developer_uid: huohuo12
submission_id: tanliboy-lambda-qwen2-5_93066_v1
model_name: tanliboy-lambda-qwen2-5_93066_v1
model_group: tanliboy/lambda-qwen2.5-
status: torndown
timestamp: 2025-02-20T07:56:49+00:00
num_battles: 6394
num_wins: 3050
celo_rating: 1227.15
family_friendly_score: 0.6426000000000001
family_friendly_standard_error: 0.006777392418917471
submission_type: basic
model_repo: tanliboy/lambda-qwen2.5-14b-dpo-test
model_architecture: Qwen2ForCausalLM
model_num_parameters: 14769689600.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.46957840234824044, 'latency_mean': 2.12947992682457, 'latency_p50': 2.1212093830108643, 'latency_p90': 2.3403300046920776}, {'batch_size': 3, 'throughput': 0.8617348545710923, 'latency_mean': 3.474229402542114, 'latency_p50': 3.483394742012024, 'latency_p90': 3.8836386442184447}, {'batch_size': 5, 'throughput': 1.0494237835624496, 'latency_mean': 4.733738992214203, 'latency_p50': 4.722400784492493, 'latency_p90': 5.29849796295166}, {'batch_size': 6, 'throughput': 1.1152183807978886, 'latency_mean': 5.3533391189575195, 'latency_p50': 5.383808612823486, 'latency_p90': 6.003993344306946}, {'batch_size': 10, 'throughput': 1.186301133760627, 'latency_mean': 8.366665300130844, 'latency_p50': 8.464170575141907, 'latency_p90': 9.424357914924622}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tanliboy-lambda-qwen2-5_93066_v1
is_internal_developer: False
language_model: tanliboy/lambda-qwen2.5-14b-dpo-test
model_size: 15B
ranking_group: single
throughput_3p7s: 0.91
us_pacific_date: 2025-02-19
win_ratio: 0.47700969659055364
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 tanliboy-lambda-qwen2-5-93066-v1-mkmlizer
Waiting for job on tanliboy-lambda-qwen2-5-93066-v1-mkmlizer to finish
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ║     _____            __           __                                ║
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ║       /___/                                                         ║
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ║                                                                     ║
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ║  https://mk1.ai                                                     ║
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ║                                                                     ║
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ║  belonging to:                                                      ║
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ║                                                                     ║
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ║  Chai Research Corp.                                                ║
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ║                                                                     ║
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: Downloaded to shared memory in 60.646s
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_nl6cd9n, device:0
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-20250219-c-4epoc_80755_v1: HTTPConnectionPool(host='chaiml-20250219-c-4epoc-80755-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: quantized model in 37.961s
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: Processed model tanliboy/lambda-qwen2.5-14b-dpo-test in 98.608s
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: creating bucket guanaco-mkml-models
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/tanliboy-lambda-qwen2-5-93066-v1
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/tanliboy-lambda-qwen2-5-93066-v1/config.json
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/tanliboy-lambda-qwen2-5-93066-v1/added_tokens.json
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/tanliboy-lambda-qwen2-5-93066-v1/special_tokens_map.json
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/tanliboy-lambda-qwen2-5-93066-v1/tokenizer_config.json
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/tanliboy-lambda-qwen2-5-93066-v1/merges.txt
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/tanliboy-lambda-qwen2-5-93066-v1/vocab.json
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/tanliboy-lambda-qwen2-5-93066-v1/tokenizer.json
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/tanliboy-lambda-qwen2-5-93066-v1/flywheel_model.1.safetensors
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/tanliboy-lambda-qwen2-5-93066-v1/flywheel_model.0.safetensors
