nischaydnk-qwen-dpo-v7-rp-v1

developer_uid: NischayDnk

submission_id: nischaydnk-qwen-dpo-v7-rp-v1_v2

model_name: qwen-dpov1-diffformat

model_group: NischayDnk/qwen-dpo-v7-r

status: torndown

timestamp: 2025-02-20T03:45:44+00:00

num_battles: 5447

num_wins: 2485

celo_rating: 1236.72

family_friendly_score: 0.6348

family_friendly_standard_error: 0.006809243129746507

submission_type: basic

model_repo: NischayDnk/qwen-dpo-v7-rp-v1

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': 0.4718078373180141, 'latency_mean': 2.119411244392395, 'latency_p50': 2.121645450592041, 'latency_p90': 2.332872462272644}, {'batch_size': 3, 'throughput': 0.873164632950666, 'latency_mean': 3.427941712141037, 'latency_p50': 3.428264617919922, 'latency_p90': 3.801045227050781}, {'batch_size': 5, 'throughput': 1.0496673220576493, 'latency_mean': 4.740881558656692, 'latency_p50': 4.776911020278931, 'latency_p90': 5.231018328666687}, {'batch_size': 6, 'throughput': 1.1093901014378413, 'latency_mean': 5.377160919904709, 'latency_p50': 5.37011456489563, 'latency_p90': 6.012754034996033}, {'batch_size': 10, 'throughput': 1.193771491301326, 'latency_mean': 8.306587677001954, 'latency_p50': 8.327322006225586, 'latency_p90': 9.395365262031556}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: qwen-dpov1-diffformat

is_internal_developer: False

language_model: NischayDnk/qwen-dpo-v7-rp-v1

model_size: 15B

ranking_group: single

throughput_3p7s: 0.92

us_pacific_date: 2025-02-19

win_ratio: 0.4562144299614467

generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, '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': 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 nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer
Waiting for job on nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer to finish
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ║     _____            __           __                                ║
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ║       /___/                                                         ║
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ║                                                                     ║
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ║  https://mk1.ai                                                     ║
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ║                                                                     ║
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ║  belonging to:                                                      ║
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ║                                                                     ║
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ║  Chai Research Corp.                                                ║
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ║                                                                     ║
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-20250219-c-4epoc_80755_v1: HTTPConnectionPool(host='chaiml-20250219-c-4epoc-80755-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: Downloaded to shared memory in 43.251s
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdt1sfjhj, device:0
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: quantized model in 38.075s
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: Processed model NischayDnk/qwen-dpo-v7-rp-v1 in 81.326s
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: creating bucket guanaco-mkml-models
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nischaydnk-qwen-dpo-v7-rp-v1-v2
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nischaydnk-qwen-dpo-v7-rp-v1-v2/config.json
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nischaydnk-qwen-dpo-v7-rp-v1-v2/tokenizer_config.json
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nischaydnk-qwen-dpo-v7-rp-v1-v2/special_tokens_map.json
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/nischaydnk-qwen-dpo-v7-rp-v1-v2/added_tokens.json
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/nischaydnk-qwen-dpo-v7-rp-v1-v2/merges.txt
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/nischaydnk-qwen-dpo-v7-rp-v1-v2/flywheel_model.1.safetensors
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nischaydnk-qwen-dpo-v7-rp-v1-v2/flywheel_model.0.safetensors
nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:04, 125.34it/s]
Loading 0:   5%|▍         | 28/579 [00:00<00:04, 120.87it/s]
Loading 0:   7%|▋         | 41/579 [00:00<00:04, 119.55it/s]
Loading 0:  10%|█         | 58/579 [00:00<00:03, 138.02it/s]
Loading 0:  13%|█▎        | 74/579 [00:00<00:03, 145.54it/s]
Loading 0:  15%|█▌        | 89/579 [00:00<00:06, 81.37it/s] 
Loading 0:  18%|█▊        | 106/579 [00:01<00:04, 95.84it/s]
Loading 0:  21%|██        | 119/579 [00:01<00:04, 101.40it/s]
Loading 0:  23%|██▎       | 132/579 [00:01<00:04, 105.93it/s]
Loading 0:  26%|██▌       | 151/579 [00:01<00:03, 126.64it/s]
Loading 0:  29%|██▊       | 166/579 [00:01<00:03, 132.10it/s]
Loading 0:  31%|███▏      | 181/579 [00:01<00:03, 129.24it/s]
Loading 0:  34%|███▎      | 195/579 [00:01<00:04, 85.65it/s] 
Loading 0:  36%|███▌      | 208/579 [00:01<00:03, 93.11it/s]
Loading 0:  38%|███▊      | 221/579 [00:02<00:03, 100.18it/s]
Loading 0:  41%|████▏     | 239/579 [00:02<00:02, 118.42it/s]
Loading 0:  44%|████▍     | 255/579 [00:02<00:02, 126.57it/s]
Loading 0:  46%|████▋     | 269/579 [00:02<00:02, 122.51it/s]
Loading 0:  50%|████▉     | 287/579 [00:02<00:02, 136.20it/s]
Loading 0:  52%|█████▏    | 302/579 [00:02<00:03, 91.90it/s] 
Loading 0:  54%|█████▍    | 315/579 [00:02<00:02, 96.91it/s]
Loading 0:  57%|█████▋    | 328/579 [00:03<00:02, 100.80it/s]
Loading 0:  59%|█████▉    | 341/579 [00:03<00:02, 103.62it/s]
Loading 0:  62%|██████▏   | 359/579 [00:03<00:01, 121.56it/s]
Loading 0:  65%|██████▍   | 375/579 [00:03<00:01, 128.04it/s]
Loading 0:  67%|██████▋   | 389/579 [00:03<00:01, 121.02it/s]
Loading 0:  70%|██████▉   | 405/579 [00:03<00:01, 95.29it/s] 
Loading 0:  72%|███████▏  | 416/579 [00:03<00:01, 90.77it/s]
Loading 0:  74%|███████▍  | 431/579 [00:03<00:01, 103.49it/s]
Loading 0:  77%|███████▋  | 447/579 [00:04<00:01, 115.51it/s]
Loading 0:  79%|███████▉  | 460/579 [00:04<00:01, 117.78it/s]
Loading 0:  82%|████████▏ | 473/579 [00:04<00:00, 118.79it/s]
Loading 0:  85%|████████▍ | 491/579 [00:04<00:00, 133.01it/s]
Loading 0:  88%|████████▊ | 510/579 [00:04<00:00, 146.61it/s]
Loading 0:  88%|████████▊ | 512/579 [00:22<00:00, 146.61it/s]
Loading 0:  89%|████████▊ | 513/579 [00:26<00:36,  1.81it/s] 
Loading 0:  90%|████████▉ | 521/579 [00:27<00:25,  2.29it/s]
Loading 0:  92%|█████████▏| 534/579 [00:27<00:13,  3.42it/s]
Loading 0:  95%|█████████▍| 550/579 [00:27<00:05,  5.38it/s]
Loading 0:  98%|█████████▊| 568/579 [00:27<00:01,  8.40it/s]
                                                            
