chaiml-gy-exp32-sft-sim_90812

developer_uid: bogoconic1

submission_id: chaiml-gy-exp32-sft-sim_90812_v1

model_name: chaiml-gy-exp32-sft-sim_90812_v1

model_group: ChaiML/gy-exp32-sft-simp

status: torndown

timestamp: 2025-07-01T21:37:52+00:00

num_battles: 7504

num_wins: 3872

celo_rating: 1297.84

family_friendly_score: 0.5216000000000001

family_friendly_standard_error: 0.007064466575757862

submission_type: basic

model_repo: ChaiML/gy-exp32-sft-simpo-gy-datamix-v1-dpo-rm-win-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': 0.519911884768765, 'latency_mean': 1.9233027756214143, 'latency_p50': 1.9193964004516602, 'latency_p90': 2.1301446676254274}, {'batch_size': 3, 'throughput': 1.0509668918758386, 'latency_mean': 2.849192638397217, 'latency_p50': 2.825532555580139, 'latency_p90': 3.1532155990600588}, {'batch_size': 5, 'throughput': 1.3306360919526496, 'latency_mean': 3.7342630195617676, 'latency_p50': 3.7035759687423706, 'latency_p90': 4.140998315811157}, {'batch_size': 6, 'throughput': 1.4383201766895934, 'latency_mean': 4.129520009756089, 'latency_p50': 4.13505756855011, 'latency_p90': 4.712457537651062}, {'batch_size': 8, 'throughput': 1.5622651935727623, 'latency_mean': 5.0750548362731935, 'latency_p50': 5.07388961315155, 'latency_p90': 5.763631510734558}, {'batch_size': 10, 'throughput': 1.6377776317048145, 'latency_mean': 6.050191254615783, 'latency_p50': 6.064304709434509, 'latency_p90': 6.994444942474365}]

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

display_name: chaiml-gy-exp32-sft-sim_90812_v1

is_internal_developer: False

language_model: ChaiML/gy-exp32-sft-simpo-gy-datamix-v1-dpo-rm-win-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.33

