developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v23_v3
model_name: cloudyu-nemo-dpo-v23_v2
model_group: cloudyu/Nemo-DPO-V23
status: torndown
timestamp: 2025-01-10T09:17:47+00:00
num_battles: 8547
num_wins: 4538
celo_rating: 1283.81
family_friendly_score: 0.5782
family_friendly_standard_error: 0.006984049828000943
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V23
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6149409056838617, 'latency_mean': 1.6261061668395995, 'latency_p50': 1.635454773902893, 'latency_p90': 1.7935657262802125}, {'batch_size': 3, 'throughput': 1.1655542324095944, 'latency_mean': 2.5684802865982057, 'latency_p50': 2.5706347227096558, 'latency_p90': 2.817055535316467}, {'batch_size': 5, 'throughput': 1.4099164401513842, 'latency_mean': 3.526917588710785, 'latency_p50': 3.543939232826233, 'latency_p90': 3.97267050743103}, {'batch_size': 6, 'throughput': 1.4838677360037413, 'latency_mean': 4.013428869247437, 'latency_p50': 4.012672662734985, 'latency_p90': 4.518903398513793}, {'batch_size': 8, 'throughput': 1.5615631713084301, 'latency_mean': 5.082438433170319, 'latency_p50': 5.076047778129578, 'latency_p90': 5.695587897300721}, {'batch_size': 10, 'throughput': 1.6081270892083563, 'latency_mean': 6.17447046995163, 'latency_p50': 6.226243257522583, 'latency_p90': 6.981706547737121}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v23_v2
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V23
model_size: 13B
ranking_group: single
throughput_3p7s: 1.45
us_pacific_date: 2025-01-10
win_ratio: 0.530946530946531
generation_params: {'temperature': 1.25, 'top_p': 0.99, 'min_p': 0.01, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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 cloudyu-nemo-dpo-v23-v3-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v23-v3-mkmlizer to finish
cloudyu-nemo-dpo-v23-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v23-v3-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v23-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v23-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v23-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v23-v3-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v23-v3-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v23-v3-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v23-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v23-v3-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v23-v3-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v23-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v23-v3-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v23-v3-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v23-v3-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v23-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v23-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cloudyu-nemo-dpo-v23-v3-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v23-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v23-v3-mkmlizer: Downloaded to shared memory in 44.166s
cloudyu-nemo-dpo-v23-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1gk4z_hr, device:0
cloudyu-nemo-dpo-v23-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v23-v3-mkmlizer: quantized model in 36.946s
cloudyu-nemo-dpo-v23-v3-mkmlizer: Processed model cloudyu/Nemo-DPO-V23 in 81.112s
cloudyu-nemo-dpo-v23-v3-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v23-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v23-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v3
cloudyu-nemo-dpo-v23-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v3/config.json
cloudyu-nemo-dpo-v23-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v3/special_tokens_map.json
cloudyu-nemo-dpo-v23-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v3/tokenizer_config.json
cloudyu-nemo-dpo-v23-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v3/tokenizer.json
cloudyu-nemo-dpo-v23-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v3/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v23-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:11,  3.02s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:50,  1.23it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:43,  3.38it/s]
Loading 0:   5%|▍         | 18/363 [00:06<01:04,  5.36it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:43,  7.87it/s]
Loading 0:   8%|▊         | 28/363 [00:06<00:30, 10.93it/s]
Loading 0:   9%|▉         | 33/363 [00:06<00:24, 13.41it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.62it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 18.91it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:13, 23.92it/s]
Loading 0:  15%|█▍        | 54/363 [00:07<00:11, 25.85it/s]
Loading 0:  16%|█▌        | 58/363 [00:07<00:10, 27.83it/s]
Loading 0:  17%|█▋        | 62/363 [00:07<00:10, 29.01it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:09, 32.18it/s]
Loading 0:  20%|█▉        | 71/363 [00:07<00:08, 32.52it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:08, 35.77it/s]
Loading 0:  22%|██▏       | 80/363 [00:08<00:08, 33.74it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:07, 37.32it/s]
Loading 0:  25%|██▍       | 89/363 [00:08<00:07, 35.68it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 39.81it/s]
