developer_uid: azuruce
submission_id: cloudyu-nemo-dpo-v23_v8
model_name: cloudyu-nemo-dpo-v23_v8
model_group: cloudyu/Nemo-DPO-V23
status: torndown
timestamp: 2025-01-16T20:04:18+00:00
num_battles: 7622
num_wins: 3769
celo_rating: 1261.76
family_friendly_score: 0.5806
family_friendly_standard_error: 0.0069785906886705995
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V23
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
display_name: cloudyu-nemo-dpo-v23_v8
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V23
model_size: 13B
ranking_group: single
us_pacific_date: 2025-01-16
win_ratio: 0.49448963526633427
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.001, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|eot_id|>', 'User:', 'Me:', 'Bot:', '\n', '</s>', '####', '<|im_end|>', 'You:'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', '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-v8-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v23-v8-mkmlizer to finish
cloudyu-nemo-dpo-v23-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v23-v8-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v23-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v23-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v23-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v23-v8-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v23-v8-mkmlizer: ║ ║
cloudyu-nemo-dpo-v23-v8-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v23-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v23-v8-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v23-v8-mkmlizer: ║ ║
cloudyu-nemo-dpo-v23-v8-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v23-v8-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v23-v8-mkmlizer: ║ ║
cloudyu-nemo-dpo-v23-v8-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v23-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v23-v8-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
cloudyu-nemo-dpo-v23-v8-mkmlizer: ║ ║
cloudyu-nemo-dpo-v23-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v23-v8-mkmlizer: Downloaded to shared memory in 32.311s
cloudyu-nemo-dpo-v23-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvg5tuasu, device:0
cloudyu-nemo-dpo-v23-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v23-v8-mkmlizer: quantized model in 37.189s
cloudyu-nemo-dpo-v23-v8-mkmlizer: Processed model cloudyu/Nemo-DPO-V23 in 69.501s
cloudyu-nemo-dpo-v23-v8-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v23-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v23-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v8
cloudyu-nemo-dpo-v23-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v8/config.json
cloudyu-nemo-dpo-v23-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v8/special_tokens_map.json
cloudyu-nemo-dpo-v23-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v8/tokenizer_config.json
cloudyu-nemo-dpo-v23-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v8/tokenizer.json
cloudyu-nemo-dpo-v23-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v8/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v23-v8-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:41, 3.11s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:59, 1.19it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:46, 3.29it/s] Loading 0: 5%|▌ | 19/363 [00:06<01:01, 5.64it/s] Loading 0: 7%|▋ | 24/363 [00:06<00:43, 7.86it/s] Loading 0: 9%|▉ | 32/363 [00:06<00:25, 12.95it/s] Loading 0: 10%|█ | 38/363 [00:07<00:19, 16.51it/s] Loading 0: 12%|█▏ | 43/363 [00:07<00:20, 15.87it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:14, 21.37it/s] Loading 0: 15%|█▌ | 56/363 [00:07<00:12, 24.81it/s] Loading 0: 17%|█▋ | 61/363 [00:07<00:10, 27.81it/s] Loading 0: 19%|█▊ | 68/363 [00:07<00:08, 34.13it/s] Loading 0: 20%|██ | 73/363 [00:08<00:08, 35.22it/s] Loading 0: 21%|██▏ | 78/363 [00:08<00:08, 32.92it/s] Loading 0: 24%|██▎ | 86/363 [00:08<00:06, 41.38it/s] Loading 0: 25%|██▌ | 92/363 [00:08<00:06, 40.74it/s] Loading 0: 27%|██▋ | 97/363 [00:08<00:06, 40.19it/s] Loading 0: 29%|██▊ | 104/363 [00:08<00:05, 44.87it/s] Loading 0: 30%|███ | 110/363 [00:08<00:05, 44.02it/s] Loading 0: 32%|███▏ | 115/363 [00:08<00:05, 41.51it/s] Loading 0: 33%|███▎ | 121/363 [00:09<00:08, 30.12it/s] Loading 0: 34%|███▍ | 125/363 [00:09<00:07, 30.78it/s] Loading 0: 36%|███▌ | 130/363 [00:09<00:06, 34.56it/s] Loading 0: 37%|███▋ | 134/363 [00:09<00:06, 34.22it/s] Loading 0: 39%|███▊ | 140/363 [00:09<00:05, 38.04it/s] Loading 0: 40%|███▉ | 145/363 [00:09<00:05, 39.66it/s] Loading 0: 41%|████▏ | 150/363 [00:10<00:06, 32.65it/s] Loading 0: 43%|████▎ | 157/363 [00:10<00:05, 39.08it/s] Loading 0: 45%|████▍ | 162/363 [00:10<00:05, 38.79it/s] Loading 0: 46%|████▌ | 167/363 [00:10<00:05, 38.85it/s] Loading 0: 47%|████▋ | 172/363 [00:10<00:04, 39.45it/s] Loading 0: 49%|████▉ | 177/363 [00:10<00:05, 32.43it/s] Loading 0: 51%|█████ | 184/363 [00:10<00:04, 39.55it/s] Loading 0: 52%|█████▏ | 189/363 [00:11<00:04, 39.28it/s] Loading 0: 53%|█████▎ | 194/363 [00:11<00:04, 39.44it/s] Loading 0: 55%|█████▍ | 199/363 [00:11<00:04, 40.74it/s] Loading 0: 56%|█████▌ | 204/363 [00:11<00:06, 24.45it/s] Loading 0: 58%|█████▊ | 211/363 [00:11<00:04, 31.90it/s] Loading 0: 60%|█████▉ | 216/363 [00:11<00:04, 33.89it/s] Loading 0: 61%|██████ | 221/363 [00:12<00:04, 33.91it/s] Loading 0: 62%|██████▏ | 226/363 [00:12<00:03, 36.30it/s] Loading 0: 64%|██████▎ | 231/363 [00:12<00:04, 32.20it/s] Loading 0: 66%|██████▌ | 238/363 [00:12<00:03, 39.96it/s] Loading 0: 67%|██████▋ | 243/363 [00:12<00:03, 39.97it/s] Loading 0: 68%|██████▊ | 248/363 [00:12<00:02, 39.97it/s] Loading 0: 70%|██████▉ | 253/363 [00:12<00:02, 41.15it/s] Loading 0: 71%|███████ | 258/363 [00:13<00:03, 34.04it/s] Loading 0: 73%|███████▎ | 265/363 [00:13<00:02, 39.72it/s] Loading 0: 74%|███████▍ | 270/363 [00:13<00:02, 39.64it/s] Loading 0: 76%|███████▌ | 275/363 [00:13<00:02, 40.05it/s] Loading 0: 77%|███████▋ | 280/363 [00:13<00:01, 42.06it/s] Loading 0: 79%|███████▊ | 285/363 [00:13<00:02, 26.14it/s] Loading 0: 80%|████████ | 292/363 [00:14<00:02, 33.30it/s] Loading 0: 82%|████████▏ | 297/363 [00:14<00:01, 34.90it/s] Loading 0: 83%|████████▎ | 302/363 [00:14<00:01, 36.54it/s] Loading 0: 85%|████████▍ | 307/363 [00:14<00:01, 39.57it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:01, 34.07it/s] Loading 0: 88%|████████▊ | 319/363 [00:14<00:01, 41.20it/s] Loading 0: 89%|████████▉ | 324/363 [00:14<00:00, 41.46it/s] Loading 0: 91%|█████████ | 329/363 [00:14<00:00, 42.57it/s] Loading 0: 92%|█████████▏| 334/363 [00:15<00:00, 44.39it/s] Loading 0: 93%|█████████▎| 339/363 [00:15<00:00, 36.86it/s] Loading 0: 95%|█████████▌| 346/363 [00:15<00:00, 44.23it/s] Loading 0: 97%|█████████▋| 351/363 [00:15<00:00, 41.99it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 43.10it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 41.66it/s]
Job cloudyu-nemo-dpo-v23-v8-mkmlizer completed after 104.51s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v23-v8-mkmlizer
Pipeline stage MKMLizer completed in 105.07s
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 cloudyu-nemo-dpo-v23-v8
Waiting for inference service cloudyu-nemo-dpo-v23-v8 to be ready
Inference service cloudyu-nemo-dpo-v23-v8 ready after 120.65722227096558s
Pipeline stage MKMLDeployer completed in 121.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8590292930603027s
Received healthy response to inference request in 1.6943047046661377s
Received healthy response to inference request in 1.4660465717315674s
Received healthy response to inference request in 1.5809082984924316s
Received healthy response to inference request in 1.4330637454986572s
5 requests
0 failed requests
5th percentile: 1.4396603107452393
10th percentile: 1.4462568759918213
20th percentile: 1.4594500064849854
30th percentile: 1.4890189170837402
40th percentile: 1.534963607788086
50th percentile: 1.5809082984924316
60th percentile: 1.626266860961914
70th percentile: 1.6716254234313965
80th percentile: 1.7272496223449707
90th percentile: 1.7931394577026367
95th percentile: 1.8260843753814697
99th percentile: 1.852440309524536
mean time: 1.6066705226898192
Pipeline stage StressChecker completed in 9.14s
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 0.60s
Shutdown handler de-registered
cloudyu-nemo-dpo-v23_v8 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-nemo-dpo-v23-v8-profiler
Waiting for inference service cloudyu-nemo-dpo-v23-v8-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 4443.64s
Shutdown handler de-registered
cloudyu-nemo-dpo-v23_v8 status is now inactive due to auto deactivation removed underperforming models
cloudyu-nemo-dpo-v23_v8 status is now torndown due to DeploymentManager action