stark2000s-llama-3-test

developer_uid: stark2000s

submission_id: stark2000s-llama-3-test_v2

model_name: stark2000s-llama-3-test_v2

model_group: stark2000s/llama-3_test

status: torndown

timestamp: 2025-01-25T07:31:29+00:00

num_battles: 12724

num_wins: 5126

celo_rating: 1200.8

family_friendly_score: 0.5913999999999999

family_friendly_standard_error: 0.006951921173316049

submission_type: basic

model_repo: stark2000s/llama-3_test

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

display_name: stark2000s-llama-3-test_v2

is_internal_developer: False

language_model: stark2000s/llama-3_test

model_size: 8B

ranking_group: single

us_pacific_date: 2025-01-24

win_ratio: 0.4028607356177303

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, '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': "{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': False}

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 stark2000s-llama-3-test-v2-mkmlizer
Waiting for job on stark2000s-llama-3-test-v2-mkmlizer to finish
stark2000s-llama-3-test-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
stark2000s-llama-3-test-v2-mkmlizer: ║     _____            __           __                                ║
stark2000s-llama-3-test-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
stark2000s-llama-3-test-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
stark2000s-llama-3-test-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
stark2000s-llama-3-test-v2-mkmlizer: ║       /___/                                                         ║
stark2000s-llama-3-test-v2-mkmlizer: ║                                                                     ║
stark2000s-llama-3-test-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
stark2000s-llama-3-test-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
stark2000s-llama-3-test-v2-mkmlizer: ║  https://mk1.ai                                                     ║
stark2000s-llama-3-test-v2-mkmlizer: ║                                                                     ║
stark2000s-llama-3-test-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
stark2000s-llama-3-test-v2-mkmlizer: ║  belonging to:                                                      ║
stark2000s-llama-3-test-v2-mkmlizer: ║                                                                     ║
stark2000s-llama-3-test-v2-mkmlizer: ║  Chai Research Corp.                                                ║
stark2000s-llama-3-test-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
stark2000s-llama-3-test-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
stark2000s-llama-3-test-v2-mkmlizer: ║                                                                     ║
stark2000s-llama-3-test-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
stark2000s-llama-3-test-v2-mkmlizer: Downloaded to shared memory in 33.100s
stark2000s-llama-3-test-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpowe19b9k, device:0
stark2000s-llama-3-test-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
stark2000s-llama-3-test-v2-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.
stark2000s-llama-3-test-v2-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
stark2000s-llama-3-test-v2-mkmlizer: quantized model in 25.893s
stark2000s-llama-3-test-v2-mkmlizer: Processed model stark2000s/llama-3_test in 58.993s
stark2000s-llama-3-test-v2-mkmlizer: creating bucket guanaco-mkml-models
stark2000s-llama-3-test-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
stark2000s-llama-3-test-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/stark2000s-llama-3-test-v2
stark2000s-llama-3-test-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/stark2000s-llama-3-test-v2/config.json
stark2000s-llama-3-test-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/stark2000s-llama-3-test-v2/special_tokens_map.json
stark2000s-llama-3-test-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/stark2000s-llama-3-test-v2/tokenizer_config.json
stark2000s-llama-3-test-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/stark2000s-llama-3-test-v2/tokenizer.json
stark2000s-llama-3-test-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/stark2000s-llama-3-test-v2/flywheel_model.0.safetensors
stark2000s-llama-3-test-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 54.07it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:03, 77.99it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 85.95it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 85.27it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 78.09it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:02, 78.99it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 82.14it/s]
Loading 0:  26%|██▋       | 77/291 [00:00<00:02, 87.26it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:09, 20.89it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:07, 25.71it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 32.93it/s]
Loading 0:  39%|███▉      | 114/291 [00:02<00:04, 43.46it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 50.43it/s]
Loading 0:  45%|████▌     | 132/291 [00:02<00:02, 55.68it/s]
Loading 0:  48%|████▊     | 141/291 [00:02<00:02, 62.16it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:02, 64.00it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:01, 68.65it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 68.77it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 73.91it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:04, 21.21it/s]
Loading 0:  68%|██████▊   | 197/291 [00:04<00:03, 28.31it/s]
Loading 0:  71%|███████   | 206/291 [00:04<00:02, 34.89it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:01, 40.77it/s]
Loading 0:  77%|███████▋  | 223/291 [00:04<00:01, 48.48it/s]
Loading 0:  80%|███████▉  | 232/291 [00:04<00:01, 56.32it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 63.34it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 69.43it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 71.94it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 76.31it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 79.79it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 82.17it/s]
                                                            
Job stark2000s-llama-3-test-v2-mkmlizer completed after 84.15s with status: succeeded
Stopping job with name stark2000s-llama-3-test-v2-mkmlizer
Pipeline stage MKMLizer completed in 84.64s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service stark2000s-llama-3-test-v2
Waiting for inference service stark2000s-llama-3-test-v2 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service stark2000s-llama-3-test-v2 ready after 181.11776685714722s
Pipeline stage MKMLDeployer completed in 182.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6001183986663818s
Received healthy response to inference request in 1.326826810836792s
Received healthy response to inference request in 1.3057971000671387s
Received healthy response to inference request in 1.1619668006896973s
Received healthy response to inference request in 1.568098783493042s
5 requests
0 failed requests
5th percentile: 1.1907328605651855
10th percentile: 1.2194989204406739
20th percentile: 1.2770310401916505
30th percentile: 1.3100030422210693
40th percentile: 1.3184149265289307
50th percentile: 1.326826810836792
60th percentile: 1.423335599899292
70th percentile: 1.5198443889617919
80th percentile: 1.57450270652771
90th percentile: 1.587310552597046
95th percentile: 1.5937144756317139
99th percentile: 1.5988376140594482
mean time: 1.3925615787506103
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 0.78s
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 0.61s
Shutdown handler de-registered
stark2000s-llama-3-test_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.08s
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 stark2000s-llama-3-test-v2-profiler
Waiting for inference service stark2000s-llama-3-test-v2-profiler to be ready
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 2956.08s
Shutdown handler de-registered
stark2000s-llama-3-test_v2 status is now inactive due to auto deactivation removed underperforming models
stark2000s-llama-3-test_v2 status is now torndown due to DeploymentManager action