developer_uid: NischayDnk
submission_id: chaiml-qwen-dpo-exp1-da_53786_v3
model_name: chaiml-qwen-dpo-exp1-da_53786_v3
model_group: ChaiML/qwen-dpo-exp1-dat
status: torndown
timestamp: 2025-04-14T15:02:54+00:00
num_battles: 8897
num_wins: 4287
celo_rating: 1270.7
family_friendly_score: 0.5754
family_friendly_standard_error: 0.0069902051472041935
submission_type: basic
model_repo: ChaiML/qwen-dpo-exp1-datav1noffsftfull
model_architecture: Qwen2ForCausalLM
model_num_parameters: 32763417600.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.2991687678997295, 'latency_mean': 3.3425209295749663, 'latency_p50': 3.3189826011657715, 'latency_p90': 3.7481906175613404}, {'batch_size': 3, 'throughput': 0.6985951715537234, 'latency_mean': 4.270192630290985, 'latency_p50': 4.2763694524765015, 'latency_p90': 4.699401950836181}, {'batch_size': 5, 'throughput': 1.0249239404065613, 'latency_mean': 4.849379934072495, 'latency_p50': 4.8976757526397705, 'latency_p90': 5.313835525512695}, {'batch_size': 6, 'throughput': 1.151732688916493, 'latency_mean': 5.162355777025223, 'latency_p50': 5.173844933509827, 'latency_p90': 5.772366380691528}, {'batch_size': 10, 'throughput': 1.5668426862305236, 'latency_mean': 6.311667768955231, 'latency_p50': 6.30804705619812, 'latency_p90': 7.187207436561584}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-qwen-dpo-exp1-da_53786_v3
is_internal_developer: False
language_model: ChaiML/qwen-dpo-exp1-datav1noffsftfull
model_size: 33B
ranking_group: single
throughput_3p7s: 0.48
us_pacific_date: 2025-04-14
win_ratio: 0.48184781386984377
generation_params: {'temperature': 0.5, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>Family Friendly{memory}\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-qwen-dpo-exp1-da-53786-v3-mkmlizer
Waiting for job on chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer to finish
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ║ _____ __ __ ║
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ║ /___/ ║
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ║ ║
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ║ ║
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ║ belonging to: ║
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ║ ║
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ║ ║
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: Downloaded to shared memory in 86.901s
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpub3kd2k5, device:0
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: quantized model in 63.624s
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: Processed model ChaiML/qwen-dpo-exp1-datav1noffsftfull in 150.526s
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v3
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v3/config.json
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v3/added_tokens.json
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v3/special_tokens_map.json
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v3/tokenizer_config.json
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v3/merges.txt
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v3/vocab.json
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v3/tokenizer.json
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v3/flywheel_model.2.safetensors
