developer_uid: rirv938
submission_id: qwen-qwen2-5-32b_v10
model_name: qwen-qwen2-5-32b_v10
model_group: Qwen/Qwen2.5-32B
status: torndown
timestamp: 2025-01-03T04:09:30+00:00
num_battles: 12
num_wins: 7
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: Qwen/Qwen2.5-32B
model_architecture: Qwen2ForCausalLM
model_num_parameters: 32763417600.0
best_of: 4
max_input_tokens: 768
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.2784993971980816, 'latency_mean': 3.590575385093689, 'latency_p50': 3.600664734840393, 'latency_p90': 4.008476042747498}, {'batch_size': 2, 'throughput': 0.4583750621074913, 'latency_mean': 4.35310826420784, 'latency_p50': 4.294194579124451, 'latency_p90': 4.818256855010986}, {'batch_size': 3, 'throughput': 0.6124652095436746, 'latency_mean': 4.867410397529602, 'latency_p50': 4.841572880744934, 'latency_p90': 5.407927060127259}, {'batch_size': 4, 'throughput': 0.7323244710115284, 'latency_mean': 5.447680518627167, 'latency_p50': 5.485622406005859, 'latency_p90': 6.12975754737854}, {'batch_size': 5, 'throughput': 0.823608083980053, 'latency_mean': 6.016263654232025, 'latency_p50': 6.005221724510193, 'latency_p90': 6.645604681968688}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: qwen-qwen2-5-32b_v10
ineligible_reason: num_battles<5000
is_internal_developer: True
language_model: Qwen/Qwen2.5-32B
model_size: 33B
ranking_group: single
throughput_3p7s: 0.31
us_pacific_date: 2025-01-02
win_ratio: 0.5833333333333334
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', '<|end_of_text|>', 'You:'], 'max_input_tokens': 768, 'best_of': 4, '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 qwen-qwen2-5-32b-v10-mkmlizer
Waiting for job on qwen-qwen2-5-32b-v10-mkmlizer to finish
qwen-qwen2-5-32b-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
qwen-qwen2-5-32b-v10-mkmlizer: ║ _____ __ __ ║
qwen-qwen2-5-32b-v10-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
qwen-qwen2-5-32b-v10-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
qwen-qwen2-5-32b-v10-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
qwen-qwen2-5-32b-v10-mkmlizer: ║ /___/ ║
qwen-qwen2-5-32b-v10-mkmlizer: ║ ║
qwen-qwen2-5-32b-v10-mkmlizer: ║ Version: 0.11.38 ║
qwen-qwen2-5-32b-v10-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
qwen-qwen2-5-32b-v10-mkmlizer: ║ https://mk1.ai ║
qwen-qwen2-5-32b-v10-mkmlizer: ║ ║
qwen-qwen2-5-32b-v10-mkmlizer: ║ The license key for the current software has been verified as ║
qwen-qwen2-5-32b-v10-mkmlizer: ║ belonging to: ║
qwen-qwen2-5-32b-v10-mkmlizer: ║ ║
qwen-qwen2-5-32b-v10-mkmlizer: ║ Chai Research Corp. ║
qwen-qwen2-5-32b-v10-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
qwen-qwen2-5-32b-v10-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
qwen-qwen2-5-32b-v10-mkmlizer: ║ ║
qwen-qwen2-5-32b-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission qwen-qwen2-5-32b_v9: HTTPConnectionPool(host='qwen-qwen2-5-32b-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
qwen-qwen2-5-32b-v10-mkmlizer: Downloaded to shared memory in 90.125s
qwen-qwen2-5-32b-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv15jyx0a, device:0
qwen-qwen2-5-32b-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission qwen-qwen2-5-32b_v9: HTTPConnectionPool(host='qwen-qwen2-5-32b-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
qwen-qwen2-5-32b-v10-mkmlizer: quantized model in 62.904s
qwen-qwen2-5-32b-v10-mkmlizer: Processed model Qwen/Qwen2.5-32B in 153.030s
qwen-qwen2-5-32b-v10-mkmlizer: creating bucket guanaco-mkml-models
qwen-qwen2-5-32b-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
qwen-qwen2-5-32b-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/qwen-qwen2-5-32b-v10
qwen-qwen2-5-32b-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/qwen-qwen2-5-32b-v10/config.json
qwen-qwen2-5-32b-v10-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/qwen-qwen2-5-32b-v10/added_tokens.json
qwen-qwen2-5-32b-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/qwen-qwen2-5-32b-v10/tokenizer_config.json
