developer_uid: udbhavbamba
submission_id: udbhavbamba-nemo13b-dpo-v2_v1
model_name: dpo
model_group: udbhavbamba/nemo13b_dpo_
status: torndown
timestamp: 2025-03-23T08:18:35+00:00
num_battles: 8164
num_wins: 3936
celo_rating: 1263.69
family_friendly_score: 0.6093999999999999
family_friendly_standard_error: 0.006899733907912681
submission_type: basic
model_repo: udbhavbamba/nemo13b_dpo_v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6020098106277416, 'latency_mean': 1.6610283589363097, 'latency_p50': 1.6475328207015991, 'latency_p90': 1.8437158107757567}, {'batch_size': 3, 'throughput': 1.0910299714085676, 'latency_mean': 2.7398815679550172, 'latency_p50': 2.7504113912582397, 'latency_p90': 3.015893793106079}, {'batch_size': 5, 'throughput': 1.3163641891314724, 'latency_mean': 3.7813214004039764, 'latency_p50': 3.781013250350952, 'latency_p90': 4.2010924339294435}, {'batch_size': 6, 'throughput': 1.3902814681364932, 'latency_mean': 4.29400810956955, 'latency_p50': 4.318438649177551, 'latency_p90': 4.826735043525696}, {'batch_size': 8, 'throughput': 1.4578579515737506, 'latency_mean': 5.450191704034805, 'latency_p50': 5.510921239852905, 'latency_p90': 6.084208607673645}, {'batch_size': 10, 'throughput': 1.4929118451256587, 'latency_mean': 6.653810869455338, 'latency_p50': 6.656875133514404, 'latency_p90': 7.5455879211425785}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: dpo
is_internal_developer: False
language_model: udbhavbamba/nemo13b_dpo_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.31
us_pacific_date: 2025-03-23
win_ratio: 0.4821166095051445
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.1, 'frequency_penalty': 0.0, 'stopping_words': ['</s>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "<s>{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}', 'bot_template': '{bot_name}: {message}</s>', 'user_template': '[INST]{user_name}: {message}[/INST]', '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 udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer
Waiting for job on udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer to finish
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ║ _____ __ __ ║
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ║ /___/ ║
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ║ ║
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ║ Version: 0.12.8 ║
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ║ https://mk1.ai ║
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ║ ║
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ║ belonging to: ║
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ║ ║
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ║ Chai Research Corp. ║
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ║ ║
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: quantized model in 37.318s
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: Processed model udbhavbamba/nemo13b_dpo_v2 in 83.474s
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: creating bucket guanaco-mkml-models
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/udbhavbamba-nemo13b-dpo-v2-v1
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/udbhavbamba-nemo13b-dpo-v2-v1/config.json
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/udbhavbamba-nemo13b-dpo-v2-v1/special_tokens_map.json
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/udbhavbamba-nemo13b-dpo-v2-v1/tokenizer_config.json
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/udbhavbamba-nemo13b-dpo-v2-v1/tokenizer.json
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/udbhavbamba-nemo13b-dpo-v2-v1/flywheel_model.0.safetensors
udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 26.09it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 45.22it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:08, 42.48it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 42.57it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 49.75it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 46.42it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 45.52it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 50.20it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 44.63it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 34.63it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 32.92it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:07, 37.61it/s] Loading 0: 21%|██ | 76/363 [00:01<00:07, 36.69it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:07, 38.19it/s] Loading 0: 24%|██▎ | 86/363 [00:02<00:06, 40.47it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:07, 34.45it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 40.94it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:06, 39.03it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:06, 