chaiml-gy-exp110-dpo-ex_95685

developer_uid: bogoconic1

submission_id: chaiml-gy-exp110-dpo-ex_95685_v2

model_name: chaiml-gy-exp110-dpo-ex_95685_v2

model_group: ChaiML/gy-exp110-dpo-exp

status: torndown

timestamp: 2025-07-07T16:25:32+00:00

num_battles: 9045

num_wins: 4827

celo_rating: 1310.67

family_friendly_score: 0.4706

family_friendly_standard_error: 0.0070588333313657435

submission_type: basic

model_repo: ChaiML/gy-exp110-dpo-exp93ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep1

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': 0.5248501538785655, 'latency_mean': 1.9051956844329834, 'latency_p50': 1.8861885070800781, 'latency_p90': 2.141327142715454}, {'batch_size': 3, 'throughput': 1.0572218252914507, 'latency_mean': 2.8295338809490205, 'latency_p50': 2.8356192111968994, 'latency_p90': 3.156048631668091}, {'batch_size': 5, 'throughput': 1.3301683794049513, 'latency_mean': 3.740179131031036, 'latency_p50': 3.7032068967819214, 'latency_p90': 4.206500363349915}, {'batch_size': 6, 'throughput': 1.4331188618315682, 'latency_mean': 4.1644171631336215, 'latency_p50': 4.17410945892334, 'latency_p90': 4.66666796207428}, {'batch_size': 8, 'throughput': 1.5539743088459659, 'latency_mean': 5.106942685842514, 'latency_p50': 5.135450959205627, 'latency_p90': 5.639640188217163}, {'batch_size': 10, 'throughput': 1.6222036118081637, 'latency_mean': 6.09620371222496, 'latency_p50': 6.140671253204346, 'latency_p90': 6.87673864364624}]

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

display_name: chaiml-gy-exp110-dpo-ex_95685_v2

is_internal_developer: False

language_model: ChaiML/gy-exp110-dpo-exp93ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep1

