qwen-qwen2-5-14b-instruct-1m

developer_uid: azuruce

submission_id: qwen-qwen2-5-14b-instruct-1m_v5

model_name: nis-best-config

model_group: Qwen/Qwen2.5-14B-Instruc

status: torndown

timestamp: 2025-04-11T19:35:40+00:00

num_battles: 7677

num_wins: 2720

celo_rating: 1166.26

family_friendly_score: 0.97

family_friendly_standard_error: 0.0024124676163629634

submission_type: basic

model_repo: Qwen/Qwen2.5-14B-Instruct-1M

model_architecture: Qwen2ForCausalLM

model_num_parameters: 14769689600.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.47291720513969193, 'latency_mean': 2.114432005882263, 'latency_p50': 2.1404170989990234, 'latency_p90': 2.312889838218689}, {'batch_size': 3, 'throughput': 0.877110261982556, 'latency_mean': 3.40906507730484, 'latency_p50': 3.416392683982849, 'latency_p90': 3.7704801321029664}, {'batch_size': 5, 'throughput': 1.0698213535865613, 'latency_mean': 4.6484154605865475, 'latency_p50': 4.654118299484253, 'latency_p90': 5.097297334671021}, {'batch_size': 6, 'throughput': 1.131376662290192, 'latency_mean': 5.263774296045304, 'latency_p50': 5.270462989807129, 'latency_p90': 5.9084104061126705}, {'batch_size': 10, 'throughput': 1.2190161590460373, 'latency_mean': 8.14548187494278, 'latency_p50': 8.13468337059021, 'latency_p90': 9.138744139671326}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: nis-best-config

