developer_uid: NischayDnk
submission_id: chaiml-qwenrp-32b-sft-exp2_v1
model_name: chaiml-qwenrp-32b-sft-exp2_v1
model_group: ChaiML/qwenrp-32b-sft-ex
status: torndown
timestamp: 2025-04-24T12:05:52+00:00
num_battles: 7728
num_wins: 3826
celo_rating: 1283.76
family_friendly_score: 0.5562
family_friendly_standard_error: 0.007026258748437891
submission_type: basic
model_repo: ChaiML/qwenrp-32b-sft-exp2
model_architecture: Qwen2ForCausalLM
model_num_parameters: 32763417600.0
best_of: 5
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.39100561459121297, 'latency_mean': 2.5574529504776002, 'latency_p50': 2.545537829399109, 'latency_p90': 2.866646885871887}, {'batch_size': 3, 'throughput': 0.8688581106300567, 'latency_mean': 3.435677852630615, 'latency_p50': 3.413334369659424, 'latency_p90': 3.8989372730255125}, {'batch_size': 5, 'throughput': 1.1919553443818023, 'latency_mean': 4.17304743051529, 'latency_p50': 4.161129117012024, 'latency_p90': 4.750917077064514}, {'batch_size': 6, 'throughput': 1.2979767683021148, 'latency_mean': 4.585021039247513, 'latency_p50': 4.586847186088562, 'latency_p90': 5.06680269241333}, {'batch_size': 8, 'throughput': 1.455417286437834, 'latency_mean': 5.451555249691009, 'latency_p50': 5.49825119972229, 'latency_p90': 6.1032472372055055}, {'batch_size': 10, 'throughput': 1.6040095465992532, 'latency_mean': 6.178142465353012, 'latency_p50': 6.227833151817322, 'latency_p90': 6.944606614112854}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-qwenrp-32b-sft-exp2_v1
is_internal_developer: False
language_model: ChaiML/qwenrp-32b-sft-exp2
model_size: 33B
ranking_group: single
throughput_3p7s: 1.0
us_pacific_date: 2025-04-24
win_ratio: 0.49508281573498963
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_start|>', '\n', '<|im_end|>'], 'max_input_tokens': 768, 'best_of': 5, '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-qwenrp-32b-sft-exp2-v1-mkmlizer
Waiting for job on chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer to finish
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ║ _____ __ __ ║
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ║ /___/ ║
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ║ ║
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ║ ║
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ║ belonging to: ║
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ║ ║
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ║ ║
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: Downloaded to shared memory in 106.568s
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzff8cs1k, device:0
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: quantized model in 63.633s
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: Processed model ChaiML/qwenrp-32b-sft-exp2 in 170.202s
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp2-v1
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp2-v1/config.json
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp2-v1/added_tokens.json
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp2-v1/tokenizer_config.json
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp2-v1/special_tokens_map.json
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp2-v1/merges.txt
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp2-v1/vocab.json
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp2-v1/tokenizer.json