model_size: 24B

ranking_group: single

throughput_3p7s: 1.33

us_pacific_date: 2025-07-07

win_ratio: 0.5336650082918739

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-exp110-dpo-ex-95685-v2-mkmlizer
Waiting for job on chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer to finish
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: Downloaded to shared memory in 106.287s
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: Checking if ChaiML/gy-exp110-dpo-exp93ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep1 already exists in ChaiML
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpx1xwompy, device:0
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: quantized model in 93.148s
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: Processed model ChaiML/gy-exp110-dpo-exp93ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep1 in 199.436s
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp110-dpo-ex-95685-v2/nvidia
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp110-dpo-ex-95685-v2/nvidia/config.json
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp110-dpo-ex-95685-v2/nvidia/special_tokens_map.json
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp110-dpo-ex-95685-v2/nvidia/tokenizer_config.json
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp110-dpo-ex-95685-v2/nvidia/tokenizer.json
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp110-dpo-ex-95685-v2/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp110-dpo-ex-95685-v2/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:17, 20.30it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:30, 11.60it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:21, 16.54it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:20, 17.25it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:23, 14.85it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:18, 19.01it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:19, 17.66it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:21, 15.71it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.28it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.46it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:24, 13.63it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:24, 13.17it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:22, 14.63it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:22, 14.03it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 16.96it/s]
Loading 0:  13%|█▎        | 49/363 [00:03<00:18, 16.95it/s]
Loading 0:  14%|█▍        | 51/363 [00:03<00:19, 15.60it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:15, 19.74it/s]
Loading 0:  16%|█▌        | 58/363 [00:03<00:15, 19.68it/s]
Loading 0:  17%|█▋        | 61/363 [00:03<00:16, 18.26it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:14, 20.30it/s]
Loading 0:  19%|█▊        | 68/363 [00:03<00:12, 24.20it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:22, 13.19it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:23, 12.09it/s]
Loading 0:  21%|██▏       | 78/363 [00:04<00:18, 15.69it/s]
Loading 0:  22%|██▏       | 81/363 [00:05<00:19, 14.84it/s]
Loading 0:  23%|██▎       | 84/363 [00:05<00:17, 16.34it/s]
Loading 0:  24%|██▍       | 87/363 [00:05<00:19, 14.52it/s]
Loading 0:  25%|██▍       | 90/363 [00:05<00:16, 16.86it/s]
Loading 0:  26%|██▌       | 93/363 [00:05<00:18, 14.32it/s]
Loading 0:  27%|██▋       | 97/363 [00:05<00:15, 17.52it/s]
Loading 0:  28%|██▊       | 100/363 [00:06<00:15, 17.35it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:17, 15.19it/s]
Loading 0:  29%|██▉       | 106/363 [00:06<00:13, 19.04it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:17, 14.27it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:16, 15.08it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:20, 12.48it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 17.35it/s]
Loading 0:  33%|███▎      | 121/363 [00:07<00:13, 17.56it/s]
Loading 0:  34%|███▍      | 123/363 [00:07<00:15, 15.89it/s]
Loading 0:  35%|███▍      | 127/363 [00:07<00:12, 18.51it/s]
Loading 0:  36%|███▌      | 130/363 [00:07<00:12, 18.15it/s]
Loading 0:  36%|███▋      | 132/363 [00:08<00:14, 15.91it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:13, 17.34it/s]
Loading 0:  38%|███▊      | 139/363 [00:08<00:13, 16.93it/s]
Loading 0:  39%|███▉      | 141/363 [00:08<00:15, 14.43it/s]
Loading 0:  40%|███▉      | 145/363 [00:08<00:12, 17.67it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:10, 20.08it/s]
Loading 0:  42%|████▏     | 152/363 [00:09<00:16, 12.57it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:18, 11.08it/s]
Loading 0:  43%|████▎     | 156/363 [00:09<00:17, 11.94it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:19, 10.52it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:12, 16.31it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:11, 16.54it/s]
Loading 0:  47%|████▋     | 169/363 [00:10<00:11, 16.40it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.47it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:10, 18.31it/s]
Loading 0:  49%|████▉     | 178/363 [00:11<00:10, 18.22it/s]
Loading 0:  50%|████▉     | 181/363 [00:11<00:09, 19.74it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:07, 23.71it/s]
Loading 0:  52%|█████▏    | 188/363 [00:11<00:13, 13.34it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:14, 12.20it/s]
Loading 0:  53%|█████▎    | 193/363 [00:12<00:12, 13.74it/s]
Loading 0:  54%|█████▎    | 195/363 [00:12<00:13, 12.60it/s]
Loading 0:  55%|█████▍    | 199/363 [00:12<00:10, 16.34it/s]
Loading 0:  55%|█████▌    | 200/363 [00:29<00:09, 16.34it/s]
Loading 0:  55%|█████▌    | 201/363 [00:42<09:02,  3.35s/it]
Loading 0:  56%|█████▌    | 203/363 [00:42<06:53,  2.58s/it]
Loading 0:  57%|█████▋    | 208/363 [00:42<03:38,  1.41s/it]
Loading 0:  58%|█████▊    | 211/363 [00:43<02:37,  1.03s/it]
Loading 0:  59%|█████▊    | 213/363 [00:43<02:05,  1.20it/s]
Loading 0:  60%|█████▉    | 217/363 [00:43<01:17,  1.88it/s]
Loading 0:  61%|██████    | 220/363 [00:43<00:57,  2.47it/s]
Loading 0:  61%|██████▏   | 223/363 [00:43<00:42,  3.32it/s]
Loading 0:  62%|██████▏   | 225/363 [00:44<00:38,  3.54it/s]
Loading 0:  63%|██████▎   | 229/363 [00:44<00:25,  5.24it/s]
Loading 0:  64%|██████▎   | 231/363 [00:44<00:22,  5.75it/s]
Loading 0:  65%|██████▍   | 235/363 [00:44<00:15,  8.07it/s]
Loading 0:  66%|██████▌   | 238/363 [00:45<00:13,  9.37it/s]
Loading 0:  66%|██████▌   | 240/363 [00:45<00:13,  9.12it/s]
Loading 0:  67%|██████▋   | 244/363 [00:45<00:09, 12.50it/s]
Loading 0:  68%|██████▊   | 247/363 [00:45<00:08, 13.82it/s]
Loading 0:  69%|██████▊   | 249/363 [00:45<00:08, 13.00it/s]
Loading 0:  70%|██████▉   | 253/363 [00:45<00:06, 16.57it/s]
Loading 0:  71%|███████   | 256/363 [00:46<00:06, 17.42it/s]
Loading 0:  71%|███████▏  | 259/363 [00:46<00:06, 16.40it/s]
Loading 0:  72%|███████▏  | 262/363 [00:46<00:05, 17.61it/s]
Loading 0:  73%|███████▎  | 266/363 [00:46<00:04, 19.95it/s]
Loading 0:  74%|███████▍  | 269/363 [00:47<00:08, 11.57it/s]
Loading 0:  75%|███████▍  | 271/363 [00:47<00:08, 11.28it/s]
Loading 0:  75%|███████▌  | 273/363 [00:47<00:07, 12.50it/s]
Loading 0:  76%|███████▌  | 275/363 [00:47<00:08, 10.14it/s]
Loading 0:  77%|███████▋  | 280/363 [00:47<00:05, 14.96it/s]
Loading 0:  78%|███████▊  | 283/363 [00:48<00:05, 15.85it/s]
Loading 0:  79%|███████▊  | 285/363 [00:48<00:05, 14.52it/s]
Loading 0:  80%|███████▉  | 289/363 [00:48<00:04, 17.67it/s]
Loading 0:  80%|████████  | 291/363 [00:48<00:03, 18.07it/s]
Loading 0:  81%|████████  | 293/363 [00:48<00:05, 13.97it/s]
Loading 0:  82%|████████▏ | 298/363 [00:48<00:03, 19.77it/s]
Loading 0:  83%|████████▎ | 302/363 [00:49<00:02, 23.79it/s]
Loading 0:  84%|████████▍ | 305/363 [00:49<00:04, 13.08it/s]
Loading 0:  85%|████████▍ | 308/363 [00:49<00:04, 12.93it/s]
Loading 0:  85%|████████▌ | 310/363 [00:49<00:04, 12.72it/s]
Loading 0:  86%|████████▌ | 312/363 [00:50<00:04, 12.18it/s]
Loading 0:  87%|████████▋ | 316/363 [00:50<00:02, 15.91it/s]
Loading 0:  88%|████████▊ | 319/363 [00:50<00:02, 17.26it/s]
Loading 0:  89%|████████▊ | 322/363 [00:50<00:02, 16.26it/s]
Loading 0:  90%|████████▉ | 325/363 [00:50<00:02, 17.43it/s]
Loading 0:  90%|█████████ | 328/363 [00:50<00:01, 18.39it/s]
Loading 0:  91%|█████████ | 330/363 [00:51<00:02, 15.35it/s]
Loading 0:  92%|█████████▏| 334/363 [00:51<00:01, 19.21it/s]
Loading 0:  93%|█████████▎| 337/363 [00:51<00:01, 15.69it/s]
Loading 0:  94%|█████████▎| 340/363 [00:51<00:01, 17.15it/s]
Loading 0:  94%|█████████▍| 342/363 [00:52<00:02,  8.75it/s]
Loading 0:  95%|█████████▌| 346/363 [00:52<00:01, 11.39it/s]
Loading 0:  96%|█████████▌| 348/363 [00:52<00:01, 10.01it/s]
Loading 0:  97%|█████████▋| 353/363 [00:52<00:00, 14.63it/s]
Loading 0:  98%|█████████▊| 356/363 [00:52<00:00, 16.15it/s]
Loading 0:  99%|█████████▉| 359/363 [00:53<00:00, 16.35it/s]
Loading 0: 100%|█████████▉| 362/363 [00:53<00:00, 18.14it/s]
                                                            
