developer_uid: NischayDnk
submission_id: chaiml-qwen25rp-ft-sft-_88298_v5
model_name: chaiml-qwen25rp-ft-sft-_88298_v5
model_group: ChaiML/qwen25rp-ft-sft-e
status: torndown
timestamp: 2025-04-04T17:58:59+00:00
num_battles: 35
num_wins: 20
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/qwen25rp-ft-sft-exp2-del12k
model_architecture: Qwen2ForCausalLM
model_num_parameters: 32763417600.0
best_of: 2
max_input_tokens: 720
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.28723896314810105, 'latency_mean': 3.4813586354255674, 'latency_p50': 3.5011661052703857, 'latency_p90': 3.895076847076416}, {'batch_size': 2, 'throughput': 0.4717786006361994, 'latency_mean': 4.225996795892716, 'latency_p50': 4.2246915102005005, 'latency_p90': 4.661677026748658}, {'batch_size': 3, 'throughput': 0.6410170805649116, 'latency_mean': 4.669748741388321, 'latency_p50': 4.6814576387405396, 'latency_p90': 5.202693271636963}, {'batch_size': 4, 'throughput': 0.7806024094910115, 'latency_mean': 5.101843806505204, 'latency_p50': 5.110501527786255, 'latency_p90': 5.60406494140625}, {'batch_size': 5, 'throughput': 0.9051479564923762, 'latency_mean': 5.484746595621109, 'latency_p50': 5.464408874511719, 'latency_p90': 6.047755551338196}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-qwen25rp-ft-sft-_88298_v5
ineligible_reason: num_battles<5000
is_internal_developer: False
language_model: ChaiML/qwen25rp-ft-sft-exp2-del12k
model_size: 33B
ranking_group: single
throughput_3p7s: 0.35
us_pacific_date: 2025-04-04
win_ratio: 0.5714285714285714
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': ['\n', '<|im_end|>'], 'max_input_tokens': 720, 'best_of': 2, '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-v5-mkmlizer
Waiting for job on chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer to finish
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ║     _____            __           __                                ║
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ║       /___/                                                         ║
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ║                                                                     ║
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ║                                                                     ║
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ║  belonging to:                                                      ║
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ║                                                                     ║
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ║                                                                     ║
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: Downloaded to shared memory in 90.046s
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptaarbvct, device:0
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: quantized model in 64.670s
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: Processed model ChaiML/qwen25rp-ft-sft-exp2-del12k in 154.717s
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v5
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v5/config.json
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v5/added_tokens.json
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v5/special_tokens_map.json
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v5/tokenizer_config.json
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v5/merges.txt
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v5/vocab.json
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v5/flywheel_model.2.safetensors
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v5/flywheel_model.0.safetensors
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen25rp-ft-sft-88298-v5/flywheel_model.1.safetensors
chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:20, 38.16it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:10, 73.20it/s]
Loading 0:   4%|▎         | 27/771 [00:00<00:08, 86.42it/s]
Loading 0:   5%|▍         | 36/771 [00:00<00:08, 85.29it/s]
