cloudyu-nemo-dpo-v22

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v22_v10

model_name: cloudyu-nemo-dpo-v22_v1

model_group: cloudyu/Nemo-DPO-V22

status: inactive

timestamp: 2024-12-19T11:36:06+00:00

num_battles: 13642

num_wins: 7129

celo_rating: 1279.67

family_friendly_score: 0.5598000000000001

family_friendly_standard_error: 0.007020312813543283

submission_type: basic

model_repo: cloudyu/Nemo-DPO-V22

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6164949929720182, 'latency_mean': 1.6220021212100983, 'latency_p50': 1.6112812757492065, 'latency_p90': 1.7867111206054687}, {'batch_size': 3, 'throughput': 1.1381061394906604, 'latency_mean': 2.624893536567688, 'latency_p50': 2.640925168991089, 'latency_p90': 2.900929856300354}, {'batch_size': 5, 'throughput': 1.3883406391781077, 'latency_mean': 3.5817428719997406, 'latency_p50': 3.6218358278274536, 'latency_p90': 4.0226950407028195}, {'batch_size': 6, 'throughput': 1.4642475984436107, 'latency_mean': 4.08678769826889, 'latency_p50': 4.112005114555359, 'latency_p90': 4.555278277397155}, {'batch_size': 8, 'throughput': 1.5315804928676318, 'latency_mean': 5.189047026634216, 'latency_p50': 5.170283079147339, 'latency_p90': 5.915378761291504}, {'batch_size': 10, 'throughput': 1.5742736331448275, 'latency_mean': 6.3010536587238315, 'latency_p50': 6.275789260864258, 'latency_p90': 7.209383535385132}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-nemo-dpo-v22_v1

is_internal_developer: False

language_model: cloudyu/Nemo-DPO-V22

model_size: 13B

ranking_group: single

throughput_3p7s: 1.41

us_pacific_date: 2024-12-19

win_ratio: 0.5225773347016567

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-v22-v10-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v22-v10-mkmlizer to finish
cloudyu-nemo-dpo-v22-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v22-v10-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v22-v10-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v22-v10-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v22-v10-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v22-v10-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v22-v10-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v10-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v22-v10-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v22-v10-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v22-v10-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v10-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v22-v10-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v22-v10-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v10-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v22-v10-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v22-v10-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v22-v10-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v22-v10-mkmlizer: Downloaded to shared memory in 30.878s
cloudyu-nemo-dpo-v22-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpe8bm995f, device:0
cloudyu-nemo-dpo-v22-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v22-v10-mkmlizer: quantized model in 37.004s
cloudyu-nemo-dpo-v22-v10-mkmlizer: Processed model cloudyu/Nemo-DPO-V22 in 67.882s
cloudyu-nemo-dpo-v22-v10-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v22-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v22-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v10
cloudyu-nemo-dpo-v22-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v10/config.json
cloudyu-nemo-dpo-v22-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v10/special_tokens_map.json
cloudyu-nemo-dpo-v22-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v10/tokenizer_config.json
cloudyu-nemo-dpo-v22-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v10/tokenizer.json
cloudyu-nemo-dpo-v22-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v10/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v22-v10-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.98it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 45.40it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 46.09it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 37.49it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 47.31it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.37it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 42.66it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 47.41it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:06, 47.62it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 44.27it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 29.38it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:08, 35.51it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 36.69it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:07, 37.63it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 43.18it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:06, 44.18it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:07, 36.03it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 40.90it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 44.95it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 42.69it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:05, 43.56it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 36.56it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 43.25it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 44.59it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:07, 28.39it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 30.44it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 38.82it/s]
Loading 0:  45%|████▍     | 162/363 [00:04<00:05, 40.18it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:05, 34.05it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 39.67it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 38.72it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 38.58it/s]
Loading 0:  52%|█████▏    | 189/363 [00:04<00:04, 39.47it/s]
Loading 0:  53%|█████▎    | 194/363 [00:05<00:05, 32.36it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 39.46it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:03, 39.94it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 41.25it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 43.04it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 44.83it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 27.43it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 27.43it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 35.32it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 36.79it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 38.15it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 40.11it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 34.51it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 41.98it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 41.40it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 41.57it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 42.89it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 37.13it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 44.71it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 43.10it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 44.55it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:23,  2.46it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:16,  3.18it/s]
Loading 0:  87%|████████▋ | 315/363 [00:14<00:10,  4.45it/s]
Loading 0:  88%|████████▊ | 321/363 [00:14<00:06,  6.36it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:03,  9.98it/s]
Loading 0:  92%|█████████▏| 334/363 [00:15<00:02, 12.58it/s]
Loading 0:  93%|█████████▎| 339/363 [00:15<00:01, 14.42it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 19.76it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 22.39it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.42it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 29.07it/s]
                                                            
Job cloudyu-nemo-dpo-v22-v10-mkmlizer completed after 94.49s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v22-v10-mkmlizer
Pipeline stage MKMLizer completed in 95.00s
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 cloudyu-nemo-dpo-v22-v10
Waiting for inference service cloudyu-nemo-dpo-v22-v10 to be ready
Inference service cloudyu-nemo-dpo-v22-v10 ready after 251.29207754135132s
Pipeline stage MKMLDeployer completed in 251.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6945040225982666s
Received healthy response to inference request in 1.7923479080200195s
Received healthy response to inference request in 1.8877851963043213s
Received healthy response to inference request in 1.7809507846832275s
Received healthy response to inference request in 1.788064956665039s
5 requests
0 failed requests
5th percentile: 1.7823736190795898
10th percentile: 1.783796453475952
20th percentile: 1.7866421222686768
30th percentile: 1.7889215469360351
40th percentile: 1.7906347274780274
50th percentile: 1.7923479080200195
60th percentile: 1.8305228233337403
70th percentile: 1.868697738647461
80th percentile: 2.0491289615631105
90th percentile: 2.3718164920806886
95th percentile: 2.5331602573394774
99th percentile: 2.6622352695465086
mean time: 1.9887305736541747
Pipeline stage StressChecker completed in 11.31s
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 2.31s
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 2.12s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v10 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-v22-v10-profiler
Waiting for inference service cloudyu-nemo-dpo-v22-v10-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 3400.90s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v10 status is now inactive due to auto deactivation removed underperforming models