chaiml-qwen25rp-ft-sft-_88298

developer_uid: NischayDnk

submission_id: chaiml-qwen25rp-ft-sft-_88298_v1

model_name: chaiml-qwen25rp-ft-sft-_88298_v1

model_group: ChaiML/qwen25rp-ft-sft-e

status: torndown

timestamp: 2025-04-04T15:59:31+00:00

num_battles: 10505

num_wins: 5185

celo_rating: 1279.77

family_friendly_score: 0.5876

family_friendly_standard_error: 0.006961698643291018

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: 512

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.3054482292371663, 'latency_mean': 3.2738126873970033, 'latency_p50': 3.2641724348068237, 'latency_p90': 3.675624394416809}, {'batch_size': 3, 'throughput': 0.7140311703359781, 'latency_mean': 4.18725154042244, 'latency_p50': 4.158518552780151, 'latency_p90': 4.752957463264465}, {'batch_size': 5, 'throughput': 1.0455801840520256, 'latency_mean': 4.7611652433872225, 'latency_p50': 4.802518606185913, 'latency_p90': 5.2677592754364015}, {'batch_size': 6, 'throughput': 1.178555898174632, 'latency_mean': 5.06458692073822, 'latency_p50': 5.078717827796936, 'latency_p90': 5.70034761428833}, {'batch_size': 10, 'throughput': 1.5848045504141375, 'latency_mean': 6.213481841087341, 'latency_p50': 6.183664917945862, 'latency_p90': 7.052917170524597}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-qwen25rp-ft-sft-_88298_v1

