yamatazen-iris-light-12b

developer_uid: azuruce

submission_id: yamatazen-iris-light-12b_v1

model_name: yamatazen-iris-light-12b_v1

model_group: yamatazen/Iris-Light-12B

status: torndown

timestamp: 2025-02-27T00:40:58+00:00

num_battles: 5562

num_wins: 2801

celo_rating: 1258.47

family_friendly_score: 0.5611999999999999

family_friendly_standard_error: 0.0070178994008178825

submission_type: basic

model_repo: yamatazen/Iris-Light-12B

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5961290171851361, 'latency_mean': 1.6773772859573364, 'latency_p50': 1.6922731399536133, 'latency_p90': 1.835823392868042}, {'batch_size': 3, 'throughput': 1.0987203295662227, 'latency_mean': 2.717085009813309, 'latency_p50': 2.7198017835617065, 'latency_p90': 2.999700689315796}, {'batch_size': 5, 'throughput': 1.3270572420452447, 'latency_mean': 3.746566262245178, 'latency_p50': 3.748780608177185, 'latency_p90': 4.236909317970276}, {'batch_size': 6, 'throughput': 1.3929129346242335, 'latency_mean': 4.2819723844528195, 'latency_p50': 4.288096904754639, 'latency_p90': 4.774964451789856}, {'batch_size': 8, 'throughput': 1.464544911853348, 'latency_mean': 5.42536985039711, 'latency_p50': 5.451168179512024, 'latency_p90': 6.122270679473877}, {'batch_size': 10, 'throughput': 1.493060309962378, 'latency_mean': 6.635278332233429, 'latency_p50': 6.680665016174316, 'latency_p90': 7.459989213943482}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: yamatazen-iris-light-12b_v1

