chaiml-gy-exp77-dpo-exp_70018

developer_uid: bogoconic1

submission_id: chaiml-gy-exp77-dpo-exp_70018_v1

model_name: chaiml-gy-exp77-dpo-exp_70018_v1

model_group: ChaiML/gy-exp77-dpo-exp5

status: torndown

timestamp: 2025-07-04T04:59:07+00:00

num_battles: 9809

num_wins: 5035

celo_rating: 1297.6

family_friendly_score: 0.5646

family_friendly_standard_error: 0.0070118020508283035

submission_type: basic

model_repo: ChaiML/gy-exp77-dpo-exp5sftdpos3-majib-0630-ep1

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5970152763356865, 'latency_mean': 1.6748156023025513, 'latency_p50': 1.6739487648010254, 'latency_p90': 1.864253568649292}, {'batch_size': 3, 'throughput': 1.0760019404239742, 'latency_mean': 2.782007328271866, 'latency_p50': 2.7733572721481323, 'latency_p90': 3.0732630252838136}, {'batch_size': 5, 'throughput': 1.283466921545008, 'latency_mean': 3.8721782398223876, 'latency_p50': 3.8694056272506714, 'latency_p90': 4.258714556694031}, {'batch_size': 6, 'throughput': 1.361208468451365, 'latency_mean': 4.383030177354812, 'latency_p50': 4.372164487838745, 'latency_p90': 4.86322820186615}, {'batch_size': 8, 'throughput': 1.4061412435264256, 'latency_mean': 5.634042880535126, 'latency_p50': 5.70991325378418, 'latency_p90': 6.363210201263428}, {'batch_size': 10, 'throughput': 1.4616623847546713, 'latency_mean': 6.7722607624530795, 'latency_p50': 6.694020867347717, 'latency_p90': 7.699900698661804}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp77-dpo-exp_70018_v1

is_internal_developer: True

language_model: ChaiML/gy-exp77-dpo-exp5sftdpos3-majib-0630-ep1

model_size: 13B

ranking_group: single

throughput_3p7s: 1.27

us_pacific_date: 2025-07-03

win_ratio: 0.5133041084718116

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|>', '<|im_start|>', '\n'], '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-exp77-dpo-exp-70018-v1-mkmlizer
Waiting for job on chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer to finish
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: Downloaded to shared memory in 41.479s
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: Checking if ChaiML/gy-exp77-dpo-exp5sftdpos3-majib-0630-ep1 already exists in ChaiML
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpip55q8vl, device:0
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: quantized model in 30.765s
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: Processed model ChaiML/gy-exp77-dpo-exp5sftdpos3-majib-0630-ep1 in 72.245s
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp77-dpo-exp-70018-v1/nvidia
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp77-dpo-exp-70018-v1/nvidia/config.json
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp77-dpo-exp-70018-v1/nvidia/special_tokens_map.json
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp77-dpo-exp-70018-v1/nvidia/tokenizer_config.json
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp77-dpo-exp-70018-v1/nvidia/tokenizer.json
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp77-dpo-exp-70018-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.92it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 52.36it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 46.85it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.38it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 49.68it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 47.14it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.56it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 48.83it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:06, 48.25it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 45.31it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 30.20it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 37.00it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 37.58it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:07, 37.44it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 42.65it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:06, 43.27it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:07, 36.68it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 41.54it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 45.88it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 44.24it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:05, 44.17it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 36.20it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 43.61it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 43.44it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:07, 27.38it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 29.46it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 36.00it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.69it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.93it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 40.50it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 32.66it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:05, 36.33it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 35.75it/s]
Loading 0:  53%|█████▎    | 191/363 [00:04<00:04, 39.02it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:04, 36.84it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 38.83it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:03, 39.33it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 40.07it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 41.81it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 42.42it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:05, 27.06it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 26.98it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 33.73it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 33.66it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 37.04it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:03, 36.22it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:03, 35.92it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 35.37it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 38.99it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 39.05it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 39.41it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:02, 41.14it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 34.31it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 40.24it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 40.41it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 44.69it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:02, 20.76it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:02, 22.85it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 30.86it/s]
Loading 0:  90%|████████▉ | 325/363 [00:08<00:01, 34.12it/s]
Loading 0:  91%|█████████ | 330/363 [00:08<00:01, 32.02it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 40.17it/s]
Loading 0:  94%|█████████▍| 343/363 [00:09<00:00, 41.62it/s]
Loading 0:  96%|█████████▌| 348/363 [00:09<00:00, 37.13it/s]
Loading 0:  98%|█████████▊| 356/363 [00:09<00:00, 44.92it/s]
Loading 0: 100%|█████████▉| 362/363 [00:09<00:00, 42.22it/s]
                                                            
Job chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer completed after 95.02s with status: succeeded
Stopping job with name chaiml-gy-exp77-dpo-exp-70018-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.61s
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-exp77-dpo-exp-70018-v1
Waiting for inference service chaiml-gy-exp77-dpo-exp-70018-v1 to be ready
Inference service chaiml-gy-exp77-dpo-exp-70018-v1 ready after 200.84003162384033s
Pipeline stage MKMLDeployer completed in 201.50s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.537813663482666s
Received healthy response to inference request in 1.735860824584961s
Received healthy response to inference request in 1.668097972869873s
Received healthy response to inference request in 1.5158915519714355s
Received healthy response to inference request in 2.064892053604126s
5 requests
0 failed requests
5th percentile: 1.546332836151123
10th percentile: 1.5767741203308105
20th percentile: 1.6376566886901855
30th percentile: 1.6816505432128905
40th percentile: 1.7087556838989257
50th percentile: 1.735860824584961
60th percentile: 1.867473316192627
70th percentile: 1.9990858078002929
80th percentile: 2.159476375579834
90th percentile: 2.34864501953125
95th percentile: 2.443229341506958
99th percentile: 2.5188967990875244
mean time: 1.9045112133026123
Pipeline stage StressChecker completed in 11.01s
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 0.72s
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 0.84s
Shutdown handler de-registered
chaiml-gy-exp77-dpo-exp_70018_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp77-dpo-exp-70018-v1-profiler
Waiting for inference service chaiml-gy-exp77-dpo-exp-70018-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 5313.03s
Shutdown handler de-registered
chaiml-gy-exp77-dpo-exp_70018_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp77-dpo-exp_70018_v1 status is now torndown due to DeploymentManager action