leosheng-no-repeat-writ_60066

developer_uid: leosheng

submission_id: leosheng-no-repeat-writ_60066_v1

model_name: leosheng-no-repeat-writ_60066_v1

model_group: leosheng/no-repeat-write

status: torndown

timestamp: 2025-01-24T04:30:01+00:00

num_battles: 6355

num_wins: 2840

celo_rating: 1209.85

family_friendly_score: 0.5920000000000001

family_friendly_standard_error: 0.006950338121271511

submission_type: basic

model_repo: leosheng/no-repeat-write-reason

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

display_name: leosheng-no-repeat-writ_60066_v1

is_internal_developer: False

language_model: leosheng/no-repeat-write-reason

model_size: 8B

ranking_group: single

us_pacific_date: 2025-01-23

win_ratio: 0.44689221085759245

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 leosheng-no-repeat-writ-60066-v1-mkmlizer
Waiting for job on leosheng-no-repeat-writ-60066-v1-mkmlizer to finish
leosheng-no-repeat-writ-60066-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
leosheng-no-repeat-writ-60066-v1-mkmlizer: ║     _____            __           __                                ║
leosheng-no-repeat-writ-60066-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
leosheng-no-repeat-writ-60066-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
leosheng-no-repeat-writ-60066-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
leosheng-no-repeat-writ-60066-v1-mkmlizer: ║       /___/                                                         ║
leosheng-no-repeat-writ-60066-v1-mkmlizer: ║                                                                     ║
leosheng-no-repeat-writ-60066-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
leosheng-no-repeat-writ-60066-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
leosheng-no-repeat-writ-60066-v1-mkmlizer: ║  https://mk1.ai                                                     ║
leosheng-no-repeat-writ-60066-v1-mkmlizer: ║                                                                     ║
leosheng-no-repeat-writ-60066-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
leosheng-no-repeat-writ-60066-v1-mkmlizer: ║  belonging to:                                                      ║
leosheng-no-repeat-writ-60066-v1-mkmlizer: ║                                                                     ║
leosheng-no-repeat-writ-60066-v1-mkmlizer: ║  Chai Research Corp.                                                ║
leosheng-no-repeat-writ-60066-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
leosheng-no-repeat-writ-60066-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
leosheng-no-repeat-writ-60066-v1-mkmlizer: ║                                                                     ║
leosheng-no-repeat-writ-60066-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
leosheng-no-repeat-writ-60066-v1-mkmlizer: Downloaded to shared memory in 33.958s
leosheng-no-repeat-writ-60066-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpo5c78b9h, device:0
leosheng-no-repeat-writ-60066-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
leosheng-no-repeat-writ-60066-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.
leosheng-no-repeat-writ-60066-v1-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
leosheng-no-repeat-writ-60066-v1-mkmlizer: creating bucket guanaco-mkml-models
leosheng-no-repeat-writ-60066-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
leosheng-no-repeat-writ-60066-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/leosheng-no-repeat-writ-60066-v1
leosheng-no-repeat-writ-60066-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/leosheng-no-repeat-writ-60066-v1/config.json
leosheng-no-repeat-writ-60066-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/leosheng-no-repeat-writ-60066-v1/special_tokens_map.json
leosheng-no-repeat-writ-60066-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/leosheng-no-repeat-writ-60066-v1/tokenizer_config.json
leosheng-no-repeat-writ-60066-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/leosheng-no-repeat-writ-60066-v1/tokenizer.json
leosheng-no-repeat-writ-60066-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/leosheng-no-repeat-writ-60066-v1/flywheel_model.0.safetensors
leosheng-no-repeat-writ-60066-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 38.13it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 56.09it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:04, 58.55it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:04, 62.35it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 63.89it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 64.19it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 64.81it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:03, 64.95it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 63.69it/s]
Loading 0:  29%|██▊       | 83/291 [00:02<00:11, 18.15it/s]
Loading 0:  30%|███       | 88/291 [00:02<00:10, 19.37it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:07, 24.72it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:06, 30.14it/s]
Loading 0:  40%|███▉      | 115/291 [00:03<00:05, 34.89it/s]
Loading 0:  43%|████▎     | 124/291 [00:03<00:04, 38.84it/s]
Loading 0:  46%|████▌     | 133/291 [00:03<00:03, 42.10it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:03, 48.54it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 46.04it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 47.17it/s]
Loading 0:  57%|█████▋    | 166/291 [00:04<00:02, 47.49it/s]
Loading 0:  60%|██████    | 175/291 [00:04<00:02, 47.70it/s]
Loading 0:  63%|██████▎   | 184/291 [00:04<00:02, 48.47it/s]
Loading 0:  65%|██████▌   | 190/291 [00:05<00:06, 16.23it/s]
Loading 0:  67%|██████▋   | 196/291 [00:05<00:05, 18.54it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:03, 23.92it/s]
Loading 0:  73%|███████▎  | 211/291 [00:06<00:02, 28.05it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:02, 33.18it/s]
Loading 0:  79%|███████▊  | 229/291 [00:06<00:01, 36.85it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:01, 40.51it/s]
Loading 0:  85%|████████▍ | 247/291 [00:06<00:00, 44.59it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 48.61it/s]
Loading 0:  91%|█████████ | 265/291 [00:07<00:00, 51.04it/s]
Loading 0:  94%|█████████▍| 274/291 [00:07<00:00, 52.39it/s]
Loading 0:  97%|█████████▋| 283/291 [00:07<00:00, 54.83it/s]
Loading 0:  99%|█████████▉| 289/291 [00:07<00:00, 32.37it/s]
                                                            