is_internal_developer: False

language_model: Qwen/Qwen2.5-14B-Instruct-1M

model_size: 15B

ranking_group: single

throughput_3p7s: 0.94

us_pacific_date: 2025-04-11

win_ratio: 0.3543050670834962

generation_params: {'temperature': 0.75, 'top_p': 0.96, 'min_p': 0.02, 'top_k': 60, 'presence_penalty': 0.2, 'frequency_penalty': 0.2, 'stopping_words': ['<|im_end|>', '\n'], 'max_input_tokens': 1024, 'best_of': 8, '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 qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer
Waiting for job on qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer to finish
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ║     _____            __           __                                ║
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ║       /___/                                                         ║
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ║                                                                     ║
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ║  Version: 0.12.8                                                    ║
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ║  https://mk1.ai                                                     ║
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ║                                                                     ║
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ║  belonging to:                                                      ║
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ║                                                                     ║
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ║  Chai Research Corp.                                                ║
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ║                                                                     ║
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: Downloaded to shared memory in 47.065s
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpf4mmm7gj, device:0
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission jellywibble-tyler-james_92283_v1: HTTPConnectionPool(host='jellywibble-tyler-james-92283-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: quantized model in 36.507s
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: Processed model Qwen/Qwen2.5-14B-Instruct-1M in 83.573s
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: creating bucket guanaco-mkml-models
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-1m-v5
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-1m-v5/added_tokens.json
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-1m-v5/config.json
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-1m-v5/special_tokens_map.json
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-1m-v5/tokenizer_config.json
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-1m-v5/merges.txt
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-1m-v5/vocab.json
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-1m-v5/tokenizer.json
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/qwen-qwen2-5-14b-instruct-1m-v5/flywheel_model.1.safetensors
qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:03, 143.44it/s]
Loading 0:   5%|▌         | 30/579 [00:00<00:04, 133.13it/s]
Loading 0:   9%|▉         | 54/579 [00:00<00:03, 173.78it/s]
Loading 0:  12%|█▏        | 72/579 [00:00<00:05, 100.53it/s]
Loading 0:  15%|█▍        | 85/579 [00:00<00:04, 107.12it/s]
Loading 0:  17%|█▋        | 98/579 [00:00<00:04, 109.33it/s]
Loading 0:  19%|█▉        | 111/579 [00:00<00:04, 114.41it/s]
Loading 0:  23%|██▎       | 131/579 [00:01<00:03, 137.15it/s]
Loading 0:  25%|██▌       | 146/579 [00:01<00:04, 92.26it/s] 
Loading 0:  27%|██▋       | 159/579 [00:01<00:04, 97.41it/s]
Loading 0:  30%|██▉       | 172/579 [00:01<00:03, 104.20it/s]
Loading 0:  32%|███▏      | 185/579 [00:01<00:03, 109.67it/s]
Loading 0:  35%|███▌      | 203/579 [00:01<00:02, 126.60it/s]
Loading 0:  38%|███▊      | 219/579 [00:01<00:02, 132.05it/s]
Loading 0:  40%|████      | 234/579 [00:02<00:03, 86.98it/s] 
Loading 0:  44%|████▎     | 252/579 [00:02<00:03, 105.18it/s]
Loading 0:  46%|████▌     | 267/579 [00:02<00:02, 111.23it/s]
Loading 0:  49%|████▊     | 281/579 [00:02<00:02, 106.18it/s]
Loading 0:  51%|█████▏    | 297/579 [00:02<00:02, 118.11it/s]
Loading 0:  54%|█████▍    | 315/579 [00:02<00:02, 90.02it/s] 
Loading 0:  57%|█████▋    | 328/579 [00:03<00:02, 96.77it/s]
Loading 0:  59%|█████▉    | 341/579 [00:03<00:02, 103.71it/s]
Loading 0:  63%|██████▎   | 363/579 [00:03<00:01, 125.47it/s]
Loading 0:  65%|██████▌   | 377/579 [00:03<00:01, 123.73it/s]
Loading 0:  69%|██████▉   | 400/579 [00:03<00:01, 150.19it/s]
Loading 0:  72%|███████▏  | 417/579 [00:03<00:01, 98.42it/s] 
Loading 0:  75%|███████▌  | 435/579 [00:03<00:01, 112.56it/s]
Loading 0:  78%|███████▊  | 450/579 [00:04<00:01, 116.47it/s]
Loading 0:  81%|████████▏ | 471/579 [00:04<00:00, 133.35it/s]
Loading 0:  84%|████████▍ | 489/579 [00:04<00:00, 144.12it/s]
Loading 0:  87%|████████▋ | 505/579 [00:04<00:00, 103.15it/s]
Loading 0:  90%|████████▉ | 520/579 [00:04<00:00, 108.90it/s]
Loading 0:  92%|█████████▏| 533/579 [00:18<00:12,  3.61it/s] 
Loading 0:  96%|█████████▌| 555/579 [00:18<00:04,  5.73it/s]
Loading 0:  98%|█████████▊| 570/579 [00:18<00:01,  7.72it/s]
                                                            
Job qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer completed after 115.8s with status: succeeded
Stopping job with name qwen-qwen2-5-14b-instruct-1m-v5-mkmlizer
Pipeline stage MKMLizer completed in 116.28s
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 qwen-qwen2-5-14b-instruct-1m-v5
Waiting for inference service qwen-qwen2-5-14b-instruct-1m-v5 to be ready
Inference service qwen-qwen2-5-14b-instruct-1m-v5 ready after 110.42517113685608s
Pipeline stage MKMLDeployer completed in 110.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2306368350982666s
Received healthy response to inference request in 1.8998878002166748s
Received healthy response to inference request in 1.8309948444366455s
Received healthy response to inference request in 2.1885063648223877s
Received healthy response to inference request in 1.8969383239746094s
5 requests
0 failed requests
5th percentile: 1.8441835403442384
10th percentile: 1.857372236251831
20th percentile: 1.8837496280670165
30th percentile: 1.8975282192230225
40th percentile: 1.8987080097198485
50th percentile: 1.8998878002166748
60th percentile: 2.01533522605896
70th percentile: 2.130782651901245
80th percentile: 2.1969324588775634
90th percentile: 2.213784646987915
95th percentile: 2.222210741043091
99th percentile: 2.2289516162872314
mean time: 2.009392833709717
Pipeline stage StressChecker completed in 11.32s
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 0.61s
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 0.66s
Shutdown handler de-registered
qwen-qwen2-5-14b-instruct-1m_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 4640.62s
Shutdown handler de-registered
qwen-qwen2-5-14b-instruct-1m_v5 status is now inactive due to auto deactivation removed underperforming models
qwen-qwen2-5-14b-instruct-1m_v5 status is now torndown due to DeploymentManager action