chaiml-qwenbsft-dpoexp8_44986

developer_uid: NischayDnk

submission_id: chaiml-qwenbsft-dpoexp8_44986_v1

model_name: chaiml-qwenbsft-dpoexp8_44986_v1

model_group: ChaiML/qwenbsft-dpoexp8-

status: torndown

timestamp: 2025-04-10T19:36:30+00:00

num_battles: 8029

num_wins: 4044

celo_rating: 1283.6

family_friendly_score: 0.47019999999999995

family_friendly_standard_error: 0.007058497857193129

submission_type: basic

model_repo: ChaiML/qwenbsft-dpoexp8-qwendatav1-dpo10kfixv2

model_architecture: Qwen2ForCausalLM

model_num_parameters: 14769689600.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.47016054430453247, 'latency_mean': 2.1268682408332826, 'latency_p50': 2.120657444000244, 'latency_p90': 2.3470784187316895}, {'batch_size': 3, 'throughput': 0.8788809996282334, 'latency_mean': 3.404992527961731, 'latency_p50': 3.415843963623047, 'latency_p90': 3.757229232788086}, {'batch_size': 5, 'throughput': 1.060719662312986, 'latency_mean': 4.702481280565262, 'latency_p50': 4.718767166137695, 'latency_p90': 5.331270933151245}, {'batch_size': 6, 'throughput': 1.1140891593444309, 'latency_mean': 5.356311435699463, 'latency_p50': 5.316015124320984, 'latency_p90': 6.142176151275635}, {'batch_size': 10, 'throughput': 1.2035729142560128, 'latency_mean': 8.263816776275634, 'latency_p50': 8.261066436767578, 'latency_p90': 9.246809244155884}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-qwenbsft-dpoexp8_44986_v1

