developer_uid: azuruce
submission_id: yamatazen-iris-sce-12b_v1
model_name: yamatazen-iris-sce-12b_v1
model_group: yamatazen/Iris-SCE-12B
status: torndown
timestamp: 2025-02-27T00:41:49+00:00
num_battles: 5397
num_wins: 2772
celo_rating: 1264.32
family_friendly_score: 0.5624
family_friendly_standard_error: 0.007015785629564233
submission_type: basic
model_repo: yamatazen/Iris-SCE-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': 0.6041044884904846, 'latency_mean': 1.655238060951233, 'latency_p50': 1.667635202407837, 'latency_p90': 1.8219892740249635}, {'batch_size': 3, 'throughput': 1.1128707321548947, 'latency_mean': 2.6920562636852265, 'latency_p50': 2.693146586418152, 'latency_p90': 2.9839987754821777}, {'batch_size': 5, 'throughput': 1.3399883736160052, 'latency_mean': 3.7150255811214445, 'latency_p50': 3.7193284034729004, 'latency_p90': 4.0958823442459105}, {'batch_size': 6, 'throughput': 1.4109491707534538, 'latency_mean': 4.223542122840882, 'latency_p50': 4.224519610404968, 'latency_p90': 4.7122029781341555}, {'batch_size': 8, 'throughput': 1.4739249818758846, 'latency_mean': 5.394288319349289, 'latency_p50': 5.428875684738159, 'latency_p90': 6.135828137397766}, {'batch_size': 10, 'throughput': 1.5049075167435961, 'latency_mean': 6.586905716657639, 'latency_p50': 6.67380428314209, 'latency_p90': 7.314644479751587}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: yamatazen-iris-sce-12b_v1
is_internal_developer: False
language_model: yamatazen/Iris-SCE-12B
model_size: 13B
ranking_group: single
throughput_3p7s: 1.34
us_pacific_date: 2025-02-26
win_ratio: 0.5136186770428015
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': ['Bot:', '####', '<|end_of_text|>', '###', '<|im_end|>', '<|eot_id|>', 'Me:', '</s>', 'You:', '\n', 'User:'], '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-sce-12b-v1-mkmlizer
Waiting for job on yamatazen-iris-sce-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-sce-12b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
yamatazen-iris-sce-12b-v1-mkmlizer: ║     _____            __           __                                ║
yamatazen-iris-sce-12b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
yamatazen-iris-sce-12b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
yamatazen-iris-sce-12b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
yamatazen-iris-sce-12b-v1-mkmlizer: ║       /___/                                                         ║
yamatazen-iris-sce-12b-v1-mkmlizer: ║                                                                     ║
yamatazen-iris-sce-12b-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
yamatazen-iris-sce-12b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
yamatazen-iris-sce-12b-v1-mkmlizer: ║  https://mk1.ai                                                     ║
yamatazen-iris-sce-12b-v1-mkmlizer: ║                                                                     ║
yamatazen-iris-sce-12b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
yamatazen-iris-sce-12b-v1-mkmlizer: ║  belonging to:                                                      ║
yamatazen-iris-sce-12b-v1-mkmlizer: ║                                                                     ║
yamatazen-iris-sce-12b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
yamatazen-iris-sce-12b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
yamatazen-iris-sce-12b-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
yamatazen-iris-sce-12b-v1-mkmlizer: ║                                                                     ║
yamatazen-iris-sce-12b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
yamatazen-iris-sce-12b-v1-mkmlizer: Downloaded to shared memory in 44.488s
yamatazen-iris-sce-12b-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvi4t31zo, device:0
yamatazen-iris-sce-12b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
yamatazen-iris-sce-12b-v1-mkmlizer: quantized model in 38.157s
yamatazen-iris-sce-12b-v1-mkmlizer: Processed model yamatazen/Iris-SCE-12B in 82.646s
yamatazen-iris-sce-12b-v1-mkmlizer: creating bucket guanaco-mkml-models
yamatazen-iris-sce-12b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
yamatazen-iris-sce-12b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/yamatazen-iris-sce-12b-v1
yamatazen-iris-sce-12b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/yamatazen-iris-sce-12b-v1/config.json
yamatazen-iris-sce-12b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/yamatazen-iris-sce-12b-v1/special_tokens_map.json
yamatazen-iris-sce-12b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/yamatazen-iris-sce-12b-v1/tokenizer_config.json
yamatazen-iris-sce-12b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/yamatazen-iris-sce-12b-v1/tokenizer.json
yamatazen-iris-sce-12b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/yamatazen-iris-sce-12b-v1/flywheel_model.0.safetensors
yamatazen-iris-sce-12b-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:17,  3.04s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:54,  1.21it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:10,  2.70it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:22,  4.20it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:43,  7.86it/s]
Loading 0:   7%|▋         | 27/363 [00:06<00:31, 10.79it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:23, 14.23it/s]
Loading 0:  10%|█         | 37/363 [00:06<00:17, 18.26it/s]
Loading 0:  12%|█▏        | 42/363 [00:07<00:19, 16.31it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:13, 22.70it/s]
Loading 0:  15%|█▍        | 54/363 [00:07<00:12, 25.71it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:10, 28.81it/s]
Loading 0:  18%|█▊        | 64/363 [00:07<00:09, 32.45it/s]
Loading 0:  19%|█▉        | 69/363 [00:08<00:09, 29.55it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:07, 36.94it/s]
