developer_uid: NischayDnk
submission_id: chaiml-qwen25rp-ft-sft-_88298_v9
model_name: chaiml-qwen25rp-ft-sft-_88298_v9
model_group: ChaiML/qwen25rp-ft-sft-e
status: torndown
timestamp: 2025-05-05T08:50:36+00:00
num_battles: 7939
num_wins: 3975
celo_rating: 1288.15
family_friendly_score: 0.5566
family_friendly_standard_error: 0.007025616556573523
submission_type: basic
model_repo: ChaiML/qwen25rp-ft-sft-exp2-del12k
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': 0.3877878355538541, 'latency_mean': 2.5786617755889893, 'latency_p50': 2.57326877117157, 'latency_p90': 2.8738614082336427}, {'batch_size': 3, 'throughput': 0.8689480776588989, 'latency_mean': 3.436381235122681, 'latency_p50': 3.445495128631592, 'latency_p90': 3.78338508605957}, {'batch_size': 5, 'throughput': 1.1972162708789043, 'latency_mean': 4.155869747400284, 'latency_p50': 4.162637114524841, 'latency_p90': 4.56904444694519}, {'batch_size': 6, 'throughput': 1.2965592833879191, 'latency_mean': 4.588522300720215, 'latency_p50': 4.628285050392151, 'latency_p90': 5.059227371215821}, {'batch_size': 8, 'throughput': 1.4743956619013427, 'latency_mean': 5.375518778562546, 'latency_p50': 5.380094528198242, 'latency_p90': 6.031049203872681}, {'batch_size': 10, 'throughput': 1.596347304479203, 'latency_mean': 6.186139235496521, 'latency_p50': 6.191787123680115, 'latency_p90': 7.077130937576294}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-qwen25rp-ft-sft-_88298_v9
is_internal_developer: False
language_model: ChaiML/qwen25rp-ft-sft-exp2-del12k
model_size: 33B
ranking_group: single
throughput_3p7s: 1.01
us_pacific_date: 2025-05-05
win_ratio: 0.5006927824663056
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': ['\n', '<|im_start|>', '<|im_end|>'], 'max_input_tokens': 768, 'best_of': 5, '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-v9-mkmlizer
Waiting for job on chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer to finish
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ║ _____ __ __ ║
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ║ /___/ ║
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ║ ║
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ║ ║
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ║ belonging to: ║
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ║ ║
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ║ ║
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: Downloaded to shared memory in 110.923s
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmrv02s55, device:0
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: quantized model in 64.426s
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: Processed model ChaiML/qwen25rp-ft-sft-exp2-del12k in 175.349s
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v9
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v9/config.json
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v9/added_tokens.json
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v9/special_tokens_map.json
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v9/tokenizer_config.json
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v9/merges.txt
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v9/vocab.json