tanliboy-lambda-qwen2-5-93066-v1-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:04, 136.30it/s]
Loading 0:   5%|▌         | 29/579 [00:00<00:04, 120.56it/s]
Loading 0:   8%|▊         | 45/579 [00:00<00:03, 134.27it/s]
Loading 0:  11%|█         | 63/579 [00:00<00:03, 141.72it/s]
Loading 0:  14%|█▍        | 81/579 [00:00<00:05, 91.11it/s] 
Loading 0:  16%|█▌        | 94/579 [00:00<00:04, 97.26it/s]
Loading 0:  18%|█▊        | 107/579 [00:00<00:04, 103.89it/s]
Loading 0:  21%|██        | 120/579 [00:01<00:04, 110.11it/s]
Loading 0:  24%|██▍       | 139/579 [00:01<00:03, 130.84it/s]
Loading 0:  27%|██▋       | 154/579 [00:01<00:03, 133.13it/s]
Loading 0:  29%|██▉       | 169/579 [00:01<00:03, 127.55it/s]
Loading 0:  32%|███▏      | 186/579 [00:01<00:02, 137.32it/s]
Loading 0:  35%|███▍      | 201/579 [00:01<00:04, 87.83it/s] 
Loading 0:  38%|███▊      | 219/579 [00:01<00:03, 101.72it/s]
Loading 0:  40%|████      | 232/579 [00:02<00:03, 105.48it/s]
Loading 0:  42%|████▏     | 245/579 [00:02<00:03, 109.34it/s]
Loading 0:  45%|████▌     | 263/579 [00:02<00:02, 124.95it/s]
Loading 0:  48%|████▊     | 279/579 [00:02<00:02, 129.92it/s]
Loading 0:  51%|█████▏    | 297/579 [00:02<00:02, 98.64it/s] 
Loading 0:  53%|█████▎    | 309/579 [00:02<00:02, 94.71it/s]
Loading 0:  56%|█████▋    | 327/579 [00:02<00:02, 108.76it/s]
Loading 0:  59%|█████▊    | 340/579 [00:03<00:02, 110.25it/s]
Loading 0:  61%|██████    | 353/579 [00:03<00:01, 113.31it/s]
Loading 0:  64%|██████▍   | 371/579 [00:03<00:01, 127.66it/s]
Loading 0:  67%|██████▋   | 387/579 [00:03<00:01, 131.70it/s]
Loading 0:  70%|██████▉   | 405/579 [00:03<00:01, 94.52it/s] 
Loading 0:  72%|███████▏  | 417/579 [00:03<00:01, 91.79it/s]
Loading 0:  75%|███████▌  | 435/579 [00:03<00:01, 106.60it/s]
Loading 0:  77%|███████▋  | 448/579 [00:04<00:01, 110.59it/s]
Loading 0:  80%|███████▉  | 461/579 [00:04<00:01, 114.40it/s]
Loading 0:  83%|████████▎ | 479/579 [00:04<00:00, 130.98it/s]
Loading 0:  85%|████████▌ | 495/579 [00:04<00:00, 134.95it/s]
Loading 0:  88%|████████▊ | 512/579 [00:22<00:00, 134.95it/s]
Loading 0:  89%|████████▊ | 513/579 [00:26<00:27,  2.42it/s] 
Loading 0:  90%|████████▉ | 521/579 [00:26<00:19,  2.91it/s]
Loading 0:  92%|█████████▏| 534/579 [00:26<00:11,  4.04it/s]
Loading 0:  95%|█████████▌| 552/579 [00:26<00:04,  6.25it/s]
Loading 0:  98%|█████████▊| 568/579 [00:27<00:01,  8.95it/s]
                                                            

Job tanliboy-lambda-qwen2-5-93066-v1-mkmlizer completed after 125.44s with status: succeeded
Stopping job with name tanliboy-lambda-qwen2-5-93066-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.97s
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 tanliboy-lambda-qwen2-5-93066-v1
Waiting for inference service tanliboy-lambda-qwen2-5-93066-v1 to be ready
Inference service tanliboy-lambda-qwen2-5-93066-v1 ready after 200.77693843841553s
Pipeline stage MKMLDeployer completed in 201.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.342604875564575s
Received healthy response to inference request in 1.462775707244873s
Received healthy response to inference request in 1.8812792301177979s
Received healthy response to inference request in 1.8333890438079834s
Received healthy response to inference request in 1.8715708255767822s
5 requests
0 failed requests
5th percentile: 1.5368983745574951
10th percentile: 1.6110210418701172
20th percentile: 1.7592663764953613
30th percentile: 1.8410254001617432
40th percentile: 1.8562981128692626
50th percentile: 1.8715708255767822
60th percentile: 1.8754541873931885
70th percentile: 1.8793375492095947
80th percentile: 2.1735443592071535
90th percentile: 2.7580746173858643
95th percentile: 3.0503397464752195
99th percentile: 3.284151849746704
mean time: 2.0783239364624024
Pipeline stage StressChecker completed in 11.82s
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 0.73s
Shutdown handler de-registered
tanliboy-lambda-qwen2-5_93066_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service tanliboy-lambda-qwen2-5-93066-v1-profiler
Waiting for inference service tanliboy-lambda-qwen2-5-93066-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2674.51s
Shutdown handler de-registered
tanliboy-lambda-qwen2-5_93066_v1 status is now inactive due to auto deactivation removed underperforming models
tanliboy-lambda-qwen2-5_93066_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1