Loading 0:   6%|▌         | 46/771 [00:00<00:13, 55.18it/s]
Loading 0:   7%|▋         | 53/771 [00:00<00:15, 46.14it/s]
Loading 0:   8%|▊         | 64/771 [00:01<00:12, 58.23it/s]
Loading 0:  10%|▉         | 75/771 [00:01<00:10, 68.62it/s]
Loading 0:  11%|█         | 84/771 [00:01<00:09, 72.50it/s]
Loading 0:  12%|█▏        | 93/771 [00:01<00:09, 69.64it/s]
Loading 0:  14%|█▎        | 106/771 [00:01<00:11, 60.35it/s]
Loading 0:  15%|█▍        | 113/771 [00:01<00:11, 57.69it/s]
Loading 0:  16%|█▌        | 121/771 [00:01<00:11, 58.16it/s]
Loading 0:  17%|█▋        | 132/771 [00:02<00:09, 68.43it/s]
Loading 0:  18%|█▊        | 142/771 [00:02<00:08, 75.10it/s]
Loading 0:  20%|█▉        | 152/771 [00:02<00:07, 79.92it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:08, 74.66it/s]
Loading 0:  22%|██▏       | 169/771 [00:02<00:11, 50.85it/s]
Loading 0:  23%|██▎       | 176/771 [00:02<00:11, 51.29it/s]
Loading 0:  24%|██▍       | 184/771 [00:02<00:10, 57.06it/s]
Loading 0:  25%|██▌       | 195/771 [00:03<00:08, 68.24it/s]
Loading 0:  26%|██▋       | 203/771 [00:03<00:08, 70.04it/s]
Loading 0:  27%|██▋       | 211/771 [00:03<00:08, 67.00it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:08, 60.83it/s]
Loading 0:  30%|███       | 233/771 [00:03<00:10, 50.23it/s]
Loading 0:  32%|███▏      | 244/771 [00:03<00:08, 60.64it/s]
Loading 0:  33%|███▎      | 255/771 [00:04<00:07, 70.11it/s]
Loading 0:  34%|███▍      | 264/771 [00:04<00:06, 73.23it/s]
Loading 0:  35%|███▌      | 273/771 [00:04<00:07, 70.10it/s]
Loading 0:  37%|███▋      | 286/771 [00:04<00:08, 59.79it/s]
Loading 0:  38%|███▊      | 293/771 [00:04<00:09, 50.65it/s]
Loading 0:  39%|███▉      | 303/771 [00:19<03:42,  2.10it/s]
Loading 0:  40%|████      | 311/771 [00:19<02:42,  2.82it/s]
Loading 0:  41%|████      | 318/771 [00:19<02:03,  3.68it/s]
Loading 0:  43%|████▎     | 328/771 [00:19<01:21,  5.43it/s]
Loading 0:  44%|████▍     | 338/771 [00:20<00:55,  7.81it/s]
Loading 0:  45%|████▍     | 346/771 [00:20<00:43,  9.85it/s]
Loading 0:  46%|████▌     | 353/771 [00:20<00:36, 11.41it/s]
Loading 0:  47%|████▋     | 364/771 [00:20<00:24, 16.83it/s]
Loading 0:  49%|████▊     | 375/771 [00:20<00:16, 23.52it/s]
Loading 0:  50%|████▉     | 383/771 [00:20<00:13, 28.62it/s]
Loading 0:  51%|█████     | 391/771 [00:21<00:11, 33.40it/s]
Loading 0:  53%|█████▎    | 406/771 [00:21<00:09, 40.09it/s]
Loading 0:  54%|█████▎    | 413/771 [00:21<00:09, 37.97it/s]
Loading 0:  55%|█████▍    | 424/771 [00:21<00:07, 48.03it/s]
Loading 0:  56%|█████▋    | 435/771 [00:21<00:05, 58.14it/s]
Loading 0:  58%|█████▊    | 444/771 [00:21<00:05, 63.46it/s]
Loading 0:  59%|█████▉    | 453/771 [00:22<00:05, 63.11it/s]
Loading 0:  60%|██████    | 466/771 [00:22<00:05, 55.10it/s]
Loading 0:  61%|██████▏   | 473/771 [00:22<00:06, 47.69it/s]
Loading 0:  63%|██████▎   | 484/771 [00:22<00:04, 57.92it/s]
Loading 0:  64%|██████▍   | 495/771 [00:22<00:04, 67.41it/s]
Loading 0:  65%|██████▌   | 504/771 [00:22<00:03, 71.49it/s]
Loading 0:  67%|██████▋   | 513/771 [00:23<00:03, 69.33it/s]
Loading 0:  68%|██████▊   | 526/771 [00:23<00:03, 61.67it/s]
Loading 0:  69%|██████▉   | 533/771 [00:23<00:04, 51.51it/s]
Loading 0:  71%|███████   | 545/771 [00:23<00:03, 59.98it/s]
Loading 0:  72%|███████▏  | 556/771 [00:23<00:03, 69.74it/s]
Loading 0:  74%|███████▎  | 567/771 [00:23<00:02, 77.71it/s]
Loading 0:  75%|███████▍  | 576/771 [00:23<00:02, 79.59it/s]
Loading 0:  76%|███████▌  | 586/771 [00:24<00:02, 63.06it/s]
Loading 0:  77%|███████▋  | 594/771 [00:24<00:03, 53.58it/s]
Loading 0:  78%|███████▊  | 604/771 [00:24<00:02, 62.14it/s]
Loading 0:  80%|███████▉  | 615/771 [00:24<00:02, 71.88it/s]
Loading 0:  81%|████████  | 624/771 [00:24<00:01, 75.03it/s]
Loading 0:  82%|████████▏ | 633/771 [00:39<01:03,  2.17it/s]
Loading 0:  84%|████████▍ | 646/771 [00:39<00:37,  3.33it/s]
Loading 0:  85%|████████▍ | 653/771 [00:39<00:28,  4.10it/s]
Loading 0:  86%|████████▌ | 664/771 [00:39<00:17,  6.02it/s]
Loading 0:  88%|████████▊ | 675/771 [00:39<00:11,  8.63it/s]
Loading 0:  89%|████████▊ | 683/771 [00:39<00:07, 11.08it/s]
