cloudyu-nemo-dpo-v22

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v22_v16

model_name: cloudyu-nemo-dpo-v22_v1

model_group: cloudyu/Nemo-DPO-V22

status: inactive

timestamp: 2024-12-24T22:30:19+00:00

num_battles: 29623

num_wins: 15084

celo_rating: 1270.62

family_friendly_score: 0.5780000000000001

family_friendly_standard_error: 0.006984497118619207

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': 0.6066236357786974, 'latency_mean': 1.648378450870514, 'latency_p50': 1.6471871137619019, 'latency_p90': 1.8082854986190795}, {'batch_size': 3, 'throughput': 1.1287016740258207, 'latency_mean': 2.648182281255722, 'latency_p50': 2.6398932933807373, 'latency_p90': 2.9017619371414183}, {'batch_size': 5, 'throughput': 1.3614971290301054, 'latency_mean': 3.6502130711078644, 'latency_p50': 3.63671875, 'latency_p90': 4.151653432846069}, {'batch_size': 6, 'throughput': 1.4359178034093085, 'latency_mean': 4.155345463752747, 'latency_p50': 4.1676565408706665, 'latency_p90': 4.663620710372925}, {'batch_size': 8, 'throughput': 1.5118114232323272, 'latency_mean': 5.247019958496094, 'latency_p50': 5.291890978813171, 'latency_p90': 5.860334420204163}, {'batch_size': 10, 'throughput': 1.5393637041811155, 'latency_mean': 6.445814526081085, 'latency_p50': 6.3830565214157104, 'latency_p90': 7.32371711730957}]

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: 1.38

us_pacific_date: 2024-12-24

win_ratio: 0.5091989332613173

generation_params: {'temperature': 1.25, 'top_p': 0.95, '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-v16-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v22-v16-mkmlizer to finish
cloudyu-nemo-dpo-v22-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v22-v16-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v22-v16-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v22-v16-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v22-v16-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v22-v16-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v22-v16-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v16-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v22-v16-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v22-v16-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v22-v16-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v16-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v22-v16-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v22-v16-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v16-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v22-v16-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v22-v16-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v22-v16-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v22-v16-mkmlizer: Downloaded to shared memory in 50.678s
cloudyu-nemo-dpo-v22-v16-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_27a96od, device:0
cloudyu-nemo-dpo-v22-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v22-v16-mkmlizer: quantized model in 36.655s
cloudyu-nemo-dpo-v22-v16-mkmlizer: Processed model cloudyu/Nemo-DPO-V22 in 87.333s
cloudyu-nemo-dpo-v22-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v22-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v16
cloudyu-nemo-dpo-v22-v16-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v16/config.json
cloudyu-nemo-dpo-v22-v16-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v16/special_tokens_map.json
cloudyu-nemo-dpo-v22-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v16/tokenizer_config.json
cloudyu-nemo-dpo-v22-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v16/tokenizer.json
cloudyu-nemo-dpo-v22-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v16/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v22-v16-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 27.13it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 47.65it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.93it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 42.83it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.97it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 46.18it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.39it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.37it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 45.54it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.50it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.52it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 39.01it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 40.47it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:06, 42.44it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 44.25it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 37.21it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:05, 44.88it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:05, 43.75it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:05, 44.59it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 45.89it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 43.86it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 45.92it/s]
Loading 0:  36%|███▌      | 131/363 [00:03<00:05, 46.33it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:05, 38.65it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 33.50it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 34.10it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 33.23it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 40.03it/s]
Loading 0:  45%|████▍     | 162/363 [00:03<00:04, 40.85it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:05, 34.75it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 43.02it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 42.13it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 41.18it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 46.39it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 46.70it/s]
Loading 0:  56%|█████▌    | 203/363 [00:04<00:04, 38.11it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 45.12it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 42.23it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 43.17it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 29.99it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 29.15it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 34.91it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 36.14it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 36.08it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:03, 36.28it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 37.99it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 38.46it/s]
Loading 0:  73%|███████▎  | 266/363 [00:06<00:02, 35.12it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:02, 41.44it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:02, 41.06it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 42.43it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:01, 42.72it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:01, 35.27it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 40.28it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:24,  2.45it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:17,  3.18it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:12,  4.15it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.94it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.35it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 11.79it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 16.47it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:01, 19.99it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 21.75it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 28.71it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 32.70it/s]
                                                            
Job cloudyu-nemo-dpo-v22-v16-mkmlizer completed after 115.76s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v22-v16-mkmlizer
Pipeline stage MKMLizer completed in 116.69s
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-v22-v16
Waiting for inference service cloudyu-nemo-dpo-v22-v16 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cloudyu-nemo-dpo-v22-v16 ready after 271.4951934814453s
Pipeline stage MKMLDeployer completed in 272.04s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9842162132263184s
Received healthy response to inference request in 1.710397720336914s
Received healthy response to inference request in 1.9513459205627441s
Received healthy response to inference request in 2.080610513687134s
Received healthy response to inference request in 2.564504623413086s
5 requests
0 failed requests
5th percentile: 1.75858736038208
10th percentile: 1.806777000427246
20th percentile: 1.9031562805175781
30th percentile: 1.957919979095459
40th percentile: 1.9710680961608886
50th percentile: 1.9842162132263184
60th percentile: 2.0227739334106447
70th percentile: 2.0613316535949706
80th percentile: 2.1773893356323244
90th percentile: 2.370946979522705
95th percentile: 2.4677258014678953
99th percentile: 2.5451488590240476
mean time: 2.0582149982452393
Pipeline stage StressChecker completed in 11.70s
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 0.72s
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 0.68s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v16 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-nemo-dpo-v22-v16-profiler
Waiting for inference service cloudyu-nemo-dpo-v22-v16-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 3011.66s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v16 status is now inactive due to auto deactivation removed underperforming models