chaiml-7b07-v1-dpo-b025

developer_uid: chai_backend_admin

submission_id: chaiml-7b07-v1-dpo-b025_v1

model_name: training123

model_group: ChaiML/7b07-v1-dpo_b025

status: torndown

timestamp: 2025-11-21T08:01:22+00:00

num_battles: 5619

num_wins: 2969

celo_rating: 1305.96

family_friendly_score: 0.5005999999999999

family_friendly_standard_error: 0.0070710627206948175

submission_type: basic

model_repo: ChaiML/7b07-v1-dpo_b025

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.38156218727333663, 'latency_mean': 2.620705722570419, 'latency_p50': 2.5935513973236084, 'latency_p90': 2.8939668416976927}, {'batch_size': 2, 'throughput': 0.5675891095969593, 'latency_mean': 3.510736665725708, 'latency_p50': 3.5082191228866577, 'latency_p90': 3.8540267944335938}, {'batch_size': 3, 'throughput': 0.6929917668846586, 'latency_mean': 4.311859303712845, 'latency_p50': 4.316235184669495, 'latency_p90': 4.858562064170838}, {'batch_size': 4, 'throughput': 0.7857488969191369, 'latency_mean': 5.072494295835495, 'latency_p50': 5.116365551948547, 'latency_p90': 5.7240818500518795}, {'batch_size': 5, 'throughput': 0.8481228073859708, 'latency_mean': 5.862297340631485, 'latency_p50': 5.85264527797699, 'latency_p90': 6.704371070861816}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

ineligible_reason: num_battles<10000

is_internal_developer: True

language_model: ChaiML/7b07-v1-dpo_b025

model_size: 24B

ranking_group: single

throughput_3p7s: 0.6

us_pacific_date: 2025-11-17

win_ratio: 0.5283858337782523

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', 'User:', 'You:'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', '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-7b07-v1-dpo-b025-v1-mkmlizer
Waiting for job on chaiml-7b07-v1-dpo-b025-v1-mkmlizer to finish
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ║                                                                     ║
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: Downloaded to shared memory in 79.790s
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: Checking if ChaiML/7b07-v1-dpo_b025 already exists in ChaiML
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4w3krdf6, device:0
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: quantized model in 42.739s
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: Processed model ChaiML/7b07-v1-dpo_b025 in 122.529s
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-7b07-v1-dpo-b025-v1/nvidia
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-7b07-v1-dpo-b025-v1/nvidia/config.json
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-7b07-v1-dpo-b025-v1/nvidia/special_tokens_map.json
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-7b07-v1-dpo-b025-v1/nvidia/tokenizer_config.json
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-7b07-v1-dpo-b025-v1/nvidia/tokenizer.json
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-7b07-v1-dpo-b025-v1/nvidia/flywheel_model.1.safetensors
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-7b07-v1-dpo-b025-v1/nvidia/flywheel_model.0.safetensors
chaiml-7b07-v1-dpo-b025-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.66it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 39.78it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 36.89it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 36.38it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 37.07it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 42.14it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.71it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.32it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.02it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.72it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.29it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.37it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:08, 33.72it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 30.29it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 27.01it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.97it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 32.09it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.15it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 27.47it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.86it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.79it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:11, 22.00it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:09, 25.33it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:09, 27.07it/s]
Loading 0:  33%|███▎      | 121/363 [00:04<00:08, 29.19it/s]
Loading 0:  34%|███▍      | 125/363 [00:04<00:07, 30.82it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 32.39it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.65it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.26it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:07, 31.55it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 37.36it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 25.30it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.03it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.65it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.61it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.47it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.43it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.46it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 30.04it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.34it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.31it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:15,  1.20it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:56,  1.38it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:14,  2.08it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:57,  2.63it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:43,  3.39it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.76it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  5.99it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:19,  7.11it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.41it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.31it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 16.77it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 18.89it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:04, 23.57it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 24.58it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 28.53it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 27.95it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 34.95it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:03, 23.72it/s]
Loading 0:  75%|███████▌  | 274/363 [00:22<00:03, 26.56it/s]
Loading 0:  77%|███████▋  | 278/363 [00:22<00:03, 28.09it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.53it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 28.76it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 32.42it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 30.43it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:02, 30.90it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:02, 28.09it/s]
Loading 0:  85%|████████▍ | 307/363 [00:23<00:02, 25.91it/s]
Loading 0:  86%|████████▌ | 311/363 [00:23<00:02, 23.70it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.76it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.14it/s]
Loading 0:  90%|████████▉ | 326/363 [00:23<00:01, 30.09it/s]
Loading 0:  91%|█████████ | 330/363 [00:24<00:01, 24.70it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 28.25it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 29.45it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 19.17it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 20.91it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 27.89it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 27.37it/s]
                                                            
Job chaiml-7b07-v1-dpo-b025-v1-mkmlizer completed after 186.65s with status: succeeded
Stopping job with name chaiml-7b07-v1-dpo-b025-v1-mkmlizer
Pipeline stage MKMLizer completed in 187.42s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.58s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-7b07-v1-dpo-b025-v1
Waiting for inference service chaiml-7b07-v1-dpo-b025-v1 to be ready
Inference service chaiml-7b07-v1-dpo-b025-v1 ready after 140.82535815238953s
Pipeline stage MKMLDeployer completed in 141.38s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.488546371459961s
Received healthy response to inference request in 2.347766637802124s
Received healthy response to inference request in 2.2175402641296387s
Received healthy response to inference request in 2.4008867740631104s
Received healthy response to inference request in 2.1325814723968506s
5 requests
0 failed requests
5th percentile: 2.149573230743408
10th percentile: 2.1665649890899656
20th percentile: 2.200548505783081
30th percentile: 2.243585538864136
40th percentile: 2.29567608833313
50th percentile: 2.347766637802124
60th percentile: 2.3690146923065187
70th percentile: 2.390262746810913
80th percentile: 2.4184186935424803
90th percentile: 2.4534825325012206
95th percentile: 2.471014451980591
99th percentile: 2.485039987564087
mean time: 2.317464303970337
Pipeline stage StressChecker completed in 13.91s
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 0.86s
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 0.81s
Shutdown handler de-registered
chaiml-7b07-v1-dpo-b025_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 3133.34s
Shutdown handler de-registered
chaiml-7b07-v1-dpo-b025_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-7b07-v1-dpo-b025_v1 status is now torndown due to DeploymentManager action