is_internal_developer: False

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

model_size: 33B

ranking_group: single

throughput_3p7s: 0.52

us_pacific_date: 2025-04-04

win_ratio: 0.49357448833888623

generation_params: {'temperature': 0.5, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_end|>', '\n'], 'max_input_tokens': 512, '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-v1-mkmlizer
Waiting for job on chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer to finish
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ║       /___/                                                         ║
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ║                                                                     ║
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ║                                                                     ║
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ║                                                                     ║
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ║                                                                     ║
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: Downloaded to shared memory in 113.311s
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7w2urzm0, device:0
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: quantized model in 63.014s
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: Processed model ChaiML/qwen25rp-ft-sft-exp2-del12k in 176.326s
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v1
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v1/config.json
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v1/added_tokens.json
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v1/tokenizer_config.json
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v1/special_tokens_map.json
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v1/merges.txt
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v1/vocab.json
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v1/tokenizer.json
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v1/flywheel_model.2.safetensors
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v1/flywheel_model.0.safetensors
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v1/flywheel_model.1.safetensors
chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:19, 38.88it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:10, 75.06it/s]
Loading 0:   4%|▎         | 27/771 [00:00<00:08, 88.84it/s]
Loading 0:   5%|▍         | 37/771 [00:00<00:08, 91.43it/s]
Loading 0:   6%|▌         | 47/771 [00:00<00:13, 53.37it/s]
Loading 0:   7%|▋         | 55/771 [00:00<00:13, 51.34it/s]
Loading 0:   8%|▊         | 64/771 [00:01<00:11, 59.36it/s]
Loading 0:  10%|▉         | 75/771 [00:01<00:09, 70.76it/s]
Loading 0:  11%|█         | 84/771 [00:01<00:09, 75.32it/s]
Loading 0:  12%|█▏        | 93/771 [00:01<00:09, 72.85it/s]
Loading 0:  14%|█▎        | 106/771 [00:01<00:10, 62.82it/s]
Loading 0:  15%|█▍        | 114/771 [00:01<00:10, 61.57it/s]
Loading 0:  16%|█▌        | 121/771 [00:01<00:11, 59.00it/s]
Loading 0:  17%|█▋        | 132/771 [00:01<00:09, 69.73it/s]
Loading 0:  19%|█▊        | 144/771 [00:02<00:07, 81.69it/s]
Loading 0:  20%|██        | 155/771 [00:02<00:07, 81.38it/s]
Loading 0:  22%|██▏       | 166/771 [00:02<00:09, 62.06it/s]
Loading 0:  23%|██▎       | 174/771 [00:02<00:11, 53.90it/s]
Loading 0:  24%|██▍       | 185/771 [00:02<00:09, 60.49it/s]
Loading 0:  26%|██▌       | 197/771 [00:02<00:08, 67.65it/s]
Loading 0:  27%|██▋       | 208/771 [00:03<00:07, 75.85it/s]
Loading 0:  28%|██▊       | 218/771 [00:03<00:06, 80.77it/s]
Loading 0:  29%|██▉       | 227/771 [00:03<00:08, 61.33it/s]
Loading 0:  30%|███       | 235/771 [00:03<00:09, 57.20it/s]
Loading 0:  32%|███▏      | 245/771 [00:03<00:08, 62.01it/s]
Loading 0:  33%|███▎      | 256/771 [00:03<00:07, 72.38it/s]
Loading 0:  35%|███▍      | 268/771 [00:03<00:06, 76.61it/s]
Loading 0:  36%|███▌      | 278/771 [00:04<00:06, 81.86it/s]
Loading 0:  37%|███▋      | 287/771 [00:04<00:07, 63.11it/s]
Loading 0:  38%|███▊      | 295/771 [00:04<00:08, 58.23it/s]
Loading 0:  39%|███▉      | 303/771 [00:18<03:45,  2.08it/s]
Loading 0:  41%|████      | 315/771 [00:18<02:21,  3.22it/s]
Loading 0:  42%|████▏     | 327/771 [00:18<01:32,  4.80it/s]
Loading 0:  43%|████▎     | 335/771 [00:18<01:09,  6.25it/s]
Loading 0:  45%|████▍     | 346/771 [00:19<00:49,  8.57it/s]
Loading 0:  46%|████▌     | 353/771 [00:19<00:42,  9.95it/s]
Loading 0:  47%|████▋     | 364/771 [00:19<00:28, 14.38it/s]
Loading 0:  49%|████▉     | 376/771 [00:19<00:19, 20.19it/s]
Loading 0:  50%|█████     | 387/771 [00:19<00:14, 26.99it/s]
Loading 0:  51%|█████▏    | 396/771 [00:19<00:11, 32.98it/s]
Loading 0:  53%|█████▎    | 406/771 [00:20<00:10, 34.70it/s]
Loading 0:  54%|█████▎    | 414/771 [00:20<00:10, 35.03it/s]
Loading 0:  55%|█████▍    | 424/771 [00:20<00:07, 43.84it/s]
Loading 0:  56%|█████▋    | 435/771 [00:20<00:06, 54.27it/s]
Loading 0:  58%|█████▊    | 444/771 [00:20<00:05, 60.66it/s]
Loading 0:  59%|█████▉    | 453/771 [00:20<00:05, 62.14it/s]
Loading 0:  60%|██████    | 466/771 [00:21<00:05, 56.30it/s]
Loading 0:  61%|██████▏   | 473/771 [00:21<00:06, 48.77it/s]
Loading 0:  63%|██████▎   | 484/771 [00:21<00:04, 59.53it/s]
Loading 0:  64%|██████▍   | 495/771 [00:21<00:03, 69.25it/s]
Loading 0:  65%|██████▌   | 504/771 [00:21<00:03, 73.34it/s]
Loading 0:  67%|██████▋   | 513/771 [00:21<00:03, 71.45it/s]
Loading 0:  68%|██████▊   | 526/771 [00:22<00:03, 62.05it/s]
Loading 0:  69%|██████▉   | 534/771 [00:22<00:04, 52.86it/s]
Loading 0:  71%|███████   | 544/771 [00:22<00:03, 61.37it/s]
Loading 0:  72%|███████▏  | 555/771 [00:22<00:03, 71.02it/s]
Loading 0:  73%|███████▎  | 564/771 [00:22<00:02, 74.55it/s]
Loading 0:  74%|███████▍  | 573/771 [00:22<00:02, 71.72it/s]
Loading 0:  76%|███████▌  | 586/771 [00:22<00:02, 61.86it/s]
Loading 0:  77%|███████▋  | 593/771 [00:23<00:03, 52.19it/s]
Loading 0:  78%|███████▊  | 604/771 [00:23<00:02, 63.05it/s]
Loading 0:  80%|███████▉  | 615/771 [00:23<00:02, 72.75it/s]
Loading 0:  81%|████████  | 624/771 [00:23<00:01, 76.61it/s]
Loading 0:  82%|████████▏ | 633/771 [00:37<01:03,  2.18it/s]
Loading 0:  84%|████████▍ | 646/771 [00:38<00:37,  3.35it/s]
Loading 0:  85%|████████▍ | 654/771 [00:38<00:27,  4.23it/s]
Loading 0:  86%|████████▌ | 664/771 [00:38<00:17,  5.97it/s]
Loading 0:  88%|████████▊ | 675/771 [00:38<00:11,  8.58it/s]
Loading 0:  89%|████████▉ | 685/771 [00:38<00:07, 11.75it/s]
Loading 0:  90%|█████████ | 694/771 [00:38<00:05, 15.21it/s]
Loading 0:  92%|█████████▏| 706/771 [00:39<00:03, 19.90it/s]
Loading 0:  93%|█████████▎| 714/771 [00:39<00:02, 22.36it/s]
Loading 0:  94%|█████████▍| 725/771 [00:39<00:01, 29.24it/s]
Loading 0:  95%|█████████▌| 736/771 [00:39<00:00, 37.97it/s]
Loading 0:  97%|█████████▋| 747/771 [00:39<00:00, 47.67it/s]
Loading 0:  98%|█████████▊| 756/771 [00:39<00:00, 54.37it/s]
Loading 0:  99%|█████████▉| 766/771 [00:47<00:01,  4.09it/s]
                                                            
