chaiml-exp11-qwen14bsft_68041

developer_uid: NischayDnk

submission_id: chaiml-exp11-qwen14bsft_68041_v1

model_name: chaiml-exp11-qwen14bsft_68041_v1

model_group: ChaiML/exp11-qwen14bsfte

status: torndown

timestamp: 2025-04-08T16:39:34+00:00

num_battles: 8707

num_wins: 4323

celo_rating: 1279.22

family_friendly_score: 0.5354

family_friendly_standard_error: 0.007053323188398501

submission_type: basic

model_repo: ChaiML/exp11-qwen14bsftexp2-sftstage2-sftv1

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': 0.4752861368288694, 'latency_mean': 2.10389711022377, 'latency_p50': 2.096514940261841, 'latency_p90': 2.337284708023071}, {'batch_size': 3, 'throughput': 0.8786848279206877, 'latency_mean': 3.406109272241592, 'latency_p50': 3.4186158180236816, 'latency_p90': 3.745267629623413}, {'batch_size': 5, 'throughput': 1.0694487725812647, 'latency_mean': 4.654889897108078, 'latency_p50': 4.6696473360061646, 'latency_p90': 5.171118950843811}, {'batch_size': 6, 'throughput': 1.122854768641568, 'latency_mean': 5.306669814586639, 'latency_p50': 5.287018299102783, 'latency_p90': 5.913965082168579}, {'batch_size': 10, 'throughput': 1.2113413283989318, 'latency_mean': 8.186428555250167, 'latency_p50': 8.154204368591309, 'latency_p90': 9.241016864776611}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-exp11-qwen14bsft_68041_v1