38.88it/s] Loading 0: 31%|███ | 113/363 [00:02<00:07, 35.52it/s] Loading 0: 33%|███▎ | 118/363 [00:03<00:06, 35.85it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:05, 42.27it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:06, 37.13it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:06, 36.02it/s] Loading 0: 38%|███▊ | 138/363 [00:03<00:06, 35.28it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:08, 26.97it/s] Loading 0: 40%|████ | 146/363 [00:03<00:07, 28.48it/s] Loading 0: 41%|████▏ | 150/363 [00:04<00:07, 27.63it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:06, 33.07it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 32.40it/s] Loading 0: 45%|████▌ | 165/363 [00:04<00:05, 35.46it/s] Loading 0: 47%|████▋ | 169/363 [00:04<00:05, 34.48it/s] Loading 0: 48%|████▊ | 174/363 [00:04<00:05, 37.58it/s] Loading 0: 49%|████▉ | 178/363 [00:04<00:05, 36.19it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 38.65it/s] Loading 0: 52%|█████▏ | 187/363 [00:05<00:04, 37.77it/s] Loading 0: 53%|█████▎ | 193/363 [00:05<00:04, 41.71it/s] Loading 0: 55%|█████▍ | 198/363 [00:05<00:03, 42.37it/s] Loading 0: 56%|█████▌ | 203/363 [00:05<00:04, 34.83it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 42.72it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 42.03it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:03, 43.55it/s] Loading 0: 62%|██████▏ | 225/363 [00:06<00:05, 27.39it/s] Loading 0: 63%|██████▎ | 230/363 [00:06<00:04, 29.60it/s] Loading 0: 66%|██████▌ | 238/363 [00:06<00:03, 37.97it/s] Loading 0: 67%|██████▋ | 243/363 [00:06<00:02, 40.00it/s] Loading 0: 68%|██████▊ | 248/363 [00:06<00:03, 31.21it/s] Loading 0: 70%|██████▉ | 253/363 [00:06<00:03, 34.46it/s] Loading 0: 71%|███████ | 258/363 [00:06<00:03, 34.95it/s] Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 40.20it/s] Loading 0: 74%|███████▍ | 269/363 [00:07<00:02, 40.25it/s] Loading 0: 75%|███████▌ | 274/363 [00:07<00:02, 40.84it/s] Loading 0: 77%|███████▋ | 279/363 [00:07<00:02, 41.63it/s] Loading 0: 78%|███████▊ | 284/363 [00:07<00:02, 30.88it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 37.96it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 38.12it/s] Loading 0: 83%|████████▎ | 301/363 [00:08<00:01, 39.00it/s] Loading 0: 84%|████████▍ | 306/363 [00:15<00:23, 2.38it/s] Loading 0: 85%|████████▌ | 309/363 [00:15<00:18, 2.91it/s] Loading 0: 86%|████████▌ | 312/363 [00:15<00:14, 3.61it/s] Loading 0: 88%|████████▊ | 320/363 [00:15<00:06, 6.35it/s] Loading 0: 90%|████████▉ | 326/363 [00:15<00:04, 8.80it/s] Loading 0: 91%|█████████ | 331/363 [00:15<00:02, 11.32it/s] Loading 0: 93%|█████████▎| 338/363 [00:15<00:01, 16.10it/s] Loading 0: 94%|█████████▍| 343/363 [00:15<00:01, 19.66it/s] Loading 0: 96%|█████████▌| 348/363 [00:16<00:00, 21.27it/s] Loading 0: 98%|█████████▊| 355/363 [00:16<00:00, 28.24it/s] Loading 0: 99%|█████████▉| 361/363 [00:16<00:00, 32.04it/s]
Job udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer completed after 104.55s with status: succeeded
Stopping job with name udbhavbamba-nemo13b-dpo-v2-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.09s
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 udbhavbamba-nemo13b-dpo-v2-v1
Waiting for inference service udbhavbamba-nemo13b-dpo-v2-v1 to be ready
Inference service udbhavbamba-nemo13b-dpo-v2-v1 ready after 90.43487453460693s
Pipeline stage MKMLDeployer completed in 91.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3572680950164795s
Received healthy response to inference request in 1.680345058441162s
Received healthy response to inference request in 1.748857021331787s
Received healthy response to inference request in 1.647702693939209s
Received healthy response to inference request in 1.8905131816864014s
5 requests
0 failed requests
5th percentile: 1.6542311668395997
10th percentile: 1.6607596397399902
20th percentile: 1.6738165855407714
30th percentile: 1.694047451019287
40th percentile: 1.721452236175537
50th percentile: 1.748857021331787
60th percentile: 1.8055194854736327
70th percentile: 1.8621819496154786
80th percentile: 1.983864164352417
90th percentile: 2.170566129684448
95th percentile: 2.263917112350464
99th percentile: 2.3385978984832763
mean time: 1.8649372100830077
Pipeline stage StressChecker completed in 10.83s
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 0.63s
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 0.70s
Shutdown handler de-registered
udbhavbamba-nemo13b-dpo-v2_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2574.01s
Shutdown handler de-registered
udbhavbamba-nemo13b-dpo-v2_v1 status is now inactive due to auto deactivation removed underperforming models
udbhavbamba-nemo13b-dpo-v2_v1 status is now torndown due to DeploymentManager action