teknium-airoboros-mistr_79536

developer_uid: huohuo12

submission_id: teknium-airoboros-mistr_79536_v1

model_name: teknium-airoboros-mistr_79536_v1

model_group: teknium/airoboros-mistra

status: torndown

timestamp: 2025-02-18T03:35:49+00:00

num_battles: 5636

num_wins: 2489

celo_rating: 1201.77

family_friendly_score: 0.5860000000000001

family_friendly_standard_error: 0.006965687331484238

submission_type: basic

model_repo: teknium/airoboros-mistral2.2-7b

model_architecture: MistralForCausalLM

model_num_parameters: 7241732096.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

display_name: teknium-airoboros-mistr_79536_v1

is_internal_developer: False

language_model: teknium/airoboros-mistral2.2-7b

model_size: 7B

ranking_group: single

us_pacific_date: 2025-02-17

win_ratio: 0.44162526614620295

generation_params: {'temperature': 0.7, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.6, 'frequency_penalty': 0.3, '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 teknium-airoboros-mistr-79536-v1-mkmlizer
Waiting for job on teknium-airoboros-mistr-79536-v1-mkmlizer to finish
teknium-airoboros-mistr-79536-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
teknium-airoboros-mistr-79536-v1-mkmlizer: ║     _____            __           __                                ║
teknium-airoboros-mistr-79536-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
teknium-airoboros-mistr-79536-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
teknium-airoboros-mistr-79536-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
teknium-airoboros-mistr-79536-v1-mkmlizer: ║       /___/                                                         ║
teknium-airoboros-mistr-79536-v1-mkmlizer: ║                                                                     ║
teknium-airoboros-mistr-79536-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
teknium-airoboros-mistr-79536-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
teknium-airoboros-mistr-79536-v1-mkmlizer: ║  https://mk1.ai                                                     ║
teknium-airoboros-mistr-79536-v1-mkmlizer: ║                                                                     ║
teknium-airoboros-mistr-79536-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
teknium-airoboros-mistr-79536-v1-mkmlizer: ║  belonging to:                                                      ║
teknium-airoboros-mistr-79536-v1-mkmlizer: ║                                                                     ║
teknium-airoboros-mistr-79536-v1-mkmlizer: ║  Chai Research Corp.                                                ║
teknium-airoboros-mistr-79536-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
teknium-airoboros-mistr-79536-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
teknium-airoboros-mistr-79536-v1-mkmlizer: ║                                                                     ║
teknium-airoboros-mistr-79536-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
teknium-airoboros-mistr-79536-v1-mkmlizer: Downloaded to shared memory in 26.106s
teknium-airoboros-mistr-79536-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpf5ihlud8, device:0
teknium-airoboros-mistr-79536-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
teknium-airoboros-mistr-79536-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.
teknium-airoboros-mistr-79536-v1-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
teknium-airoboros-mistr-79536-v1-mkmlizer: quantized model in 19.738s
teknium-airoboros-mistr-79536-v1-mkmlizer: Processed model teknium/airoboros-mistral2.2-7b in 45.845s
teknium-airoboros-mistr-79536-v1-mkmlizer: creating bucket guanaco-mkml-models
teknium-airoboros-mistr-79536-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
teknium-airoboros-mistr-79536-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/teknium-airoboros-mistr-79536-v1
teknium-airoboros-mistr-79536-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/teknium-airoboros-mistr-79536-v1/config.json
teknium-airoboros-mistr-79536-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/teknium-airoboros-mistr-79536-v1/tokenizer_config.json
teknium-airoboros-mistr-79536-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/teknium-airoboros-mistr-79536-v1/special_tokens_map.json
teknium-airoboros-mistr-79536-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/teknium-airoboros-mistr-79536-v1/tokenizer.model
teknium-airoboros-mistr-79536-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/teknium-airoboros-mistr-79536-v1/tokenizer.json
teknium-airoboros-mistr-79536-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/teknium-airoboros-mistr-79536-v1/flywheel_model.0.safetensors
teknium-airoboros-mistr-79536-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:08, 33.13it/s]
Loading 0:   5%|▌         | 15/291 [00:00<00:03, 74.55it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 71.67it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 65.50it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:04, 60.45it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 62.51it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:03, 60.37it/s]
Loading 0:  24%|██▍       | 70/291 [00:01<00:03, 57.96it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:03, 55.98it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:03, 53.42it/s]
Loading 0:  33%|███▎      | 97/291 [00:01<00:03, 52.30it/s]
Loading 0:  36%|███▋      | 106/291 [00:01<00:03, 54.99it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 54.50it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 53.71it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 50.97it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 50.31it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:02, 50.88it/s]
Loading 0:  55%|█████▍    | 160/291 [00:02<00:02, 52.02it/s]
Loading 0:  58%|█████▊    | 168/291 [00:02<00:02, 57.49it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 52.76it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:02, 52.39it/s]
Loading 0:  66%|██████▋   | 193/291 [00:03<00:01, 52.69it/s]
Loading 0:  69%|██████▉   | 202/291 [00:03<00:01, 53.06it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:05, 15.87it/s]
Loading 0:  74%|███████▎  | 214/291 [00:05<00:04, 18.21it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:02, 23.11it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:02, 28.09it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 32.74it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:01, 36.69it/s]
Loading 0:  89%|████████▉ | 259/291 [00:06<00:00, 39.98it/s]
Loading 0:  92%|█████████▏| 268/291 [00:06<00:00, 42.96it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 45.61it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 47.16it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 15.39it/s]
                                                            
Job teknium-airoboros-mistr-79536-v1-mkmlizer completed after 73.7s with status: succeeded
Stopping job with name teknium-airoboros-mistr-79536-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.18s
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 teknium-airoboros-mistr-79536-v1
Waiting for inference service teknium-airoboros-mistr-79536-v1 to be ready
Inference service teknium-airoboros-mistr-79536-v1 ready after 220.72392630577087s
Pipeline stage MKMLDeployer completed in 221.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1034460067749023s
Received healthy response to inference request in 1.3161427974700928s
Received healthy response to inference request in 1.218186378479004s
Received healthy response to inference request in 1.2666621208190918s
Received healthy response to inference request in 1.061492919921875s
5 requests
0 failed requests
5th percentile: 1.0928316116333008
10th percentile: 1.1241703033447266
20th percentile: 1.1868476867675781
30th percentile: 1.2278815269470216
40th percentile: 1.2472718238830567
50th percentile: 1.2666621208190918
60th percentile: 1.2864543914794921
70th percentile: 1.3062466621398925
80th percentile: 1.4736034393310549
90th percentile: 1.7885247230529786
95th percentile: 1.9459853649139403
99th percentile: 2.07195387840271
mean time: 1.3931860446929931
Pipeline stage StressChecker completed in 8.21s
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 0.65s
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 0.65s
Shutdown handler de-registered
teknium-airoboros-mistr_79536_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 2629.20s
Shutdown handler de-registered
teknium-airoboros-mistr_79536_v1 status is now inactive due to auto deactivation removed underperforming models
teknium-airoboros-mistr_79536_v1 status is now torndown due to DeploymentManager action
teknium-airoboros-mistr_79536_v1 status is now torndown due to DeploymentManager action
teknium-airoboros-mistr_79536_v1 status is now torndown due to DeploymentManager action