chaiml-qwen25rp-ft-sft-_88298

developer_uid: NischayDnk

submission_id: chaiml-qwen25rp-ft-sft-_88298_v8

model_name: chaiml-qwen25rp-ft-sft-_88298_v8

model_group: ChaiML/qwen25rp-ft-sft-e

status: torndown

timestamp: 2025-04-17T22:38:04+00:00

num_battles: 8105

num_wins: 3880

celo_rating: 1270.74

family_friendly_score: 0.5884

family_friendly_standard_error: 0.006959675854520813

submission_type: basic

model_repo: ChaiML/qwen25rp-ft-sft-exp2-del12k

model_architecture: Qwen2ForCausalLM

model_num_parameters: 32763417600.0

best_of: 1

max_input_tokens: 720

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.285873977766275, 'latency_mean': 3.4979485154151915, 'latency_p50': 3.512415647506714, 'latency_p90': 3.8472164154052733}, {'batch_size': 2, 'throughput': 0.4828387133669794, 'latency_mean': 4.136206252574921, 'latency_p50': 4.121069431304932, 'latency_p90': 4.587775850296021}, {'batch_size': 3, 'throughput': 0.6488531942227734, 'latency_mean': 4.621056693792343, 'latency_p50': 4.626352429389954, 'latency_p90': 5.041535496711731}, {'batch_size': 4, 'throughput': 0.7943928137010086, 'latency_mean': 5.011564469337463, 'latency_p50': 5.0217427015304565, 'latency_p90': 5.640573883056641}, {'batch_size': 5, 'throughput': 0.9143211997589136, 'latency_mean': 5.440144499540329, 'latency_p50': 5.486921429634094, 'latency_p90': 6.068798685073853}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-qwen25rp-ft-sft-_88298_v8

is_internal_developer: False

language_model: ChaiML/qwen25rp-ft-sft-exp2-del12k

model_size: 33B

ranking_group: single

throughput_3p7s: 0.36

us_pacific_date: 2025-04-17

win_ratio: 0.47871684145589144

generation_params: {'temperature': 0.55, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.35, 'frequency_penalty': 0.35, 'stopping_words': ['<|im_end|>', '\n'], 'max_input_tokens': 720, 'best_of': 1, 'max_output_tokens': 64}

