chaiml-gy-exp123-dpo-ex_39438

developer_uid: bogoconic1

submission_id: chaiml-gy-exp123-dpo-ex_39438_v2

model_name: chaiml-gy-exp123-dpo-ex_39438_v2

model_group: ChaiML/gy-exp123-dpo-exp

status: torndown

timestamp: 2025-07-08T13:36:03+00:00

num_battles: 8040

num_wins: 4316

celo_rating: 1318.34

family_friendly_score: 0.4766

family_friendly_standard_error: 0.007063319899310805

submission_type: basic

model_repo: ChaiML/gy-exp123-dpo-exp72ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-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': 0.5222003799585255, 'latency_mean': 1.9148752009868621, 'latency_p50': 1.9098398685455322, 'latency_p90': 2.122251558303833}, {'batch_size': 3, 'throughput': 1.0568601733685201, 'latency_mean': 2.824337500333786, 'latency_p50': 2.807214140892029, 'latency_p90': 3.1418908834457397}, {'batch_size': 5, 'throughput': 1.3459947904246023, 'latency_mean': 3.696424148082733, 'latency_p50': 3.6676896810531616, 'latency_p90': 4.094905877113343}, {'batch_size': 6, 'throughput': 1.4443955317477606, 'latency_mean': 4.131739041805267, 'latency_p50': 4.161992073059082, 'latency_p90': 4.637959623336792}, {'batch_size': 8, 'throughput': 1.5849060947151872, 'latency_mean': 5.002450329065323, 'latency_p50': 4.937667608261108, 'latency_p90': 5.635920071601867}, {'batch_size': 10, 'throughput': 1.6638501808730721, 'latency_mean': 5.950009392499924, 'latency_p50': 5.944287896156311, 'latency_p90': 6.627396941184998}]

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

display_name: chaiml-gy-exp123-dpo-ex_39438_v2

is_internal_developer: False

language_model: ChaiML/gy-exp123-dpo-exp72ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.35

