chaiml-gy-exp106-sftlor_20659

developer_uid: bogoconic1

submission_id: chaiml-gy-exp106-sftlor_20659_v2

model_name: chaiml-gy-exp106-sftlor_20659_v2

model_group: ChaiML/gy-exp106-sftlora

status: torndown

timestamp: 2025-07-10T13:26:59+00:00

num_battles: 6760

num_wins: 3214

celo_rating: 1271.69

family_friendly_score: 0.5532

family_friendly_standard_error: 0.0070309282459715084

submission_type: basic

model_repo: ChaiML/gy-exp106-sftlora-retry2-ep2

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.519709184731754, 'latency_mean': 1.9240534281730652, 'latency_p50': 1.929635763168335, 'latency_p90': 2.130283260345459}, {'batch_size': 3, 'throughput': 1.0459821068899748, 'latency_mean': 2.8579696583747864, 'latency_p50': 2.8516823053359985, 'latency_p90': 3.1254703521728513}, {'batch_size': 5, 'throughput': 1.3331277994628075, 'latency_mean': 3.724770803451538, 'latency_p50': 3.748447060585022, 'latency_p90': 4.125283026695251}, {'batch_size': 6, 'throughput': 1.4304979857232767, 'latency_mean': 4.159952907562256, 'latency_p50': 4.165482521057129, 'latency_p90': 4.634829592704773}, {'batch_size': 8, 'throughput': 1.5662390008905107, 'latency_mean': 5.058605581521988, 'latency_p50': 5.046988368034363, 'latency_p90': 5.688774657249451}, {'batch_size': 10, 'throughput': 1.6595510297349416, 'latency_mean': 5.956130423545837, 'latency_p50': 5.909401535987854, 'latency_p90': 6.68831844329834}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-gy-exp106-sftlor_20659_v2

is_internal_developer: False

language_model: ChaiML/gy-exp106-sftlora-retry2-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-10

win_ratio: 0.47544378698224854

generation_params: {'temperature': 0.0, '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': True}

