chaiml-qwen-dpo-exp1-da_53786

developer_uid: NischayDnk

submission_id: chaiml-qwen-dpo-exp1-da_53786_v1

model_name: chaiml-qwen-dpo-exp1-da_53786_v1

model_group: ChaiML/qwen-dpo-exp1-dat

status: torndown

timestamp: 2025-04-14T08:00:05+00:00

num_battles: 7153

num_wins: 3800

celo_rating: 1303.08

family_friendly_score: 0.5456

family_friendly_standard_error: 0.007041599818223129

submission_type: basic

model_repo: ChaiML/qwen-dpo-exp1-datav1noffsftfull

model_architecture: Qwen2ForCausalLM

model_num_parameters: 32763417600.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.2542058871044816, 'latency_mean': 3.9337199354171752, 'latency_p50': 3.9357516765594482, 'latency_p90': 4.349207139015197}, {'batch_size': 2, 'throughput': 0.3975004276148732, 'latency_mean': 5.019901206493378, 'latency_p50': 5.04118275642395, 'latency_p90': 5.525078988075256}, {'batch_size': 5, 'throughput': 0.6408613456745359, 'latency_mean': 7.734143822193146, 'latency_p50': 7.740549564361572, 'latency_p90': 8.679019379615784}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-qwen-dpo-exp1-da_53786_v1

is_internal_developer: False

language_model: ChaiML/qwen-dpo-exp1-datav1noffsftfull

model_size: 33B

ranking_group: single

us_pacific_date: 2025-04-14

win_ratio: 0.5312456312036907

generation_params: {'temperature': 0.4, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['<|im_start|>', '\n', '<|im_end|>'], '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': False}