Job chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer completed after 206.2s with status: succeeded
Stopping job with name chaiml-qwen25rp-ft-sft-88298-v1-mkmlizer
Pipeline stage MKMLizer completed in 206.65s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen25rp-ft-sft-88298-v1
Waiting for inference service chaiml-qwen25rp-ft-sft-88298-v1 to be ready
Inference service chaiml-qwen25rp-ft-sft-88298-v1 ready after 110.3597047328949s
Pipeline stage MKMLDeployer completed in 110.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.6474685668945312s
Received healthy response to inference request in 3.090643882751465s
Received healthy response to inference request in 3.0975911617279053s
Received healthy response to inference request in 3.1026718616485596s
Received healthy response to inference request in 3.070622444152832s
5 requests
0 failed requests
5th percentile: 3.0746267318725584
10th percentile: 3.0786310195922852
20th percentile: 3.0866395950317385
30th percentile: 3.092033338546753
40th percentile: 3.094812250137329
50th percentile: 3.0975911617279053
60th percentile: 3.099623441696167
70th percentile: 3.1016557216644287
80th percentile: 3.211631202697754
90th percentile: 3.4295498847961428
95th percentile: 3.538509225845337
99th percentile: 3.6256766986846922
mean time: 3.2017995834350588
Pipeline stage StressChecker completed in 17.41s
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 0.74s
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 0.88s
Shutdown handler de-registered
chaiml-qwen25rp-ft-sft-_88298_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-qwen25rp-ft-sft-88298-v1-profiler
Waiting for inference service chaiml-qwen25rp-ft-sft-88298-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 5691.71s
Shutdown handler de-registered
chaiml-qwen25rp-ft-sft-_88298_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen25rp-ft-sft-_88298_v1 status is now torndown due to DeploymentManager action