ║
deeppin-red-paper-v8-159-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
deeppin-red-paper-v8-159-v1-mkmlizer: ║ https://mk1.ai ║
deeppin-red-paper-v8-159-v1-mkmlizer: ║ ║
deeppin-red-paper-v8-159-v1-mkmlizer: ║ The license key for the current software has been verified as ║
deeppin-red-paper-v8-159-v1-mkmlizer: ║ belonging to: ║
deeppin-red-paper-v8-159-v1-mkmlizer: ║ ║
deeppin-red-paper-v8-159-v1-mkmlizer: ║ Chai Research Corp. ║
deeppin-red-paper-v8-159-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
deeppin-red-paper-v8-159-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
deeppin-red-paper-v8-159-v1-mkmlizer: ║ ║
deeppin-red-paper-v8-159-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
deeppin-red-paper-v8-159-v1-mkmlizer: Downloaded to shared memory in 32.968s
deeppin-red-paper-v8-159-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpklo4nwdj, device:0
deeppin-red-paper-v8-159-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
deeppin-red-paper-v8-159-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-v8-159-v1-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
deeppin-red-paper-v8-159-v1-mkmlizer: quantized model in 25.402s
deeppin-red-paper-v8-159-v1-mkmlizer: Processed model deeppin/red-paper-v8-159 in 58.370s
deeppin-red-paper-v8-159-v1-mkmlizer: creating bucket guanaco-mkml-models
deeppin-red-paper-v8-159-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
deeppin-red-paper-v8-159-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/deeppin-red-paper-v8-159-v1
deeppin-red-paper-v8-159-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/deeppin-red-paper-v8-159-v1/config.json
deeppin-red-paper-v8-159-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/deeppin-red-paper-v8-159-v1/special_tokens_map.json
deeppin-red-paper-v8-159-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/deeppin-red-paper-v8-159-v1/tokenizer_config.json
deeppin-red-paper-v8-159-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/deeppin-red-paper-v8-159-v1/tokenizer.json
deeppin-red-paper-v8-159-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/deeppin-red-paper-v8-159-v1/flywheel_model.0.safetensors
deeppin-red-paper-v8-159-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:08, 34.64it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 64.50it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:03, 74.07it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:03, 78.54it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:03, 81.06it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 90.42it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 87.65it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:02, 90.65it/s] Loading 0: 31%|███ | 90/291 [00:02<00:08, 24.45it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:05, 32.27it/s] Loading 0: 40%|███▉ | 115/291 [00:02<00:04, 40.11it/s] Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 46.68it/s] Loading 0: 46%|████▌ | 133/291 [00:02<00:02, 53.20it/s] Loading 0: 49%|████▉ | 142/291 [00:02<00:02, 57.01it/s] Loading 0: 52%|█████▏ | 151/291 [00:02<00:02, 63.49it/s] Loading 0: 55%|█████▌ | 161/291 [00:02<00:01, 71.46it/s] Loading 0: 58%|█████▊ | 170/291 [00:03<00:01, 75.87it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 83.26it/s] Loading 0: 67%|██████▋ | 194/291 [00:04<00:03, 25.28it/s] Loading 0: 70%|███████ | 205/291 [00:04<00:02, 31.82it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 42.97it/s] Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 48.64it/s] Loading 0: 83%|████████▎ | 241/291 [00:04<00:00, 56.09it/s] Loading 0: 88%|████████▊ | 256/291 [00:04<00:00, 67.50it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 71.16it/s] Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 70.94it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 72.44it/s]
Job deeppin-red-paper-v8-159-v1-mkmlizer completed after 84.04s with status: succeeded
Stopping job with name deeppin-red-paper-v8-159-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.47s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service deeppin-red-paper-v8-159-v1
Waiting for inference service deeppin-red-paper-v8-159-v1 to be ready
Inference service deeppin-red-paper-v8-159-v1 ready after 160.5616159439087s
Pipeline stage MKMLDeployer completed in 161.10s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5594699382781982s
Received healthy response to inference request in 1.1288347244262695s
Received healthy response to inference request in 1.2241783142089844s
Received healthy response to inference request in 1.4299073219299316s
Received healthy response to inference request in 1.2101764678955078s
5 requests
0 failed requests
5th percentile: 1.1451030731201173
10th percentile: 1.1613714218139648
20th percentile: 1.19390811920166
30th percentile: 1.212976837158203
40th percentile: 1.2185775756835937
50th percentile: 1.2241783142089844
60th percentile: 1.3064699172973633
70th percentile: 1.3887615203857422
80th percentile: 1.455819845199585
90th percentile: 1.5076448917388916
95th percentile: 1.533557415008545
99th percentile: 1.5542874336242676
mean time: 1.3105133533477784
Pipeline stage StressChecker completed in 7.93s
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 0.62s
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 0.64s
Shutdown handler de-registered
deeppin-red-paper-v8-159_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 2884.82s
Shutdown handler de-registered
deeppin-red-paper-v8-159_v1 status is now inactive due to auto deactivation removed underperforming models
deeppin-red-paper-v8-159_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1