developer_uid: NischayDnk
submission_id: chaiml-qwen32b-simpoexp_21972_v3
model_name: chaiml-qwen32b-simpoexp_21972_v3
model_group: ChaiML/qwen32b-simpoexp1
status: torndown
timestamp: 2025-04-22T03:16:12+00:00
num_battles: 8191
num_wins: 4712
celo_rating: 1346.78
family_friendly_score: 0.3822
family_friendly_standard_error: 0.0068720180442137955
submission_type: basic
model_repo: ChaiML/qwen32b-simpoexp1-s2-ftsimpoexp4-1330pref
model_architecture: Qwen2ForCausalLM
model_num_parameters: 32759331840.0
best_of: 6
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.38097484591340675, 'latency_mean': 2.624789592027664, 'latency_p50': 2.6321003437042236, 'latency_p90': 2.897000455856323}, {'batch_size': 3, 'throughput': 0.8372635673632852, 'latency_mean': 3.5660934007167815, 'latency_p50': 3.5651477575302124, 'latency_p90': 3.8914284467697144}, {'batch_size': 5, 'throughput': 1.146905700767923, 'latency_mean': 4.3236829125881195, 'latency_p50': 4.304753541946411, 'latency_p90': 4.729884648323059}, {'batch_size': 6, 'throughput': 1.2515044733350051, 'latency_mean': 4.7672521686553955, 'latency_p50': 4.787885308265686, 'latency_p90': 5.262565779685974}, {'batch_size': 8, 'throughput': 1.4302000788602358, 'latency_mean': 5.524182307720184, 'latency_p50': 5.530925393104553, 'latency_p90': 6.253943562507629}, {'batch_size': 10, 'throughput': 1.5411230093098136, 'latency_mean': 6.444482917785645, 'latency_p50': 6.46625828742981, 'latency_p90': 7.140426588058472}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-qwen32b-simpoexp_21972_v3
is_internal_developer: False
language_model: ChaiML/qwen32b-simpoexp1-s2-ftsimpoexp4-1330pref
model_size: 33B
ranking_group: single
throughput_3p7s: 0.91
us_pacific_date: 2025-04-21
win_ratio: 0.5752655353436699
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.35, 'frequency_penalty': 0.35, 'stopping_words': ['<|im_start|>', '\n', '<|im_end|>'], 'max_input_tokens': 768, 'best_of': 6, '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-qwen32b-simpoexp-21972-v3-mkmlizer
Waiting for job on chaiml-qwen32b-simpoexp-21972-v3-mkmlizer to finish
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: Downloaded to shared memory in 101.290s
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpoeu61by1, device:0
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: quantized model in 65.453s
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: Processed model ChaiML/qwen32b-simpoexp1-s2-ftsimpoexp4-1330pref in 166.744s
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v3
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v3/config.json
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v3/added_tokens.json
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v3/tokenizer_config.json
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v3/special_tokens_map.json
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v3/merges.txt
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v3/vocab.json
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v3/tokenizer.json
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v3/flywheel_model.2.safetensors