us_pacific_date: 2025-07-08

win_ratio: 0.53681592039801

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-exp123-dpo-ex-39438-v2-mkmlizer
Waiting for job on chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer to finish
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: Downloaded to shared memory in 76.852s
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: Checking if ChaiML/gy-exp123-dpo-exp72ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2 already exists in ChaiML
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprtfu6727, device:0
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: quantized model in 66.497s
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: Processed model ChaiML/gy-exp123-dpo-exp72ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2 in 143.350s
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp123-dpo-ex-39438-v2/nvidia
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp123-dpo-ex-39438-v2/nvidia/config.json
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp123-dpo-ex-39438-v2/nvidia/special_tokens_map.json
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp123-dpo-ex-39438-v2/nvidia/tokenizer_config.json
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp123-dpo-ex-39438-v2/nvidia/tokenizer.json
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp123-dpo-ex-39438-v2/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp123-dpo-ex-39438-v2/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:11, 30.66it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:15, 23.32it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:14, 24.25it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:18, 18.57it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:15, 22.58it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:15, 22.06it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:16, 20.34it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:15, 22.01it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:12, 25.60it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:21, 15.57it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:19, 16.45it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:23, 13.49it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:16, 18.74it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:15, 19.66it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:16, 19.13it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:14, 20.74it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:14, 21.13it/s]
Loading 0:  17%|█▋        | 61/363 [00:03<00:15, 20.07it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:14, 20.90it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:12, 23.26it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:18, 15.76it/s]
Loading 0:  20%|██        | 74/363 [00:03<00:19, 14.63it/s]
Loading 0:  21%|██▏       | 78/363 [00:04<00:15, 18.22it/s]
Loading 0:  22%|██▏       | 81/363 [00:04<00:17, 16.19it/s]
Loading 0:  23%|██▎       | 84/363 [00:04<00:15, 18.04it/s]
Loading 0:  24%|██▍       | 87/363 [00:04<00:18, 15.25it/s]
Loading 0:  25%|██▌       | 91/363 [00:04<00:15, 17.73it/s]
Loading 0:  26%|██▌       | 94/363 [00:05<00:15, 17.28it/s]
Loading 0:  27%|██▋       | 97/363 [00:05<00:14, 18.80it/s]
Loading 0:  28%|██▊       | 100/363 [00:05<00:13, 19.01it/s]
Loading 0:  28%|██▊       | 103/363 [00:05<00:13, 18.67it/s]
Loading 0:  29%|██▉       | 106/363 [00:05<00:12, 20.19it/s]
Loading 0:  30%|███       | 109/363 [00:05<00:16, 15.14it/s]
Loading 0:  31%|███       | 112/363 [00:06<00:15, 16.52it/s]
Loading 0:  31%|███▏      | 114/363 [00:06<00:16, 15.13it/s]
Loading 0:  33%|███▎      | 118/363 [00:06<00:12, 19.19it/s]
Loading 0:  33%|███▎      | 121/363 [00:06<00:12, 19.39it/s]
Loading 0:  34%|███▍      | 124/363 [00:06<00:12, 18.56it/s]
Loading 0:  35%|███▍      | 127/363 [00:06<00:11, 20.00it/s]
Loading 0:  36%|███▌      | 130/363 [00:06<00:11, 20.21it/s]
Loading 0:  37%|███▋      | 133/363 [00:07<00:11, 19.30it/s]
Loading 0:  37%|███▋      | 136/363 [00:07<00:10, 20.86it/s]
Loading 0:  38%|███▊      | 139/363 [00:07<00:10, 20.48it/s]
Loading 0:  39%|███▉      | 142/363 [00:07<00:11, 19.75it/s]
Loading 0:  40%|███▉      | 145/363 [00:07<00:10, 21.51it/s]
Loading 0:  41%|████      | 149/363 [00:07<00:08, 25.18it/s]
Loading 0:  42%|████▏     | 152/363 [00:08<00:13, 15.68it/s]
Loading 0:  43%|████▎     | 155/363 [00:08<00:12, 16.34it/s]
Loading 0:  44%|████▎     | 158/363 [00:08<00:15, 13.40it/s]
Loading 0:  45%|████▍     | 163/363 [00:08<00:10, 18.58it/s]
Loading 0:  46%|████▌     | 166/363 [00:08<00:10, 19.15it/s]
Loading 0:  47%|████▋     | 169/363 [00:09<00:10, 18.43it/s]
Loading 0:  47%|████▋     | 172/363 [00:09<00:09, 19.96it/s]
Loading 0:  48%|████▊     | 175/363 [00:09<00:09, 19.95it/s]
Loading 0:  49%|████▉     | 178/363 [00:09<00:09, 19.49it/s]
Loading 0:  50%|████▉     | 181/363 [00:09<00:08, 20.81it/s]
Loading 0:  51%|█████     | 185/363 [00:09<00:07, 25.08it/s]
Loading 0:  52%|█████▏    | 188/363 [00:10<00:11, 15.22it/s]
Loading 0:  53%|█████▎    | 191/363 [00:10<00:10, 16.15it/s]
Loading 0:  53%|█████▎    | 194/363 [00:10<00:12, 13.62it/s]
Loading 0:  55%|█████▍    | 199/363 [00:10<00:08, 18.33it/s]
Loading 0:  55%|█████▌    | 200/363 [00:30<00:08, 18.33it/s]
Loading 0:  55%|█████▌    | 201/363 [00:30<05:16,  1.96s/it]
Loading 0:  56%|█████▌    | 203/363 [00:31<04:10,  1.56s/it]
Loading 0:  57%|█████▋    | 208/363 [00:31<02:20,  1.11it/s]
Loading 0:  58%|█████▊    | 211/363 [00:31<01:43,  1.47it/s]
Loading 0:  59%|█████▊    | 213/363 [00:31<01:23,  1.80it/s]
Loading 0:  60%|█████▉    | 217/363 [00:31<00:52,  2.77it/s]
Loading 0:  61%|██████    | 220/363 [00:32<00:39,  3.58it/s]
Loading 0:  62%|██████▏   | 224/363 [00:32<00:28,  4.79it/s]
Loading 0:  63%|██████▎   | 228/363 [00:32<00:20,  6.68it/s]
Loading 0:  64%|██████▎   | 231/363 [00:32<00:16,  7.83it/s]
Loading 0:  65%|██████▍   | 235/363 [00:32<00:12, 10.63it/s]
Loading 0:  66%|██████▌   | 238/363 [00:32<00:10, 12.27it/s]
Loading 0:  66%|██████▋   | 241/363 [00:33<00:09, 13.28it/s]
Loading 0:  67%|██████▋   | 244/363 [00:33<00:07, 15.68it/s]
Loading 0:  68%|██████▊   | 247/363 [00:33<00:06, 17.12it/s]
Loading 0:  69%|██████▉   | 250/363 [00:33<00:06, 17.50it/s]
Loading 0:  70%|██████▉   | 253/363 [00:33<00:05, 19.83it/s]
Loading 0:  71%|███████   | 256/363 [00:33<00:05, 20.37it/s]
Loading 0:  71%|███████▏  | 259/363 [00:33<00:05, 19.23it/s]
Loading 0:  72%|███████▏  | 262/363 [00:34<00:04, 20.91it/s]
Loading 0:  73%|███████▎  | 266/363 [00:34<00:03, 24.91it/s]
Loading 0:  74%|███████▍  | 269/363 [00:34<00:05, 16.53it/s]
Loading 0:  75%|███████▍  | 272/363 [00:34<00:05, 17.67it/s]
Loading 0:  76%|███████▌  | 275/363 [00:34<00:05, 14.77it/s]
Loading 0:  77%|███████▋  | 280/363 [00:35<00:04, 20.37it/s]
Loading 0:  78%|███████▊  | 283/363 [00:35<00:03, 20.83it/s]
Loading 0:  79%|███████▉  | 286/363 [00:35<00:03, 20.73it/s]
Loading 0:  80%|███████▉  | 289/363 [00:35<00:03, 22.37it/s]
Loading 0:  80%|████████  | 292/363 [00:35<00:03, 21.38it/s]
Loading 0:  81%|████████▏ | 295/363 [00:35<00:03, 20.74it/s]
Loading 0:  82%|████████▏ | 298/363 [00:35<00:02, 22.38it/s]
Loading 0:  83%|████████▎ | 302/363 [00:35<00:02, 26.49it/s]
Loading 0:  84%|████████▍ | 305/363 [00:36<00:03, 15.29it/s]
Loading 0:  85%|████████▍ | 308/363 [00:36<00:03, 16.06it/s]
Loading 0:  86%|████████▌ | 311/363 [00:36<00:03, 13.74it/s]
Loading 0:  87%|████████▋ | 316/363 [00:36<00:02, 18.30it/s]
Loading 0:  88%|████████▊ | 319/363 [00:37<00:02, 18.74it/s]
Loading 0:  89%|████████▊ | 322/363 [00:37<00:02, 18.60it/s]
Loading 0:  90%|█████████ | 327/363 [00:37<00:01, 21.93it/s]
Loading 0:  91%|█████████ | 330/363 [00:37<00:01, 19.22it/s]
Loading 0:  92%|█████████▏| 334/363 [00:37<00:01, 22.14it/s]
Loading 0:  93%|█████████▎| 337/363 [00:38<00:01, 18.58it/s]
Loading 0:  94%|█████████▎| 340/363 [00:38<00:01, 19.63it/s]
Loading 0:  94%|█████████▍| 343/363 [00:38<00:01, 11.30it/s]
Loading 0:  96%|█████████▌| 347/363 [00:38<00:01, 14.34it/s]
Loading 0:  96%|█████████▋| 350/363 [00:39<00:00, 15.22it/s]
Loading 0:  97%|█████████▋| 353/363 [00:39<00:00, 16.87it/s]
Loading 0:  98%|█████████▊| 356/363 [00:39<00:00, 18.34it/s]
Loading 0:  99%|█████████▉| 359/363 [00:39<00:00, 18.38it/s]
Loading 0: 100%|█████████▉| 362/363 [00:39<00:00, 20.32it/s]
                                                            
