developer_uid: bogoconic1
submission_id: chaiml-gy-exp8-sftdpo-g_36279_v1
model_name: chaiml-gy-exp8-sftdpo-g_36279_v1
model_group: ChaiML/gy-exp8-sftdpo-gy
status: torndown
timestamp: 2025-06-25T13:23:00+00:00
num_battles: 13331
num_wins: 5724
celo_rating: 1234.22
family_friendly_score: 0.7188
family_friendly_standard_error: 0.0063580902793213
submission_type: basic
model_repo: ChaiML/gy-exp8-sftdpo-gy-1266-3945-pref-grok-onlylast-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': 0.5946932701638474, 'latency_mean': 1.6814363181591034, 'latency_p50': 1.6792553663253784, 'latency_p90': 1.8534675359725952}, {'batch_size': 3, 'throughput': 1.0689071838295128, 'latency_mean': 2.7979838144779205, 'latency_p50': 2.806368589401245, 'latency_p90': 3.067818832397461}, {'batch_size': 5, 'throughput': 1.2875277367254572, 'latency_mean': 3.864816598892212, 'latency_p50': 3.87008798122406, 'latency_p90': 4.324654722213745}, {'batch_size': 6, 'throughput': 1.356320361567895, 'latency_mean': 4.3988309156894685, 'latency_p50': 4.365957617759705, 'latency_p90': 4.9686901569366455}, {'batch_size': 8, 'throughput': 1.423460744374233, 'latency_mean': 5.580133719444275, 'latency_p50': 5.528905749320984, 'latency_p90': 6.303517365455628}, {'batch_size': 10, 'throughput': 1.451930477295493, 'latency_mean': 6.828543313741684, 'latency_p50': 6.768409967422485, 'latency_p90': 7.818170762062072}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-gy-exp8-sftdpo-g_36279_v1
is_internal_developer: True
language_model: ChaiML/gy-exp8-sftdpo-gy-1266-3945-pref-grok-onlylast-ep2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.27
us_pacific_date: 2025-06-25
win_ratio: 0.4293751406496137
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_start|>', '<|im_end|>', '\n'], '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-exp8-sftdpo-g-36279-v1-mkmlizer
Waiting for job on chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer to finish
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: Downloaded to shared memory in 40.430s
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: Checking if ChaiML/gy-exp8-sftdpo-gy-1266-3945-pref-grok-onlylast-ep2 already exists in ChaiML
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp020i3vqi, device:0
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: quantized model in 30.425s
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: Processed model ChaiML/gy-exp8-sftdpo-gy-1266-3945-pref-grok-onlylast-ep2 in 70.856s
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp8-sftdpo-g-36279-v1
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp8-sftdpo-g-36279-v1/config.json
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp8-sftdpo-g-36279-v1/special_tokens_map.json
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp8-sftdpo-g-36279-v1/tokenizer_config.json
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp8-sftdpo-g-36279-v1/tokenizer.json
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp8-sftdpo-g-36279-v1/flywheel_model.0.safetensors
chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.75it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.48it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.57it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 44.32it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 51.09it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 43.73it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 41.10it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 46.44it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 45.28it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 34.16it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.37it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.05it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 41.84it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:07, 36.18it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 42.08it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 40.79it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 41.09it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:06, 40.81it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 45.09it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 43.59it/s]
Loading 0:  34%|███▍      | 123/363 [00:02<00:05, 42.03it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:05, 41.70it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 44.87it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 43.48it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:08, 27.13it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 29.69it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 35.78it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.76it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.22it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 40.16it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 33.34it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 36.63it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 36.28it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:04, 39.76it/s]
Loading 0:  54%|█████▍    | 197/363 [00:04<00:04, 39.84it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 40.49it/s]
Loading 0:  57%|█████▋    | 207/363 [00:05<00:03, 41.91it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 33.25it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 38.06it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 28.85it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 29.83it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 29.33it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 33.61it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 33.86it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 38.62it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 39.32it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 38.64it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 44.03it/s]
Loading 0:  74%|███████▍  | 270/363 [00:06<00:02, 44.77it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 38.64it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 46.25it/s]
Loading 0:  80%|███████▉  | 289/363 [00:07<00:01, 44.26it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 41.64it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 42.14it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 23.79it/s]
Loading 0:  85%|████████▍ | 308/363 [00:08<00:02, 26.05it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:01, 26.71it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 36.92it/s]
Loading 0:  90%|████████▉ | 326/363 [00:08<00:00, 39.02it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 40.43it/s]
Loading 0:  93%|█████████▎| 338/363 [00:08<00:00, 46.35it/s]
Loading 0:  95%|█████████▍| 344/363 [00:08<00:00, 44.33it/s]
Loading 0:  96%|█████████▌| 349/363 [00:09<00:00, 43.12it/s]
Loading 0:  98%|█████████▊| 356/363 [00:09<00:00, 47.74it/s]
Loading 0:  99%|█████████▉| 361/363 [00:09<00:00, 46.89it/s]
                                                            

Job chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer completed after 94.67s with status: succeeded
Stopping job with name chaiml-gy-exp8-sftdpo-g-36279-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.21s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp8-sftdpo-g-36279-v1
Waiting for inference service chaiml-gy-exp8-sftdpo-g-36279-v1 to be ready
Inference service chaiml-gy-exp8-sftdpo-g-36279-v1 ready after 130.50762367248535s
Pipeline stage MKMLDeployer completed in 131.10s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4990906715393066s
Received healthy response to inference request in 1.7761681079864502s
Received healthy response to inference request in 1.718257188796997s
Received healthy response to inference request in 2.0720930099487305s
Received healthy response to inference request in 1.62420654296875s
5 requests
0 failed requests
5th percentile: 1.6430166721343995
10th percentile: 1.6618268013000488
20th percentile: 1.6994470596313476
30th percentile: 1.7298393726348877
40th percentile: 1.7530037403106689
50th percentile: 1.7761681079864502
60th percentile: 1.8945380687713622
70th percentile: 2.0129080295562742
80th percentile: 2.1574925422668456
90th percentile: 2.3282916069030763
95th percentile: 2.4136911392211915
99th percentile: 2.4820107650756835
mean time: 1.937963104248047
Pipeline stage StressChecker completed in 11.13s
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 0.76s
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 0.83s
Shutdown handler de-registered
chaiml-gy-exp8-sftdpo-g_36279_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5283.71s
Shutdown handler de-registered
chaiml-gy-exp8-sftdpo-g_36279_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp8-sftdpo-g_36279_v1 status is now torndown due to DeploymentManager action