chaiml-qwen14b-dpoexp2-s_8149

developer_uid: NischayDnk

submission_id: chaiml-qwen14b-dpoexp2-s_8149_v2

model_name: chaiml-qwen14b-dpoexp2-s_8149_v2

model_group: ChaiML/qwen14b-dpoexp2-s

status: torndown

timestamp: 2025-04-08T04:30:09+00:00

num_battles: 10826

num_wins: 5334

celo_rating: 1276.68

family_friendly_score: 0.49219999999999997

family_friendly_standard_error: 0.007070207351980562

submission_type: basic

model_repo: ChaiML/qwen14b-dpoexp2-sftdel12kexp5

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': 0.4765129717632478, 'latency_mean': 2.0985157334804536, 'latency_p50': 2.097528100013733, 'latency_p90': 2.29399893283844}, {'batch_size': 3, 'throughput': 0.8734838051986694, 'latency_mean': 3.4303679180145266, 'latency_p50': 3.4244368076324463, 'latency_p90': 3.796527862548828}, {'batch_size': 5, 'throughput': 1.0634688928178435, 'latency_mean': 4.678120985031128, 'latency_p50': 4.6730605363845825, 'latency_p90': 5.215749740600586}, {'batch_size': 6, 'throughput': 1.1220611403745315, 'latency_mean': 5.312534152269364, 'latency_p50': 5.2740737199783325, 'latency_p90': 5.93685257434845}, {'batch_size': 10, 'throughput': 1.2060719625414413, 'latency_mean': 8.242937211990357, 'latency_p50': 8.249877214431763, 'latency_p90': 9.23118462562561}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-qwen14b-dpoexp2-s_8149_v2