Job leosheng-no-repeat-writ-60066-v1-mkmlizer completed after 94.32s with status: succeeded
Stopping job with name leosheng-no-repeat-writ-60066-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.82s
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 leosheng-no-repeat-writ-60066-v1
Waiting for inference service leosheng-no-repeat-writ-60066-v1 to be ready
Failed to get response for submission doctor-shotgun-l3-3-70b_70691_v2: HTTPConnectionPool(host='doctor-shotgun-l3-3-70b-70691-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission doctor-shotgun-l3-3-70b_70691_v2: HTTPConnectionPool(host='doctor-shotgun-l3-3-70b-70691-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Tearing down inference service leosheng-no-repeat-writ-60066-v1
%s, retrying in %s seconds...
Creating inference service leosheng-no-repeat-writ-60066-v1
Waiting for inference service leosheng-no-repeat-writ-60066-v1 to be ready
Failed to get response for submission doctor-shotgun-l3-3-70b_70691_v2: HTTPConnectionPool(host='doctor-shotgun-l3-3-70b-70691-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service leosheng-no-repeat-writ-60066-v1 ready after 80.61005353927612s
Pipeline stage MKMLDeployer completed in 684.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5840873718261719s
Received healthy response to inference request in 1.2008113861083984s
Received healthy response to inference request in 1.2684147357940674s
Received healthy response to inference request in 1.2925357818603516s
Received healthy response to inference request in 1.0679032802581787s
5 requests
0 failed requests
5th percentile: 1.0944849014282227
10th percentile: 1.1210665225982666
20th percentile: 1.1742297649383544
30th percentile: 1.2143320560455322
40th percentile: 1.2413733959198
50th percentile: 1.2684147357940674
60th percentile: 1.2780631542205811
70th percentile: 1.2877115726470947
80th percentile: 1.3508460998535157
90th percentile: 1.4674667358398437
95th percentile: 1.5257770538330078
99th percentile: 1.572425308227539
mean time: 1.2827505111694335
Pipeline stage StressChecker completed in 7.68s
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 0.98s
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 0.77s
Shutdown handler de-registered
leosheng-no-repeat-writ_60066_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 2720.78s
Shutdown handler de-registered
leosheng-no-repeat-writ_60066_v1 status is now inactive due to auto deactivation removed underperforming models
leosheng-no-repeat-writ_60066_v1 status is now torndown due to DeploymentManager action