Job chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer completed after 249.65s with status: succeeded
Stopping job with name chaiml-gy-exp110-dpo-ex-95685-v2-mkmlizer
Pipeline stage MKMLizer completed in 250.21s
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-exp110-dpo-ex-95685-v2
Waiting for inference service chaiml-gy-exp110-dpo-ex-95685-v2 to be ready
Inference service chaiml-gy-exp110-dpo-ex-95685-v2 ready after 190.9884774684906s
Pipeline stage MKMLDeployer completed in 192.18s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2648472785949707s
Received healthy response to inference request in 2.2300281524658203s
Received healthy response to inference request in 2.032351493835449s
Received healthy response to inference request in 2.3506431579589844s
Received healthy response to inference request in 2.3674468994140625s
5 requests
0 failed requests
5th percentile: 2.0718868255615233
10th percentile: 2.1114221572875977
20th percentile: 2.1904928207397463
30th percentile: 2.254151153564453
40th percentile: 2.3023971557617187
50th percentile: 2.3506431579589844
60th percentile: 2.3573646545410156
70th percentile: 2.364086151123047
80th percentile: 2.546926975250244
90th percentile: 2.9058871269226074
95th percentile: 3.085367202758789
99th percentile: 3.228951263427734
mean time: 2.4490633964538575
Pipeline stage StressChecker completed in 13.61s
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 0.68s
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 0.69s
Shutdown handler de-registered
chaiml-gy-exp110-dpo-ex_95685_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 6233.95s
Shutdown handler de-registered
chaiml-gy-exp110-dpo-ex_95685_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp110-dpo-ex_95685_v2 status is now torndown due to DeploymentManager action