chaiml-gy-exp138-dpo-ex_87417

developer_uid: bogoconic1

submission_id: chaiml-gy-exp138-dpo-ex_87417_v1

model_name: chaiml-gy-exp138-dpo-ex_87417_v1

model_group: ChaiML/gy-exp138-dpo-exp

status: torndown

timestamp: 2025-07-10T16:51:18+00:00

num_battles: 8304

num_wins: 4534

celo_rating: 1314.79

family_friendly_score: 0.478

family_friendly_standard_error: 0.007064219702132713

submission_type: basic

model_repo: ChaiML/gy-exp138-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-gt0.7-diffgt0.01-lpdiffgt0-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': 0.5207867270729939, 'latency_mean': 1.9200590443611145, 'latency_p50': 1.9161760807037354, 'latency_p90': 2.141983699798584}, {'batch_size': 3, 'throughput': 1.0464141058412966, 'latency_mean': 2.856219092607498, 'latency_p50': 2.858738660812378, 'latency_p90': 3.110050106048584}, {'batch_size': 5, 'throughput': 1.3347557433528898, 'latency_mean': 3.7253828275203706, 'latency_p50': 3.73723566532135, 'latency_p90': 4.162294578552246}, {'batch_size': 6, 'throughput': 1.440105433347674, 'latency_mean': 4.132952446937561, 'latency_p50': 4.151734471321106, 'latency_p90': 4.572904443740844}, {'batch_size': 8, 'throughput': 1.5787126429144696, 'latency_mean': 5.026755862236023, 'latency_p50': 5.000438928604126, 'latency_p90': 5.608702921867371}, {'batch_size': 10, 'throughput': 1.6627467267279352, 'latency_mean': 5.962741374969482, 'latency_p50': 5.994595408439636, 'latency_p90': 6.702427077293396}]

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

display_name: chaiml-gy-exp138-dpo-ex_87417_v1

is_internal_developer: False

language_model: ChaiML/gy-exp138-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-gt0.7-diffgt0.01-lpdiffgt0-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-10

win_ratio: 0.5460019267822736

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_end|>', '<|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-exp138-dpo-ex-87417-v1-mkmlizer
Waiting for job on chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer to finish
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: Downloaded to shared memory in 76.973s
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: Checking if ChaiML/gy-exp138-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-gt0.7-diffgt0.01-lpdiffgt0-ep2 already exists in ChaiML
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpd39pc2ad, device:0
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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 0x7a674864c950>, 'Connection to chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: quantized model in 47.551s
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: Processed model ChaiML/gy-exp138-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-gt0.7-diffgt0.01-lpdiffgt0-ep2 in 124.524s
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp138-dpo-ex-87417-v1/nvidia
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp138-dpo-ex-87417-v1/nvidia/config.json
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp138-dpo-ex-87417-v1/nvidia/special_tokens_map.json
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp138-dpo-ex-87417-v1/nvidia/tokenizer_config.json
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp138-dpo-ex-87417-v1/nvidia/tokenizer.json
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp138-dpo-ex-87417-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp138-dpo-ex-87417-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 38.44it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.35it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 32.06it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 28.74it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 32.82it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 29.51it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 34.37it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:16, 20.30it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 23.00it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 23.42it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 26.83it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:12, 25.79it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.25it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.28it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 26.95it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.10it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 19.72it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 24.91it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.30it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.00it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.35it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.27it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 27.96it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:10, 24.60it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.30it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 25.41it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 23.31it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.80it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 25.08it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.33it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 27.57it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.17it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:08, 26.09it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.68it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:09, 23.20it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 21.75it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 22.90it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.19it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.32it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.83it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.29it/s]
Loading 0:  49%|████▉     | 177/363 [00:06<00:07, 25.47it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 27.98it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 25.06it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.93it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.87it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.18it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 24.18it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:00,  1.11s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:29,  1.07it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:30,  1.72it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:08,  2.21it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.90it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.13it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.27it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.27it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.25it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.03it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.93it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.96it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.11it/s]
Loading 0:  69%|██████▊   | 249/363 [00:24<00:05, 20.87it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.87it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 25.67it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 30.41it/s]
Loading 0:  74%|███████▍  | 268/363 [00:24<00:03, 23.75it/s]
Loading 0:  75%|███████▍  | 271/363 [00:24<00:04, 22.03it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:03, 23.13it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 23.92it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:02, 27.17it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 24.68it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 29.61it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 28.15it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.73it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 25.03it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 23.53it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 24.47it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 24.97it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 28.19it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 25.17it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 30.02it/s]
Loading 0:  91%|█████████ | 331/363 [00:27<00:01, 28.83it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 28.94it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 27.60it/s]
Loading 0:  94%|█████████▍| 341/363 [00:27<00:01, 16.49it/s]
Loading 0:  96%|█████████▌| 347/363 [00:27<00:00, 22.28it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 23.01it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 26.42it/s]
Loading 0:  99%|█████████▉| 359/363 [00:28<00:00, 26.07it/s]
                                                            
Job chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer completed after 156.98s with status: succeeded
Stopping job with name chaiml-gy-exp138-dpo-ex-87417-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.48s
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-exp138-dpo-ex-87417-v1
Waiting for inference service chaiml-gy-exp138-dpo-ex-87417-v1 to be ready
Inference service chaiml-gy-exp138-dpo-ex-87417-v1 ready after 200.84841513633728s
Pipeline stage MKMLDeployer completed in 201.72s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.707648277282715s
Received healthy response to inference request in 1.8441104888916016s
Received healthy response to inference request in 2.1725685596466064s
Received healthy response to inference request in 1.8804545402526855s
Received healthy response to inference request in 1.8833825588226318s
5 requests
0 failed requests
5th percentile: 1.8513792991638183
10th percentile: 1.8586481094360352
20th percentile: 1.8731857299804688
30th percentile: 1.8810401439666748
40th percentile: 1.8822113513946532
50th percentile: 1.8833825588226318
60th percentile: 1.9990569591522216
70th percentile: 2.1147313594818113
80th percentile: 2.279584503173828
90th percentile: 2.4936163902282713
95th percentile: 2.600632333755493
99th percentile: 2.6862450885772704
mean time: 2.097632884979248
Pipeline stage StressChecker completed in 12.05s
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 0.66s
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 1.03s
Shutdown handler de-registered
chaiml-gy-exp138-dpo-ex_87417_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 5871.46s
Shutdown handler de-registered
chaiml-gy-exp138-dpo-ex_87417_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp138-dpo-ex_87417_v1 status is now torndown due to DeploymentManager action