developer_uid: NischayDnk
submission_id: chaiml-qwen14b-dpoexp2-s_6544_v1
model_name: chaiml-qwen14b-dpoexp2-s_6544_v1
model_group: ChaiML/qwen14b-dpoexp2-s
status: torndown
timestamp: 2025-04-08T22:49:59+00:00
num_battles: 8924
num_wins: 4539
celo_rating: 1275.63
family_friendly_score: 0.5324
family_friendly_standard_error: 0.007056206346189147
submission_type: basic
model_repo: ChaiML/qwen14b-dpoexp2-sftdel12kexp4-oldformat
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': 0.4722957615099723, 'latency_mean': 2.1172327828407287, 'latency_p50': 2.12787401676178, 'latency_p90': 2.3301868200302125}, {'batch_size': 3, 'throughput': 0.876924533694052, 'latency_mean': 3.413523939847946, 'latency_p50': 3.4172126054763794, 'latency_p90': 3.722565841674805}, {'batch_size': 5, 'throughput': 1.0607789329985347, 'latency_mean': 4.691764281988144, 'latency_p50': 4.665650129318237, 'latency_p90': 5.255731534957886}, {'batch_size': 6, 'throughput': 1.1137673921896272, 'latency_mean': 5.366416792869568, 'latency_p50': 5.369059205055237, 'latency_p90': 5.9899046421051025}, {'batch_size': 10, 'throughput': 1.2180183053604903, 'latency_mean': 8.147691423892974, 'latency_p50': 8.156267881393433, 'latency_p90': 9.156285071372986}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-qwen14b-dpoexp2-s_6544_v1
is_internal_developer: False
language_model: ChaiML/qwen14b-dpoexp2-sftdel12kexp4-oldformat
model_size: 15B
ranking_group: single
throughput_3p7s: 0.93
us_pacific_date: 2025-04-08
win_ratio: 0.508628417749888
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': ['You:', '###', '</s>', '\n'], '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': 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-dpoexp2-s-6544-v1-mkmlizer
Waiting for job on chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer to finish
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ║ _____ __ __ ║
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ║ /___/ ║
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ║ belonging to: ║
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: Downloaded to shared memory in 51.964s
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprpow6zo3, device:0
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: quantized model in 37.173s
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: Processed model ChaiML/qwen14b-dpoexp2-sftdel12kexp4-oldformat in 89.138s
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v1
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v1/config.json
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v1/added_tokens.json
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v1/special_tokens_map.json
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v1/tokenizer_config.json
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v1/merges.txt
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v1/vocab.json
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v1/tokenizer.json
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v1/flywheel_model.1.safetensors
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v1/flywheel_model.0.safetensors
chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer: Loading 0: 0%| | 0/579 [00:00<?, ?it/s] Loading 0: 3%|▎ | 15/579 [00:00<00:04, 130.17it/s] Loading 0: 5%|▌ | 29/579 [00:00<00:04, 117.50it/s] Loading 0: 8%|▊ | 47/579 [00:00<00:03, 140.48it/s] Loading 0: 11%|█ | 63/579 [00:00<00:03, 142.35it/s] Loading 0: 14%|█▍ | 81/579 [00:00<00:05, 90.07it/s] Loading 0: 16%|█▌ | 94/579 [00:00<00:04, 97.19it/s] Loading 0: 18%|█▊ | 107/579 [00:00<00:04, 103.48it/s] Loading 0: 21%|██ | 120/579 [00:01<00:04, 108.52it/s] Loading 0: 24%|██▍ | 138/579 [00:01<00:03, 126.03it/s] Loading 0: 27%|██▋ | 154/579 [00:01<00:03, 130.97it/s] Loading 0: 29%|██▉ | 168/579 [00:01<00:03, 123.32it/s] Loading 0: 32%|███▏ | 184/579 [00:01<00:02, 132.90it/s] Loading 0: 34%|███▍ | 198/579 [00:01<00:04, 77.90it/s] Loading 0: 37%|███▋ | 215/579 [00:02<00:03, 94.20it/s] Loading 0: 40%|███▉ | 231/579 [00:02<00:03, 105.32it/s] Loading 0: 42%|████▏ | 245/579 [00:02<00:03, 105.95it/s] Loading 0: 45%|████▌ | 263/579 [00:02<00:02, 121.72it/s] Loading 0: 48%|████▊ | 279/579 [00:02<00:02, 128.51it/s] Loading 0: 51%|█████▏ | 297/579 [00:02<00:02, 94.51it/s] Loading 0: 53%|█████▎ | 309/579 [00:02<00:02, 91.89it/s] Loading 0: 56%|█████▋ | 327/579 [00:03<00:02, 105.49it/s] Loading 0: 59%|█████▊ | 340/579 [00:03<00:02, 108.63it/s] Loading 0: 61%|██████ | 353/579 [00:03<00:02, 112.33it/s] Loading 0: 64%|██████▍ | 371/579 [00:03<00:01, 128.19it/s] Loading 0: 67%|██████▋ | 387/579 [00:03<00:01, 134.50it/s] Loading 0: 70%|██████▉ | 405/579 [00:03<00:01, 97.86it/s] Loading 0: 72%|███████▏ | 417/579 [00:03<00:01, 94.39it/s] Loading 0: 75%|███████▌ | 435/579 [00:03<00:01, 108.42it/s] Loading 0: 77%|███████▋ | 448/579 [00:04<00:01, 111.72it/s] Loading 0: 80%|███████▉ | 461/579 [00:04<00:01, 114.97it/s] Loading 0: 83%|████████▎ | 479/579 [00:04<00:00, 131.42it/s] Loading 0: 85%|████████▌ | 495/579 [00:04<00:00, 136.41it/s] Loading 0: 88%|████████▊ | 512/579 [00:22<00:00, 136.41it/s] Loading 0: 89%|████████▊ | 513/579 [00:26<00:26, 2.45it/s] Loading 0: 90%|████████▉ | 521/579 [00:26<00:19, 2.94it/s] Loading 0: 92%|█████████▏| 534/579 [00:26<00:11, 4.08it/s] Loading 0: 95%|█████████▌| 552/579 [00:26<00:04, 6.32it/s] Loading 0: 98%|█████████▊| 568/579 [00:26<00:01, 9.05it/s]
Job chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer completed after 114.72s with status: succeeded
Stopping job with name chaiml-qwen14b-dpoexp2-s-6544-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.19s
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-6544-v1
Waiting for inference service chaiml-qwen14b-dpoexp2-s-6544-v1 to be ready
Inference service chaiml-qwen14b-dpoexp2-s-6544-v1 ready after 110.41439819335938s
Pipeline stage MKMLDeployer completed in 110.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4540963172912598s
Received healthy response to inference request in 1.9803595542907715s
Received healthy response to inference request in 2.2912752628326416s
Received healthy response to inference request in 2.11198353767395s
Received healthy response to inference request in 2.119997501373291s
5 requests
0 failed requests
5th percentile: 2.006684350967407
10th percentile: 2.033009147644043
20th percentile: 2.0856587409973146
30th percentile: 2.1135863304138183
40th percentile: 2.116791915893555
50th percentile: 2.119997501373291
60th percentile: 2.1885086059570313
70th percentile: 2.2570197105407717
80th percentile: 2.323839473724365
90th percentile: 2.3889678955078124
95th percentile: 2.4215321063995363
99th percentile: 2.447583475112915
mean time: 2.1915424346923826
Pipeline stage StressChecker completed in 12.09s
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 0.68s
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 0.94s
Shutdown handler de-registered
chaiml-qwen14b-dpoexp2-s_6544_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 4769.45s
Shutdown handler de-registered
chaiml-qwen14b-dpoexp2-s_6544_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen14b-dpoexp2-s_6544_v1 status is now torndown due to DeploymentManager action