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v3/flywheel_model.1.safetensors
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-simpoexp-21972-v3/flywheel_model.0.safetensors
chaiml-qwen32b-simpoexp-21972-v3-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:19, 38.35it/s] Loading 0: 2%|▏ | 16/771 [00:00<00:10, 73.19it/s] Loading 0: 4%|▎ | 27/771 [00:00<00:08, 86.86it/s] Loading 0: 5%|▍ | 36/771 [00:00<00:08, 86.64it/s] Loading 0: 6%|▌ | 46/771 [00:00<00:13, 55.53it/s] Loading 0: 7%|▋ | 53/771 [00:00<00:15, 46.88it/s] Loading 0: 8%|▊ | 64/771 [00:01<00:11, 59.55it/s] Loading 0: 10%|▉ | 75/771 [00:01<00:09, 70.52it/s] Loading 0: 11%|█ | 84/771 [00:01<00:09, 74.71it/s] Loading 0: 12%|█▏ | 93/771 [00:01<00:09, 71.29it/s] Loading 0: 14%|█▎ | 106/771 [00:01<00:10, 62.00it/s] Loading 0: 15%|█▍ | 114/771 [00:01<00:10, 60.99it/s] Loading 0: 16%|█▌ | 121/771 [00:01<00:11, 58.33it/s] Loading 0: 17%|█▋ | 132/771 [00:02<00:09, 69.40it/s] Loading 0: 18%|█▊ | 142/771 [00:02<00:08, 76.23it/s] Loading 0: 20%|█▉ | 152/771 [00:02<00:07, 81.68it/s] Loading 0: 21%|██ | 161/771 [00:02<00:07, 76.89it/s] Loading 0: 22%|██▏ | 170/771 [00:02<00:11, 54.14it/s] Loading 0: 23%|██▎ | 177/771 [00:02<00:11, 53.48it/s] Loading 0: 24%|██▍ | 185/771 [00:02<00:10, 55.13it/s] Loading 0: 25%|██▌ | 196/771 [00:03<00:08, 66.59it/s] Loading 0: 27%|██▋ | 207/771 [00:03<00:07, 76.03it/s] Loading 0: 28%|██▊ | 216/771 [00:03<00:07, 78.91it/s] Loading 0: 29%|██▉ | 226/771 [00:03<00:08, 60.72it/s] Loading 0: 30%|███ | 234/771 [00:03<00:10, 52.51it/s] Loading 0: 32%|███▏ | 244/771 [00:03<00:08, 61.48it/s] Loading 0: 33%|███▎ | 255/771 [00:03<00:07, 71.48it/s] Loading 0: 34%|███▍ | 264/771 [00:04<00:06, 75.23it/s] Loading 0: 35%|███▌ | 273/771 [00:04<00:06, 72.52it/s] Loading 0: 37%|███▋ | 286/771 [00:04<00:07, 62.24it/s] Loading 0: 38%|███▊ | 294/771 [00:04<00:08, 53.51it/s] Loading 0: 39%|███▉ | 303/771 [00:19<03:45, 2.07it/s] Loading 0: 40%|████ | 311/771 [00:19<02:44, 2.79it/s] Loading 0: 41%|████ | 318/771 [00:19<02:03, 3.65it/s] Loading 0: 43%|████▎ | 329/771 [00:19<01:19, 5.55it/s] Loading 0: 45%|████▍ | 346/771 [00:20<00:46, 9.14it/s] Loading 0: 46%|████▌ | 353/771 [00:20<00:40, 10.43it/s] Loading 0: 47%|████▋ | 364/771 [00:20<00:27, 14.60it/s] Loading 0: 49%|████▊ | 375/771 [00:20<00:19, 19.97it/s] Loading 0: 50%|████▉ | 383/771 [00:20<00:15, 24.34it/s] Loading 0: 51%|█████ | 391/771 [00:20<00:13, 28.15it/s] Loading 0: 53%|█████▎ | 406/771 [00:21<00:10, 33.89it/s] Loading 0: 54%|█████▎ | 413/771 [00:21<00:10, 33.70it/s] Loading 0: 55%|█████▍ | 424/771 [00:21<00:07, 43.48it/s] Loading 0: 57%|█████▋ | 436/771 [00:21<00:06, 52.42it/s] Loading 0: 58%|█████▊ | 447/771 [00:21<00:05, 62.17it/s] Loading 0: 59%|█████▉ | 456/771 [00:21<00:04, 67.41it/s] Loading 0: 60%|██████ | 466/771 [00:22<00:05, 56.79it/s] Loading 0: 61%|██████▏ | 474/771 [00:22<00:05, 50.99it/s] Loading 0: 63%|██████▎ | 484/771 [00:22<00:04, 59.47it/s] Loading 0: 64%|██████▍ | 495/771 [00:22<00:03, 69.97it/s] Loading 0: 65%|██████▌ | 504/771 [00:22<00:03, 73.70it/s] Loading 0: 67%|██████▋ | 513/771 [00:22<00:03, 70.83it/s] Loading 0: 68%|██████▊ | 526/771 [00:23<00:04, 60.24it/s] Loading 0: 69%|██████▉ | 533/771 [00:23<00:04, 49.23it/s] Loading 0: 71%|███████ | 544/771 [00:23<00:03, 59.78it/s] Loading 0: 72%|███████▏ | 555/771 [00:23<00:03, 69.40it/s] Loading 0: 73%|███████▎ | 564/771 [00:23<00:02, 73.59it/s] Loading 0: 74%|███████▍ | 573/771 [00:23<00:02, 71.52it/s] Loading 0: 76%|███████▌ | 586/771 [00:24<00:02, 61.69it/s] Loading 0: 77%|███████▋ | 593/771 [00:24<00:03, 52.10it/s] Loading 0: 78%|███████▊ | 604/771 [00:24<00:02, 62.47it/s] Loading 0: 80%|███████▉ | 615/771 [00:24<00:02, 72.49it/s] Loading 0: 81%|████████ | 624/771 [00:24<00:01, 76.35it/s] Loading 0: 82%|████████▏ | 633/771 [00:39<01:05, 2.10it/s] Loading 0: 84%|████████▍ | 646/771 [00:39<00:38, 3.24it/s] Loading 0: 85%|████████▍ | 654/771 [00:40<00:28, 4.09it/s] Loading 0: 86%|████████▌ | 664/771 [00:40<00:18, 5.75it/s] Loading 0: 88%|████████▊ | 675/771 [00:40<00:11, 8.25it/s] Loading 0: 89%|████████▊ | 683/771 [00:40<00:08, 10.56it/s] Loading 0: 90%|████████▉ | 691/771 [00:40<00:05, 13.37it/s] Loading 0: 92%|█████████▏| 706/771 [00:40<00:03, 19.16it/s] Loading 0: 92%|█████████▏| 713/771 [00:41<00:02, 21.12it/s] Loading 0: 94%|█████████▍| 724/771 [00:41<00:01, 28.60it/s] Loading 0: 95%|█████████▌| 735/771 [00:41<00:00, 37.40it/s] Loading 0: 96%|█████████▋| 744/771 [00:41<00:00, 44.16it/s] Loading 0: 98%|█████████▊| 753/771 [00:41<00:00, 48.66it/s] Loading 0: 99%|█████████▉| 766/771 [00:49<00:01, 4.24it/s]
Job chaiml-qwen32b-simpoexp-21972-v3-mkmlizer completed after 205.53s with status: succeeded
Stopping job with name chaiml-qwen32b-simpoexp-21972-v3-mkmlizer
Pipeline stage MKMLizer completed in 205.99s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen32b-simpoexp-21972-v3
Waiting for inference service chaiml-qwen32b-simpoexp-21972-v3 to be ready
Inference service chaiml-qwen32b-simpoexp-21972-v3 ready after 130.5350091457367s
Pipeline stage MKMLDeployer completed in 131.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2047290802001953s
Received healthy response to inference request in 2.5764386653900146s
Received healthy response to inference request in 2.6265273094177246s
Received healthy response to inference request in 2.5300099849700928s
Received healthy response to inference request in 2.645678758621216s
5 requests
0 failed requests
5th percentile: 2.539295721054077
10th percentile: 2.5485814571380616
20th percentile: 2.5671529293060305
30th percentile: 2.5864563941955567
40th percentile: 2.6064918518066404
50th percentile: 2.6265273094177246
60th percentile: 2.6341878890991213
70th percentile: 2.6418484687805175
80th percentile: 2.757488822937012
90th percentile: 2.9811089515686033
95th percentile: 3.0929190158843993
99th percentile: 3.182367067337036
mean time: 2.7166767597198485
Pipeline stage StressChecker completed in 14.86s
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 0.72s
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-qwen32b-simpoexp_21972_v3 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4124.17s
Shutdown handler de-registered
chaiml-qwen32b-simpoexp_21972_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen32b-simpoexp_21972_v3 status is now torndown due to DeploymentManager action