developer_uid: bogoconic1
submission_id: chaiml-gy-exp2-sft-simp_72771_v1
model_name: chaiml-gy-exp2-sft-simp_72771_v1
model_group: ChaiML/gy-exp2-sft-simpo
status: torndown
timestamp: 2025-06-24T14:48:17+00:00
num_battles: 9243
num_wins: 4786
celo_rating: 1298.71
family_friendly_score: 0.5204
family_friendly_standard_error: 0.007065179969399223
submission_type: basic
model_repo: ChaiML/gy-exp2-sft-simpo-nis-mistral32-preferences-sftv1-1306-ep2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.5884845380216139, 'latency_mean': 1.699152729511261, 'latency_p50': 1.7059848308563232, 'latency_p90': 1.8814969539642334}, {'batch_size': 3, 'throughput': 1.0716990770796104, 'latency_mean': 2.791787425279617, 'latency_p50': 2.7945691347122192, 'latency_p90': 3.068913722038269}, {'batch_size': 5, 'throughput': 1.2852039818518695, 'latency_mean': 3.872167936563492, 'latency_p50': 3.862439751625061, 'latency_p90': 4.30406277179718}, {'batch_size': 6, 'throughput': 1.358339652792873, 'latency_mean': 4.395032378435135, 'latency_p50': 4.350522398948669, 'latency_p90': 4.974682784080505}, {'batch_size': 8, 'throughput': 1.4059103498990195, 'latency_mean': 5.646360496282577, 'latency_p50': 5.585724115371704, 'latency_p90': 6.373040556907654}, {'batch_size': 10, 'throughput': 1.4443767200394457, 'latency_mean': 6.8810979795455935, 'latency_p50': 6.892882347106934, 'latency_p90': 7.751177382469177}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-gy-exp2-sft-simp_72771_v1
is_internal_developer: True
language_model: ChaiML/gy-exp2-sft-simpo-nis-mistral32-preferences-sftv1-1306-ep2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.27
us_pacific_date: 2025-06-24
win_ratio: 0.5177972519744671
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_end|>', '\n', '<|im_start|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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 chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer
Waiting for job on chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer to finish
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: Downloaded to shared memory in 40.937s
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: Checking if ChaiML/gy-exp2-sft-simpo-nis-mistral32-preferences-sftv1-1306-ep2 already exists in ChaiML
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfyi_qkxc, device:0
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: quantized model in 31.007s
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: Processed model ChaiML/gy-exp2-sft-simpo-nis-mistral32-preferences-sftv1-1306-ep2 in 71.945s
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp2-sft-simp-72771-v1
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp2-sft-simp-72771-v1/config.json
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp2-sft-simp-72771-v1/special_tokens_map.json
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp2-sft-simp-72771-v1/tokenizer_config.json
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp2-sft-simp-72771-v1/tokenizer.json
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp2-sft-simp-72771-v1/flywheel_model.0.safetensors
chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.47it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 48.49it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 48.20it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 39.25it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 44.28it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 43.35it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 42.94it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 44.01it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 35.71it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 40.75it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:10, 28.94it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 28.90it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 34.84it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:07, 36.10it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 37.09it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 38.91it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 33.14it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 39.86it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 39.99it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:06, 41.90it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:07, 35.50it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 35.64it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 42.28it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 41.59it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 40.94it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.25it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 25.40it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 26.14it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.27it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 34.79it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 36.43it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 38.90it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 33.39it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 40.46it/s]
Loading 0:  52%|█████▏    | 188/363 [00:05<00:04, 40.81it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:04, 41.29it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 42.88it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 35.83it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 42.58it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 42.11it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 43.52it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:05, 26.54it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 29.02it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 35.90it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 37.12it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 38.15it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 40.41it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 34.01it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 40.47it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 40.67it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 41.02it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 42.57it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 35.21it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 41.95it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 41.38it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 42.77it/s]
Loading 0:  84%|████████▍ | 306/363 [00:08<00:02, 22.98it/s]
Loading 0:  85%|████████▌ | 310/363 [00:08<00:02, 24.16it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 26.14it/s]
Loading 0:  88%|████████▊ | 319/363 [00:08<00:01, 30.47it/s]
Loading 0:  89%|████████▉ | 323/363 [00:08<00:01, 31.71it/s]
Loading 0:  91%|█████████ | 329/363 [00:09<00:00, 36.57it/s]
Loading 0:  92%|█████████▏| 334/363 [00:09<00:00, 39.34it/s]
Loading 0:  93%|█████████▎| 339/363 [00:09<00:00, 34.09it/s]
Loading 0:  95%|█████████▌| 346/363 [00:09<00:00, 41.70it/s]
Loading 0:  97%|█████████▋| 351/363 [00:09<00:00, 41.62it/s]
Loading 0:  98%|█████████▊| 356/363 [00:09<00:00, 41.84it/s]
Loading 0:  99%|█████████▉| 361/363 [00:09<00:00, 42.88it/s]
                                                            

Job chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer completed after 95.21s with status: succeeded
Stopping job with name chaiml-gy-exp2-sft-simp-72771-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.77s
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 chaiml-gy-exp2-sft-simp-72771-v1
Waiting for inference service chaiml-gy-exp2-sft-simp-72771-v1 to be ready
Failed to get response for submission chaiml-giyu-disabled-hu_13897_v2: ('http://chaiml-giyu-disabled-hu-13897-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service chaiml-gy-exp2-sft-simp-72771-v1 ready after 191.0107297897339s
Pipeline stage MKMLDeployer completed in 191.87s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2611734867095947s
Received healthy response to inference request in 2.0851194858551025s
Received healthy response to inference request in 1.9397430419921875s
Received healthy response to inference request in 2.014343500137329s
Received healthy response to inference request in 1.970686435699463s
5 requests
0 failed requests
5th percentile: 1.9459317207336426
10th percentile: 1.9521203994750977
20th percentile: 1.9644977569580078
30th percentile: 1.9794178485870362
40th percentile: 1.9968806743621825
50th percentile: 2.014343500137329
60th percentile: 2.0426538944244386
70th percentile: 2.070964288711548
80th percentile: 2.120330286026001
90th percentile: 2.190751886367798
95th percentile: 2.225962686538696
99th percentile: 2.254131326675415
mean time: 2.0542131900787353
Pipeline stage StressChecker completed in 11.96s
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 0.69s
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 0.79s
Shutdown handler de-registered
chaiml-gy-exp2-sft-simp_72771_v1 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp2-sft-simp-72771-v1-profiler
Waiting for inference service chaiml-gy-exp2-sft-simp-72771-v1-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 3140.15s
Shutdown handler de-registered
chaiml-gy-exp2-sft-simp_72771_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp2-sft-simp_72771_v1 status is now torndown due to DeploymentManager action