Loading 0:  22%|██▏       | 81/363 [00:08<00:07, 37.16it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:07, 38.25it/s]
Loading 0:  25%|██▌       | 91/363 [00:08<00:06, 40.08it/s]
Loading 0:  26%|██▋       | 96/363 [00:08<00:07, 33.75it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:06, 40.58it/s]
Loading 0:  30%|██▉       | 108/363 [00:08<00:06, 40.70it/s]
Loading 0:  31%|███       | 113/363 [00:09<00:06, 39.90it/s]
Loading 0:  33%|███▎      | 118/363 [00:09<00:05, 40.95it/s]
Loading 0:  34%|███▍      | 123/363 [00:09<00:09, 25.58it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:07, 32.49it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:06, 33.29it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:06, 33.91it/s]
Loading 0:  40%|███▉      | 144/363 [00:10<00:06, 34.65it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:06, 35.80it/s]
Loading 0:  42%|████▏     | 152/363 [00:10<00:05, 35.60it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 38.46it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:05, 38.50it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:05, 38.15it/s]
Loading 0:  47%|████▋     | 170/363 [00:10<00:05, 37.37it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:04, 39.82it/s]
Loading 0:  50%|████▉     | 180/363 [00:11<00:04, 38.16it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:04, 36.79it/s]
Loading 0:  52%|█████▏    | 188/363 [00:11<00:05, 34.11it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:04, 35.79it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:04, 34.39it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:06, 25.68it/s]
Loading 0:  56%|█████▋    | 205/363 [00:11<00:06, 25.35it/s]
Loading 0:  58%|█████▊    | 209/363 [00:12<00:05, 28.33it/s]
Loading 0:  59%|█████▊    | 213/363 [00:12<00:05, 28.10it/s]
Loading 0:  60%|██████    | 218/363 [00:12<00:04, 33.09it/s]
Loading 0:  61%|██████    | 222/363 [00:12<00:04, 31.01it/s]
Loading 0:  63%|██████▎   | 227/363 [00:12<00:03, 35.19it/s]
Loading 0:  64%|██████▎   | 231/363 [00:12<00:04, 32.75it/s]
Loading 0:  65%|██████▌   | 236/363 [00:12<00:03, 36.81it/s]
Loading 0:  66%|██████▌   | 240/363 [00:12<00:03, 32.88it/s]
Loading 0:  67%|██████▋   | 245/363 [00:13<00:03, 36.13it/s]
Loading 0:  69%|██████▊   | 249/363 [00:13<00:03, 32.65it/s]
Loading 0:  70%|██████▉   | 254/363 [00:13<00:03, 36.25it/s]
Loading 0:  71%|███████   | 258/363 [00:13<00:03, 32.34it/s]
Loading 0:  72%|███████▏  | 263/363 [00:13<00:02, 36.29it/s]
Loading 0:  74%|███████▎  | 267/363 [00:13<00:02, 33.12it/s]
Loading 0:  75%|███████▌  | 274/363 [00:13<00:02, 39.28it/s]
Loading 0:  77%|███████▋  | 279/363 [00:14<00:02, 36.42it/s]
Loading 0:  78%|███████▊  | 283/363 [00:14<00:03, 25.72it/s]
Loading 0:  79%|███████▉  | 287/363 [00:14<00:02, 26.93it/s]
Loading 0:  80%|████████  | 292/363 [00:14<00:02, 30.04it/s]
Loading 0:  82%|████████▏ | 296/363 [00:14<00:02, 30.40it/s]
Loading 0:  83%|████████▎ | 301/363 [00:14<00:01, 33.39it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:01, 32.91it/s]
Loading 0:  85%|████████▌ | 310/363 [00:15<00:01, 35.10it/s]
Loading 0:  87%|████████▋ | 314/363 [00:15<00:01, 34.26it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:01, 35.10it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:01, 33.96it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:00, 36.05it/s]
Loading 0:  91%|█████████▏| 332/363 [00:15<00:00, 34.98it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:00, 37.13it/s]
Loading 0:  94%|█████████▍| 341/363 [00:15<00:00, 35.34it/s]
Loading 0:  95%|█████████▌| 346/363 [00:16<00:00, 37.08it/s]
Loading 0:  96%|█████████▋| 350/363 [00:16<00:00, 35.89it/s]
Loading 0:  98%|█████████▊| 355/363 [00:16<00:00, 37.67it/s]
Loading 0:  99%|█████████▉| 359/363 [00:16<00:00, 35.77it/s]
                                                            

Job yamatazen-iris-sce-12b-v1-mkmlizer completed after 156.14s with status: succeeded
Stopping job with name yamatazen-iris-sce-12b-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.64s
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 yamatazen-iris-sce-12b-v1
Waiting for inference service yamatazen-iris-sce-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)
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
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-sce-12b-v1 ready after 281.68618988990784s
Pipeline stage MKMLDeployer completed in 282.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5560309886932373s
Received healthy response to inference request in 1.5332143306732178s
Received healthy response to inference request in 1.485241174697876s
Received healthy response to inference request in 1.4213569164276123s
Received healthy response to inference request in 1.4954206943511963s
5 requests
0 failed requests
5th percentile: 1.434133768081665
10th percentile: 1.4469106197357178
20th percentile: 1.4724643230438232
30th percentile: 1.48727707862854
40th percentile: 1.491348886489868
50th percentile: 1.4954206943511963
60th percentile: 1.510538148880005
70th percentile: 1.5256556034088136
80th percentile: 1.5377776622772217
90th percentile: 1.5469043254852295
95th percentile: 1.5514676570892334
99th percentile: 1.5551183223724365
mean time: 1.4982528209686279
Pipeline stage StressChecker completed in 8.62s
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 0.59s
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 0.62s
Shutdown handler de-registered
yamatazen-iris-sce-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 2466.21s
Shutdown handler de-registered
yamatazen-iris-sce-12b_v1 status is now inactive due to auto deactivation removed underperforming models
yamatazen-iris-sce-12b_v1 status is now torndown due to DeploymentManager action