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v9/tokenizer.json
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v9/flywheel_model.2.safetensors
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v9/flywheel_model.1.safetensors
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v9/flywheel_model.0.safetensors
chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:21, 36.16it/s] Loading 0: 2%|▏ | 16/771 [00:00<00:10, 70.50it/s] Loading 0: 4%|▎ | 27/771 [00:00<00:08, 83.22it/s] Loading 0: 5%|▍ | 36/771 [00:00<00:08, 83.45it/s] Loading 0: 6%|▌ | 46/771 [00:00<00:14, 51.78it/s] Loading 0: 7%|▋ | 53/771 [00:00<00:16, 44.85it/s] Loading 0: 8%|▊ | 64/771 [00:01<00:12, 56.98it/s] Loading 0: 10%|▉ | 75/771 [00:01<00:10, 67.54it/s] Loading 0: 11%|█ | 84/771 [00:01<00:09, 71.74it/s] Loading 0: 12%|█▏ | 93/771 [00:01<00:09, 69.41it/s] Loading 0: 14%|█▎ | 106/771 [00:01<00:11, 57.46it/s] Loading 0: 15%|█▍ | 113/771 [00:01<00:11, 55.43it/s] Loading 0: 16%|█▌ | 121/771 [00:02<00:11, 56.02it/s] Loading 0: 17%|█▋ | 132/771 [00:02<00:09, 66.70it/s] Loading 0: 18%|█▊ | 142/771 [00:02<00:08, 73.40it/s] Loading 0: 20%|█▉ | 152/771 [00:02<00:07, 79.09it/s] Loading 0: 21%|██ | 161/771 [00:02<00:08, 73.68it/s] Loading 0: 22%|██▏ | 169/771 [00:02<00:12, 50.01it/s] Loading 0: 23%|██▎ | 176/771 [00:02<00:11, 50.57it/s] Loading 0: 24%|██▍ | 184/771 [00:03<00:10, 56.52it/s] Loading 0: 25%|██▌ | 195/771 [00:03<00:08, 67.91it/s] Loading 0: 26%|██▋ | 203/771 [00:03<00:08, 70.51it/s] Loading 0: 27%|██▋ | 211/771 [00:03<00:08, 67.69it/s] Loading 0: 29%|██▉ | 226/771 [00:03<00:09, 59.06it/s] Loading 0: 30%|███ | 233/771 [00:03<00:10, 50.31it/s] Loading 0: 32%|███▏ | 244/771 [00:03<00:08, 61.03it/s] Loading 0: 33%|███▎ | 255/771 [00:04<00:07, 70.63it/s] Loading 0: 34%|███▍ | 264/771 [00:04<00:06, 74.65it/s] Loading 0: 35%|███▌ | 273/771 [00:04<00:06, 71.60it/s] Loading 0: 37%|███▋ | 286/771 [00:04<00:08, 60.04it/s] Loading 0: 38%|███▊ | 293/771 [00:04<00:09, 50.97it/s] Loading 0: 39%|███▉ | 303/771 [00:19<03:44, 2.08it/s] Loading 0: 40%|████ | 311/771 [00:19<02:44, 2.80it/s] Loading 0: 41%|████ | 318/771 [00:20<02:04, 3.65it/s] Loading 0: 43%|████▎ | 328/771 [00:20<01:22, 5.38it/s] Loading 0: 44%|████▍ | 338/771 [00:20<00:55, 7.76it/s] Loading 0: 45%|████▌ | 347/771 [00:20<00:44, 9.52it/s] Loading 0: 46%|████▌ | 354/771 [00:20<00:35, 11.73it/s] Loading 0: 47%|████▋ | 365/771 [00:21<00:24, 16.82it/s] Loading 0: 49%|████▉ | 376/771 [00:21<00:16, 23.51it/s] Loading 0: 50%|█████ | 387/771 [00:21<00:12, 31.55it/s] Loading 0: 51%|█████▏ | 396/771 [00:21<00:09, 38.40it/s] Loading 0: 53%|█████▎ | 406/771 [00:21<00:09, 37.99it/s] Loading 0: 54%|█████▎ | 414/771 [00:21<00:09, 37.87it/s] Loading 0: 55%|█████▌ | 425/771 [00:21<00:07, 45.91it/s] Loading 0: 57%|█████▋ | 436/771 [00:22<00:05, 56.43it/s] Loading 0: 58%|█████▊ | 448/771 [00:22<00:05, 63.86it/s] Loading 0: 60%|█████▉ | 460/771 [00:22<00:04, 75.09it/s] Loading 0: 61%|██████ | 470/771 [00:22<00:05, 55.53it/s] Loading 0: 62%|██████▏ | 478/771 [00:22<00:05, 55.70it/s] Loading 0: 63%|██████▎ | 485/771 [00:22<00:05, 56.06it/s] Loading 0: 64%|██████▍ | 497/771 [00:22<00:04, 