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v3/flywheel_model.1.safetensors
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen-dpo-exp1-da-53786-v3/flywheel_model.0.safetensors
chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:20, 37.28it/s] Loading 0: 2%|▏ | 16/771 [00:00<00:10, 72.41it/s] Loading 0: 4%|▎ | 27/771 [00:00<00:08, 86.09it/s] Loading 0: 5%|▍ | 36/771 [00:00<00:08, 85.03it/s] Loading 0: 6%|▌ | 46/771 [00:00<00:13, 54.96it/s] Loading 0: 7%|▋ | 53/771 [00:00<00:15, 46.29it/s] Loading 0: 8%|▊ | 64/771 [00:01<00:12, 58.55it/s] Loading 0: 10%|▉ | 75/771 [00:01<00:10, 69.56it/s] Loading 0: 11%|█ | 84/771 [00:01<00:09, 72.67it/s] Loading 0: 12%|█▏ | 93/771 [00:01<00:09, 69.92it/s] Loading 0: 14%|█▎ | 106/771 [00:01<00:11, 59.94it/s] Loading 0: 15%|█▍ | 113/771 [00:01<00:11, 56.64it/s] Loading 0: 16%|█▌ | 121/771 [00:01<00:11, 56.57it/s] Loading 0: 17%|█▋ | 132/771 [00:02<00:09, 66.81it/s] Loading 0: 18%|█▊ | 142/771 [00:02<00:08, 73.66it/s] Loading 0: 20%|█▉ | 152/771 [00:02<00:07, 79.20it/s] Loading 0: 21%|██ | 161/771 [00:02<00:08, 74.76it/s] Loading 0: 22%|██▏ | 169/771 [00:02<00:11, 50.80it/s] Loading 0: 23%|██▎ | 176/771 [00:02<00:11, 51.58it/s] Loading 0: 24%|██▍ | 184/771 [00:02<00:10, 57.22it/s] Loading 0: 25%|██▌ | 195/771 [00:03<00:08, 68.23it/s] Loading 0: 26%|██▋ | 203/771 [00:03<00:08, 70.23it/s] Loading 0: 27%|██▋ | 211/771 [00:03<00:08, 67.46it/s] Loading 0: 29%|██▉ | 226/771 [00:03<00:08, 61.46it/s] Loading 0: 30%|███ | 233/771 [00:03<00:10, 51.96it/s] Loading 0: 32%|███▏ | 245/771 [00:03<00:08, 60.61it/s] Loading 0: 33%|███▎ | 257/771 [00:04<00:07, 66.98it/s] Loading 0: 35%|███▍ | 268/771 [00:04<00:06, 75.51it/s] Loading 0: 36%|███▌ | 278/771 [00:04<00:06, 80.17it/s] Loading 0: 37%|███▋ | 287/771 [00:04<00:07, 60.79it/s] Loading 0: 38%|███▊ | 295/771 [00:04<00:08, 56.30it/s] Loading 0: 39%|███▉ | 303/771 [00:18<03:47, 2.06it/s] Loading 0: 40%|████ | 311/771 [00:19<02:43, 2.81it/s] Loading 0: 41%|████ | 318/771 [00:19<02:02, 3.71it/s] Loading 0: 43%|████▎ | 328/771 [00:19<01:20, 5.53it/s] Loading 0: 44%|████▍ | 338/771 [00:19<00:53, 8.02it/s] Loading 0: 45%|████▍ | 346/771 [00:19<00:42, 9.92it/s] Loading 0: 46%|████▌ | 353/771 [00:19<00:35, 11.68it/s] Loading 0: 47%|████▋ | 365/771 [00:20<00:23, 17.48it/s] Loading 0: 49%|████▉ | 377/771 [00:20<00:16, 24.40it/s] Loading 0: 50%|█████ | 388/771 [00:20<00:11, 32.25it/s] Loading 0: 52%|█████▏ | 398/771 [00:20<00:09, 39.85it/s] Loading 0: 53%|█████▎ | 407/771 [00:20<00:09, 38.77it/s] Loading 0: 54%|█████▎ | 414/771 [00:20<00:09, 39.34it/s] Loading 0: 55%|█████▍ | 424/771 [00:20<00:07, 48.69it/s] Loading 0: 56%|█████▋ | 435/771 [00:21<00:05, 59.43it/s] Loading 0: 58%|█████▊ | 444/771 [00:21<00:05, 64.95it/s] Loading 0: 59%|█████▉ | 453/771 [00:21<00:04, 64.70it/s] Loading 0: 60%|██████ | 466/771 [00:21<00:05, 58.06it/s] Loading 0: 61%|██████▏ | 473/771 [00:21<00:06, 49.41it/s] Loading 0: 63%|██████▎ | 484/771 [00:21<00:04, 59.90it/s] Loading 0: 64%|██████▍ | 495/771 [00:22<00:03, 69.89it/s] Loading 0: 65%|██████▌ | 504/771 [00:22<00:03, 73.94it/s] Loading 0: 67%|██████▋ | 513/771 [00:22<00:03, 71.44it/s] Loading 0: 68%|██████▊ | 526/771 [00:22<00:03, 62.88it/s] Loading 0: 69%|██████▉ | 534/771 [00:22<00:04, 53.98it/s] Loading 0: 71%|███████ | 544/771 [00:22<00:03, 62.09it/s] Loading 0: 72%|███████▏ | 555/771 [00:22<00:03, 71.52it/s] Loading 0: 73%|███████▎ | 564/771 [00:23<00:02, 75.00it/s] Loading 0: 74%|███████▍ | 573/771 [00:23<00:02, 71.61it/s] Loading 0: 76%|███████▌ | 586/771 [00:23<00:02, 61.71it/s] Loading 0: 77%|███████▋ | 593/771 [00:23<00:03, 51.58it/s] Loading 0: 78%|███████▊ | 604/771 [00:23<00:02, 62.29it/s] Loading 0: 80%|███████▉ | 615/771 [00:23<00:02, 71.78it/s] Loading 0: 81%|████████ | 624/771 [00:23<00:01, 75.44it/s] Loading 0: 82%|████████▏ | 633/771 [00:38<01:04, 2.14it/s] Loading 0: 84%|████████▍ | 646/771 [00:38<00:37, 3.30it/s] Loading 0: 85%|████████▍ | 654/771 [00:39<00:28, 4.17it/s] Loading 0: 86%|████████▌ | 664/771 [00:39<00:18, 5.87it/s] Loading 0: 88%|████████▊ | 675/771 [00:39<00:11, 8.44it/s] Loading 0: 89%|████████▊ | 684/771 [00:39<00:07, 11.20it/s] Loading 0: 90%|████████▉ | 693/771 [00:39<00:05, 14.58it/s] Loading 0: 92%|█████████▏| 706/771 [00:39<00:03, 19.70it/s] Loading 0: 92%|█████████▏| 713/771 [00:40<00:02, 21.51it/s] Loading 0: 94%|█████████▍| 724/771 [00:40<00:01, 29.16it/s] Loading 0: 95%|█████████▌| 735/771 [00:40<00:00, 38.08it/s] Loading 0: 96%|█████████▋| 744/771 [00:40<00:00, 44.97it/s] Loading 0: 98%|█████████▊| 753/771 [00:40<00:00, 49.21it/s] Loading 0: 99%|█████████▉| 766/771 [00:48<00:01, 4.30it/s]
Job chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer completed after 187.0s with status: succeeded
Stopping job with name chaiml-qwen-dpo-exp1-da-53786-v3-mkmlizer
Pipeline stage MKMLizer completed in 187.64s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen-dpo-exp1-da-53786-v3
Waiting for inference service chaiml-qwen-dpo-exp1-da-53786-v3 to be ready
Inference service chaiml-qwen-dpo-exp1-da-53786-v3 ready after 120.46869492530823s
Pipeline stage MKMLDeployer completed in 121.07s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.704498767852783s
Received healthy response to inference request in 3.0895979404449463s
Received healthy response to inference request in 3.0801823139190674s
Received healthy response to inference request in 3.0488216876983643s
Received healthy response to inference request in 3.0554325580596924s
5 requests
0 failed requests
5th percentile: 3.05014386177063
10th percentile: 3.0514660358428953
20th percentile: 3.054110383987427
30th percentile: 3.0603825092315673
40th percentile: 3.0702824115753176
50th percentile: 3.0801823139190674
60th percentile: 3.083948564529419
70th percentile: 3.0877148151397704
80th percentile: 3.212578105926514
90th percentile: 3.4585384368896483
95th percentile: 3.5815186023712156
99th percentile: 3.6799027347564697
mean time: 3.1957066535949705
Pipeline stage StressChecker completed in 17.21s
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 0.88s
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 0.62s
Shutdown handler de-registered
chaiml-qwen-dpo-exp1-da_53786_v3 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-qwen-dpo-exp1-da-53786-v3-profiler
Waiting for inference service chaiml-qwen-dpo-exp1-da-53786-v3-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 5438.72s
Shutdown handler de-registered
chaiml-qwen-dpo-exp1-da_53786_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen-dpo-exp1-da_53786_v3 status is now torndown due to DeploymentManager action