chaiml-7b07-v1-dpo-cosine

developer_uid: chai_backend_admin

submission_id: chaiml-7b07-v1-dpo-cosine_v1

model_name: training123

model_group: ChaiML/7b07-v1-dpo_cosin

status: torndown

timestamp: 2025-11-21T06:41:36+00:00

num_battles: 5798

num_wins: 3070

celo_rating: 1304.08

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/7b07-v1-dpo_cosine

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': 0.3801256697455842, 'latency_mean': 2.630611987113953, 'latency_p50': 2.6393699645996094, 'latency_p90': 2.891928219795227}, {'batch_size': 2, 'throughput': 0.5676959892788976, 'latency_mean': 3.5169224178791048, 'latency_p50': 3.5353482961654663, 'latency_p90': 3.783598470687866}, {'batch_size': 3, 'throughput': 0.7040788173778176, 'latency_mean': 4.249213443994522, 'latency_p50': 4.220710754394531, 'latency_p90': 4.739702987670898}, {'batch_size': 4, 'throughput': 0.8002250900169613, 'latency_mean': 4.990372750759125, 'latency_p50': 4.963541150093079, 'latency_p90': 5.527239871025085}, {'batch_size': 5, 'throughput': 0.8602973857118944, 'latency_mean': 5.778975108861923, 'latency_p50': 5.808323860168457, 'latency_p90': 6.501498079299926}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/7b07-v1-dpo_cosine

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-11-17

win_ratio: 0.5294929285960676

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': ['</s>', 'You:', 'User:', '\n'], '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-cosine-v1-mkmlizer
Waiting for job on chaiml-7b07-v1-dpo-cosine-v1-mkmlizer to finish
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-4d70-fd43-linear-w01_v8: ('http://guanaco-model-mesh-load-balancer.model-mesh.k2.chaiverse.com/models/chaiml-4d70-fd43-linear-w01_v8/predict', '{"detail":"1 validation error for RuntimeResponse\\npredictions\\n  Field required [type=missing, input_value={\'detail\': \\"503, message=...linear-w01_v8/predict\'\\"}, input_type=dict]\\n    For further information visit https://errors.pydantic.dev/2.11/v/missing"}')
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: quantized model in 42.491s
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: Processed model ChaiML/7b07-v1-dpo_cosine in 132.788s
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-7b07-v1-dpo-cosine-v1/nvidia
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-7b07-v1-dpo-cosine-v1/nvidia/config.json
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-7b07-v1-dpo-cosine-v1/nvidia/special_tokens_map.json
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-7b07-v1-dpo-cosine-v1/nvidia/tokenizer_config.json
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-7b07-v1-dpo-cosine-v1/nvidia/tokenizer.json
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-7b07-v1-dpo-cosine-v1/nvidia/flywheel_model.1.safetensors
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-7b07-v1-dpo-cosine-v1/nvidia/flywheel_model.0.safetensors
chaiml-7b07-v1-dpo-cosine-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.54it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 39.58it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 36.37it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 36.31it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 37.26it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 42.67it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.95it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 23.91it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 31.63it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.55it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 33.69it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.15it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 32.37it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 28.30it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:15, 19.12it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:12, 23.29it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:10, 25.62it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:12, 22.92it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:10, 26.08it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:09, 27.57it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 29.98it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.78it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:11, 23.11it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:09, 26.22it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:10, 23.71it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:15, 15.77it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:14, 16.94it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:09, 24.84it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 25.61it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.49it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.62it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 35.37it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 23.71it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.25it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.82it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 30.55it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 33.87it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 32.60it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 33.62it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 30.53it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.02it/s]
Loading 0:  54%|█████▎    | 195/363 [00:07<00:06, 26.31it/s]
Loading 0:  55%|█████▌    | 200/363 [00:20<00:06, 26.31it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<02:14,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:20<01:55,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:13,  2.11it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:57,  2.66it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:43,  3.44it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:29,  4.84it/s]
Loading 0:  61%|██████    | 222/363 [00:20<00:21,  6.66it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:16,  8.37it/s]
Loading 0:  63%|██████▎   | 230/363 [00:21<00:12, 10.32it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:07, 16.17it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 18.27it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 22.63it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 24.10it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 28.51it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.43it/s]
Loading 0:  73%|███████▎  | 266/363 [00:22<00:02, 35.56it/s]
Loading 0:  75%|███████▍  | 271/363 [00:22<00:03, 26.59it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.84it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.99it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 31.55it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 34.83it/s]
Loading 0:  81%|████████▏ | 295/363 [00:23<00:02, 31.90it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:01, 33.00it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:01, 30.53it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 29.51it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.26it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.99it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.82it/s]
Loading 0:  90%|█████████ | 327/363 [00:24<00:01, 34.57it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:00, 32.75it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 33.81it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 34.54it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.67it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 22.19it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 29.91it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 29.73it/s]
                                                            
Job chaiml-7b07-v1-dpo-cosine-v1-mkmlizer completed after 205.86s with status: succeeded
Stopping job with name chaiml-7b07-v1-dpo-cosine-v1-mkmlizer
Pipeline stage MKMLizer completed in 206.43s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-7b07-v1-dpo-cosine-v1
Waiting for inference service chaiml-7b07-v1-dpo-cosine-v1 to be ready
Inference service chaiml-7b07-v1-dpo-cosine-v1 ready after 150.64110612869263s
Pipeline stage MKMLDeployer completed in 151.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.809190034866333s
Received healthy response to inference request in 2.3438360691070557s
Received healthy response to inference request in 2.4536478519439697s
Received healthy response to inference request in 2.16939115524292s
Received healthy response to inference request in 2.304739475250244s
5 requests
0 failed requests
5th percentile: 2.196460819244385
10th percentile: 2.22353048324585
20th percentile: 2.277669811248779
30th percentile: 2.3125587940216064
40th percentile: 2.3281974315643312
50th percentile: 2.3438360691070557
60th percentile: 2.387760782241821
70th percentile: 2.4316854953765867
80th percentile: 2.5247562885284425
90th percentile: 2.6669731616973875
95th percentile: 2.7380815982818603
99th percentile: 2.7949683475494385
mean time: 2.4161609172821046
Pipeline stage StressChecker completed in 14.26s
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 1.10s
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 0.75s
Shutdown handler de-registered
chaiml-7b07-v1-dpo-cosine_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-7b07-v1-dpo-cosine-v1-profiler
Waiting for inference service chaiml-7b07-v1-dpo-cosine-v1-profiler to be ready
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 5889.93s
Shutdown handler de-registered
chaiml-7b07-v1-dpo-cosine_v1 status is now torndown due to DeploymentManager action