ineligible_reason: num_battles<10000

is_internal_developer: False

language_model: yamatazen/Iris-Light-12B

model_size: 13B

ranking_group: single

throughput_3p7s: 1.33

us_pacific_date: 2025-02-26

win_ratio: 0.5035958288385473

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['You:', '\n', '<|eot_id|>', 'User:', 'Bot:', 'Me:', '###', '</s>', '<|im_end|>', '####', '<|end_of_text|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', '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 yamatazen-iris-light-12b-v1-mkmlizer
Waiting for job on yamatazen-iris-light-12b-v1-mkmlizer to finish
Failed to get response for submission nischaydnk-mistral24bas_99124_v4: HTTPConnectionPool(host='nischaydnk-mistral24bas-99124-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
yamatazen-iris-light-12b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
yamatazen-iris-light-12b-v1-mkmlizer: ║     _____            __           __                                ║
yamatazen-iris-light-12b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
yamatazen-iris-light-12b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
yamatazen-iris-light-12b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
yamatazen-iris-light-12b-v1-mkmlizer: ║       /___/                                                         ║
yamatazen-iris-light-12b-v1-mkmlizer: ║                                                                     ║
yamatazen-iris-light-12b-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
yamatazen-iris-light-12b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
yamatazen-iris-light-12b-v1-mkmlizer: ║  https://mk1.ai                                                     ║
yamatazen-iris-light-12b-v1-mkmlizer: ║                                                                     ║
yamatazen-iris-light-12b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
yamatazen-iris-light-12b-v1-mkmlizer: ║  belonging to:                                                      ║
yamatazen-iris-light-12b-v1-mkmlizer: ║                                                                     ║
yamatazen-iris-light-12b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
yamatazen-iris-light-12b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
yamatazen-iris-light-12b-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
yamatazen-iris-light-12b-v1-mkmlizer: ║                                                                     ║
yamatazen-iris-light-12b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
yamatazen-iris-light-12b-v1-mkmlizer: Downloaded to shared memory in 49.552s
yamatazen-iris-light-12b-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2qc9zfx9, device:0
yamatazen-iris-light-12b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
yamatazen-iris-light-12b-v1-mkmlizer: quantized model in 38.605s
yamatazen-iris-light-12b-v1-mkmlizer: Processed model yamatazen/Iris-Light-12B in 88.157s
yamatazen-iris-light-12b-v1-mkmlizer: creating bucket guanaco-mkml-models
yamatazen-iris-light-12b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
yamatazen-iris-light-12b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/yamatazen-iris-light-12b-v1
yamatazen-iris-light-12b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/yamatazen-iris-light-12b-v1/config.json
yamatazen-iris-light-12b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/yamatazen-iris-light-12b-v1/special_tokens_map.json
yamatazen-iris-light-12b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/yamatazen-iris-light-12b-v1/tokenizer_config.json
yamatazen-iris-light-12b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/yamatazen-iris-light-12b-v1/tokenizer.json
yamatazen-iris-light-12b-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:35,  3.09s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:58,  1.20it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:11,  2.68it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:23,  4.17it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:43,  7.77it/s]
Loading 0:   7%|▋         | 27/363 [00:06<00:31, 10.65it/s]
Loading 0:   9%|▊         | 31/363 [00:06<00:25, 13.27it/s]
Loading 0:  10%|▉         | 35/363 [00:07<00:20, 15.87it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:20, 15.74it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:18, 17.02it/s]
Loading 0:  13%|█▎        | 47/363 [00:07<00:15, 20.50it/s]
Loading 0:  14%|█▍        | 51/363 [00:07<00:14, 21.74it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:11, 26.94it/s]
Loading 0:  17%|█▋        | 60/363 [00:08<00:11, 26.88it/s]
Loading 0:  18%|█▊        | 65/363 [00:08<00:09, 31.56it/s]
Loading 0:  19%|█▉        | 69/363 [00:08<00:09, 29.95it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:07, 37.37it/s]
Loading 0:  22%|██▏       | 81/363 [00:08<00:07, 36.36it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:07, 35.23it/s]
Loading 0:  25%|██▍       | 89/363 [00:08<00:08, 34.22it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:07, 36.94it/s]
Loading 0:  27%|██▋       | 98/363 [00:09<00:07, 35.19it/s]
Loading 0:  28%|██▊       | 103/363 [00:09<00:07, 36.68it/s]
Loading 0:  29%|██▉       | 107/363 [00:09<00:07, 34.74it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:06, 36.76it/s]
Loading 0:  32%|███▏      | 116/363 [00:09<00:07, 34.96it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:09, 25.15it/s]
Loading 0:  34%|███▍      | 124/363 [00:10<00:09, 24.98it/s]
Loading 0:  35%|███▌      | 128/363 [00:10<00:08, 27.35it/s]
Loading 0:  36%|███▋      | 132/363 [00:10<00:08, 27.16it/s]
Loading 0:  38%|███▊      | 139/363 [00:10<00:06, 34.95it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:06, 33.70it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:06, 35.27it/s]
Loading 0:  42%|████▏     | 152/363 [00:10<00:06, 34.30it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 37.00it/s]
Loading 0:  44%|████▍     | 161/363 [00:11<00:05, 35.58it/s]
Loading 0:  46%|████▌     | 166/363 [00:11<00:05, 37.04it/s]
Loading 0:  47%|████▋     | 170/363 [00:11<00:05, 35.67it/s]
Loading 0:  48%|████▊     | 175/363 [00:11<00:05, 37.23it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:05, 34.84it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:04, 36.44it/s]
Loading 0:  52%|█████▏    | 188/363 [00:11<00:05, 34.86it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:04, 36.76it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:04, 35.49it/s]
Loading 0:  56%|█████▌    | 202/363 [00:12<00:06, 25.67it/s]
Loading 0:  56%|█████▋    | 205/363 [00:12<00:06, 25.99it/s]
Loading 0:  58%|█████▊    | 211/363 [00:12<00:05, 29.95it/s]
Loading 0:  59%|█████▉    | 215/363 [00:12<00:04, 30.78it/s]
Loading 0:  61%|██████    | 220/363 [00:12<00:04, 34.36it/s]
Loading 0:  62%|██████▏   | 224/363 [00:12<00:04, 34.51it/s]
Loading 0:  63%|██████▎   | 229/363 [00:13<00:03, 37.89it/s]
Loading 0:  64%|██████▍   | 233/363 [00:13<00:03, 37.41it/s]
Loading 0:  66%|██████▌   | 238/363 [00:13<00:03, 40.32it/s]
Loading 0:  67%|██████▋   | 243/363 [00:13<00:02, 40.56it/s]
Loading 0:  68%|██████▊   | 248/363 [00:13<00:02, 40.16it/s]
Loading 0:  70%|██████▉   | 253/363 [00:13<00:02, 41.35it/s]
Loading 0:  71%|███████   | 258/363 [00:13<00:03, 34.52it/s]
Loading 0:  73%|███████▎  | 265/363 [00:13<00:02, 40.41it/s]
Loading 0:  74%|███████▍  | 270/363 [00:14<00:02, 40.70it/s]
Loading 0:  76%|███████▌  | 275/363 [00:14<00:02, 40.21it/s]
Loading 0:  77%|███████▋  | 280/363 [00:14<00:01, 41.66it/s]
Loading 0:  79%|███████▊  | 285/363 [00:14<00:03, 25.69it/s]
Loading 0:  80%|████████  | 292/363 [00:14<00:02, 32.38it/s]
Loading 0:  82%|████████▏ | 297/363 [00:14<00:01, 33.47it/s]
Loading 0:  83%|████████▎ | 301/363 [00:15<00:01, 34.80it/s]
Loading 0:  84%|████████▍ | 305/363 [00:15<00:01, 35.04it/s]
Loading 0:  85%|████████▌ | 310/363 [00:15<00:01, 36.33it/s]
Loading 0:  87%|████████▋ | 314/363 [00:15<00:01, 34.21it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:01, 36.90it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:01, 34.98it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:00, 36.61it/s]
Loading 0:  91%|█████████▏| 332/363 [00:15<00:00, 35.36it/s]
Loading 0:  93%|█████████▎| 337/363 [00:16<00:00, 37.94it/s]
Loading 0:  94%|█████████▍| 341/363 [00:16<00:00, 36.42it/s]
Loading 0:  95%|█████████▌| 346/363 [00:16<00:00, 38.64it/s]
Loading 0:  96%|█████████▋| 350/363 [00:16<00:00, 35.56it/s]
Loading 0:  98%|█████████▊| 355/363 [00:16<00:00, 37.64it/s]
Loading 0:  99%|█████████▉| 359/363 [00:16<00:00, 35.68it/s]
                                                            
