chaiml-exp11-qwen14bsft_68041

developer_uid: NischayDnk

submission_id: chaiml-exp11-qwen14bsft_68041_v2

model_name: chaiml-exp11-qwen14bsft_68041_v2

model_group: ChaiML/exp11-qwen14bsfte

status: torndown

timestamp: 2025-04-08T16:45:37+00:00

num_battles: 8378

num_wins: 4116

celo_rating: 1275.02

family_friendly_score: 0.5406

family_friendly_standard_error: 0.007047717928521259

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': 0.4718348414083536, 'latency_mean': 2.119292094707489, 'latency_p50': 2.121216058731079, 'latency_p90': 2.3287849187850953}, {'batch_size': 3, 'throughput': 0.872989653045857, 'latency_mean': 3.4257593965530395, 'latency_p50': 3.4127384424209595, 'latency_p90': 3.8233168363571166}, {'batch_size': 5, 'throughput': 1.0478142233424168, 'latency_mean': 4.756534101963044, 'latency_p50': 4.746352553367615, 'latency_p90': 5.300471949577331}, {'batch_size': 6, 'throughput': 1.1014203474483015, 'latency_mean': 5.40813179731369, 'latency_p50': 5.421219706535339, 'latency_p90': 6.110019540786743}, {'batch_size': 10, 'throughput': 1.1901936288223687, 'latency_mean': 8.333425937891006, 'latency_p50': 8.34665560722351, 'latency_p90': 9.36094925403595}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-exp11-qwen14bsft_68041_v2

is_internal_developer: False

language_model: ChaiML/exp11-qwen14bsftexp2-sftstage2-sftv1

model_size: 15B

ranking_group: single

throughput_3p7s: 0.92

us_pacific_date: 2025-04-08

win_ratio: 0.4912867032704703

generation_params: {'temperature': 0.7, 'top_p': 0.95, 'min_p': 0.025, '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': '<|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: {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-v2-mkmlizer
Waiting for job on chaiml-exp11-qwen14bsft-68041-v2-mkmlizer to finish
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ║       /___/                                                         ║
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ║                                                                     ║
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ║                                                                     ║
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ║                                                                     ║
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ║                                                                     ║
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: Downloaded to shared memory in 37.459s
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxu1lujh4, device:0
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-exp11-qwen14bsft_68041_v1: HTTPConnectionPool(host='chaiml-exp11-qwen14bsft-68041-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: quantized model in 36.642s
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: Processed model ChaiML/exp11-qwen14bsftexp2-sftstage2-sftv1 in 74.102s
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v2
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v2/config.json
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v2/added_tokens.json
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v2/special_tokens_map.json
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v2/tokenizer_config.json
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v2/merges.txt
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v2/vocab.json
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v2/tokenizer.json
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v2/flywheel_model.1.safetensors
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp11-qwen14bsft-68041-v2/flywheel_model.0.safetensors
chaiml-exp11-qwen14bsft-68041-v2-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:04, 136.51it/s]
Loading 0:   5%|▌         | 29/579 [00:00<00:04, 119.61it/s]
Loading 0:   8%|▊         | 47/579 [00:00<00:03, 142.95it/s]
Loading 0:  11%|█         | 63/579 [00:00<00:03, 145.89it/s]
Loading 0:  14%|█▍        | 81/579 [00:00<00:05, 92.56it/s] 
Loading 0:  16%|█▌        | 94/579 [00:00<00:04, 99.48it/s]
Loading 0:  18%|█▊        | 107/579 [00:00<00:04, 105.75it/s]
Loading 0:  21%|██        | 120/579 [00:01<00:04, 110.55it/s]
Loading 0:  24%|██▍       | 138/579 [00:01<00:03, 127.82it/s]
Loading 0:  27%|██▋       | 154/579 [00:01<00:03, 134.38it/s]
Loading 0:  29%|██▉       | 169/579 [00:01<00:03, 129.45it/s]
Loading 0:  32%|███▏      | 186/579 [00:01<00:02, 138.78it/s]
Loading 0:  35%|███▍      | 201/579 [00:01<00:04, 86.75it/s] 
Loading 0:  38%|███▊      | 219/579 [00:01<00:03, 102.47it/s]
Loading 0:  40%|████      | 232/579 [00:02<00:03, 107.49it/s]
Loading 0:  42%|████▏     | 245/579 [00:02<00:02, 112.03it/s]
Loading 0:  45%|████▌     | 263/579 [00:02<00:02, 128.80it/s]
Loading 0:  48%|████▊     | 279/579 [00:02<00:02, 132.97it/s]
Loading 0:  51%|█████▏    | 297/579 [00:02<00:02, 98.37it/s] 
Loading 0:  53%|█████▎    | 309/579 [00:02<00:02, 95.12it/s]
Loading 0:  56%|█████▋    | 327/579 [00:02<00:02, 109.30it/s]
Loading 0:  59%|█████▊    | 340/579 [00:03<00:02, 112.98it/s]
Loading 0:  61%|██████    | 353/579 [00:03<00:01, 115.78it/s]
Loading 0:  64%|██████▍   | 371/579 [00:03<00:01, 131.20it/s]
Loading 0:  67%|██████▋   | 387/579 [00:03<00:01, 135.60it/s]
Loading 0:  70%|██████▉   | 405/579 [00:03<00:01, 98.99it/s] 
Loading 0:  72%|███████▏  | 417/579 [00:03<00:01, 95.17it/s]
Loading 0:  75%|███████▌  | 435/579 [00:03<00:01, 109.89it/s]
Loading 0:  77%|███████▋  | 448/579 [00:03<00:01, 113.62it/s]
Loading 0:  80%|███████▉  | 461/579 [00:04<00:01, 116.81it/s]
Loading 0:  83%|████████▎ | 479/579 [00:04<00:00, 131.77it/s]
Loading 0:  85%|████████▌ | 495/579 [00:04<00:00, 135.65it/s]
Loading 0:  88%|████████▊ | 512/579 [00:25<00:00, 135.65it/s]
Loading 0:  89%|████████▊ | 513/579 [00:25<00:26,  2.53it/s] 
Loading 0:  90%|████████▉ | 521/579 [00:25<00:19,  3.04it/s]
Loading 0:  92%|█████████▏| 534/579 [00:25<00:10,  4.22it/s]
Loading 0:  95%|█████████▌| 552/579 [00:25<00:04,  6.53it/s]
Loading 0:  98%|█████████▊| 568/579 [00:25<00:01,  9.34it/s]
                                                            
