developer_uid: NischayDnk
submission_id: chaiml-qwen14b-dpoexp5-_42651_v1
model_name: chaiml-qwen14b-dpoexp5-_42651_v1
model_group: ChaiML/qwen14b-dpoexp5-q
status: torndown
timestamp: 2025-04-09T17:54:56+00:00
num_battles: 8573
num_wins: 3894
celo_rating: 1249.83
family_friendly_score: 0.556
family_friendly_standard_error: 0.007026578114559035
submission_type: basic
model_repo: ChaiML/qwen14b-dpoexp5-qwendatav1-dpo10k
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': 0.4750463147629506, 'latency_mean': 2.104997680187225, 'latency_p50': 2.09817636013031, 'latency_p90': 2.3357535362243653}, {'batch_size': 3, 'throughput': 0.8766640347402168, 'latency_mean': 3.415269104242325, 'latency_p50': 3.3949047327041626, 'latency_p90': 3.746078705787659}, {'batch_size': 5, 'throughput': 1.0665935949583574, 'latency_mean': 4.680324249267578, 'latency_p50': 4.679892301559448, 'latency_p90': 5.274093437194824}, {'batch_size': 6, 'throughput': 1.1281190434146515, 'latency_mean': 5.286986008882523, 'latency_p50': 5.270129084587097, 'latency_p90': 5.930107450485229}, {'batch_size': 10, 'throughput': 1.1959793450004648, 'latency_mean': 8.284146698713302, 'latency_p50': 8.370804190635681, 'latency_p90': 9.400819277763366}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-qwen14b-dpoexp5-_42651_v1
is_internal_developer: False
language_model: ChaiML/qwen14b-dpoexp5-qwendatav1-dpo10k
model_size: 15B
ranking_group: single
throughput_3p7s: 0.93
us_pacific_date: 2025-04-09
win_ratio: 0.45421672693339554
generation_params: {'temperature': 0.7, 'top_p': 0.95, 'min_p': 0.025, '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': '\n{bot_name}:{message}', 'user_template': '\nYou:{message}', 'response_template': '\n####', 'truncate_by_message': True}
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-dpoexp5-42651-v1-mkmlizer
Waiting for job on chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer to finish
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ║ _____ __ __ ║
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ║ /___/ ║
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ║ belonging to: ║
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: Downloaded to shared memory in 52.776s
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpijp7w65c, device:0
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: quantized model in 36.548s
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: Processed model ChaiML/qwen14b-dpoexp5-qwendatav1-dpo10k in 89.324s
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v1
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v1/config.json
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v1/added_tokens.json
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v1/special_tokens_map.json
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v1/tokenizer_config.json
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v1/merges.txt
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v1/vocab.json
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v1/tokenizer.json
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp5-42651-v1/flywheel_model.1.safetensors
chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer: Loading 0: 0%| | 0/579 [00:00<?, ?it/s] Loading 0: 3%|▎ | 15/579 [00:00<00:04, 130.86it/s] Loading 0: 5%|▌ | 29/579 [00:00<00:04, 118.48it/s] Loading 0: 8%|▊ | 49/579 [00:00<00:03, 150.88it/s] Loading 0: 11%|█ | 65/579 [00:00<00:03, 131.93it/s] Loading 0: 14%|█▍ | 81/579 [00:00<00:05, 93.64it/s] Loading 0: 16%|█▌ | 94/579 [00:00<00:04, 101.30it/s] Loading 0: 18%|█▊ | 107/579 [00:00<00:04, 106.65it/s] Loading 0: 21%|██ | 120/579 [00:01<00:04, 111.76it/s] Loading 0: 24%|██▍ | 139/579 [00:01<00:03, 132.56it/s] Loading 0: 27%|██▋ | 154/579 [00:01<00:03, 135.59it/s] Loading 0: 29%|██▉ | 169/579 [00:01<00:03, 130.82it/s] Loading 0: 32%|███▏ | 186/579 [00:01<00:02, 141.16it/s] Loading 0: 35%|███▍ | 201/579 [00:01<00:04, 88.97it/s] Loading 0: 38%|███▊ | 219/579 [00:01<00:03, 104.42it/s] Loading 0: 40%|████ | 232/579 [00:02<00:03, 109.34it/s] Loading 0: 42%|████▏ | 245/579 [00:02<00:02, 113.72it/s] Loading 0: 46%|████▌ | 267/579 [00:02<00:02, 134.05it/s] Loading 0: 49%|████▊ | 282/579 [00:02<00:02, 130.28it/s] Loading 0: 51%|█████▏ | 297/579 [00:02<00:02, 104.54it/s] Loading 0: 53%|█████▎ | 309/579 [00:02<00:02, 99.49it/s] Loading 0: 56%|█████▋ | 327/579 [00:02<00:02, 114.75it/s] Loading 0: 59%|█████▊ | 340/579 [00:02<00:02, 117.09it/s] Loading 0: 61%|██████ | 353/579 [00:03<00:01, 118.92it/s] Loading 0: 64%|██████▍ | 371/579 [00:03<00:01, 134.79it/s] Loading 0: 67%|██████▋ | 387/579 [00:03<00:01, 140.52it/s] Loading 0: 70%|██████▉ | 405/579 [00:03<00:01, 102.17it/s] Loading 0: 72%|███████▏ | 418/579 [00:03<00:01, 100.23it/s] Loading 0: 75%|███████▌ | 435/579 [00:03<00:01, 112.77it/s] Loading 0: 77%|███████▋ | 448/579 [00:03<00:01, 116.34it/s] Loading 0: 80%|███████▉ | 461/579 [00:03<00:00, 118.11it/s] Loading 0: 83%|████████▎ | 483/579 [00:04<00:00, 137.85it/s] Loading 0: 86%|████████▌ | 498/579 [00:04<00:00, 133.44it/s] Loading 0: 88%|████████▊ | 512/579 [00:21<00:00, 133.44it/s] Loading 0: 89%|████████▊ | 513/579 [00:25<00:27, 2.40it/s] Loading 0: 90%|█████████ | 522/579 [00:26<00:19, 2.96it/s] Loading 0: 94%|█████████▎| 542/579 [00:26<00:07, 4.76it/s] Loading 0: 96%|█████████▌| 557/579 [00:26<00:03, 6.61it/s] Loading 0: 99%|█████████▊| 571/579 [00:26<00:00, 9.00it/s]
Job chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer completed after 115.55s with status: succeeded
Stopping job with name chaiml-qwen14b-dpoexp5-42651-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.03s
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-dpoexp5-42651-v1
Waiting for inference service chaiml-qwen14b-dpoexp5-42651-v1 to be ready
Inference service chaiml-qwen14b-dpoexp5-42651-v1 ready after 110.44259595870972s
Pipeline stage MKMLDeployer completed in 110.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.708573341369629s
Received healthy response to inference request in 2.3228673934936523s
Received healthy response to inference request in 1.9290742874145508s
Received healthy response to inference request in 2.103822946548462s
Received healthy response to inference request in 2.1448400020599365s
5 requests
0 failed requests
5th percentile: 1.964024019241333
10th percentile: 1.9989737510681151
20th percentile: 2.0688732147216795
30th percentile: 2.1120263576507567
40th percentile: 2.128433179855347
50th percentile: 2.1448400020599365
60th percentile: 2.216050958633423
70th percentile: 2.2872619152069094
80th percentile: 2.4000085830688476
90th percentile: 2.5542909622192385
95th percentile: 2.6314321517944337
99th percentile: 2.6931451034545897
mean time: 2.241835594177246
Pipeline stage StressChecker completed in 12.44s
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 0.63s
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 0.67s
Shutdown handler de-registered
chaiml-qwen14b-dpoexp5-_42651_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2741.76s
Shutdown handler de-registered
chaiml-qwen14b-dpoexp5-_42651_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen14b-dpoexp5-_42651_v1 status is now torndown due to DeploymentManager action