us_pacific_date: 2025-07-01

win_ratio: 0.5159914712153518

generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_start|>', '<|im_end|>'], '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-exp32-sft-sim-90812-v1-mkmlizer
Waiting for job on chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer to finish
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7cd524c6f8d0>, 'Connection to chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: Downloaded to shared memory in 77.720s
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: Checking if ChaiML/gy-exp32-sft-simpo-gy-datamix-v1-dpo-rm-win-ep2 already exists in ChaiML
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjsk7wyhj, device:0
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: quantized model in 49.672s
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: Processed model ChaiML/gy-exp32-sft-simpo-gy-datamix-v1-dpo-rm-win-ep2 in 127.392s
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp32-sft-sim-90812-v1
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp32-sft-sim-90812-v1/config.json
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp32-sft-sim-90812-v1/special_tokens_map.json
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp32-sft-sim-90812-v1/tokenizer_config.json
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp32-sft-sim-90812-v1/tokenizer.json
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp32-sft-sim-90812-v1/flywheel_model.1.safetensors
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp32-sft-sim-90812-v1/flywheel_model.0.safetensors
chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 36.16it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 28.94it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.06it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 26.75it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 30.78it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 27.93it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:09, 33.32it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:17, 19.19it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 21.71it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:14, 22.44it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:12, 25.82it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:13, 22.83it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:11, 27.79it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.35it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 26.46it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 22.56it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:14, 19.62it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 24.57it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 23.93it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.78it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:11, 24.76it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 19.43it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:10, 26.10it/s]
Loading 0:  28%|██▊       | 102/363 [00:04<00:11, 23.38it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:12, 20.66it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 23.77it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:11, 21.68it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:09, 26.16it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:10, 23.68it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 27.80it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 24.62it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 28.57it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:08, 25.33it/s]
Loading 0:  40%|████      | 146/363 [00:05<00:07, 30.20it/s]
Loading 0:  41%|████▏     | 150/363 [00:06<00:09, 23.02it/s]
Loading 0:  42%|████▏     | 153/363 [00:06<00:10, 19.21it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 22.35it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 22.97it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:08, 24.19it/s]
Loading 0:  46%|████▌     | 166/363 [00:06<00:07, 24.74it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 24.80it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:06, 27.99it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:07, 24.12it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 26.55it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 22.95it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:08, 21.22it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.43it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 23.00it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 23.00it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:08,  1.16s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<02:35,  1.03it/s]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:32,  1.67it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:11,  2.13it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:53,  2.80it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:36,  4.00it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.10it/s]
Loading 0:  62%|██████▏   | 224/363 [00:24<00:23,  6.02it/s]
Loading 0:  63%|██████▎   | 229/363 [00:24<00:15,  8.90it/s]
Loading 0:  64%|██████▍   | 232/363 [00:24<00:12, 10.61it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 14.24it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:08, 14.84it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 19.95it/s]
Loading 0:  69%|██████▊   | 249/363 [00:25<00:05, 19.43it/s]
Loading 0:  70%|███████   | 255/363 [00:25<00:04, 23.93it/s]
Loading 0:  71%|███████   | 258/363 [00:25<00:04, 22.28it/s]
Loading 0:  72%|███████▏  | 263/363 [00:25<00:03, 27.50it/s]
Loading 0:  74%|███████▎  | 267/363 [00:25<00:04, 21.93it/s]
Loading 0:  74%|███████▍  | 270/363 [00:25<00:04, 18.90it/s]
Loading 0:  75%|███████▌  | 274/363 [00:26<00:04, 22.02it/s]
Loading 0:  76%|███████▋  | 277/363 [00:26<00:03, 22.49it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 25.17it/s]
Loading 0:  79%|███████▊  | 285/363 [00:26<00:03, 22.77it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 27.31it/s]
Loading 0:  81%|████████  | 294/363 [00:26<00:02, 24.51it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 26.84it/s]
Loading 0:  84%|████████▎ | 304/363 [00:27<00:02, 23.17it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 21.32it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 22.06it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 22.88it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 26.00it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 23.63it/s]
Loading 0:  90%|█████████ | 327/363 [00:28<00:01, 28.45it/s]
Loading 0:  91%|█████████ | 330/363 [00:28<00:01, 25.16it/s]
Loading 0:  92%|█████████▏| 335/363 [00:28<00:01, 27.36it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:00, 26.01it/s]
Loading 0:  94%|█████████▍| 341/363 [00:29<00:01, 15.36it/s]
Loading 0:  96%|█████████▌| 347/363 [00:29<00:00, 20.75it/s]
Loading 0:  96%|█████████▋| 350/363 [00:29<00:00, 21.48it/s]
Loading 0:  97%|█████████▋| 353/363 [00:29<00:00, 22.55it/s]
Loading 0:  98%|█████████▊| 357/363 [00:29<00:00, 21.12it/s]
                                                            
Job chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer completed after 156.36s with status: succeeded
Stopping job with name chaiml-gy-exp32-sft-sim-90812-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.91s
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 chaiml-gy-exp32-sft-sim-90812-v1
Waiting for inference service chaiml-gy-exp32-sft-sim-90812-v1 to be ready
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
Inference service chaiml-gy-exp32-sft-sim-90812-v1 ready after 211.33152151107788s
Pipeline stage MKMLDeployer completed in 211.86s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.451029062271118s
Received healthy response to inference request in 2.433976173400879s
Received healthy response to inference request in 2.1542680263519287s
Received healthy response to inference request in 2.042851209640503s
Received healthy response to inference request in 2.125175952911377s
5 requests
0 failed requests
5th percentile: 2.0593161582946777
10th percentile: 2.0757811069488525
20th percentile: 2.108711004257202
30th percentile: 2.130994367599487
40th percentile: 2.142631196975708
50th percentile: 2.1542680263519287
60th percentile: 2.266151285171509
70th percentile: 2.3780345439910886
80th percentile: 2.4373867511749268
90th percentile: 2.4442079067230225
95th percentile: 2.4476184844970703
99th percentile: 2.4503469467163086
mean time: 2.241460084915161
Pipeline stage StressChecker completed in 12.64s
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 0.77s
Shutdown handler de-registered
chaiml-gy-exp32-sft-sim_90812_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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp32-sft-sim-90812-v1-profiler
Waiting for inference service chaiml-gy-exp32-sft-sim-90812-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 3139.09s
Shutdown handler de-registered
chaiml-gy-exp32-sft-sim_90812_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp32-sft-sim_90812_v1 status is now torndown due to DeploymentManager action