cloudyu-nemo-dpo-v22

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v22_v1

model_name: cloudyu-nemo-dpo-v22_v1

model_group: cloudyu/Nemo-DPO-V22

status: inactive

timestamp: 2024-12-18T10:38:36+00:00

num_battles: 12807

num_wins: 6652

celo_rating: 1277.44

family_friendly_score: 0.5609999999999999

family_friendly_standard_error: 0.007018247644533499

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': 0.6066418060483573, 'latency_mean': 1.6482445418834686, 'latency_p50': 1.6517914533615112, 'latency_p90': 1.812518548965454}, {'batch_size': 3, 'throughput': 1.1172395111702622, 'latency_mean': 2.6754492473602296, 'latency_p50': 2.692584276199341, 'latency_p90': 2.9197916507720945}, {'batch_size': 5, 'throughput': 1.353428318786647, 'latency_mean': 3.6767866444587707, 'latency_p50': 3.6952168941497803, 'latency_p90': 4.12539541721344}, {'batch_size': 6, 'throughput': 1.42304995097687, 'latency_mean': 4.1959527814388276, 'latency_p50': 4.204224467277527, 'latency_p90': 4.7103461742401125}, {'batch_size': 8, 'throughput': 1.4890603569127614, 'latency_mean': 5.334075578451157, 'latency_p50': 5.308105111122131, 'latency_p90': 5.9711692333221436}, {'batch_size': 10, 'throughput': 1.5363550120341285, 'latency_mean': 6.467430990934372, 'latency_p50': 6.46744430065155, 'latency_p90': 7.313269805908203}]

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: 1.36

us_pacific_date: 2024-12-18

win_ratio: 0.5194034512376045

generation_params: {'temperature': 0.95, '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-v1-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v22-v1-mkmlizer to finish
cloudyu-nemo-dpo-v22-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v22-v1-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v22-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v22-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v22-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v22-v1-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v22-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v22-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v22-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v22-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v22-v1-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v22-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v22-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v22-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v22-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v22-v1-mkmlizer: Downloaded to shared memory in 45.963s
cloudyu-nemo-dpo-v22-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4m6pfg70, device:0
cloudyu-nemo-dpo-v22-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v22-v1-mkmlizer: quantized model in 35.614s
cloudyu-nemo-dpo-v22-v1-mkmlizer: Processed model cloudyu/Nemo-DPO-V22 in 81.578s
cloudyu-nemo-dpo-v22-v1-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v22-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v22-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v1
cloudyu-nemo-dpo-v22-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v1/config.json
cloudyu-nemo-dpo-v22-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v1/special_tokens_map.json
cloudyu-nemo-dpo-v22-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v1/tokenizer_config.json
cloudyu-nemo-dpo-v22-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v1/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v22-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.71it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 46.84it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.05it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 44.32it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 51.03it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 46.38it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.84it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 50.22it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 47.34it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 34.64it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 34.78it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 39.58it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 40.70it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 41.87it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 47.22it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:05, 47.57it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:06, 38.99it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 48.26it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 45.09it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 44.11it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 49.00it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:04, 47.37it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:04, 45.66it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 34.40it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 34.76it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 33.83it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 41.04it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 41.44it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 42.14it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:03, 47.69it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:03, 46.78it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:03, 45.30it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 50.02it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 47.37it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 44.64it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 48.96it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 46.20it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 35.55it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 36.01it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 34.84it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:02, 41.87it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 42.70it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 43.01it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 47.45it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 46.46it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 42.83it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:01, 46.80it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 46.33it/s]
Loading 0:  78%|███████▊  | 284/363 [00:06<00:01, 41.25it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 48.25it/s]
Loading 0:  82%|████████▏ | 298/363 [00:06<00:01, 43.62it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:20,  2.88it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:15,  3.59it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:11,  4.56it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:05,  7.36it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.88it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 12.44it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 17.37it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 20.53it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 23.36it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 29.72it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 31.44it/s]
                                                            
Job cloudyu-nemo-dpo-v22-v1-mkmlizer completed after 114.16s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v22-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.62s
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-v1
Waiting for inference service cloudyu-nemo-dpo-v22-v1 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service cloudyu-nemo-dpo-v22-v1 ready after 241.21244740486145s
Pipeline stage MKMLDeployer completed in 241.78s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2790017127990723s
Received healthy response to inference request in 1.9053676128387451s
Received healthy response to inference request in 1.7832982540130615s
Received healthy response to inference request in 1.7743980884552002s
Received healthy response to inference request in 1.969087839126587s
5 requests
0 failed requests
5th percentile: 1.7761781215667725
10th percentile: 1.7779581546783447
20th percentile: 1.7815182209014893
30th percentile: 1.8077121257781983
40th percentile: 1.8565398693084716
50th percentile: 1.9053676128387451
60th percentile: 1.9308557033538818
70th percentile: 1.9563437938690185
80th percentile: 2.031070613861084
90th percentile: 2.1550361633300783
95th percentile: 2.2170189380645753
99th percentile: 2.266605157852173
mean time: 1.9422307014465332
Pipeline stage StressChecker completed in 11.12s
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 2.27s
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 2.06s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v1 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-nemo-dpo-v22-v1-profiler
Waiting for inference service cloudyu-nemo-dpo-v22-v1-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 3118.37s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v1 status is now inactive due to auto deactivation removed underperforming models