cloudyu-chaiml-nemo-dpo-v17

developer_uid: cloudyu

submission_id: cloudyu-chaiml-nemo-dpo-v17_v5

model_name: cloudyu-chaiml-nemo-dpo-v17_v4

model_group: cloudyu/ChaiML-Nemo-DPO-

status: inactive

timestamp: 2024-12-06T07:37:28+00:00

num_battles: 6859

num_wins: 3686

celo_rating: 1276.87

family_friendly_score: 0.5558000000000001

family_friendly_standard_error: 0.0070268963276826565

submission_type: basic

model_repo: cloudyu/ChaiML-Nemo-DPO-V17

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6090975984078477, 'latency_mean': 1.6416395103931427, 'latency_p50': 1.6339651346206665, 'latency_p90': 1.813419508934021}, {'batch_size': 3, 'throughput': 1.1309868344580736, 'latency_mean': 2.643588761091232, 'latency_p50': 2.618529438972473, 'latency_p90': 2.944743275642395}, {'batch_size': 5, 'throughput': 1.3551035564526943, 'latency_mean': 3.6683218371868134, 'latency_p50': 3.673676371574402, 'latency_p90': 4.12292628288269}, {'batch_size': 6, 'throughput': 1.4338830949421062, 'latency_mean': 4.154283744096756, 'latency_p50': 4.187056660652161, 'latency_p90': 4.624620628356934}, {'batch_size': 8, 'throughput': 1.5076622412983707, 'latency_mean': 5.273316305875778, 'latency_p50': 5.282809495925903, 'latency_p90': 5.8281368017196655}, {'batch_size': 10, 'throughput': 1.5327587214214229, 'latency_mean': 6.4783707773685455, 'latency_p50': 6.49720311164856, 'latency_p90': 7.284177637100219}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-chaiml-nemo-dpo-v17_v4

is_internal_developer: False

language_model: cloudyu/ChaiML-Nemo-DPO-V17

model_size: 13B

ranking_group: single

throughput_3p7s: 1.37

us_pacific_date: 2024-12-05

win_ratio: 0.5373961218836565

generation_params: {'temperature': 0.99, '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-chaiml-nemo-dpo-v17-v5-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ║     _____            __           __                                ║
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ║       /___/                                                         ║
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ║  belonging to:                                                      ║
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: Downloaded to shared memory in 29.820s
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpd5v5_zpi, device:0
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: quantized model in 36.287s
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V17 in 66.107s
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v17-v5
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v17-v5/config.json
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v17-v5/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v17-v5/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v17-v5/tokenizer.json
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v17-v5/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.49it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 47.43it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 46.49it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 45.18it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 51.35it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 47.82it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.19it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 48.68it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 45.17it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 45.94it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 29.31it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:08, 35.84it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 38.20it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:07, 39.14it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 44.31it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:05, 45.11it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:07, 36.40it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 45.98it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 43.86it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 42.93it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 48.03it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:04, 46.79it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:04, 46.03it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 34.43it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 35.20it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 34.73it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 41.49it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 41.85it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:04, 42.46it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:03, 48.21it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:03, 45.58it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 42.22it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 47.09it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 45.63it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 44.54it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 46.11it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 45.39it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 34.19it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 34.62it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 34.14it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 41.05it/s]
Loading 0:  67%|██████▋   | 243/363 [00:05<00:02, 41.64it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 33.96it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 42.05it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 42.07it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 41.00it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:02, 44.71it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 45.41it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 46.42it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 44.85it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 42.16it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 48.75it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:20,  2.72it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:14,  3.63it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.66it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.56it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.47it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.21it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:01, 16.24it/s]
Loading 0:  96%|█████████▌| 348/363 [00:14<00:00, 18.60it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.88it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.19it/s]
                                                            
Job cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer completed after 91.09s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v17-v5-mkmlizer
Pipeline stage MKMLizer completed in 92.92s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v17-v5
Waiting for inference service cloudyu-chaiml-nemo-dpo-v17-v5 to be ready
Inference service cloudyu-chaiml-nemo-dpo-v17-v5 ready after 193.4256157875061s
Pipeline stage MKMLDeployer completed in 195.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.22395920753479s
Received healthy response to inference request in 1.8103575706481934s
Received healthy response to inference request in 1.8242242336273193s
Received healthy response to inference request in 1.7100121974945068s
Received healthy response to inference request in 1.8012683391571045s
5 requests
0 failed requests
5th percentile: 1.7282634258270264
10th percentile: 1.746514654159546
20th percentile: 1.783017110824585
30th percentile: 1.8030861854553222
40th percentile: 1.8067218780517578
50th percentile: 1.8103575706481934
60th percentile: 1.8159042358398438
70th percentile: 1.821450901031494
80th percentile: 1.9041712284088135
90th percentile: 2.0640652179718018
95th percentile: 2.144012212753296
99th percentile: 2.207969808578491
mean time: 1.8739643096923828
Pipeline stage StressChecker completed in 10.51s
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 2.15s
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 1.97s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v17_v5 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v17-v5-profiler
Waiting for inference service cloudyu-chaiml-nemo-dpo-v17-v5-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 2492.40s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v17_v5 status is now inactive due to auto deactivation removed underperforming models