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp2-v1/flywheel_model.2.safetensors
Failed to get response for submission chaiml-ghost-girl-letha_81645_v3: HTTPConnectionPool(host='chaiml-ghost-girl-letha-81645-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp2-v1/flywheel_model.1.safetensors
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp2-v1/flywheel_model.0.safetensors
chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:19, 39.92it/s] Loading 0: 2%|▏ | 16/771 [00:00<00:09, 75.83it/s] Loading 0: 4%|▎ | 27/771 [00:00<00:08, 89.71it/s] Loading 0: 5%|▍ | 37/771 [00:00<00:07, 92.42it/s] Loading 0: 6%|▌ | 47/771 [00:00<00:13, 55.40it/s] Loading 0: 7%|▋ | 55/771 [00:00<00:13, 53.07it/s] Loading 0: 8%|▊ | 65/771 [00:01<00:12, 58.20it/s] Loading 0: 10%|▉ | 76/771 [00:01<00:09, 69.58it/s] Loading 0: 11%|█▏ | 87/771 [00:01<00:08, 79.08it/s] Loading 0: 12%|█▏ | 96/771 [00:01<00:08, 81.64it/s] Loading 0: 14%|█▎ | 106/771 [00:01<00:10, 63.15it/s] Loading 0: 15%|█▍ | 114/771 [00:01<00:10, 62.15it/s] Loading 0: 16%|█▌ | 121/771 [00:01<00:10, 60.33it/s] Loading 0: 17%|█▋ | 133/771 [00:01<00:09, 68.69it/s] Loading 0: 20%|█▉ | 151/771 [00:02<00:06, 91.44it/s] Loading 0: 21%|██ | 161/771 [00:02<00:07, 78.93it/s] Loading 0: 22%|██▏ | 170/771 [00:02<00:10, 59.92it/s] Loading 0: 23%|██▎ | 178/771 [00:02<00:09, 59.66it/s] Loading 0: 24%|██▍ | 185/771 [00:02<00:10, 57.92it/s] Loading 0: 25%|██▌ | 196/771 [00:02<00:08, 68.72it/s] Loading 0: 27%|██▋ | 207/771 [00:03<00:07, 77.94it/s] Loading 0: 28%|██▊ | 216/771 [00:03<00:06, 80.85it/s] Loading 0: 29%|██▉ | 226/771 [00:03<00:08, 62.16it/s] Loading 0: 30%|███ | 234/771 [00:03<00:10, 52.81it/s] Loading 0: 32%|███▏ | 244/771 [00:03<00:08, 62.01it/s] Loading 0: 33%|███▎ | 255/771 [00:03<00:07, 72.05it/s] Loading 0: 34%|███▍ | 264/771 [00:03<00:06, 75.92it/s] Loading 0: 35%|███▌ | 273/771 [00:04<00:06, 73.01it/s] Loading 0: 37%|███▋ | 286/771 [00:04<00:07, 63.48it/s] Loading 0: 38%|███▊ | 294/771 [00:04<00:08, 54.49it/s] Loading 0: 39%|███▉ | 303/771 [00:19<03:43, 2.10it/s] Loading 0: 40%|████ | 311/771 [00:19<02:42, 2.82it/s] Loading 0: 41%|████ | 318/771 [00:19<02:02, 3.69it/s] Loading 0: 43%|████▎ | 328/771 [00:19<01:21, 5.46it/s] Loading 0: 44%|████▍ | 338/771 [00:19<00:54, 7.88it/s] Loading 0: 45%|████▌ | 347/771 [00:20<00:43, 9.79it/s] Loading 0: 46%|████▌ | 354/771 [00:20<00:34, 12.02it/s] Loading 0: 47%|████▋ | 364/771 [00:20<00:23, 17.02it/s] Loading 0: 49%|████▉ | 376/771 [00:20<00:16, 24.04it/s] Loading 0: 50%|█████ | 388/771 [00:20<00:12, 31.89it/s] Loading 0: 52%|█████▏ | 398/771 [00:20<00:09, 39.66it/s] Loading 0: 53%|█████▎ | 407/771 [00:20<00:09, 39.35it/s] Loading 0: 54%|█████▍ | 415/771 [00:21<00:08, 40.91it/s] Loading 0: 55%|█████▌ | 425/771 [00:21<00:07, 47.28it/s] Loading 0: 57%|█████▋ | 437/771 [00:21<00:05, 56.33it/s] Loading 0: 58%|█████▊ | 449/771 [00:21<00:05, 64.15it/s] Loading 0: 60%|██████ | 466/771 [00:21<00:04, 65.12it/s] Loading 0: 61%|██████▏ | 474/771 [00:21<00:05, 56.98it/s] Loading 0: 63%|██████▎ | 485/771 [00:22<00:04, 62.22it/s] Loading 0: 64%|██████▍ | 497/771 [00:22<00:04, 68.23it/s] Loading 0: 66%|██████▌ | 509/771 [00:22<00:03, 73.03it/s] Loading 0: 68%|██████▊ | 526/771 [00:22<00:03, 71.17it/s] Loading 0: 69%|██████▉ | 534/771 [00:22<00:03, 60.30it/s] Loading 0: 71%|███████ | 544/771 [00:22<00:03, 67.49it/s] Loading 0: 72%|███████▏ | 555/771 [00:23<00:02, 76.06it/s] Loading 0: 73%|███████▎ | 564/771 [00:23<00:02, 78.98it/s] Loading 0: 74%|███████▍ | 573/771 [00:23<00:02, 75.68it/s] Loading 0: 76%|███████▌ | 586/771 [00:23<00:02, 65.16it/s] Loading 0: 77%|███████▋ | 594/771 [00:23<00:03, 55.10it/s] Loading 0: 78%|███████▊ | 604/771 [00:23<00:02, 63.00it/s] Loading 0: 80%|███████▉ | 615/771 [00:23<00:02, 71.80it/s] Loading 0: 81%|████████ | 624/771 [00:24<00:01, 74.86it/s] Loading 0: 82%|████████▏ | 633/771 [00:38<01:04, 2.15it/s] Loading 0: 84%|████████▍ | 646/771 [00:38<00:37, 3.31it/s] Loading 0: 85%|████████▍ | 654/771 [00:39<00:28, 4.18it/s] Loading 0: 86%|████████▌ | 664/771 [00:39<00:18, 5.88it/s] Loading 0: 88%|████████▊ | 676/771 [00:39<00:11, 8.63it/s] Loading 0: 89%|████████▉ | 688/771 [00:39<00:06, 12.25it/s] Loading 0: 91%|█████████ | 698/771 [00:39<00:04, 16.25it/s] Loading 0: 92%|█████████▏| 707/771 [00:40<00:03, 18.97it/s] Loading 0: 93%|█████████▎| 714/771 [00:40<00:02, 21.62it/s] Loading 0: 94%|█████████▍| 725/771 [00:40<00:01, 28.63it/s] Loading 0: 95%|█████████▌| 736/771 [00:40<00:00, 37.56it/s] Loading 0: 97%|█████████▋| 748/771 [00:40<00:00, 46.38it/s] Loading 0: 98%|█████████▊| 759/771 [00:40<00:00, 56.20it/s] Loading 0: 100%|█████████▉| 768/771 [00:48<00:00, 4.15it/s]
Job chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer completed after 206.73s with status: succeeded
Stopping job with name chaiml-qwenrp-32b-sft-exp2-v1-mkmlizer
Pipeline stage MKMLizer completed in 207.19s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwenrp-32b-sft-exp2-v1
Waiting for inference service chaiml-qwenrp-32b-sft-exp2-v1 to be ready
Inference service chaiml-qwenrp-32b-sft-exp2-v1 ready after 140.4504451751709s
Pipeline stage MKMLDeployer completed in 140.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.6335606575012207s
Received healthy response to inference request in 2.6989657878875732s
Received healthy response to inference request in 2.801847219467163s
Received healthy response to inference request in 2.868757486343384s
Received healthy response to inference request in 2.5918774604797363s
5 requests
0 failed requests
5th percentile: 2.6132951259613035
10th percentile: 2.634712791442871
20th percentile: 2.677548122406006
30th percentile: 2.719542074203491
40th percentile: 2.760694646835327
50th percentile: 2.801847219467163
60th percentile: 2.8286113262176515
70th percentile: 2.8553754329681396
80th percentile: 3.0217181205749513
90th percentile: 3.3276393890380858
95th percentile: 3.4806000232696532
99th percentile: 3.6029685306549073
mean time: 2.9190017223358153
Pipeline stage StressChecker completed in 16.22s
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 0.71s
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 0.66s
Shutdown handler de-registered
chaiml-qwenrp-32b-sft-exp2_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 0.11s
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-qwenrp-32b-sft-exp2-v1-profiler
Waiting for inference service chaiml-qwenrp-32b-sft-exp2-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 6019.85s
Shutdown handler de-registered
chaiml-qwenrp-32b-sft-exp2_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwenrp-32b-sft-exp2_v1 status is now torndown due to DeploymentManager action