huihui-ai-qwen2-5-14b-i_61612

developer_uid: Luna1040
submission_id: huihui-ai-qwen2-5-14b-i_61612_v1
model_name: huihui-ai-qwen2-5-14b-i_61612_v1
model_group: huihui-ai/Qwen2.5-14B-In
status: torndown
timestamp: 2025-02-13T08:04:26+00:00
num_battles: 6154
num_wins: 2733
celo_rating: 1214.49
family_friendly_score: 0.6646000000000001
family_friendly_standard_error: 0.006676928036155549
submission_type: basic
model_repo: huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated
model_architecture: Qwen2ForCausalLM
model_num_parameters: 14769689600.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
display_name: huihui-ai-qwen2-5-14b-i_61612_v1
is_internal_developer: False
language_model: huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated
model_size: 15B
ranking_group: single
us_pacific_date: 2025-02-13
win_ratio: 0.4441013974650634
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'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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 huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer
Waiting for job on huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer to finish
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ║     _____            __           __                                ║
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ║       /___/                                                         ║
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ║                                                                     ║
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ║  https://mk1.ai                                                     ║
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ║                                                                     ║
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ║  belonging to:                                                      ║
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ║                                                                     ║
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ║  Chai Research Corp.                                                ║
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ║                                                                     ║
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: Downloaded to shared memory in 56.115s
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpktl4xjpj, device:0
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: quantized model in 35.659s
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: Processed model huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated in 91.774s
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: creating bucket guanaco-mkml-models
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/huihui-ai-qwen2-5-14b-i-61612-v1
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/huihui-ai-qwen2-5-14b-i-61612-v1/added_tokens.json
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/huihui-ai-qwen2-5-14b-i-61612-v1/special_tokens_map.json
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/huihui-ai-qwen2-5-14b-i-61612-v1/config.json
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/huihui-ai-qwen2-5-14b-i-61612-v1/tokenizer_config.json
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/huihui-ai-qwen2-5-14b-i-61612-v1/merges.txt
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/huihui-ai-qwen2-5-14b-i-61612-v1/vocab.json
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/huihui-ai-qwen2-5-14b-i-61612-v1/tokenizer.json
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/huihui-ai-qwen2-5-14b-i-61612-v1/flywheel_model.1.safetensors
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/huihui-ai-qwen2-5-14b-i-61612-v1/flywheel_model.0.safetensors
huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:03, 148.03it/s]
Loading 0:   5%|▌         | 30/579 [00:00<00:04, 136.11it/s]
Loading 0:   9%|▉         | 51/579 [00:00<00:03, 158.05it/s]
Loading 0:  12%|█▏        | 67/579 [00:00<00:03, 148.48it/s]
Loading 0:  14%|█▍        | 82/579 [00:00<00:05, 94.12it/s] 
Loading 0:  17%|█▋        | 96/579 [00:00<00:04, 100.81it/s]
Loading 0:  20%|██        | 118/579 [00:00<00:03, 124.65it/s]
Loading 0:  23%|██▎       | 133/579 [00:01<00:03, 125.40it/s]
Loading 0:  27%|██▋       | 154/579 [00:01<00:02, 142.99it/s]
Loading 0:  29%|██▉       | 170/579 [00:01<00:02, 143.12it/s]
Loading 0:  33%|███▎      | 189/579 [00:01<00:03, 108.10it/s]
Loading 0:  35%|███▍      | 202/579 [00:01<00:03, 105.78it/s]
Loading 0:  38%|███▊      | 219/579 [00:01<00:03, 119.01it/s]
Loading 0:  40%|████      | 233/579 [00:01<00:02, 121.51it/s]
Loading 0:  44%|████▍     | 255/579 [00:02<00:02, 141.43it/s]
Loading 0:  47%|████▋     | 271/579 [00:02<00:02, 138.77it/s]
Loading 0:  50%|█████     | 291/579 [00:02<00:01, 154.02it/s]
Loading 0:  53%|█████▎    | 308/579 [00:02<00:02, 97.27it/s] 
Loading 0:  56%|█████▋    | 327/579 [00:02<00:02, 112.48it/s]
Loading 0:  59%|█████▉    | 342/579 [00:02<00:02, 117.75it/s]
Loading 0:  63%|██████▎   | 363/579 [00:02<00:01, 136.34it/s]
Loading 0:  65%|██████▌   | 379/579 [00:03<00:01, 136.06it/s]
Loading 0:  69%|██████▉   | 400/579 [00:03<00:01, 152.72it/s]
Loading 0:  72%|███████▏  | 417/579 [00:03<00:01, 101.26it/s]
Loading 0:  75%|███████▌  | 435/579 [00:03<00:01, 114.84it/s]
Loading 0:  78%|███████▊  | 450/579 [00:03<00:01, 119.07it/s]
Loading 0:  81%|████████▏ | 471/579 [00:03<00:00, 135.61it/s]
Loading 0:  84%|████████▍ | 487/579 [00:03<00:00, 134.39it/s]
Loading 0:  87%|████████▋ | 504/579 [00:03<00:00, 143.03it/s]
Loading 0:  88%|████████▊ | 512/579 [00:24<00:00, 143.03it/s]
Loading 0:  89%|████████▊ | 513/579 [00:24<00:27,  2.38it/s] 
Loading 0:  90%|█████████ | 522/579 [00:24<00:19,  2.97it/s]
Loading 0:  94%|█████████▍| 544/579 [00:24<00:06,  5.05it/s]
Loading 0:  97%|█████████▋| 559/579 [00:24<00:02,  7.00it/s]
                                                            