formatter: {'memory_template': '', '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-qwen25rp-ft-sft-88298-v8-mkmlizer
Waiting for job on chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer to finish
Stopping job with name chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer
Waiting for job on chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer to finish
Stopping job with name chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer
%s, retrying in %s seconds...
Stopping job with name chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer
%s, retrying in %s seconds...
Stopping job with name chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer
Waiting for job on chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer to finish
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ║     _____            __           __                                ║
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ║       /___/                                                         ║
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ║                                                                     ║
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ║                                                                     ║
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ║  belonging to:                                                      ║
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ║                                                                     ║
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ║                                                                     ║
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: Downloaded to shared memory in 91.475s
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3f53z_w9, device:0
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v8
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v8/config.json
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v8/added_tokens.json
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v8/special_tokens_map.json
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v8/tokenizer_config.json
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v8/merges.txt
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v8/vocab.json
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v8/tokenizer.json
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v8/flywheel_model.2.safetensors
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v8/flywheel_model.1.safetensors
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v8/flywheel_model.0.safetensors
chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:19, 39.21it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:09, 75.96it/s]
Loading 0:   4%|▎         | 27/771 [00:00<00:08, 90.05it/s]
Loading 0:   5%|▍         | 37/771 [00:00<00:07, 92.56it/s]
Loading 0:   6%|▌         | 47/771 [00:00<00:13, 53.78it/s]
Loading 0:   7%|▋         | 55/771 [00:00<00:13, 52.05it/s]
Loading 0:   8%|▊         | 64/771 [00:01<00:11, 60.02it/s]
Loading 0:  10%|▉         | 75/771 [00:01<00:09, 71.61it/s]
Loading 0:  11%|█         | 84/771 [00:01<00:09, 76.10it/s]
Loading 0:  12%|█▏        | 93/771 [00:01<00:09, 73.40it/s]
Loading 0:  14%|█▎        | 106/771 [00:01<00:10, 62.52it/s]
Loading 0:  15%|█▍        | 114/771 [00:01<00:10, 61.91it/s]
Loading 0:  16%|█▌        | 121/771 [00:01<00:10, 59.77it/s]
Loading 0:  17%|█▋        | 132/771 [00:01<00:08, 71.01it/s]
Loading 0:  18%|█▊        | 142/771 [00:02<00:08, 78.02it/s]
Loading 0:  20%|█▉        | 152/771 [00:02<00:07, 83.68it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:07, 78.09it/s]
Loading 0:  22%|██▏       | 170/771 [00:02<00:11, 54.11it/s]
Loading 0:  23%|██▎       | 177/771 [00:02<00:11, 53.90it/s]
Loading 0:  24%|██▍       | 185/771 [00:02<00:10, 55.85it/s]
Loading 0:  25%|██▌       | 196/771 [00:02<00:08, 67.52it/s]
Loading 0:  27%|██▋       | 207/771 [00:03<00:07, 77.28it/s]
Loading 0:  28%|██▊       | 216/771 [00:03<00:06, 80.27it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:08, 61.28it/s]
Loading 0:  30%|███       | 234/771 [00:03<00:10, 52.80it/s]
Loading 0:  32%|███▏      | 245/771 [00:03<00:08, 59.81it/s]
Loading 0:  33%|███▎      | 257/771 [00:03<00:07, 66.75it/s]
Loading 0:  35%|███▍      | 268/771 [00:04<00:06, 75.66it/s]
Loading 0:  36%|███▌      | 279/771 [00:04<00:05, 83.41it/s]
Loading 0:  37%|███▋      | 289/771 [00:04<00:08, 59.23it/s]
Loading 0:  39%|███▊      | 297/771 [00:04<00:07, 59.47it/s]
Loading 0:  39%|███▉      | 304/771 [00:19<03:56,  1.97it/s]
Loading 0:  41%|████      | 315/771 [00:19<02:32,  2.98it/s]
Loading 0:  42%|████▏     | 324/771 [00:19<01:48,  4.13it/s]
Loading 0:  43%|████▎     | 333/771 [00:19<01:17,  5.69it/s]
Loading 0:  45%|████▍     | 346/771 [00:19<00:50,  8.49it/s]
Loading 0:  46%|████▌     | 353/771 [00:20<00:42,  9.83it/s]
Loading 0:  47%|████▋     | 365/771 [00:20<00:28, 14.33it/s]
Loading 0:  49%|████▉     | 377/771 [00:20<00:19, 19.91it/s]
Loading 0:  50%|█████     | 388/771 [00:20<00:14, 26.53it/s]
Loading 0:  52%|█████▏    | 398/771 [00:20<00:11, 33.46it/s]
Loading 0:  53%|█████▎    | 407/771 [00:20<00:10, 34.19it/s]
Loading 0:  54%|█████▍    | 415/771 [00:21<00:09, 37.00it/s]
Loading 0:  55%|█████▌    | 425/771 [00:21<00:07, 43.89it/s]
Loading 0:  57%|█████▋    | 437/771 [00:21<00:06, 53.42it/s]
Loading 0:  58%|█████▊    | 449/771 [00:21<00:05, 61.30it/s]
Loading 0:  60%|██████    | 466/771 [00:21<00:04, 64.19it/s]
Loading 0:  61%|██████▏   | 474/771 [00:21<00:05, 56.62it/s]
Loading 0:  63%|██████▎   | 484/771 [00:22<00:04, 63.71it/s]
Loading 0:  64%|██████▍   | 495/771 [00:22<00:03, 72.79it/s]
Loading 0:  66%|██████▌   | 507/771 [00:22<00:03, 76.79it/s]
Loading 0:  67%|██████▋   | 516/771 [00:22<00:03, 79.46it/s]
Loading 0:  68%|██████▊   | 526/771 [00:22<00:03, 61.91it/s]
Loading 0:  69%|██████▉   | 534/771 [00:22<00:04, 53.82it/s]
Loading 0:  71%|███████   | 545/771 [00:22<00:03, 60.39it/s]
Loading 0:  72%|███████▏  | 556/771 [00:23<00:03, 69.12it/s]
Loading 0:  74%|███████▎  | 567/771 [00:23<00:02, 77.98it/s]
Loading 0:  75%|███████▍  | 576/771 [00:23<00:02, 80.76it/s]
Loading 0:  76%|███████▌  | 586/771 [00:23<00:02, 62.29it/s]
Loading 0:  77%|███████▋  | 594/771 [00:23<00:03, 53.92it/s]
Loading 0:  78%|███████▊  | 605/771 [00:23<00:02, 60.45it/s]
Loading 0:  80%|████████  | 617/771 [00:24<00:02, 67.27it/s]
Loading 0:  81%|████████▏ | 627/771 [00:38<01:00,  2.39it/s]
Loading 0:  83%|████████▎ | 637/771 [00:38<00:40,  3.35it/s]
Loading 0:  84%|████████▍ | 646/771 [00:38<00:28,  4.44it/s]
Loading 0:  85%|████████▍ | 653/771 [00:38<00:21,  5.42it/s]
Loading 0:  86%|████████▌ | 664/771 [00:38<00:13,  8.04it/s]
Loading 0:  88%|████████▊ | 675/771 [00:39<00:08, 11.57it/s]
Loading 0:  89%|████████▉ | 685/771 [00:39<00:05, 15.73it/s]
Loading 0:  90%|█████████ | 694/771 [00:39<00:03, 19.79it/s]
Loading 0:  92%|█████████▏| 706/771 [00:39<00:02, 24.82it/s]
Loading 0:  92%|█████████▏| 713/771 [00:39<00:02, 26.49it/s]
Loading 0:  94%|█████████▍| 724/771 [00:39<00:01, 35.48it/s]
Loading 0:  95%|█████████▌| 735/771 [00:39<00:00, 45.42it/s]
Loading 0:  96%|█████████▋| 744/771 [00:40<00:00, 52.50it/s]
Loading 0:  98%|█████████▊| 753/771 [00:40<00:00, 56.00it/s]
Loading 0:  99%|█████████▉| 766/771 [00:47<00:01,  4.34it/s]
                                                            