is_internal_developer: False

language_model: ChaiML/exp11-qwen14bsftexp2-sftstage2-sftv1

model_size: 15B

ranking_group: single

throughput_3p7s: 0.94

us_pacific_date: 2025-04-08

win_ratio: 0.4964970713219249

generation_params: {'temperature': 0.75, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.3, 'frequency_penalty': 0.3, 'stopping_words': ['<|im_end|>', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:<|im_sep|>{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-exp11-qwen14bsft-68041-v1-mkmlizer
Waiting for job on chaiml-exp11-qwen14bsft-68041-v1-mkmlizer to finish
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ║       /___/                                                         ║
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ║                                                                     ║
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ║                                                                     ║
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ║                                                                     ║
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ║                                                                     ║
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: Downloaded to shared memory in 54.888s
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmps08so_6b, device:0
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: quantized model in 36.699s
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: Processed model ChaiML/exp11-qwen14bsftexp2-sftstage2-sftv1 in 91.587s
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v1
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v1/config.json
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v1/added_tokens.json
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v1/tokenizer_config.json
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v1/special_tokens_map.json
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v1/merges.txt
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v1/vocab.json
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v1/tokenizer.json
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v1/flywheel_model.1.safetensors
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v1/flywheel_model.0.safetensors
chaiml-exp11-qwen14bsft-68041-v1-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:04, 139.73it/s]
Loading 0:   5%|▌         | 29/579 [00:00<00:04, 122.31it/s]
Loading 0:   8%|▊         | 47/579 [00:00<00:03, 143.91it/s]
Loading 0:  11%|█         | 63/579 [00:00<00:03, 146.10it/s]
Loading 0:  14%|█▍        | 81/579 [00:00<00:05, 90.90it/s] 
Loading 0:  16%|█▌        | 94/579 [00:00<00:04, 98.33it/s]
Loading 0:  18%|█▊        | 107/579 [00:00<00:04, 105.05it/s]
Loading 0:  21%|██        | 120/579 [00:01<00:04, 110.73it/s]
Loading 0:  24%|██▍       | 138/579 [00:01<00:03, 128.55it/s]
Loading 0:  27%|██▋       | 154/579 [00:01<00:03, 135.14it/s]
Loading 0:  29%|██▉       | 169/579 [00:01<00:03, 129.51it/s]
Loading 0:  32%|███▏      | 186/579 [00:01<00:02, 139.19it/s]
Loading 0:  35%|███▍      | 201/579 [00:01<00:04, 85.02it/s] 
Loading 0:  38%|███▊      | 219/579 [00:01<00:03, 100.53it/s]
Loading 0:  40%|████      | 232/579 [00:02<00:03, 105.56it/s]
Loading 0:  42%|████▏     | 245/579 [00:02<00:03, 109.97it/s]
Loading 0:  45%|████▌     | 263/579 [00:02<00:02, 125.96it/s]
Loading 0:  48%|████▊     | 279/579 [00:02<00:02, 131.12it/s]
Loading 0:  51%|█████▏    | 297/579 [00:02<00:02, 96.92it/s] 
Loading 0:  53%|█████▎    | 309/579 [00:02<00:02, 93.18it/s]
Loading 0:  56%|█████▋    | 327/579 [00:02<00:02, 109.05it/s]
Loading 0:  59%|█████▊    | 340/579 [00:03<00:02, 113.52it/s]
Loading 0:  61%|██████    | 353/579 [00:03<00:01, 117.08it/s]
Loading 0:  64%|██████▍   | 372/579 [00:03<00:01, 135.87it/s]
Loading 0:  67%|██████▋   | 387/579 [00:03<00:01, 138.14it/s]
Loading 0:  70%|██████▉   | 405/579 [00:03<00:01, 104.06it/s]
Loading 0:  72%|███████▏  | 418/579 [00:03<00:01, 100.53it/s]
Loading 0:  75%|███████▌  | 435/579 [00:03<00:01, 112.00it/s]
Loading 0:  77%|███████▋  | 448/579 [00:03<00:01, 115.69it/s]
Loading 0:  80%|███████▉  | 461/579 [00:04<00:01, 116.61it/s]
Loading 0:  83%|████████▎ | 482/579 [00:04<00:00, 140.69it/s]
Loading 0:  86%|████████▌ | 497/579 [00:04<00:00, 128.61it/s]
Loading 0:  88%|████████▊ | 512/579 [00:22<00:00, 128.61it/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,  4.07it/s]
Loading 0:  96%|█████████▌| 553/579 [00:26<00:04,  6.46it/s]
Loading 0:  98%|█████████▊| 568/579 [00:26<00:01,  9.04it/s]
                                                            
Job chaiml-exp11-qwen14bsft-68041-v1-mkmlizer completed after 115.15s with status: succeeded
Stopping job with name chaiml-exp11-qwen14bsft-68041-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.75s
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 chaiml-exp11-qwen14bsft-68041-v1
Waiting for inference service chaiml-exp11-qwen14bsft-68041-v1 to be ready
Inference service chaiml-exp11-qwen14bsft-68041-v1 ready after 110.39163160324097s
Pipeline stage MKMLDeployer completed in 110.88s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5528361797332764s
Received healthy response to inference request in 1.9734489917755127s
Received healthy response to inference request in 1.9512953758239746s
Received healthy response to inference request in 2.1384530067443848s
Received healthy response to inference request in 1.926692247390747s
5 requests
0 failed requests
5th percentile: 1.9316128730773925
10th percentile: 1.9365334987640381
20th percentile: 1.9463747501373292
30th percentile: 1.9557260990142822
40th percentile: 1.9645875453948975
50th percentile: 1.9734489917755127
60th percentile: 2.0394505977630617
70th percentile: 2.1054522037506103
80th percentile: 2.2213296413421633
90th percentile: 2.38708291053772
95th percentile: 2.469959545135498
99th percentile: 2.5362608528137205
mean time: 2.108545160293579
Pipeline stage StressChecker completed in 11.84s
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 0.73s
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 0.72s
Shutdown handler de-registered
chaiml-exp11-qwen14bsft_68041_v1 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 4948.60s
Shutdown handler de-registered
chaiml-exp11-qwen14bsft_68041_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp11-qwen14bsft_68041_v1 status is now torndown due to DeploymentManager action