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-exp106-sftlor-20659-v2-mkmlizer
Waiting for job on chaiml-gy-exp106-sftlor-20659-v2-mkmlizer to finish
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: Downloaded to shared memory in 92.534s
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: Checking if ChaiML/gy-exp106-sftlora-retry2-ep2 already exists in ChaiML
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7tgwjqp1, device:0
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: quantized model in 57.651s
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: Processed model ChaiML/gy-exp106-sftlora-retry2-ep2 in 150.185s
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp106-sftlor-20659-v2/nvidia
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp106-sftlor-20659-v2/nvidia/config.json
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp106-sftlor-20659-v2/nvidia/special_tokens_map.json
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp106-sftlor-20659-v2/nvidia/tokenizer_config.json
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp106-sftlor-20659-v2/nvidia/tokenizer.json
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp106-sftlor-20659-v2/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp106-sftlor-20659-v2/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp106-sftlor-20659-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 34.82it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:13, 26.35it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 27.30it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:15, 22.17it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 28.71it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 23.79it/s]
Loading 0:   8%|▊         | 29/363 [00:01<00:11, 29.51it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:15, 21.81it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:18, 17.56it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:15, 20.55it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:15, 20.52it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:14, 21.69it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:13, 22.89it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:14, 22.13it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:13, 23.21it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:12, 24.43it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:13, 23.04it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:12, 24.24it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 26.96it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:15, 18.30it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:15, 18.70it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:13, 20.86it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:15, 18.21it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:13, 20.25it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:15, 18.33it/s]
Loading 0:  25%|██▌       | 91/363 [00:04<00:12, 21.68it/s]
Loading 0:  26%|██▌       | 94/363 [00:04<00:12, 21.21it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:11, 22.71it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:11, 23.42it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:11, 22.68it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:10, 23.86it/s]
Loading 0:  30%|███       | 109/363 [00:05<00:14, 18.12it/s]
Loading 0:  31%|███       | 112/363 [00:05<00:12, 20.05it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:12, 20.13it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:11, 22.05it/s]
Loading 0:  33%|███▎      | 121/363 [00:05<00:10, 22.66it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:10, 22.11it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:09, 23.70it/s]
Loading 0:  36%|███▌      | 130/363 [00:05<00:09, 23.89it/s]
Loading 0:  37%|███▋      | 133/363 [00:06<00:10, 22.11it/s]
Loading 0:  37%|███▋      | 136/363 [00:06<00:09, 23.68it/s]
Loading 0:  38%|███▊      | 139/363 [00:06<00:09, 24.38it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:09, 23.08it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:08, 24.38it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:07, 27.94it/s]
Loading 0:  42%|████▏     | 152/363 [00:06<00:11, 18.38it/s]
Loading 0:  43%|████▎     | 155/363 [00:07<00:11, 18.75it/s]
Loading 0:  44%|████▎     | 158/363 [00:07<00:12, 15.86it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:09, 21.42it/s]
Loading 0:  46%|████▌     | 166/363 [00:07<00:08, 21.90it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:08, 21.74it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:08, 23.29it/s]
Loading 0:  48%|████▊     | 175/363 [00:07<00:08, 22.22it/s]
Loading 0:  49%|████▉     | 178/363 [00:08<00:08, 21.99it/s]
Loading 0:  50%|█████     | 182/363 [00:08<00:07, 22.94it/s]
Loading 0:  51%|█████     | 186/363 [00:08<00:06, 26.57it/s]
Loading 0:  52%|█████▏    | 189/363 [00:08<00:10, 16.46it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 19.94it/s]
Loading 0:  54%|█████▍    | 196/363 [00:09<00:08, 20.18it/s]
Loading 0:  55%|█████▌    | 200/363 [00:20<00:08, 20.18it/s]
Loading 0:  55%|█████▌    | 201/363 [00:26<03:41,  1.37s/it]
Loading 0:  56%|█████▌    | 203/363 [00:26<03:02,  1.14s/it]
Loading 0:  57%|█████▋    | 208/363 [00:26<01:48,  1.42it/s]
Loading 0:  58%|█████▊    | 211/363 [00:26<01:23,  1.83it/s]
Loading 0:  59%|█████▉    | 214/363 [00:27<01:01,  2.41it/s]
Loading 0:  60%|██████    | 218/363 [00:27<00:41,  3.46it/s]
Loading 0:  61%|██████    | 221/363 [00:27<00:32,  4.42it/s]
Loading 0:  62%|██████▏   | 224/363 [00:27<00:26,  5.29it/s]
Loading 0:  63%|██████▎   | 228/363 [00:27<00:18,  7.50it/s]
Loading 0:  64%|██████▎   | 231/363 [00:27<00:15,  8.65it/s]
Loading 0:  65%|██████▍   | 235/363 [00:28<00:10, 11.67it/s]
Loading 0:  66%|██████▌   | 238/363 [00:28<00:09, 13.57it/s]
Loading 0:  66%|██████▋   | 241/363 [00:28<00:08, 14.92it/s]
Loading 0:  67%|██████▋   | 244/363 [00:28<00:06, 17.31it/s]
Loading 0:  68%|██████▊   | 247/363 [00:28<00:06, 19.07it/s]
Loading 0:  69%|██████▉   | 250/363 [00:28<00:05, 19.48it/s]
Loading 0:  70%|██████▉   | 253/363 [00:28<00:05, 21.28it/s]
Loading 0:  71%|███████   | 256/363 [00:28<00:04, 22.33it/s]
Loading 0:  71%|███████▏  | 259/363 [00:29<00:04, 21.93it/s]
Loading 0:  72%|███████▏  | 263/363 [00:29<00:03, 25.91it/s]
Loading 0:  74%|███████▎  | 267/363 [00:29<00:04, 19.91it/s]
Loading 0:  74%|███████▍  | 270/363 [00:29<00:05, 16.88it/s]
Loading 0:  75%|███████▌  | 274/363 [00:29<00:04, 20.34it/s]
Loading 0:  76%|███████▋  | 277/363 [00:29<00:04, 20.58it/s]
Loading 0:  77%|███████▋  | 280/363 [00:30<00:03, 21.82it/s]
Loading 0:  78%|███████▊  | 283/363 [00:30<00:03, 23.08it/s]
Loading 0:  79%|███████▉  | 286/363 [00:30<00:03, 22.53it/s]
Loading 0:  80%|███████▉  | 290/363 [00:30<00:02, 26.64it/s]
Loading 0:  81%|████████  | 293/363 [00:30<00:03, 19.51it/s]
Loading 0:  82%|████████▏ | 298/363 [00:30<00:02, 25.48it/s]
Loading 0:  83%|████████▎ | 303/363 [00:30<00:02, 27.76it/s]
Loading 0:  85%|████████▍ | 307/363 [00:31<00:02, 19.22it/s]
Loading 0:  85%|████████▌ | 310/363 [00:31<00:02, 19.90it/s]
Loading 0:  86%|████████▌ | 313/363 [00:31<00:02, 20.47it/s]
Loading 0:  87%|████████▋ | 316/363 [00:31<00:02, 21.25it/s]
Loading 0:  88%|████████▊ | 319/363 [00:31<00:01, 22.56it/s]
Loading 0:  89%|████████▊ | 322/363 [00:31<00:01, 22.52it/s]
Loading 0:  90%|████████▉ | 325/363 [00:32<00:01, 23.44it/s]
Loading 0:  90%|█████████ | 328/363 [00:32<00:01, 24.06it/s]
Loading 0:  91%|█████████ | 331/363 [00:32<00:01, 23.15it/s]
Loading 0:  92%|█████████▏| 334/363 [00:32<00:01, 24.53it/s]
Loading 0:  93%|█████████▎| 337/363 [00:32<00:01, 20.13it/s]
Loading 0:  94%|█████████▎| 340/363 [00:32<00:01, 21.81it/s]
Loading 0:  94%|█████████▍| 343/363 [00:33<00:01, 12.86it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:00, 16.63it/s]
Loading 0:  96%|█████████▋| 350/363 [00:33<00:00, 17.57it/s]
Loading 0:  97%|█████████▋| 353/363 [00:33<00:00, 19.36it/s]
Loading 0:  98%|█████████▊| 356/363 [00:33<00:00, 21.09it/s]
Loading 0:  99%|█████████▉| 359/363 [00:33<00:00, 20.70it/s]
Loading 0: 100%|█████████▉| 362/363 [00:33<00:00, 22.29it/s]
                                                            
