cloudyu-nemo-dpo-v22

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v22_v7

model_name: cloudyu-nemo-dpo-v22_v1

model_group: cloudyu/Nemo-DPO-V22

status: inactive

timestamp: 2024-12-18T22:36:53+00:00

num_battles: 14543

num_wins: 7659

celo_rating: 1278.33

family_friendly_score: 0.5634

family_friendly_standard_error: 0.007013992301107837

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': 0.6095631278904426, 'latency_mean': 1.6404602861404418, 'latency_p50': 1.632585048675537, 'latency_p90': 1.8150031089782714}, {'batch_size': 3, 'throughput': 1.1128878850569373, 'latency_mean': 2.6804065895080567, 'latency_p50': 2.675361156463623, 'latency_p90': 2.9980597257614137}, {'batch_size': 5, 'throughput': 1.3473852495176621, 'latency_mean': 3.694028061628342, 'latency_p50': 3.7239625453948975, 'latency_p90': 4.1211086988449095}, {'batch_size': 6, 'throughput': 1.4152284444794219, 'latency_mean': 4.221471058130264, 'latency_p50': 4.191214561462402, 'latency_p90': 4.752798104286194}, {'batch_size': 8, 'throughput': 1.4800072481929984, 'latency_mean': 5.363841879367828, 'latency_p50': 5.354669451713562, 'latency_p90': 6.086170315742493}, {'batch_size': 10, 'throughput': 1.5186935132062709, 'latency_mean': 6.5352763283252715, 'latency_p50': 6.596480131149292, 'latency_p90': 7.41139669418335}]

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: 1.35

us_pacific_date: 2024-12-18

win_ratio: 0.5266451213642303

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-v7-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v22-v7-mkmlizer to finish
cloudyu-nemo-dpo-v22-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v22-v7-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v22-v7-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v22-v7-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v22-v7-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v22-v7-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v22-v7-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v7-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v22-v7-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v22-v7-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v22-v7-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v22-v7-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v22-v7-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v7-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v22-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v22-v7-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v22-v7-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v22-v7-mkmlizer: Downloaded to shared memory in 34.010s
cloudyu-nemo-dpo-v22-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmput72qsz0, device:0
cloudyu-nemo-dpo-v22-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v22-v7-mkmlizer: quantized model in 35.649s
cloudyu-nemo-dpo-v22-v7-mkmlizer: Processed model cloudyu/Nemo-DPO-V22 in 69.659s
cloudyu-nemo-dpo-v22-v7-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v22-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v22-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v7
cloudyu-nemo-dpo-v22-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v7/config.json
cloudyu-nemo-dpo-v22-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v7/special_tokens_map.json
cloudyu-nemo-dpo-v22-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v7/tokenizer_config.json
cloudyu-nemo-dpo-v22-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v7/tokenizer.json
cloudyu-nemo-dpo-v22-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v7/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v22-v7-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:14, 25.41it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 42.20it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 40.79it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 40.11it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:07, 42.35it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 37.29it/s]
Loading 0:  11%|█         | 39/363 [00:00<00:07, 45.73it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:07, 44.54it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 44.74it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:06, 45.17it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 43.95it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 28.59it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:08, 35.12it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:07, 37.15it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:07, 38.27it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 43.68it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:06, 44.46it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:07, 36.08it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 39.65it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 40.12it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:06, 38.92it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 45.59it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 45.62it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:04, 46.60it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:04, 45.82it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 32.35it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 32.45it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 39.68it/s]
Loading 0:  45%|████▍     | 163/363 [00:04<00:04, 41.38it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:04, 42.62it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:03, 48.33it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:03, 47.08it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:03, 46.29it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 51.56it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 49.30it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:03, 49.13it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:02, 51.74it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:02, 49.60it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 35.85it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 35.90it/s]
Loading 0:  64%|██████▍   | 233/363 [00:05<00:03, 38.57it/s]
Loading 0:  66%|██████▌   | 239/363 [00:05<00:03, 37.74it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 45.72it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 42.71it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 42.55it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 47.85it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:01, 47.15it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:01, 46.22it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 49.96it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 47.93it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 45.66it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 51.46it/s]
Loading 0:  85%|████████▍ | 307/363 [00:13<00:19,  2.84it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:13,  3.76it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.82it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.71it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.78it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.75it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 17.25it/s]
Loading 0:  96%|█████████▋| 350/363 [00:14<00:00, 21.29it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 26.16it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.85it/s]
                                                            
Job cloudyu-nemo-dpo-v22-v7-mkmlizer completed after 94.38s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v22-v7-mkmlizer
Pipeline stage MKMLizer completed in 94.86s
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-v7
Waiting for inference service cloudyu-nemo-dpo-v22-v7 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
Inference service cloudyu-nemo-dpo-v22-v7 ready after 241.15783715248108s
Pipeline stage MKMLDeployer completed in 241.67s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0414202213287354s
Received healthy response to inference request in 2.745652675628662s
Received healthy response to inference request in 2.1898415088653564s
Received healthy response to inference request in 1.6437294483184814s
Received healthy response to inference request in 2.0045340061187744s
5 requests
0 failed requests
5th percentile: 1.71589035987854
10th percentile: 1.7880512714385985
20th percentile: 1.9323730945587159
30th percentile: 2.0119112491607667
40th percentile: 2.026665735244751
50th percentile: 2.0414202213287354
60th percentile: 2.1007887363433837
70th percentile: 2.160157251358032
80th percentile: 2.301003742218018
90th percentile: 2.5233282089233398
95th percentile: 2.6344904422760007
99th percentile: 2.7234202289581297
mean time: 2.1250355720520018
Pipeline stage StressChecker completed in 11.99s
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 2.16s
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 2.04s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v7 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 0.11s
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-v7-profiler
Waiting for inference service cloudyu-nemo-dpo-v22-v7-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 3083.19s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v7 status is now inactive due to auto deactivation removed underperforming models