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-qwen-dpo-exp1-da-53786-v1-mkmlizer
Waiting for job on chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer to finish
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ║       /___/                                                         ║
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ║                                                                     ║
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ║                                                                     ║
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ║                                                                     ║
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ║                                                                     ║
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: Downloaded to shared memory in 109.588s
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnueppfc2, device:0
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: quantized model in 64.160s
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: Processed model ChaiML/qwen-dpo-exp1-datav1noffsftfull in 173.749s
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v1
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v1/config.json
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v1/added_tokens.json
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v1/tokenizer_config.json
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v1/special_tokens_map.json
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v1/merges.txt
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v1/vocab.json
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v1/tokenizer.json
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v1/flywheel_model.2.safetensors
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v1/flywheel_model.1.safetensors
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v1/flywheel_model.0.safetensors
chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:19, 38.87it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:10, 74.13it/s]
Loading 0:   4%|▎         | 27/771 [00:00<00:08, 86.54it/s]
Loading 0:   5%|▍         | 36/771 [00:00<00:08, 85.00it/s]
Loading 0:   6%|▌         | 46/771 [00:00<00:13, 54.62it/s]
Loading 0:   7%|▋         | 53/771 [00:00<00:15, 45.27it/s]
Loading 0:   8%|▊         | 64/771 [00:01<00:12, 56.79it/s]
Loading 0:  10%|▉         | 75/771 [00:01<00:10, 67.03it/s]
Loading 0:  11%|█         | 83/771 [00:01<00:09, 68.88it/s]
Loading 0:  12%|█▏        | 91/771 [00:01<00:10, 65.39it/s]
Loading 0:  14%|█▎        | 106/771 [00:01<00:11, 57.57it/s]
Loading 0:  15%|█▍        | 113/771 [00:01<00:11, 55.28it/s]
Loading 0:  16%|█▌        | 121/771 [00:02<00:11, 56.21it/s]
Loading 0:  17%|█▋        | 132/771 [00:02<00:09, 66.56it/s]
Loading 0:  18%|█▊        | 142/771 [00:02<00:08, 71.61it/s]
Loading 0:  20%|█▉        | 152/771 [00:02<00:08, 77.24it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:08, 73.66it/s]
Loading 0:  22%|██▏       | 169/771 [00:02<00:11, 50.69it/s]
Loading 0:  23%|██▎       | 176/771 [00:02<00:11, 51.45it/s]
Loading 0:  24%|██▍       | 185/771 [00:03<00:10, 55.15it/s]
Loading 0:  25%|██▌       | 196/771 [00:03<00:08, 66.75it/s]
Loading 0:  27%|██▋       | 207/771 [00:03<00:07, 76.73it/s]
Loading 0:  28%|██▊       | 216/771 [00:03<00:06, 79.79it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:08, 60.88it/s]
Loading 0:  30%|███       | 234/771 [00:03<00:10, 53.07it/s]
Loading 0:  32%|███▏      | 245/771 [00:03<00:08, 59.73it/s]
Loading 0:  33%|███▎      | 256/771 [00:04<00:07, 69.47it/s]
Loading 0:  35%|███▍      | 268/771 [00:04<00:06, 74.19it/s]
Loading 0:  36%|███▌      | 278/771 [00:04<00:06, 79.82it/s]
Loading 0:  37%|███▋      | 287/771 [00:04<00:07, 60.61it/s]
Loading 0:  38%|███▊      | 295/771 [00:04<00:08, 56.69it/s]
Loading 0:  39%|███▉      | 303/771 [00:19<03:53,  2.00it/s]
Loading 0:  40%|████      | 311/771 [00:19<02:47,  2.74it/s]
Loading 0:  41%|████      | 318/771 [00:19<02:05,  3.62it/s]
Loading 0:  43%|████▎     | 329/771 [00:19<01:19,  5.56it/s]
Loading 0:  45%|████▍     | 346/771 [00:19<00:45,  9.25it/s]
Loading 0:  46%|████▌     | 353/771 [00:20<00:39, 10.56it/s]
Loading 0:  47%|████▋     | 364/771 [00:20<00:27, 14.81it/s]
Loading 0:  49%|████▊     | 375/771 [00:20<00:19, 20.25it/s]
Loading 0:  50%|████▉     | 385/771 [00:20<00:14, 26.28it/s]
Loading 0:  51%|█████     | 394/771 [00:20<00:11, 31.49it/s]
Loading 0:  53%|█████▎    | 406/771 [00:21<00:10, 34.62it/s]
Loading 0:  54%|█████▎    | 413/771 [00:21<00:10, 34.33it/s]
Loading 0:  55%|█████▍    | 424/771 [00:21<00:07, 43.43it/s]
Loading 0:  56%|█████▋    | 435/771 [00:21<00:06, 53.77it/s]
Loading 0:  58%|█████▊    | 444/771 [00:21<00:05, 59.30it/s]
Loading 0:  59%|█████▉    | 453/771 [00:21<00:05, 60.78it/s]
Loading 0:  60%|██████    | 466/771 [00:21<00:05, 57.16it/s]
Loading 0:  61%|██████▏   | 473/771 [00:22<00:05, 49.74it/s]
Loading 0:  63%|██████▎   | 484/771 [00:22<00:04, 59.96it/s]
Loading 0:  64%|██████▍   | 495/771 [00:22<00:03, 69.29it/s]
Loading 0:  65%|██████▌   | 504/771 [00:22<00:03, 73.67it/s]
Loading 0:  67%|██████▋   | 513/771 [00:22<00:03, 71.99it/s]
Loading 0:  68%|██████▊   | 526/771 [00:22<00:03, 63.35it/s]
Loading 0:  69%|██████▉   | 534/771 [00:23<00:04, 55.02it/s]
Loading 0:  71%|███████   | 544/771 [00:23<00:03, 63.05it/s]
Loading 0:  72%|███████▏  | 555/771 [00:23<00:02, 72.72it/s]
Loading 0:  73%|███████▎  | 564/771 [00:23<00:02, 76.64it/s]
Loading 0:  74%|███████▍  | 573/771 [00:23<00:02, 74.11it/s]
Loading 0:  76%|███████▌  | 586/771 [00:23<00:02, 63.28it/s]
Loading 0:  77%|███████▋  | 594/771 [00:23<00:03, 53.84it/s]
Loading 0:  78%|███████▊  | 605/771 [00:24<00:02, 59.92it/s]
Loading 0:  80%|███████▉  | 616/771 [00:24<00:02, 69.73it/s]
Loading 0:  81%|████████▏ | 627/771 [00:38<01:01,  2.35it/s]
Loading 0:  83%|████████▎ | 637/771 [00:38<00:40,  3.28it/s]
Loading 0:  84%|████████▍ | 646/771 [00:39<00:28,  4.34it/s]
Loading 0:  85%|████████▍ | 653/771 [00:39<00:22,  5.31it/s]
Loading 0:  86%|████████▋ | 665/771 [00:39<00:13,  8.03it/s]
Loading 0:  88%|████████▊ | 676/771 [00:39<00:08, 11.43it/s]
Loading 0:  89%|████████▉ | 687/771 [00:39<00:05, 15.81it/s]
Loading 0:  90%|█████████ | 696/771 [00:40<00:03, 20.22it/s]
Loading 0:  92%|█████████▏| 706/771 [00:40<00:02, 23.81it/s]
Loading 0:  93%|█████████▎| 714/771 [00:40<00:02, 26.42it/s]
Loading 0:  94%|█████████▍| 724/771 [00:40<00:01, 34.28it/s]
Loading 0:  95%|█████████▌| 735/771 [00:40<00:00, 44.26it/s]
Loading 0:  97%|█████████▋| 745/771 [00:40<00:00, 53.06it/s]
Loading 0:  98%|█████████▊| 754/771 [00:40<00:00, 56.69it/s]
Loading 0:  99%|█████████▉| 766/771 [00:48<00:01,  4.24it/s]
                                                            
Job chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer completed after 207.94s with status: succeeded
Stopping job with name chaiml-qwen-dpo-exp1-da-53786-v1-mkmlizer
Pipeline stage MKMLizer completed in 208.40s
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-qwen-dpo-exp1-da-53786-v1
Waiting for inference service chaiml-qwen-dpo-exp1-da-53786-v1 to be ready
Inference service chaiml-qwen-dpo-exp1-da-53786-v1 ready after 120.4336769580841s
Pipeline stage MKMLDeployer completed in 121.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.969879627227783s
Received healthy response to inference request in 3.5254757404327393s
Received healthy response to inference request in 3.350645065307617s
Received healthy response to inference request in 3.4201483726501465s
Received healthy response to inference request in 3.479621648788452s
5 requests
0 failed requests
5th percentile: 3.364545726776123
10th percentile: 3.3784463882446287
20th percentile: 3.4062477111816407
30th percentile: 3.432043027877808
40th percentile: 3.45583233833313
50th percentile: 3.479621648788452
60th percentile: 3.497963285446167
70th percentile: 3.516304922103882
80th percentile: 3.614356517791748
90th percentile: 3.7921180725097656
95th percentile: 3.8809988498687744
99th percentile: 3.9521034717559815
mean time: 3.5491540908813475
Pipeline stage StressChecker completed in 18.92s
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 0.61s
Shutdown handler de-registered
chaiml-qwen-dpo-exp1-da_53786_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5994.20s
Shutdown handler de-registered
chaiml-qwen-dpo-exp1-da_53786_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen-dpo-exp1-da_53786_v1 status is now torndown due to DeploymentManager action