Job chaiml-exp11-qwen14bsft-68041-v2-mkmlizer completed after 104.91s with status: succeeded
Stopping job with name chaiml-exp11-qwen14bsft-68041-v2-mkmlizer
Pipeline stage MKMLizer completed in 105.35s
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 chaiml-exp11-qwen14bsft-68041-v2
Waiting for inference service chaiml-exp11-qwen14bsft-68041-v2 to be ready
Inference service chaiml-exp11-qwen14bsft-68041-v2 ready after 110.44443488121033s
Pipeline stage MKMLDeployer completed in 110.98s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8660550117492676s
Received healthy response to inference request in 2.094320297241211s
Received healthy response to inference request in 1.9260516166687012s
Received healthy response to inference request in 1.8642158508300781s
Received healthy response to inference request in 1.925722599029541s
5 requests
0 failed requests
5th percentile: 1.8765172004699706
10th percentile: 1.8888185501098633
20th percentile: 1.9134212493896485
30th percentile: 1.925788402557373
40th percentile: 1.925920009613037
50th percentile: 1.9260516166687012
60th percentile: 1.993359088897705
70th percentile: 2.060666561126709
80th percentile: 2.2486672401428223
90th percentile: 2.557361125946045
95th percentile: 2.7117080688476562
99th percentile: 2.8351856231689454
mean time: 2.13527307510376
Pipeline stage StressChecker completed in 11.97s
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 0.75s
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 0.79s
Shutdown handler de-registered
chaiml-exp11-qwen14bsft_68041_v2 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 0.10s
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 chaiml-exp11-qwen14bsft-68041-v2-profiler
Waiting for inference service chaiml-exp11-qwen14bsft-68041-v2-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...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4873.97s
Shutdown handler de-registered
chaiml-exp11-qwen14bsft_68041_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp11-qwen14bsft_68041_v2 status is now torndown due to DeploymentManager action