chaiml-gy-exp143-dpo-ex_63584

developer_uid: bogoconic1

submission_id: chaiml-gy-exp143-dpo-ex_63584_v1

model_name: chaiml-gy-exp143-dpo-ex_63584_v1

model_group: ChaiML/gy-exp143-dpo-exp

status: torndown

timestamp: 2025-07-11T09:29:55+00:00

num_battles: 9458

num_wins: 4961

celo_rating: 1307.49

family_friendly_score: 0.5102

family_friendly_standard_error: 0.007069596310964298

submission_type: basic

model_repo: ChaiML/gy-exp143-dpo-exp142ep3s2-exp140data-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': 0.5262464802163895, 'latency_mean': 1.9001478993892669, 'latency_p50': 1.8812841176986694, 'latency_p90': 2.13755350112915}, {'batch_size': 3, 'throughput': 1.0505045385551008, 'latency_mean': 2.842232965230942, 'latency_p50': 2.8303511142730713, 'latency_p90': 3.157073187828064}, {'batch_size': 5, 'throughput': 1.3373260580437696, 'latency_mean': 3.7169246661663053, 'latency_p50': 3.7171884775161743, 'latency_p90': 4.221756887435913}, {'batch_size': 6, 'throughput': 1.4442556345048274, 'latency_mean': 4.120264120101929, 'latency_p50': 4.124040722846985, 'latency_p90': 4.655489110946656}, {'batch_size': 8, 'throughput': 1.5642796371311058, 'latency_mean': 5.076501791477203, 'latency_p50': 5.030524253845215, 'latency_p90': 5.702273797988892}, {'batch_size': 10, 'throughput': 1.6389908754175124, 'latency_mean': 6.040016337633133, 'latency_p50': 6.071488618850708, 'latency_p90': 6.708921146392822}]

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

display_name: chaiml-gy-exp143-dpo-ex_63584_v1

is_internal_developer: False

language_model: ChaiML/gy-exp143-dpo-exp142ep3s2-exp140data-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-11

win_ratio: 0.5245294988369634

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': ['<|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-exp143-dpo-ex-63584-v1-mkmlizer
Waiting for job on chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer to finish
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: Downloaded to shared memory in 76.371s
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: Checking if ChaiML/gy-exp143-dpo-exp142ep3s2-exp140data-ep2 already exists in ChaiML
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8uimo8rh, device:0
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: quantized model in 48.562s
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: Processed model ChaiML/gy-exp143-dpo-exp142ep3s2-exp140data-ep2 in 124.934s
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp143-dpo-ex-63584-v1/nvidia
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp143-dpo-ex-63584-v1/nvidia/config.json
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp143-dpo-ex-63584-v1/nvidia/special_tokens_map.json
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp143-dpo-ex-63584-v1/nvidia/tokenizer_config.json
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp143-dpo-ex-63584-v1/nvidia/tokenizer.json
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp143-dpo-ex-63584-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp143-dpo-ex-63584-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.47it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.63it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 31.90it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 27.88it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 31.91it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 28.93it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 34.42it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:16, 20.28it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 23.02it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 23.66it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 26.97it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:12, 25.54it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.66it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 27.20it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.39it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.02it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 19.93it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 25.04it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.56it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.19it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.36it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.54it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 27.68it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 26.45it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 21.58it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:10, 24.53it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:10, 24.69it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.26it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.68it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:08, 29.10it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 27.21it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 28.90it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:08, 25.77it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.46it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:09, 23.39it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 21.71it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 22.90it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.23it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.49it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.91it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.42it/s]
Loading 0:  49%|████▉     | 177/363 [00:06<00:07, 25.27it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 27.03it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.34it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 21.97it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.98it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.31it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 23.31it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:05,  1.14s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:32,  1.05it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:31,  1.69it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:10,  2.15it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:52,  2.83it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:35,  4.05it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.16it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.15it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.10it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:12, 10.78it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 14.59it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:07, 15.44it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 20.58it/s]
Loading 0:  69%|██████▊   | 249/363 [00:24<00:05, 20.26it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.18it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 24.93it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 29.70it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 22.19it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 21.43it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:03, 22.70it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 23.42it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.09it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 23.56it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 28.23it/s]
Loading 0:  81%|████████  | 294/363 [00:26<00:02, 25.56it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 28.08it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 24.49it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 22.61it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.73it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 24.13it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 27.30it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 24.69it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 29.53it/s]
Loading 0:  91%|█████████ | 331/363 [00:27<00:01, 27.94it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:01, 27.68it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 25.94it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 15.12it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 20.68it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 21.60it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 25.12it/s]
Loading 0:  99%|█████████▊| 358/363 [00:28<00:00, 23.41it/s]
                                                            
Job chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer completed after 157.48s with status: succeeded
Stopping job with name chaiml-gy-exp143-dpo-ex-63584-v1-mkmlizer
Pipeline stage MKMLizer completed in 158.07s
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 chaiml-gy-exp143-dpo-ex-63584-v1
Waiting for inference service chaiml-gy-exp143-dpo-ex-63584-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-exp143-dpo-ex-63584-v1 ready after 200.8233733177185s
Pipeline stage MKMLDeployer completed in 201.42s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.951478958129883s
Received healthy response to inference request in 1.9487433433532715s
Received healthy response to inference request in 1.9080407619476318s
Received healthy response to inference request in 2.2704100608825684s
Received healthy response to inference request in 2.044189214706421s
5 requests
0 failed requests
5th percentile: 1.9161812782287597
10th percentile: 1.9243217945098876
20th percentile: 1.9406028270721436
30th percentile: 1.9678325176239013
40th percentile: 2.006010866165161
50th percentile: 2.044189214706421
60th percentile: 2.13467755317688
70th percentile: 2.2251658916473387
80th percentile: 2.4066238403320312
90th percentile: 2.679051399230957
95th percentile: 2.81526517868042
99th percentile: 2.92423620223999
mean time: 2.224572467803955
Pipeline stage StressChecker completed in 12.62s
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 0.73s
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 0.74s
Shutdown handler de-registered
chaiml-gy-exp143-dpo-ex_63584_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 3038.27s
Shutdown handler de-registered
chaiml-gy-exp143-dpo-ex_63584_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp143-dpo-ex_63584_v1 status is now torndown due to DeploymentManager action