developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v22_v13
model_name: cloudyu-nemo-dpo-v22_v1
model_group: cloudyu/Nemo-DPO-V22
status: inactive
timestamp: 2024-12-20T13:19:16+00:00
num_battles: 16901
num_wins: 8764
celo_rating: 1275.06
family_friendly_score: 0.5668
family_friendly_standard_error: 0.007007678074797671
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': 0.6208483581055954, 'latency_mean': 1.610641222000122, 'latency_p50': 1.59987211227417, 'latency_p90': 1.7988243341445922}, {'batch_size': 3, 'throughput': 1.1495726413034142, 'latency_mean': 2.6045367777347566, 'latency_p50': 2.592419385910034, 'latency_p90': 2.9255160331726073}, {'batch_size': 5, 'throughput': 1.3905794273185088, 'latency_mean': 3.5806612968444824, 'latency_p50': 3.6007572412490845, 'latency_p90': 4.037997317314148}, {'batch_size': 6, 'throughput': 1.4656933760919488, 'latency_mean': 4.071047848463058, 'latency_p50': 4.059600830078125, 'latency_p90': 4.614031529426574}, {'batch_size': 8, 'throughput': 1.5270760792578417, 'latency_mean': 5.200787947177887, 'latency_p50': 5.181227684020996, 'latency_p90': 5.857963752746582}, {'batch_size': 10, 'throughput': 1.5646676644648134, 'latency_mean': 6.3380308902263645, 'latency_p50': 6.360247611999512, 'latency_p90': 7.157291388511657}]
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: 1.42
us_pacific_date: 2024-12-20
win_ratio: 0.5185491982722916
generation_params: {'temperature': 1.2, '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-v13-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v22-v13-mkmlizer to finish
cloudyu-nemo-dpo-v22-v13-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v22-v13-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v22-v13-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v22-v13-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v22-v13-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v22-v13-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v22-v13-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v13-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v22-v13-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v22-v13-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v22-v13-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v13-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v22-v13-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v22-v13-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v13-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v22-v13-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v22-v13-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v22-v13-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v13-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v22-v13-mkmlizer: Downloaded to shared memory in 33.913s
cloudyu-nemo-dpo-v22-v13-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpejp6u_6u, device:0
cloudyu-nemo-dpo-v22-v13-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v22-v13-mkmlizer: quantized model in 37.173s
cloudyu-nemo-dpo-v22-v13-mkmlizer: Processed model cloudyu/Nemo-DPO-V22 in 71.086s
cloudyu-nemo-dpo-v22-v13-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v22-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v22-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v13
cloudyu-nemo-dpo-v22-v13-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v13/config.json
cloudyu-nemo-dpo-v22-v13-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v13/special_tokens_map.json
cloudyu-nemo-dpo-v22-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v13/tokenizer_config.json
cloudyu-nemo-dpo-v22-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v13/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v22-v13-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.98it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 46.64it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 39.00it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 38.72it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 45.37it/s]
Loading 0:  10%|▉         | 36/363 [00:00<00:07, 45.91it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:08, 39.63it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 47.89it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 45.67it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.97it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 31.88it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 38.22it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 39.64it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:06, 40.08it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 45.81it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:05, 46.27it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:06, 39.79it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 42.69it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 44.56it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:06, 40.89it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:05, 41.07it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:07, 32.92it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 38.99it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 39.38it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:08, 26.77it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 29.06it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 35.95it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.63it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.46it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 40.97it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 35.20it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 42.91it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 38.63it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:04, 36.13it/s]
Loading 0:  54%|█████▍    | 197/363 [00:05<00:05, 32.65it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:05, 30.80it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:05, 28.71it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:04, 33.21it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:04, 33.50it/s]
Loading 0:  60%|██████    | 219/363 [00:05<00:03, 37.37it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:05, 27.58it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 29.32it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 29.45it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 36.91it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 38.04it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 35.27it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 42.89it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 42.93it/s]
Loading 0:  73%|███████▎  | 265/363 [00:07<00:02, 44.19it/s]
Loading 0:  75%|███████▍  | 271/363 [00:07<00:02, 43.10it/s]
Loading 0:  76%|███████▌  | 276/363 [00:07<00:02, 41.60it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:01, 46.08it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 45.32it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 45.23it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 44.80it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 45.60it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:23,  2.34it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:15,  3.25it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:08,  5.29it/s]
Loading 0:  90%|████████▉ | 326/363 [00:15<00:05,  7.18it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:03,  9.18it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 13.02it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:01, 16.11it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 18.23it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.31it/s]
Loading 0: 100%|█████████▉| 362/363 [00:16<00:00, 28.16it/s]
                                                            

Job cloudyu-nemo-dpo-v22-v13-mkmlizer completed after 94.09s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v22-v13-mkmlizer
Pipeline stage MKMLizer completed in 94.69s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v22-v13
Waiting for inference service cloudyu-nemo-dpo-v22-v13 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cloudyu-nemo-dpo-v22-v13 ready after 261.1478009223938s
Pipeline stage MKMLDeployer completed in 261.75s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.129031181335449s
Received healthy response to inference request in 2.2973055839538574s
Received healthy response to inference request in 2.0673389434814453s
Received healthy response to inference request in 1.9732561111450195s
Received healthy response to inference request in 2.1276323795318604s
5 requests
0 failed requests
5th percentile: 1.9920726776123048
10th percentile: 2.01088924407959
20th percentile: 2.04852237701416
30th percentile: 2.0793976306915285
40th percentile: 2.1035150051116944
50th percentile: 2.1276323795318604
60th percentile: 2.128191900253296
70th percentile: 2.1287514209747314
80th percentile: 2.162686061859131
90th percentile: 2.2299958229064942
95th percentile: 2.2636507034301756
99th percentile: 2.290574607849121
mean time: 2.1189128398895263
Pipeline stage StressChecker completed in 11.94s
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 0.68s
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 0.81s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v13 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-nemo-dpo-v22-v13-profiler
Waiting for inference service cloudyu-nemo-dpo-v22-v13-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 2626.12s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v13 status is now inactive due to auto deactivation removed underperforming models