qwen-qwen2-5-32b-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/qwen-qwen2-5-32b-v10/special_tokens_map.json
qwen-qwen2-5-32b-v10-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/qwen-qwen2-5-32b-v10/merges.txt
qwen-qwen2-5-32b-v10-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/qwen-qwen2-5-32b-v10/vocab.json
qwen-qwen2-5-32b-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/qwen-qwen2-5-32b-v10/tokenizer.json
qwen-qwen2-5-32b-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/qwen-qwen2-5-32b-v10/flywheel_model.2.safetensors
qwen-qwen2-5-32b-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/qwen-qwen2-5-32b-v10/flywheel_model.0.safetensors
qwen-qwen2-5-32b-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/qwen-qwen2-5-32b-v10/flywheel_model.1.safetensors
qwen-qwen2-5-32b-v10-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:17, 43.49it/s] Loading 0: 2%|▏ | 17/771 [00:00<00:10, 71.59it/s] Loading 0: 4%|▍ | 34/771 [00:00<00:10, 69.08it/s] Loading 0: 5%|▌ | 41/771 [00:00<00:13, 54.91it/s] Loading 0: 7%|▋ | 53/771 [00:00<00:11, 64.41it/s] Loading 0: 8%|▊ | 65/771 [00:00<00:09, 71.88it/s] Loading 0: 11%|█ | 82/771 [00:01<00:10, 68.84it/s] Loading 0: 12%|█▏ | 92/771 [00:01<00:09, 74.72it/s] Loading 0: 13%|█▎ | 101/771 [00:01<00:09, 74.10it/s] Loading 0: 14%|█▍ | 109/771 [00:01<00:09, 72.02it/s] Loading 0: 16%|█▌ | 121/771 [00:01<00:08, 76.69it/s] Loading 0: 17%|█▋ | 130/771 [00:01<00:09, 67.73it/s] Loading 0: 18%|█▊ | 138/771 [00:02<00:11, 57.16it/s] Loading 0: 19%|█▉ | 149/771 [00:02<00:09, 64.25it/s] Loading 0: 21%|██ | 161/771 [00:02<00:08, 71.02it/s] Loading 0: 23%|██▎ | 178/771 [00:02<00:08, 73.96it/s] Loading 0: 24%|██▍ | 186/771 [00:02<00:09, 62.15it/s] Loading 0: 26%|██▌ | 197/771 [00:02<00:08, 67.45it/s] Loading 0: 27%|██▋ | 209/771 [00:03<00:07, 73.44it/s] Loading 0: 29%|██▉ | 226/771 [00:03<00:07, 75.32it/s] Loading 0: 30%|███ | 234/771 [00:03<00:08, 62.79it/s] Loading 0: 32%|███▏ | 245/771 [00:03<00:07, 67.69it/s] Loading 0: 33%|███▎ | 257/771 [00:03<00:07, 72.90it/s] Loading 0: 36%|███▌ | 274/771 [00:03<00:06, 73.73it/s] Loading 0: 37%|███▋ | 282/771 [00:04<00:07, 62.06it/s] Loading 0: 38%|███▊ | 293/771 [00:04<00:07, 66.77it/s] Loading 0: 39%|███▉ | 303/771 [00:18<03:09, 2.47it/s] Loading 0: 41%|████ | 314/771 [00:18<02:11, 3.48it/s] Loading 0: 42%|████▏ | 322/771 [00:19<01:41, 4.41it/s] Loading 0: 43%|████▎ | 329/771 [00:19<01:21, 5.39it/s] Loading 0: 44%|████▍ | 341/771 [00:19<00:52, 8.14it/s] Loading 0: 46%|████▌ | 353/771 [00:19<00:35, 11.78it/s] Loading 0: 48%|████▊ | 370/771 [00:19<00:22, 17.84it/s] Loading 0: 49%|████▉ | 378/771 [00:20<00:19, 20.18it/s] Loading 0: 50%|█████ | 389/771 [00:20<00:14, 26.08it/s] Loading 0: 52%|█████▏ | 401/771 [00:20<00:11, 33.58it/s] Loading 0: 54%|█████▍ | 418/771 [00:20<00:08, 43.16it/s] Loading 0: 55%|█████▌ | 426/771 [00:20<00:08, 42.34it/s] Loading 0: 57%|█████▋ | 437/771 [00:21<00:06, 49.43it/s] Loading 0: 58%|█████▊ | 449/771 [00:21<00:05, 57.49it/s] Loading 0: 60%|██████ | 466/771 [00:21<00:04, 64.66it/s] Loading 0: 61%|██████▏ | 474/771 [00:21<00:05, 56.34it/s] Loading 0: 63%|██████▎ | 485/771 [00:21<00:04, 62.47it/s] Loading 0: 64%|██████▍ | 497/771 [00:21<00:03, 68.82it/s] Loading 0: 67%|██████▋ | 514/771 [00:22<00:03, 71.10it/s] Loading 0: 68%|██████▊ | 522/771 [00:22<00:04, 60.89it/s] Loading 0: 69%|██████▉ | 533/771 [00:22<00:03, 65.80it/s] Loading 0: 71%|███████ | 545/771 [00:22<00:03, 71.48it/s] Loading 0: 73%|███████▎ | 562/771 [00:22<00:02, 73.27it/s] Loading 0: 74%|███████▍ | 570/771 [00:22<00:03, 61.81it/s] Loading 0: 75%|███████▌ | 581/771 [00:23<00:02, 67.04it/s] Loading 0: 77%|███████▋ | 593/771 [00:23<00:02, 72.78it/s] Loading 0: 79%|███████▉ | 610/771 [00:23<00:02, 74.03it/s] Loading 0: 80%|████████ | 618/771 [00:23<00:02, 59.83it/s] Loading 0: 81%|████████▏ | 627/771 [00:38<00:58, 2.44it/s] Loading 0: 83%|████████▎ | 639/771 [00:38<00:37, 3.55it/s] Loading 0: 84%|████████▍ | 650/771 [00:38<00:24, 4.96it/s] Loading 0: 85%|████████▌ | 658/771 [00:38<00:17, 6.28it/s] Loading 0: 86%|████████▋ | 665/771 [00:38<00:14, 7.42it/s] Loading 0: 88%|████████▊ | 677/771 [00:38<00:08, 11.05it/s] Loading 0: 89%|████████▉ | 689/771 [00:39<00:05, 15.68it/s] Loading 0: 92%|█████████▏| 706/771 [00:39<00:02, 23.02it/s] Loading 0: 93%|█████████▎| 714/771 [00:39<00:02, 25.28it/s] Loading 0: 94%|█████████▍| 725/771 [00:39<00:01, 31.88it/s] Loading 0: 96%|█████████▌| 737/771 [00:39<00:00, 40.12it/s] Loading 0: 98%|█████████▊| 754/771 [00:47<00:03, 5.18it/s] Loading 0: 99%|█████████▊| 760/771 [00:47<00:01, 6.08it/s]
