developer_uid: NischayDnk
submission_id: chaiml-qwen14b-dpoexp2-_84998_v1
model_name: chaiml-qwen14b-dpoexp2-_84998_v1
model_group: ChaiML/qwen14b-dpoexp2-s
status: torndown
timestamp: 2025-04-07T20:19:02+00:00
num_battles: 9334
num_wins: 4550
celo_rating: 1272.79
family_friendly_score: 0.5462
family_friendly_standard_error: 0.007040817566163747
submission_type: basic
model_repo: ChaiML/qwen14b-dpoexp2-sftdel12kexp3
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': 0.4681238409787139, 'latency_mean': 2.1361247622966766, 'latency_p50': 2.1494598388671875, 'latency_p90': 2.348747491836548}, {'batch_size': 3, 'throughput': 0.861935332918922, 'latency_mean': 3.4760317265987397, 'latency_p50': 3.5116957426071167, 'latency_p90': 3.8221351623535154}, {'batch_size': 5, 'throughput': 1.0457201891423116, 'latency_mean': 4.76619252204895, 'latency_p50': 4.780027866363525, 'latency_p90': 5.303414344787598}, {'batch_size': 6, 'throughput': 1.1015975276312127, 'latency_mean': 5.419607584476471, 'latency_p50': 5.434480667114258, 'latency_p90': 6.046276187896728}, {'batch_size': 10, 'throughput': 1.1879953034704103, 'latency_mean': 8.333060767650604, 'latency_p50': 8.359819293022156, 'latency_p90': 9.41410298347473}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-qwen14b-dpoexp2-_84998_v1
is_internal_developer: False
language_model: ChaiML/qwen14b-dpoexp2-sftdel12kexp3
model_size: 15B
ranking_group: single
throughput_3p7s: 0.9
us_pacific_date: 2025-04-07
win_ratio: 0.48746518105849584
generation_params: {'temperature': 0.75, 'top_p': 0.96, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.2, 'frequency_penalty': 0.2, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '[INST]<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', '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': '<|im_start|>assistant\n{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-dpoexp2-84998-v1-mkmlizer
Waiting for job on chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer to finish
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ║ _____ __ __ ║
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ║ /___/ ║
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ║ belonging to: ║
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: Downloaded to shared memory in 52.176s
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4eqiye_v, device:0
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: quantized model in 36.976s
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: Processed model ChaiML/qwen14b-dpoexp2-sftdel12kexp3 in 89.153s
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-84998-v1
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-84998-v1/config.json
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-84998-v1/added_tokens.json
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-84998-v1/tokenizer_config.json
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-84998-v1/special_tokens_map.json
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-84998-v1/merges.txt
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-84998-v1/vocab.json
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-84998-v1/tokenizer.json
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-84998-v1/flywheel_model.0.safetensors
chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer: Loading 0: 0%| | 0/579 [00:00<?, ?it/s] Loading 0: 3%|▎ | 15/579 [00:00<00:04, 134.51it/s] Loading 0: 5%|▌ | 29/579 [00:00<00:04, 119.48it/s] Loading 0: 8%|▊ | 47/579 [00:00<00:03, 143.11it/s] Loading 0: 11%|█ | 63/579 [00:00<00:03, 146.42it/s] Loading 0: 14%|█▍ | 81/579 [00:00<00:05, 94.33it/s] Loading 0: 16%|█▌ | 94/579 [00:00<00:04, 101.28it/s] Loading 0: 18%|█▊ | 107/579 [00:00<00:04, 106.97it/s] Loading 0: 21%|██ | 120/579 [00:01<00:04, 110.86it/s] Loading 0: 24%|██▍ | 138/579 [00:01<00:03, 127.86it/s] Loading 0: 27%|██▋ | 154/579 [00:01<00:03, 135.13it/s] Loading 0: 29%|██▉ | 169/579 [00:01<00:03, 129.49it/s] Loading 0: 32%|███▏ | 186/579 [00:01<00:02, 138.72it/s] Loading 0: 35%|███▍ | 201/579 [00:01<00:04, 83.20it/s] Loading 0: 38%|███▊ | 219/579 [00:01<00:03, 98.59it/s] Loading 0: 40%|████ | 232/579 [00:02<00:03, 104.06it/s] Loading 0: 42%|████▏ | 245/579 [00:02<00:03, 108.21it/s] Loading 0: 45%|████▌ | 263/579 [00:02<00:02, 124.31it/s] Loading 0: 48%|████▊ | 279/579 [00:02<00:02, 131.63it/s] Loading 0: 51%|█████▏ | 297/579 [00:02<00:02, 99.01it/s] Loading 0: 53%|█████▎ | 309/579 [00:02<00:02, 94.65it/s] Loading 0: 56%|█████▋ | 327/579 [00:02<00:02, 110.00it/s] Loading 0: 59%|█████▊ | 340/579 [00:03<00:02, 114.05it/s] Loading 0: 61%|██████ | 353/579 [00:03<00:01, 116.23it/s] Loading 0: 64%|██████▍ | 371/579 [00:03<00:01, 132.22it/s] Loading 0: 67%|██████▋ | 387/579 [00:03<00:01, 137.81it/s] Loading 0: 70%|██████▉ | 405/579 [00:03<00:01, 102.38it/s] Loading 0: 72%|███████▏ | 418/579 [00:03<00:01, 99.21it/s] Loading 0: 75%|███████▌ | 435/579 [00:03<00:01, 110.00it/s] Loading 0: 77%|███████▋ | 448/579 [00:03<00:01, 112.60it/s] Loading 0: 80%|███████▉ | 461/579 [00:04<00:01, 115.25it/s] Loading 0: 83%|████████▎ | 479/579 [00:04<00:00, 131.70it/s] Loading 0: 85%|████████▌ | 495/579 [00:04<00:00, 138.44it/s] Loading 0: 88%|████████▊ | 512/579 [00:22<00:00, 138.44it/s] Loading 0: 89%|████████▊ | 513/579 [00:26<00:26, 2.45it/s] Loading 0: 90%|█████████ | 522/579 [00:26<00:18, 3.01it/s] Loading 0: 94%|█████████▎| 542/579 [00:26<00:07, 4.79it/s] Loading 0: 96%|█████████▌| 557/579 [00:26<00:03, 6.63it/s] Loading 0: 99%|█████████▊| 571/579 [00:26<00:00, 9.00it/s]
Job chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer completed after 114.65s with status: succeeded
Stopping job with name chaiml-qwen14b-dpoexp2-84998-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.10s
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-qwen14b-dpoexp2-84998-v1
Waiting for inference service chaiml-qwen14b-dpoexp2-84998-v1 to be ready
Inference service chaiml-qwen14b-dpoexp2-84998-v1 ready after 100.52530264854431s
Pipeline stage MKMLDeployer completed in 101.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6912143230438232s
Received healthy response to inference request in 2.060774564743042s
Received healthy response to inference request in 2.0424559116363525s
Received healthy response to inference request in 2.066713333129883s
Received healthy response to inference request in 2.0091402530670166s
5 requests
0 failed requests
5th percentile: 2.0158033847808836
10th percentile: 2.022466516494751
20th percentile: 2.0357927799224855
30th percentile: 2.0461196422576906
40th percentile: 2.0534471035003663
50th percentile: 2.060774564743042
60th percentile: 2.0631500720977782
70th percentile: 2.0655255794525145
80th percentile: 2.191613531112671
90th percentile: 2.441413927078247
95th percentile: 2.566314125061035
99th percentile: 2.6662342834472654
mean time: 2.1740596771240233
Pipeline stage StressChecker completed in 12.18s
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 0.69s
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 0.63s
Shutdown handler de-registered
chaiml-qwen14b-dpoexp2-_84998_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 4591.56s
Shutdown handler de-registered
chaiml-qwen14b-dpoexp2-_84998_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen14b-dpoexp2-_84998_v1 status is now torndown due to DeploymentManager action