Job huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer completed after 113.95s with status: succeeded
Stopping job with name huihui-ai-qwen2-5-14b-i-61612-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.41s
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 huihui-ai-qwen2-5-14b-i-61612-v1
Waiting for inference service huihui-ai-qwen2-5-14b-i-61612-v1 to be ready
Inference service huihui-ai-qwen2-5-14b-i-61612-v1 ready after 170.83002543449402s
Pipeline stage MKMLDeployer completed in 171.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.569697856903076s
Received healthy response to inference request in 1.874077320098877s
Received healthy response to inference request in 2.1788177490234375s
Received healthy response to inference request in 2.089491844177246s
Received healthy response to inference request in 1.788769006729126s
5 requests
0 failed requests
5th percentile: 1.8058306694030761
10th percentile: 1.8228923320770263
20th percentile: 1.8570156574249268
30th percentile: 1.9171602249145507
40th percentile: 2.0033260345458985
50th percentile: 2.089491844177246
60th percentile: 2.1252222061157227
70th percentile: 2.160952568054199
80th percentile: 2.2569937705993652
90th percentile: 2.4133458137512207
95th percentile: 2.4915218353271484
99th percentile: 2.5540626525878904
mean time: 2.1001707553863525
Pipeline stage StressChecker completed in 11.78s
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 0.88s
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 0.60s
Shutdown handler de-registered
huihui-ai-qwen2-5-14b-i_61612_v1 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service huihui-ai-qwen2-5-14b-i-61612-v1-profiler
Waiting for inference service huihui-ai-qwen2-5-14b-i-61612-v1-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...
%s, retrying in %s seconds...
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service huihui-ai-qwen2-5-14b-i-61612-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 1.95s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service huihui-ai-qwen2-5-14b-i-61612-v1-profiler
Waiting for inference service huihui-ai-qwen2-5-14b-i-61612-v1-profiler to be ready
Inference service huihui-ai-qwen2-5-14b-i-61612-v1-profiler ready after 50.22491955757141s
Pipeline stage MKMLProfilerDeployer completed in 50.50s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/huihui-ai-qwen2-5-1407c1ced2d7e6206b59362d3e32b659a8-deplotxqjz:/code/chaiverse_profiler_1739436453 --namespace tenant-chaiml-guanaco
kubectl exec -it huihui-ai-qwen2-5-1407c1ced2d7e6206b59362d3e32b659a8-deplotxqjz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1739436453 && python profiles.py profile --best_of_n 8 --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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1739436453/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/huihui-ai-qwen2-5-1407c1ced2d7e6206b59362d3e32b659a8-deplotxqjz:/code/chaiverse_profiler_1739436766 --namespace tenant-chaiml-guanaco
kubectl exec -it huihui-ai-qwen2-5-1407c1ced2d7e6206b59362d3e32b659a8-deplotxqjz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1739436766 && python profiles.py profile --best_of_n 8 --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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1739436766/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/huihui-ai-qwen2-5-1407c1ced2d7e6206b59362d3e32b659a8-deplotxqjz:/code/chaiverse_profiler_1739437078 --namespace tenant-chaiml-guanaco
kubectl exec -it huihui-ai-qwen2-5-1407c1ced2d7e6206b59362d3e32b659a8-deplotxqjz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1739437078 && python profiles.py profile --best_of_n 8 --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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1739437078/summary.json'
clean up pipeline due to error=ISVCScriptError('Command failed with error: Defaulted container "kserve-container" out of: kserve-container, queue-proxy\nUnable to use a TTY - input is not a terminal or the right kind of file\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1739437078/profiles.py", line 602, in <module>\n    cli()\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1157, in __call__\n    return self.main(*args, **kwargs)\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1078, in main\n    rv = self.invoke(ctx)\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1688, in invoke\n    return _process_result(sub_ctx.command.invoke(sub_ctx))\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1434, in invoke\n    return ctx.invoke(self.callback, **ctx.params)\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 783, in invoke\n    return __callback(*args, **kwargs)\n  File "/code/chaiverse_profiler_1739437078/profiles.py", line 103, in profile_batches\n    client.wait_for_server_startup(target, max_wait=300)\n  File "/code/inference_analysis/client.py", line 136, in wait_for_server_startup\n    raise RuntimeError(msg)\nRuntimeError: Timed out after 300s waiting for startup\ncommand terminated with exit code 1\n, output: waiting for startup of TargetModel(endpoint=\'localhost\', route=\'GPT-J-6B-lit-v2\', namespace=\'tenant-chaiml-guanaco\', max_characters=9999, reward=False, url_format=\'{endpoint}-predictor-default.{namespace}.knative.ord1.coreweave.cloud\')\n')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service huihui-ai-qwen2-5-14b-i-61612-v1-profiler is running
Tearing down inference service huihui-ai-qwen2-5-14b-i-61612-v1-profiler
Service huihui-ai-qwen2-5-14b-i-61612-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.19s
Shutdown handler de-registered
huihui-ai-qwen2-5-14b-i_61612_v1 status is now inactive due to auto deactivation removed underperforming models
huihui-ai-qwen2-5-14b-i_61612_v1 status is now torndown due to DeploymentManager action
huihui-ai-qwen2-5-14b-i_61612_v1 status is now torndown due to DeploymentManager action
huihui-ai-qwen2-5-14b-i_61612_v1 status is now torndown due to DeploymentManager action