Job chaiml-gy-exp106-sftlor-20659-v2-mkmlizer completed after 309.42s with status: succeeded
Stopping job with name chaiml-gy-exp106-sftlor-20659-v2-mkmlizer
Pipeline stage MKMLizer completed in 309.93s
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-exp106-sftlor-20659-v2
Waiting for inference service chaiml-gy-exp106-sftlor-20659-v2 to be ready
Inference service chaiml-gy-exp106-sftlor-20659-v2 ready after 291.730033159256s
Pipeline stage MKMLDeployer completed in 292.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.631284475326538s
Received healthy response to inference request in 2.1935806274414062s
Received healthy response to inference request in 2.1110129356384277s
Received healthy response to inference request in 1.7923305034637451s
Received healthy response to inference request in 1.8952198028564453s
5 requests
0 failed requests
5th percentile: 1.8129083633422851
10th percentile: 1.833486223220825
20th percentile: 1.8746419429779053
30th percentile: 1.9383784294128419
40th percentile: 2.0246956825256346
50th percentile: 2.1110129356384277
60th percentile: 2.144040012359619
70th percentile: 2.1770670890808104
80th percentile: 2.2811213970184325
90th percentile: 2.4562029361724855
95th percentile: 2.543743705749512
99th percentile: 2.613776321411133
mean time: 2.1246856689453124
Pipeline stage StressChecker completed in 11.92s
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 0.70s
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 0.72s
Shutdown handler de-registered
chaiml-gy-exp106-sftlor_20659_v2 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 3054.01s
Shutdown handler de-registered
chaiml-gy-exp106-sftlor_20659_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp106-sftlor_20659_v2 status is now torndown due to DeploymentManager action