Job chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer completed after 186.14s with status: succeeded
Stopping job with name chaiml-qwen25rp-ft-sft-88298-v8-mkmlizer
Pipeline stage MKMLizer completed in 187.70s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen25rp-ft-sft-88298-v8
Waiting for inference service chaiml-qwen25rp-ft-sft-88298-v8 to be ready
Inference service chaiml-qwen25rp-ft-sft-88298-v8 ready after 130.45163679122925s
Pipeline stage MKMLDeployer completed in 130.95s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.6589252948760986s
Received healthy response to inference request in 3.0919456481933594s
Received healthy response to inference request in 3.0954315662384033s
Received healthy response to inference request in 3.10837459564209s
Received healthy response to inference request in 3.111088752746582s
5 requests
0 failed requests
5th percentile: 3.092642831802368
10th percentile: 3.093340015411377
20th percentile: 3.0947343826293947
30th percentile: 3.0980201721191407
40th percentile: 3.103197383880615
50th percentile: 3.10837459564209
60th percentile: 3.1094602584838866
70th percentile: 3.1105459213256834
80th percentile: 3.2206560611724853
90th percentile: 3.439790678024292
95th percentile: 3.5493579864501954
99th percentile: 3.637011833190918
mean time: 3.2131531715393065
Pipeline stage StressChecker completed in 17.35s
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 0.94s
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 0.67s
Shutdown handler de-registered
chaiml-qwen25rp-ft-sft-_88298_v8 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 3222.02s
Shutdown handler de-registered
chaiml-qwen25rp-ft-sft-_88298_v8 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen25rp-ft-sft-_88298_v8 status is now torndown due to DeploymentManager action