Job yamatazen-iris-light-12b-v1-mkmlizer completed after 217.36s with status: succeeded
Stopping job with name yamatazen-iris-light-12b-v1-mkmlizer
Pipeline stage MKMLizer completed in 217.89s
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 yamatazen-iris-light-12b-v1
Waiting for inference service yamatazen-iris-light-12b-v1 to be ready
Failed to get response for submission nischaydnk-mistral24bas_99124_v4: HTTPConnectionPool(host='nischaydnk-mistral24bas-99124-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-mistral24bas_99124_v4: HTTPConnectionPool(host='nischaydnk-mistral24bas-99124-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service yamatazen-iris-light-12b-v1 ready after 271.5171070098877s
Pipeline stage MKMLDeployer completed in 272.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9994666576385498s
Received healthy response to inference request in 1.4643733501434326s
Received healthy response to inference request in 1.4133846759796143s
Received healthy response to inference request in 1.4310886859893799s
Received healthy response to inference request in 1.1198656558990479s
5 requests
0 failed requests
5th percentile: 1.178569459915161
10th percentile: 1.2372732639312745
20th percentile: 1.354680871963501
30th percentile: 1.4169254779815674
40th percentile: 1.4240070819854735
50th percentile: 1.4310886859893799
60th percentile: 1.444402551651001
70th percentile: 1.457716417312622
80th percentile: 1.5713920116424562
90th percentile: 1.785429334640503
95th percentile: 1.8924479961395262
99th percentile: 1.9780629253387452
mean time: 1.485635805130005
Pipeline stage StressChecker completed in 8.74s
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 0.76s
Shutdown handler de-registered
yamatazen-iris-light-12b_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 2436.35s
Shutdown handler de-registered
yamatazen-iris-light-12b_v1 status is now inactive due to auto deactivation removed underperforming models
yamatazen-iris-light-12b_v1 status is now torndown due to DeploymentManager action