Loading 0:  90%|████████▉ | 691/771 [00:40<00:05, 14.11it/s]
Loading 0:  92%|█████████▏| 706/771 [00:40<00:03, 20.31it/s]
Loading 0:  92%|█████████▏| 713/771 [00:40<00:02, 22.17it/s]
Loading 0:  94%|█████████▍| 724/771 [00:40<00:01, 29.88it/s]
Loading 0:  95%|█████████▌| 735/771 [00:40<00:00, 38.83it/s]
Loading 0:  96%|█████████▋| 744/771 [00:40<00:00, 45.60it/s]
Loading 0:  98%|█████████▊| 753/771 [00:41<00:00, 49.68it/s]
Loading 0:  99%|█████████▉| 766/771 [00:48<00:01,  4.28it/s]
                                                            

Job chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer completed after 188.11s with status: succeeded
Stopping job with name chaiml-qwen25rp-ft-sft-88298-v5-mkmlizer
Pipeline stage MKMLizer completed in 188.68s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.32s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen25rp-ft-sft-88298-v5
Waiting for inference service chaiml-qwen25rp-ft-sft-88298-v5 to be ready
Inference service chaiml-qwen25rp-ft-sft-88298-v5 ready after 120.8703875541687s
Pipeline stage MKMLDeployer completed in 121.40s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.9771604537963867s
Received healthy response to inference request in 3.4576432704925537s
Received healthy response to inference request in 3.261425018310547s
Received healthy response to inference request in 3.2291488647460938s
Failed to get response for submission chaiml-qwen25rp-ft-sft-_88298_v2: HTTPConnectionPool(host='chaiml-qwen25rp-ft-sft-88298-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 3.2354798316955566s
5 requests
0 failed requests
5th percentile: 3.2304150581359865
10th percentile: 3.231681251525879
20th percentile: 3.234213638305664
30th percentile: 3.2406688690185548
40th percentile: 3.2510469436645506
50th percentile: 3.261425018310547
60th percentile: 3.3399123191833495
70th percentile: 3.418399620056152
80th percentile: 3.5615467071533202
90th percentile: 3.7693535804748537
95th percentile: 3.87325701713562
99th percentile: 3.9563797664642335
mean time: 3.4321714878082275
Pipeline stage StressChecker completed in 18.57s
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 0.93s
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 0.77s
Shutdown handler de-registered
chaiml-qwen25rp-ft-sft-_88298_v5 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
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
%s, retrying in %s seconds...
Retrying (%r) after connection broken by '%r': %s
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-qwen25rp-ft-sft-88298-v5-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 1.44s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-qwen25rp-ft-sft-88298-v5-profiler
Waiting for inference service chaiml-qwen25rp-ft-sft-88298-v5-profiler to be ready
Inference service chaiml-qwen25rp-ft-sft-88298-v5-profiler ready after 70.48827648162842s
Pipeline stage MKMLProfilerDeployer completed in 70.81s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-qwen25rp-ft-s6dc4fd1fda654481a64346da5e6e8a5c-deplo2jcn4:/code/chaiverse_profiler_1743792647 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-qwen25rp-ft-s6dc4fd1fda654481a64346da5e6e8a5c-deplo2jcn4 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1743792647 && python profiles.py profile --best_of_n 2 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 720 --output_tokens 64 --summary /code/chaiverse_profiler_1743792647/summary.json'
kubectl exec -it chaiml-qwen25rp-ft-s6dc4fd1fda654481a64346da5e6e8a5c-deplo2jcn4 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1743792647/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1917.65s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-qwen25rp-ft-sft-88298-v5-profiler is running
Tearing down inference service chaiml-qwen25rp-ft-sft-88298-v5-profiler
Service chaiml-qwen25rp-ft-sft-88298-v5-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.42s
Shutdown handler de-registered
chaiml-qwen25rp-ft-sft-_88298_v5 status is now torndown due to DeploymentManager action