Job qwen-qwen2-5-32b-v10-mkmlizer completed after 186.38s with status: succeeded
Stopping job with name qwen-qwen2-5-32b-v10-mkmlizer
Pipeline stage MKMLizer completed in 186.91s
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 qwen-qwen2-5-32b-v10
Waiting for inference service qwen-qwen2-5-32b-v10 to be ready
Failed to get response for submission qwen-qwen2-5-32b_v9: HTTPConnectionPool(host='qwen-qwen2-5-32b-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission qwen-qwen2-5-32b_v9: HTTPConnectionPool(host='qwen-qwen2-5-32b-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission qwen-qwen2-5-32b_v9: HTTPConnectionPool(host='qwen-qwen2-5-32b-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission qwen-qwen2-5-32b_v9: HTTPConnectionPool(host='qwen-qwen2-5-32b-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission qwen-qwen2-5-32b_v9: HTTPConnectionPool(host='qwen-qwen2-5-32b-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission qwen-qwen2-5-32b_v9: HTTPConnectionPool(host='qwen-qwen2-5-32b-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission qwen-qwen2-5-32b_v9: HTTPConnectionPool(host='qwen-qwen2-5-32b-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission qwen-qwen2-5-32b_v9: HTTPConnectionPool(host='qwen-qwen2-5-32b-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service qwen-qwen2-5-32b-v10 ready after 331.3657205104828s
Pipeline stage MKMLDeployer completed in 331.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4916350841522217s
Failed to get response for submission qwen-qwen2-5-32b_v9: HTTPConnectionPool(host='qwen-qwen2-5-32b-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 3.3283965587615967s
Received healthy response to inference request in 1.8047966957092285s
Received healthy response to inference request in 3.349069595336914s
Received healthy response to inference request in 0.9770488739013672s
5 requests
0 failed requests
5th percentile: 1.1425984382629395
10th percentile: 1.3081480026245118
20th percentile: 1.6392471313476562
30th percentile: 1.942164373397827
40th percentile: 2.2168997287750245
50th percentile: 2.4916350841522217
60th percentile: 2.8263396739959714
70th percentile: 3.1610442638397216
80th percentile: 3.3325311660766603
90th percentile: 3.340800380706787
95th percentile: 3.3449349880218504
99th percentile: 3.3482426738739015
mean time: 2.390189361572266
Pipeline stage StressChecker completed in 13.34s
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 0.66s
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 0.71s
Shutdown handler de-registered
qwen-qwen2-5-32b_v10 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 0.12s
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 qwen-qwen2-5-32b-v10-profiler
Waiting for inference service qwen-qwen2-5-32b-v10-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError("('http://qwen-qwen2-5-32b-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')")
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError("('http://qwen-qwen2-5-32b-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')")
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError("('http://qwen-qwen2-5-32b-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')")
Shutdown handler de-registered
qwen-qwen2-5-32b_v10 status is now torndown due to DeploymentManager action
qwen-qwen2-5-32b_v10 status is now torndown due to DeploymentManager action
qwen-qwen2-5-32b_v10 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1