is_internal_developer: False

language_model: ChaiML/qwenbsft-dpoexp8-qwendatav1-dpo10kfixv2

model_size: 15B

ranking_group: single

throughput_3p7s: 0.93

us_pacific_date: 2025-04-10

win_ratio: 0.5036741810935359

generation_params: {'temperature': 0.7, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.3, 'frequency_penalty': 0.3, 'stopping_words': ['You:', '\n', '###'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}:{message}\n', 'user_template': '{user_name}:{message}\n', 'response_template': '{bot_name}:', '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-qwenbsft-dpoexp8-44986-v1-mkmlizer
Waiting for job on chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer to finish
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ║       /___/                                                         ║
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ║                                                                     ║
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ║                                                                     ║
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ║                                                                     ║
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ║                                                                     ║
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: Downloaded to shared memory in 52.346s
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_x9zwabe, device:0
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: quantized model in 36.663s
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: Processed model ChaiML/qwenbsft-dpoexp8-qwendatav1-dpo10kfixv2 in 89.010s
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwenbsft-dpoexp8-44986-v1
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwenbsft-dpoexp8-44986-v1/config.json
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwenbsft-dpoexp8-44986-v1/added_tokens.json
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwenbsft-dpoexp8-44986-v1/tokenizer_config.json
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwenbsft-dpoexp8-44986-v1/special_tokens_map.json
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwenbsft-dpoexp8-44986-v1/merges.txt
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwenbsft-dpoexp8-44986-v1/vocab.json
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwenbsft-dpoexp8-44986-v1/tokenizer.json
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwenbsft-dpoexp8-44986-v1/flywheel_model.1.safetensors
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwenbsft-dpoexp8-44986-v1/flywheel_model.0.safetensors
chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:03, 142.10it/s]
Loading 0:   5%|▌         | 30/579 [00:00<00:04, 127.33it/s]
Loading 0:   8%|▊         | 49/579 [00:00<00:03, 152.89it/s]
Loading 0:  11%|█         | 65/579 [00:00<00:03, 134.21it/s]
Loading 0:  14%|█▍        | 81/579 [00:00<00:05, 95.55it/s] 
Loading 0:  16%|█▌        | 94/579 [00:00<00:04, 102.00it/s]
Loading 0:  18%|█▊        | 107/579 [00:00<00:04, 106.52it/s]
Loading 0:  21%|██        | 120/579 [00:01<00:04, 111.79it/s]
Loading 0:  24%|██▍       | 138/579 [00:01<00:03, 129.59it/s]
Loading 0:  27%|██▋       | 154/579 [00:01<00:03, 134.37it/s]
Loading 0:  29%|██▉       | 169/579 [00:01<00:03, 129.16it/s]
Loading 0:  32%|███▏      | 188/579 [00:01<00:02, 145.34it/s]
Loading 0:  35%|███▌      | 204/579 [00:01<00:04, 90.32it/s] 
Loading 0:  38%|███▊      | 219/579 [00:01<00:03, 100.80it/s]
Loading 0:  40%|████      | 233/579 [00:02<00:03, 101.85it/s]
Loading 0:  43%|████▎     | 251/579 [00:02<00:02, 119.12it/s]
Loading 0:  46%|████▌     | 267/579 [00:02<00:02, 127.24it/s]
Loading 0:  49%|████▊     | 282/579 [00:02<00:02, 124.19it/s]
Loading 0:  51%|█████▏    | 297/579 [00:02<00:02, 102.03it/s]
Loading 0:  53%|█████▎    | 309/579 [00:02<00:02, 97.74it/s] 
Loading 0:  56%|█████▋    | 327/579 [00:02<00:02, 111.92it/s]
Loading 0:  59%|█████▊    | 340/579 [00:02<00:02, 115.16it/s]
Loading 0:  61%|██████    | 353/579 [00:03<00:01, 117.07it/s]
Loading 0:  64%|██████▎   | 369/579 [00:03<00:01, 128.10it/s]
Loading 0:  67%|██████▋   | 387/579 [00:03<00:01, 136.90it/s]
Loading 0:  70%|██████▉   | 405/579 [00:03<00:01, 99.53it/s] 
Loading 0:  72%|███████▏  | 417/579 [00:03<00:01, 94.62it/s]
Loading 0:  75%|███████▌  | 435/579 [00:03<00:01, 109.50it/s]
Loading 0:  77%|███████▋  | 448/579 [00:03<00:01, 113.62it/s]
Loading 0:  80%|███████▉  | 461/579 [00:04<00:01, 117.13it/s]
Loading 0:  83%|████████▎ | 483/579 [00:04<00:00, 137.25it/s]
Loading 0:  86%|████████▌ | 498/579 [00:04<00:00, 133.06it/s]
Loading 0:  88%|████████▊ | 512/579 [00:22<00:00, 133.06it/s]
Loading 0:  89%|████████▊ | 513/579 [00:26<00:27,  2.39it/s] 
Loading 0:  90%|████████▉ | 521/579 [00:26<00:20,  2.89it/s]
Loading 0:  92%|█████████▏| 534/579 [00:26<00:11,  4.05it/s]
Loading 0:  95%|█████████▌| 552/579 [00:26<00:04,  6.31it/s]
Loading 0:  98%|█████████▊| 568/579 [00:26<00:01,  9.07it/s]
                                                            
Job chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer completed after 116.7s with status: succeeded
Stopping job with name chaiml-qwenbsft-dpoexp8-44986-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.18s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwenbsft-dpoexp8-44986-v1
Waiting for inference service chaiml-qwenbsft-dpoexp8-44986-v1 to be ready
Inference service chaiml-qwenbsft-dpoexp8-44986-v1 ready after 110.4105818271637s
Pipeline stage MKMLDeployer completed in 110.98s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6407766342163086s
Received healthy response to inference request in 1.9119305610656738s
Received healthy response to inference request in 2.026355266571045s
Received healthy response to inference request in 2.009648561477661s
Received healthy response to inference request in 1.9665045738220215s
5 requests
0 failed requests
5th percentile: 1.9228453636169434
10th percentile: 1.933760166168213
20th percentile: 1.955589771270752
30th percentile: 1.9751333713531494
40th percentile: 1.9923909664154054
50th percentile: 2.009648561477661
60th percentile: 2.0163312435150145
70th percentile: 2.0230139255523683
80th percentile: 2.1492395401000977
90th percentile: 2.395008087158203
95th percentile: 2.517892360687256
99th percentile: 2.616199779510498
mean time: 2.111043119430542
Pipeline stage StressChecker completed in 12.03s
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 0.70s
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 0.70s
Shutdown handler de-registered
chaiml-qwenbsft-dpoexp8_44986_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 4952.89s
Shutdown handler de-registered
chaiml-qwenbsft-dpoexp8_44986_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwenbsft-dpoexp8_44986_v1 status is now torndown due to DeploymentManager action