Loading 0:  28%|██▊       | 100/363 [00:08<00:06, 41.57it/s]
Loading 0:  29%|██▉       | 105/363 [00:08<00:07, 34.81it/s]
Loading 0:  31%|███       | 112/363 [00:08<00:05, 42.53it/s]
Loading 0:  32%|███▏      | 117/363 [00:09<00:05, 41.09it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:07, 30.81it/s]
Loading 0:  35%|███▍      | 126/363 [00:09<00:07, 31.76it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:07, 32.19it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:07, 31.42it/s]
Loading 0:  38%|███▊      | 139/363 [00:09<00:06, 33.94it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:06, 34.34it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:05, 37.80it/s]
Loading 0:  42%|████▏     | 152/363 [00:10<00:05, 36.46it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:05, 40.75it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:04, 41.52it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:05, 33.24it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:04, 40.12it/s]
Loading 0:  50%|████▉     | 180/363 [00:10<00:04, 40.01it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:04, 38.23it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:04, 38.82it/s]
Loading 0:  54%|█████▎    | 195/363 [00:11<00:05, 31.51it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:05, 28.81it/s]
Loading 0:  57%|█████▋    | 206/363 [00:11<00:05, 29.95it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 32.35it/s]
Loading 0:  59%|█████▉    | 215/363 [00:12<00:04, 33.29it/s]
Loading 0:  61%|██████    | 221/363 [00:12<00:03, 37.65it/s]
Loading 0:  62%|██████▏   | 225/363 [00:12<00:03, 37.84it/s]
Loading 0:  63%|██████▎   | 230/363 [00:12<00:03, 39.48it/s]
Loading 0:  65%|██████▍   | 235/363 [00:12<00:03, 41.25it/s]
Loading 0:  66%|██████▌   | 240/363 [00:12<00:03, 35.80it/s]
Loading 0:  68%|██████▊   | 248/363 [00:12<00:02, 44.64it/s]
Loading 0:  70%|██████▉   | 254/363 [00:12<00:02, 43.18it/s]
Loading 0:  71%|███████▏  | 259/363 [00:13<00:02, 41.80it/s]
Loading 0:  73%|███████▎  | 266/363 [00:13<00:02, 46.58it/s]
Loading 0:  75%|███████▍  | 271/363 [00:13<00:01, 47.25it/s]
Loading 0:  76%|███████▌  | 276/363 [00:13<00:02, 39.00it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:02, 34.13it/s]
Loading 0:  79%|███████▉  | 287/363 [00:13<00:02, 34.12it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:01, 37.06it/s]
Loading 0:  82%|████████▏ | 296/363 [00:14<00:01, 37.46it/s]
Loading 0:  83%|████████▎ | 302/363 [00:14<00:01, 40.88it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:01, 40.82it/s]
Loading 0:  86%|████████▌ | 313/363 [00:14<00:01, 40.43it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:00, 45.04it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:00, 43.22it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:00, 42.49it/s]
Loading 0:  92%|█████████▏| 334/363 [00:14<00:00, 42.58it/s]
Loading 0:  93%|█████████▎| 339/363 [00:15<00:00, 35.40it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 42.82it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 41.43it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 41.49it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 42.71it/s]
                                                            

Job cloudyu-nemo-dpo-v23-v3-mkmlizer completed after 104.89s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v23-v3-mkmlizer
Pipeline stage MKMLizer completed in 105.45s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v23-v3
Waiting for inference service cloudyu-nemo-dpo-v23-v3 to be ready
Failed to get response for submission zzyabc-unsloth2_v3: HTTPConnectionPool(host='zzyabc-unsloth2-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service cloudyu-nemo-dpo-v23-v3 ready after 361.22876715660095s
Pipeline stage MKMLDeployer completed in 361.79s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0064332485198975s
Received healthy response to inference request in 1.7337872982025146s
Received healthy response to inference request in 1.6748640537261963s
Received healthy response to inference request in 1.6815485954284668s
Received healthy response to inference request in 1.5434343814849854s
5 requests
0 failed requests
5th percentile: 1.5697203159332276
10th percentile: 1.5960062503814698
20th percentile: 1.648578119277954
30th percentile: 1.6762009620666505
40th percentile: 1.6788747787475586
50th percentile: 1.6815485954284668
60th percentile: 1.702444076538086
70th percentile: 1.723339557647705
80th percentile: 1.7883164882659912
90th percentile: 1.8973748683929443
95th percentile: 1.951904058456421
99th percentile: 1.995527410507202
mean time: 1.728013515472412
Pipeline stage StressChecker completed in 10.61s
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 0.77s
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 0.74s
Shutdown handler de-registered
cloudyu-nemo-dpo-v23_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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-nemo-dpo-v23-v3-profiler
Waiting for inference service cloudyu-nemo-dpo-v23-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2785.15s
Shutdown handler de-registered
cloudyu-nemo-dpo-v23_v3 status is now inactive due to auto deactivation removed underperforming models
cloudyu-nemo-dpo-v23_v3 status is now torndown due to DeploymentManager action