cloudyu-nemo-dpo-v20

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v20_v4

model_name: cloudyu-nemo-dpo-v20_v1

model_group: cloudyu/Nemo-DPO-V20

status: inactive

timestamp: 2024-12-16T14:46:24+00:00

num_battles: 15732

num_wins: 8184

celo_rating: 1278.25

family_friendly_score: 0.563

family_friendly_standard_error: 0.007014713108887633

submission_type: basic

model_repo: cloudyu/Nemo-DPO-V20

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6148579029639536, 'latency_mean': 1.6263310277462006, 'latency_p50': 1.6400662660598755, 'latency_p90': 1.7892454862594604}, {'batch_size': 3, 'throughput': 1.1399461198700702, 'latency_mean': 2.6209029734134672, 'latency_p50': 2.6312488317489624, 'latency_p90': 2.889725136756897}, {'batch_size': 5, 'throughput': 1.379569191801212, 'latency_mean': 3.6010187315940856, 'latency_p50': 3.598159074783325, 'latency_p90': 4.069190835952758}, {'batch_size': 6, 'throughput': 1.4584172790449554, 'latency_mean': 4.097243660688401, 'latency_p50': 4.114746928215027, 'latency_p90': 4.592455554008484}, {'batch_size': 8, 'throughput': 1.5354558821934268, 'latency_mean': 5.181417260169983, 'latency_p50': 5.160615563392639, 'latency_p90': 5.803210330009461}, {'batch_size': 10, 'throughput': 1.5651315487744788, 'latency_mean': 6.335697450637817, 'latency_p50': 6.398029565811157, 'latency_p90': 7.102577161788941}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-nemo-dpo-v20_v1

is_internal_developer: False

language_model: cloudyu/Nemo-DPO-V20

model_size: 13B

ranking_group: single

throughput_3p7s: 1.41

us_pacific_date: 2024-12-16

win_ratio: 0.5202135774218154

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-v20-v4-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v20-v4-mkmlizer to finish
cloudyu-nemo-dpo-v20-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v20-v4-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v20-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v20-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v20-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v20-v4-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v20-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v4-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v20-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v20-v4-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v20-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v20-v4-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v20-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v4-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v20-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v20-v4-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v20-v4-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v20-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v20-v4-mkmlizer: Downloaded to shared memory in 36.855s
cloudyu-nemo-dpo-v20-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpg9rbwna0, device:0
cloudyu-nemo-dpo-v20-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v20-v4-mkmlizer: quantized model in 36.347s
cloudyu-nemo-dpo-v20-v4-mkmlizer: Processed model cloudyu/Nemo-DPO-V20 in 73.203s
cloudyu-nemo-dpo-v20-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v20-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v4
cloudyu-nemo-dpo-v20-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v4/config.json
cloudyu-nemo-dpo-v20-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v4/special_tokens_map.json
cloudyu-nemo-dpo-v20-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v4/tokenizer_config.json
cloudyu-nemo-dpo-v20-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v4/tokenizer.json
cloudyu-nemo-dpo-v20-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v4/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v20-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.95it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 47.73it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 43.04it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 42.22it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 47.73it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.06it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.22it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 48.11it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:06, 47.97it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 44.71it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 30.83it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 36.29it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 37.72it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:07, 40.20it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:07, 39.11it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:06, 39.41it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 41.13it/s]
Loading 0:  28%|██▊       | 102/363 [00:02<00:06, 38.73it/s]
Loading 0:  29%|██▉       | 107/363 [00:02<00:06, 40.88it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 41.92it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:06, 40.65it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:05, 43.04it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 36.57it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 44.50it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:04, 45.17it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:07, 27.86it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 30.24it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 37.89it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 38.46it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 40.72it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 38.89it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 38.66it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 41.69it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 40.93it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 42.16it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 43.55it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 35.37it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 42.85it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 43.00it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 44.37it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:04, 28.87it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 30.87it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 38.25it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 39.20it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 40.14it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 42.35it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:02, 35.99it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 44.32it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 42.35it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 40.97it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:01, 45.22it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 45.01it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 45.08it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 45.71it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 46.03it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:23,  2.41it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:15,  3.33it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.40it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:05,  7.05it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:03,  8.79it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.25it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:01, 16.31it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 19.32it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 24.32it/s]
Loading 0:  99%|█████████▉| 360/363 [00:15<00:00, 27.29it/s]
                                                            
Job cloudyu-nemo-dpo-v20-v4-mkmlizer completed after 105.08s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v20-v4-mkmlizer
Pipeline stage MKMLizer completed in 105.58s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v20-v4
Waiting for inference service cloudyu-nemo-dpo-v20-v4 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
Inference service cloudyu-nemo-dpo-v20-v4 ready after 220.8452398777008s
Pipeline stage MKMLDeployer completed in 221.33s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.324601650238037s
Received healthy response to inference request in 1.8734285831451416s
Received healthy response to inference request in 1.6599278450012207s
Received healthy response to inference request in 1.8050286769866943s
5 requests
1 failed requests
5th percentile: 1.6889480113983155
10th percentile: 1.7179681777954101
20th percentile: 1.7760085105895995
30th percentile: 1.8187086582183838
40th percentile: 1.8460686206817627
50th percentile: 1.8734285831451416
60th percentile: 2.0538978099823
70th percentile: 2.234367036819458
80th percentile: 5.887861442565921
90th percentile: 13.014381027221681
95th percentile: 16.577640819549558
99th percentile: 19.428248653411863
mean time: 5.560777473449707
%s, retrying in %s seconds...
Received healthy response to inference request in 1.596912145614624s
Received healthy response to inference request in 1.9089851379394531s
Received healthy response to inference request in 1.7313594818115234s
Received healthy response to inference request in 1.817612648010254s
Received healthy response to inference request in 1.6999735832214355s
5 requests
0 failed requests
5th percentile: 1.6175244331359864
10th percentile: 1.6381367206573487
20th percentile: 1.6793612957000732
30th percentile: 1.7062507629394532
40th percentile: 1.7188051223754883
50th percentile: 1.7313594818115234
60th percentile: 1.7658607482910156
70th percentile: 1.8003620147705077
80th percentile: 1.8358871459960937
90th percentile: 1.8724361419677735
95th percentile: 1.8907106399536133
99th percentile: 1.9053302383422852
mean time: 1.750968599319458
Pipeline stage StressChecker completed in 39.28s
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 2.40s
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 2.45s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v4 status is now deployed due to DeploymentManager action
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 3160.87s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v4 status is now inactive due to auto deactivation removed underperforming models