is_internal_developer: False

language_model: ChaiML/qwen14b-dpoexp2-sftdel12kexp5

model_size: 15B

ranking_group: single

throughput_3p7s: 0.93

us_pacific_date: 2025-04-07

win_ratio: 0.49270275263255126

generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.3, 'frequency_penalty': 0.3, 'stopping_words': ['</s>', '\n', 'You:', '###'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '[INST]', 'prompt_template': "''", 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '[/INST]{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 chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer
Waiting for job on chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer to finish
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ║       /___/                                                         ║
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ║                                                                     ║
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ║                                                                     ║
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ║                                                                     ║
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ║                                                                     ║
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: Downloaded to shared memory in 41.022s
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpf0ljdt1j, device:0
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: quantized model in 36.508s
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: Processed model ChaiML/qwen14b-dpoexp2-sftdel12kexp5 in 77.531s
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-8149-v2
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-8149-v2/config.json
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-8149-v2/special_tokens_map.json
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-8149-v2/added_tokens.json
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-8149-v2/tokenizer_config.json
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-8149-v2/merges.txt
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-8149-v2/vocab.json
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-8149-v2/tokenizer.json
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-8149-v2/flywheel_model.1.safetensors
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-8149-v2/flywheel_model.0.safetensors
chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:04, 140.06it/s]
Loading 0:   5%|▌         | 30/579 [00:00<00:04, 128.22it/s]
Loading 0:   8%|▊         | 47/579 [00:00<00:03, 144.98it/s]
Loading 0:  11%|█         | 63/579 [00:00<00:03, 148.09it/s]
Loading 0:  14%|█▍        | 81/579 [00:00<00:05, 95.15it/s] 
Loading 0:  16%|█▌        | 94/579 [00:00<00:04, 102.22it/s]
Loading 0:  18%|█▊        | 107/579 [00:00<00:04, 106.59it/s]
Loading 0:  21%|██        | 120/579 [00:01<00:04, 111.70it/s]
Loading 0:  25%|██▍       | 142/579 [00:01<00:03, 139.87it/s]
Loading 0:  27%|██▋       | 158/579 [00:01<00:03, 129.93it/s]
Loading 0:  30%|███       | 174/579 [00:01<00:02, 135.81it/s]
Loading 0:  33%|███▎      | 189/579 [00:01<00:04, 95.27it/s] 
Loading 0:  35%|███▍      | 201/579 [00:01<00:04, 93.97it/s]
Loading 0:  38%|███▊      | 219/579 [00:01<00:03, 109.60it/s]
Loading 0:  40%|████      | 232/579 [00:02<00:03, 113.93it/s]
Loading 0:  42%|████▏     | 245/579 [00:02<00:02, 117.75it/s]
Loading 0:  46%|████▌     | 265/579 [00:02<00:02, 139.08it/s]
Loading 0:  48%|████▊     | 280/579 [00:02<00:02, 133.21it/s]
Loading 0:  51%|█████▏    | 297/579 [00:02<00:02, 98.44it/s] 
Loading 0:  53%|█████▎    | 309/579 [00:02<00:02, 94.32it/s]
Loading 0:  56%|█████▋    | 327/579 [00:02<00:02, 108.26it/s]
Loading 0:  59%|█████▊    | 340/579 [00:02<00:02, 112.47it/s]
Loading 0:  61%|██████    | 353/579 [00:03<00:01, 115.73it/s]
Loading 0:  64%|██████▍   | 371/579 [00:03<00:01, 132.15it/s]
Loading 0:  67%|██████▋   | 387/579 [00:03<00:01, 137.54it/s]
Loading 0:  70%|██████▉   | 405/579 [00:03<00:01, 100.23it/s]
Loading 0:  72%|███████▏  | 417/579 [00:03<00:01, 95.63it/s] 
Loading 0:  75%|███████▌  | 435/579 [00:03<00:01, 110.90it/s]
Loading 0:  77%|███████▋  | 448/579 [00:03<00:01, 114.64it/s]
Loading 0:  80%|███████▉  | 461/579 [00:04<00:01, 117.77it/s]
Loading 0:  83%|████████▎ | 479/579 [00:04<00:00, 132.90it/s]
Loading 0:  85%|████████▌ | 495/579 [00:04<00:00, 137.12it/s]
Loading 0:  88%|████████▊ | 512/579 [00:22<00:00, 137.12it/s]
Loading 0:  89%|████████▊ | 513/579 [00:25<00:26,  2.48it/s] 
Loading 0:  90%|████████▉ | 521/579 [00:26<00:19,  2.98it/s]
Loading 0:  92%|█████████▏| 534/579 [00:26<00:10,  4.14it/s]
Loading 0:  95%|█████████▌| 552/579 [00:26<00:04,  6.41it/s]
Loading 0:  98%|█████████▊| 568/579 [00:26<00:01,  9.18it/s]
                                                            
Job chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer completed after 105.39s with status: succeeded
Stopping job with name chaiml-qwen14b-dpoexp2-s-8149-v2-mkmlizer
Pipeline stage MKMLizer completed in 105.84s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen14b-dpoexp2-s-8149-v2
Waiting for inference service chaiml-qwen14b-dpoexp2-s-8149-v2 to be ready
Failed to get response for submission blend_nulot_2025-04-04: HTTPConnectionPool(host='blend-ropob-2025-04-04-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-qwen14b-dpoexp2-s-8149-v2 ready after 110.45472931861877s
Pipeline stage MKMLDeployer completed in 110.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4908969402313232s
Received healthy response to inference request in 1.8966975212097168s
Received healthy response to inference request in 1.9096965789794922s
Received healthy response to inference request in 1.9253637790679932s
Received healthy response to inference request in 2.155872344970703s
5 requests
0 failed requests
5th percentile: 1.899297332763672
10th percentile: 1.901897144317627
20th percentile: 1.907096767425537
30th percentile: 1.9128300189971923
40th percentile: 1.9190968990325927
50th percentile: 1.9253637790679932
60th percentile: 2.017567205429077
70th percentile: 2.109770631790161
80th percentile: 2.222877264022827
90th percentile: 2.356887102127075
95th percentile: 2.423892021179199
99th percentile: 2.4774959564208983
mean time: 2.0757054328918456
Pipeline stage StressChecker completed in 11.57s
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 0.71s
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 0.71s
Shutdown handler de-registered
chaiml-qwen14b-dpoexp2-s_8149_v2 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2754.67s
Shutdown handler de-registered
chaiml-qwen14b-dpoexp2-s_8149_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen14b-dpoexp2-s_8149_v2 status is now torndown due to DeploymentManager action