Job nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer completed after 105.68s with status: succeeded
Stopping job with name nischaydnk-qwen-dpo-v7-rp-v1-v2-mkmlizer
Pipeline stage MKMLizer completed in 106.96s
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 nischaydnk-qwen-dpo-v7-rp-v1-v2
Waiting for inference service nischaydnk-qwen-dpo-v7-rp-v1-v2 to be ready
Failed to get response for submission chaiml-20250219-c-4epoc_80755_v1: HTTPConnectionPool(host='chaiml-20250219-c-4epoc-80755-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service nischaydnk-qwen-dpo-v7-rp-v1-v2 ready after 182.89924907684326s
Pipeline stage MKMLDeployer completed in 183.47s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7926177978515625s
Received healthy response to inference request in 1.8535001277923584s
Received healthy response to inference request in 2.9083900451660156s
Received healthy response to inference request in 2.090200185775757s
Received healthy response to inference request in 1.401228427886963s
5 requests
0 failed requests
5th percentile: 1.491682767868042
10th percentile: 1.582137107849121
20th percentile: 1.7630457878112793
30th percentile: 1.9008401393890382
40th percentile: 1.9955201625823975
50th percentile: 2.090200185775757
60th percentile: 2.371167230606079
70th percentile: 2.652134275436401
80th percentile: 2.8157722473144533
90th percentile: 2.8620811462402345
95th percentile: 2.885235595703125
99th percentile: 2.9037591552734376
mean time: 2.209187316894531
Pipeline stage StressChecker completed in 12.15s
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 0.59s
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 0.58s
Shutdown handler de-registered
nischaydnk-qwen-dpo-v7-rp-v1_v2 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 2836.73s
Shutdown handler de-registered
nischaydnk-qwen-dpo-v7-rp-v1_v2 status is now inactive due to auto deactivation removed underperforming models
nischaydnk-qwen-dpo-v7-rp-v1_v2 status is now torndown due to DeploymentManager action
nischaydnk-qwen-dpo-v7-rp-v1_v2 status is now torndown due to DeploymentManager action
nischaydnk-qwen-dpo-v7-rp-v1_v2 status is now torndown due to DeploymentManager action