64.83it/s] Loading 0: 66%|██████▌ | 509/771 [00:23<00:03, 70.95it/s] Loading 0: 68%|██████▊ | 526/771 [00:23<00:03, 68.33it/s] Loading 0: 69%|██████▉ | 534/771 [00:23<00:04, 58.55it/s] Loading 0: 71%|███████ | 545/771 [00:23<00:03, 64.23it/s] Loading 0: 72%|███████▏ | 557/771 [00:23<00:03, 70.05it/s] Loading 0: 74%|███████▍ | 569/771 [00:24<00:02, 74.46it/s] Loading 0: 76%|███████▌ | 586/771 [00:24<00:02, 70.74it/s] Loading 0: 77%|███████▋ | 594/771 [00:24<00:02, 59.50it/s] Loading 0: 78%|███████▊ | 605/771 [00:24<00:02, 63.85it/s] Loading 0: 80%|███████▉ | 616/771 [00:24<00:02, 72.37it/s] Loading 0: 81%|████████▏ | 627/771 [00:39<00:57, 2.50it/s] Loading 0: 83%|████████▎ | 638/771 [00:39<00:37, 3.51it/s] Loading 0: 84%|████████▍ | 647/771 [00:39<00:27, 4.49it/s] Loading 0: 85%|████████▍ | 654/771 [00:39<00:20, 5.60it/s] Loading 0: 86%|████████▋ | 665/771 [00:40<00:13, 8.11it/s] Loading 0: 88%|████████▊ | 677/771 [00:40<00:08, 11.75it/s] Loading 0: 89%|████████▉ | 689/771 [00:40<00:04, 16.42it/s] Loading 0: 92%|█████████▏| 706/771 [00:40<00:02, 23.49it/s] Loading 0: 93%|█████████▎| 714/771 [00:40<00:02, 25.67it/s] Loading 0: 94%|█████████▍| 725/771 [00:40<00:01, 32.08it/s] Loading 0: 95%|█████████▌| 736/771 [00:41<00:00, 40.50it/s] Loading 0: 97%|█████████▋| 748/771 [00:41<00:00, 48.83it/s] Loading 0: 98%|█████████▊| 759/771 [00:41<00:00, 58.18it/s] Loading 0: 100%|█████████▉| 769/771 [00:49<00:00, 4.41it/s]
Job chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer completed after 207.71s with status: succeeded
Stopping job with name chaiml-qwen25rp-ft-sft-88298-v9-mkmlizer
Pipeline stage MKMLizer completed in 208.20s
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 chaiml-qwen25rp-ft-sft-88298-v9
Waiting for inference service chaiml-qwen25rp-ft-sft-88298-v9 to be ready
Inference service chaiml-qwen25rp-ft-sft-88298-v9 ready after 150.52982187271118s
Pipeline stage MKMLDeployer completed in 151.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2051756381988525s
Received healthy response to inference request in 2.5384342670440674s
Received healthy response to inference request in 2.484027147293091s
Received healthy response to inference request in 2.7191269397735596s
Received healthy response to inference request in 2.4886608123779297s
5 requests
0 failed requests
5th percentile: 2.4849538803100586
10th percentile: 2.4858806133270264
20th percentile: 2.487734079360962
30th percentile: 2.4986155033111572
40th percentile: 2.5185248851776123
50th percentile: 2.5384342670440674
60th percentile: 2.6107113361358643
70th percentile: 2.682988405227661
80th percentile: 2.8163366794586184
90th percentile: 3.0107561588287353
95th percentile: 3.1079658985137937
99th percentile: 3.185733690261841
mean time: 2.6870849609375
Pipeline stage StressChecker completed in 14.80s
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 0.65s
Shutdown handler de-registered
chaiml-qwen25rp-ft-sft-_88298_v9 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 3264.66s
Shutdown handler de-registered
chaiml-qwen25rp-ft-sft-_88298_v9 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen25rp-ft-sft-_88298_v9 status is now torndown due to DeploymentManager action