developer_uid: NischayDnk
submission_id: chaiml-qwen25rp-ft-sft-_88298_v7
model_name: chaiml-qwen25rp-ft-sft-_88298_v7
model_group: ChaiML/qwen25rp-ft-sft-e
status: torndown
timestamp: 2025-04-17T15:04:40+00:00
num_battles: 7295
num_wins: 3486
celo_rating: 1269.76
family_friendly_score: 0.595
family_friendly_standard_error: 0.00694226187924368
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: 720
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.29268379181045834, 'latency_mean': 3.416593427658081, 'latency_p50': 3.3912994861602783, 'latency_p90': 3.802196478843689}, {'batch_size': 2, 'throughput': 0.4760640119693204, 'latency_mean': 4.190944989919663, 'latency_p50': 4.184125781059265, 'latency_p90': 4.6663489818573}, {'batch_size': 3, 'throughput': 0.6519838422568887, 'latency_mean': 4.569716544151306, 'latency_p50': 4.530973196029663, 'latency_p90': 5.127711510658264}, {'batch_size': 4, 'throughput': 0.7907998862989863, 'latency_mean': 5.0289232742786405, 'latency_p50': 5.020775318145752, 'latency_p90': 5.604373240470886}, {'batch_size': 5, 'throughput': 0.9170966246762444, 'latency_mean': 5.411063240766525, 'latency_p50': 5.4305771589279175, 'latency_p90': 6.027446174621582}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-qwen25rp-ft-sft-_88298_v7
is_internal_developer: False
language_model: ChaiML/qwen25rp-ft-sft-exp2-del12k
model_size: 33B
ranking_group: single
throughput_3p7s: 0.37
us_pacific_date: 2025-04-17
win_ratio: 0.4778615490061686
generation_params: {'temperature': 0.55, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.35, 'frequency_penalty': 0.35, 'stopping_words': ['<|im_end|>', '\n'], 'max_input_tokens': 720, '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-v7-mkmlizer
Waiting for job on chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer to finish
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ║ _____ __ __ ║
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ║ /___/ ║
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ║ ║
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ║ ║
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ║ belonging to: ║
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ║ ║
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ║ ║
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: Downloaded to shared memory in 96.706s
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprx4mfy1p, device:0
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: quantized model in 64.170s
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: Processed model ChaiML/qwen25rp-ft-sft-exp2-del12k in 160.877s
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v7
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v7/config.json
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v7/added_tokens.json
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v7/special_tokens_map.json
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v7/tokenizer_config.json
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v7/merges.txt
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v7/vocab.json
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v7/tokenizer.json
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v7/flywheel_model.2.safetensors
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v7/flywheel_model.1.safetensors
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v7/flywheel_model.0.safetensors
chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:20, 38.18it/s] Loading 0: 2%|▏ | 16/771 [00:00<00:10, 73.22it/s] Loading 0: 4%|▎ | 27/771 [00:00<00:08, 86.58it/s] Loading 0: 5%|▍ | 36/771 [00:00<00:08, 85.79it/s] Loading 0: 6%|▌ | 46/771 [00:00<00:13, 55.48it/s] Loading 0: 7%|▋ | 53/771 [00:00<00:15, 46.37it/s] Loading 0: 8%|▊ | 64/771 [00:01<00:12, 58.72it/s] Loading 0: 10%|▉ | 75/771 [00:01<00:10, 69.25it/s] Loading 0: 11%|█ | 84/771 [00:01<00:09, 73.49it/s] Loading 0: 12%|█▏ | 93/771 [00:01<00:09, 70.76it/s] Loading 0: 14%|█▎ | 106/771 [00:01<00:10, 60.89it/s] Loading 0: 15%|█▍ | 113/771 [00:01<00:11, 58.24it/s] Loading 0: 16%|█▌ | 121/771 [00:01<00:11, 59.08it/s] Loading 0: 17%|█▋ | 133/771 [00:02<00:09, 67.15it/s] Loading 0: 20%|█▉ | 151/771 [00:02<00:07, 88.33it/s] Loading 0: 21%|██ | 161/771 [00:02<00:07, 76.62it/s] Loading 0: 22%|██▏ | 170/771 [00:02<00:10, 57.28it/s] Loading 0: 23%|██▎ | 177/771 [00:02<00:10, 55.46it/s] Loading 0: 24%|██▍ | 185/771 [00:02<00:10, 56.65it/s] Loading 0: 25%|██▌ | 196/771 [00:03<00:08, 67.03it/s] Loading 0: 27%|██▋ | 207/771 [00:03<00:07, 76.25it/s] Loading 0: 28%|██▊ | 216/771 [00:03<00:07, 78.97it/s] Loading 0: 29%|██▉ | 226/771 [00:03<00:08, 61.32it/s] Loading 0: 30%|███ | 234/771 [00:03<00:10, 52.80it/s] Loading 0: 32%|███▏ | 244/771 [00:03<00:08, 61.79it/s] Loading 0: 33%|███▎ | 255/771 [00:03<00:07, 71.83it/s] Loading 0: 34%|███▍ | 264/771 [00:04<00:06, 75.55it/s] Loading 0: 35%|███▌ | 273/771 [00:04<00:06, 72.15it/s] Loading 0: 37%|███▋ | 286/771 [00:04<00:07, 62.44it/s] Loading 0: 38%|███▊ | 294/771 [00:04<00:08, 53.93it/s] Loading 0: 39%|███▉ | 303/771 [00:19<03:42, 2.10it/s] Loading 0: 40%|████ | 311/771 [00:19<02:42, 2.83it/s] Loading 0: 41%|████ | 318/771 [00:19<02:02, 3.71it/s] Loading 0: 43%|████▎ | 328/771 [00:19<01:20, 5.48it/s] Loading 0: 44%|████▍ | 338/771 [00:19<00:54, 7.90it/s] Loading 0: 45%|████▌ | 347/771 [00:20<00:43, 9.73it/s] Loading 0: 46%|████▌ | 354/771 [00:20<00:34, 11.99it/s] Loading 0: 47%|████▋ | 364/771 [00:20<00:24, 16.95it/s] Loading 0: 49%|████▊ | 375/771 [00:20<00:16, 23.83it/s] Loading 0: 50%|████▉ | 383/771 [00:20<00:13, 29.12it/s] Loading 0: 51%|█████ | 391/771 [00:20<00:11, 34.06it/s] Loading 0: 53%|█████▎ | 406/771 [00:21<00:09, 40.12it/s] Loading 0: 54%|█████▎ | 413/771 [00:21<00:09, 38.44it/s] Loading 0: 55%|█████▍ | 424/771 [00:21<00:07, 48.56it/s] Loading 0: 56%|█████▋ | 435/771 [00:21<00:05, 58.91it/s] Loading 0: 58%|█████▊ | 444/771 [00:21<00:05, 64.57it/s] Loading 0: 59%|█████▉ | 453/771 [00:21<00:04, 64.82it/s] Loading 0: 60%|██████ | 466/771 [00:21<00:05, 57.37it/s] Loading 0: 61%|██████▏ | 473/771 [00:22<00:06, 49.42it/s] Loading 0: 63%|██████▎ | 484/771 [00:22<00:04, 60.07it/s] Loading 0: 64%|██████▍ | 495/771 [00:22<00:03, 69.78it/s] Loading 0: 65%|██████▌ | 504/771 [00:22<00:03, 73.62it/s] Loading 0: 67%|██████▋ | 513/771 [00:22<00:03, 71.31it/s] Loading 0: 68%|██████▊ | 526/771 [00:22<00:03, 62.56it/s] Loading 0: 69%|██████▉ | 534/771 [00:23<00:04, 53.67it/s] Loading 0: 71%|███████ | 544/771 [00:23<00:03, 62.25it/s] Loading 0: 72%|███████▏ | 555/771 [00:23<00:02, 72.05it/s] Loading 0: 73%|███████▎ | 564/771 [00:23<00:02, 75.39it/s] Loading 0: 74%|███████▍ | 573/771 [00:23<00:02, 72.47it/s] Loading 0: 76%|███████▌ | 586/771 [00:23<00:02, 63.48it/s] Loading 0: 77%|███████▋ | 594/771 [00:24<00:03, 54.32it/s] Loading 0: 78%|███████▊ | 605/771 [00:24<00:02, 60.37it/s] Loading 0: 80%|███████▉ | 616/771 [00:24<00:02, 69.70it/s] Loading 0: 81%|████████▏ | 627/771 [00:38<01:00, 2.37it/s] Loading 0: 83%|████████▎ | 637/771 [00:38<00:40, 3.30it/s] Loading 0: 84%|████████▍ | 646/771 [00:39<00:28, 4.33it/s] Loading 0: 85%|████████▍ | 653/771 [00:39<00:22, 5.34it/s] Loading 0: 86%|████████▌ | 664/771 [00:39<00:13, 7.91it/s] Loading 0: 88%|████████▊ | 676/771 [00:39<00:08, 11.54it/s] Loading 0: 89%|████████▉ | 687/771 [00:39<00:05, 16.00it/s] Loading 0: 90%|█████████ | 696/771 [00:39<00:03, 20.48it/s] Loading 0: 92%|█████████▏| 706/771 [00:40<00:02, 23.97it/s] Loading 0: 93%|█████████▎| 714/771 [00:40<00:02, 26.47it/s] Loading 0: 94%|█████████▍| 724/771 [00:40<00:01, 34.34it/s] Loading 0: 95%|█████████▌| 735/771 [00:40<00:00, 44.39it/s] Loading 0: 96%|█████████▋| 744/771 [00:40<00:00, 51.58it/s] Loading 0: 98%|█████████▊| 753/771 [00:40<00:00, 55.14it/s] Loading 0: 99%|█████████▉| 766/771 [00:48<00:01, 4.32it/s]
Job chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer completed after 200.35s with status: succeeded
Stopping job with name chaiml-qwen25rp-ft-sft-88298-v7-mkmlizer
Pipeline stage MKMLizer completed in 200.94s
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-v7
Waiting for inference service chaiml-qwen25rp-ft-sft-88298-v7 to be ready
Inference service chaiml-qwen25rp-ft-sft-88298-v7 ready after 130.4882161617279s
Pipeline stage MKMLDeployer completed in 130.95s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 3.5973570346832275s
Received healthy response to inference request in 3.274820566177368s
Received healthy response to inference request in 3.07376766204834s
Received healthy response to inference request in 3.0794835090637207s
5 requests
1 failed requests
5th percentile: 3.074910831451416
10th percentile: 3.076054000854492
20th percentile: 3.0783403396606444
30th percentile: 3.11855092048645
40th percentile: 3.1966857433319094
50th percentile: 3.274820566177368
60th percentile: 3.403835153579712
70th percentile: 3.5328497409820554
80th percentile: 6.904239320755008
90th percentile: 13.51800389289856
95th percentile: 16.824886178970335
99th percentile: 19.47039200782776
mean time: 6.631439447402954
%s, retrying in %s seconds...
Received healthy response to inference request in 3.0756332874298096s
Received healthy response to inference request in 3.070976495742798s
Received healthy response to inference request in 3.0924789905548096s
Received healthy response to inference request in 3.0805864334106445s
Received healthy response to inference request in 3.072950601577759s
5 requests
0 failed requests
5th percentile: 3.07137131690979
10th percentile: 3.0717661380767822
20th percentile: 3.0725557804107666
30th percentile: 3.073487138748169
40th percentile: 3.074560213088989
50th percentile: 3.0756332874298096
60th percentile: 3.0776145458221436
70th percentile: 3.0795958042144775
80th percentile: 3.0829649448394774
90th percentile: 3.0877219676971435
95th percentile: 3.0901004791259767
99th percentile: 3.092003288269043
mean time: 3.078525161743164
Pipeline stage StressChecker completed in 50.98s
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 0.74s
Shutdown handler de-registered
chaiml-qwen25rp-ft-sft-_88298_v7 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 5464.83s
Shutdown handler de-registered
chaiml-qwen25rp-ft-sft-_88298_v7 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen25rp-ft-sft-_88298_v7 status is now torndown due to DeploymentManager action