Job chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer completed after 187.71s with status: succeeded
Stopping job with name chaiml-gy-exp123-dpo-ex-39438-v2-mkmlizer
Pipeline stage MKMLizer completed in 188.36s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp123-dpo-ex-39438-v2
Waiting for inference service chaiml-gy-exp123-dpo-ex-39438-v2 to be ready
Inference service chaiml-gy-exp123-dpo-ex-39438-v2 ready after 191.42937064170837s
Pipeline stage MKMLDeployer completed in 191.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.651961088180542s
Received healthy response to inference request in 2.4087300300598145s
Received healthy response to inference request in 2.1185858249664307s
Received healthy response to inference request in 2.321653127670288s
Received healthy response to inference request in 2.16886830329895s
5 requests
0 failed requests
5th percentile: 2.1286423206329346
10th percentile: 2.1386988162994385
20th percentile: 2.1588118076324463
30th percentile: 2.1994252681732176
40th percentile: 2.260539197921753
50th percentile: 2.321653127670288
60th percentile: 2.356483888626099
70th percentile: 2.391314649581909
80th percentile: 2.65737624168396
90th percentile: 3.154668664932251
95th percentile: 3.4033148765563963
99th percentile: 3.6022318458557128
mean time: 2.533959674835205
Pipeline stage StressChecker completed in 13.94s
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 0.65s
Shutdown handler de-registered
chaiml-gy-exp123-dpo-ex_39438_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 5551.34s
Shutdown handler de-registered
chaiml-gy-exp123-dpo-ex_39438_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp123-dpo-ex_39438_v2 status is now torndown due to DeploymentManager action