cloudyu-chaiml-nemo-dpo-v6

developer_uid: cloudyu

submission_id: cloudyu-chaiml-nemo-dpo-v6_v15

model_name: cloudyu-chaiml-nemo-dpo-v6_v14

model_group: cloudyu/ChaiML-Nemo-DPO-

status: inactive

timestamp: 2024-12-04T23:36:34+00:00

num_battles: 8829

num_wins: 4393

celo_rating: 1260.04

family_friendly_score: 0.5638000000000001

family_friendly_standard_error: 0.00701326685646568

submission_type: basic

model_repo: cloudyu/ChaiML-Nemo-DPO-V6

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6197513468001923, 'latency_mean': 1.6134816956520082, 'latency_p50': 1.6083320379257202, 'latency_p90': 1.779999041557312}, {'batch_size': 3, 'throughput': 1.1434889348760104, 'latency_mean': 2.608327041864395, 'latency_p50': 2.63851797580719, 'latency_p90': 2.8754459381103517}, {'batch_size': 5, 'throughput': 1.4018504679253447, 'latency_mean': 3.555046036243439, 'latency_p50': 3.533386707305908, 'latency_p90': 3.9486033439636232}, {'batch_size': 6, 'throughput': 1.4602632834816351, 'latency_mean': 4.077270028591156, 'latency_p50': 4.096122622489929, 'latency_p90': 4.616315221786499}, {'batch_size': 8, 'throughput': 1.5244485432685573, 'latency_mean': 5.204572286605835, 'latency_p50': 5.202330946922302, 'latency_p90': 5.847665309906006}, {'batch_size': 10, 'throughput': 1.5663840200734183, 'latency_mean': 6.338175950050354, 'latency_p50': 6.3264384269714355, 'latency_p90': 7.248854374885559}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-chaiml-nemo-dpo-v6_v14

is_internal_developer: False

language_model: cloudyu/ChaiML-Nemo-DPO-V6

model_size: 13B

ranking_group: single

throughput_3p7s: 1.43

us_pacific_date: 2024-12-04

win_ratio: 0.49756484313059235

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-chaiml-nemo-dpo-v6-v15-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ║     _____            __           __                                ║
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ║       /___/                                                         ║
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ║  belonging to:                                                      ║
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: Downloaded to shared memory in 36.065s
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpt4kjxnlx, device:0
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: quantized model in 36.788s
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V6 in 72.853s
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v15
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v15/tokenizer.json
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v15/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.80it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.15it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 43.22it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.92it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 47.97it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.54it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 42.98it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:06, 46.77it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:06, 45.36it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 44.38it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 30.07it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:08, 36.25it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 39.05it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 34.80it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 42.89it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 41.50it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 39.84it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 41.95it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 40.91it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:06, 39.17it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 45.41it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 43.77it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 42.79it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 43.31it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 25.91it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:08, 26.59it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 34.01it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 33.91it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 35.98it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:05, 38.30it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 33.01it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 40.04it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 40.41it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 41.76it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 43.52it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 35.21it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 42.53it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 41.67it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 43.56it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:05, 27.46it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 29.45it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 37.92it/s]
Loading 0:  67%|██████▋   | 243/363 [00:06<00:02, 40.35it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 34.46it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 41.35it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 40.80it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 41.87it/s]
Loading 0:  74%|███████▍  | 270/363 [00:06<00:02, 43.35it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 35.80it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:01, 42.86it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 41.45it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 41.48it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 42.95it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 40.23it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:22,  2.46it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:16,  3.18it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:08,  5.24it/s]
Loading 0:  90%|████████▉ | 326/363 [00:15<00:05,  7.15it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:03,  9.21it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 13.09it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:01, 16.54it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 19.76it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.89it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.07it/s]
                                                            
Job cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer completed after 94.33s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v6-v15-mkmlizer
Pipeline stage MKMLizer completed in 94.85s
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-chaiml-nemo-dpo-v6-v15
Waiting for inference service cloudyu-chaiml-nemo-dpo-v6-v15 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
Inference service cloudyu-chaiml-nemo-dpo-v6-v15 ready after 150.66164469718933s
Pipeline stage MKMLDeployer completed in 151.18s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0766665935516357s
Received healthy response to inference request in 1.7666137218475342s
Received healthy response to inference request in 1.7360923290252686s
Received healthy response to inference request in 1.765629768371582s
Received healthy response to inference request in 1.9915921688079834s
5 requests
0 failed requests
5th percentile: 1.7419998168945312
10th percentile: 1.7479073047637939
20th percentile: 1.7597222805023194
30th percentile: 1.7658265590667725
40th percentile: 1.7662201404571534
50th percentile: 1.7666137218475342
60th percentile: 1.856605100631714
70th percentile: 1.9465964794158934
80th percentile: 2.008607053756714
90th percentile: 2.042636823654175
95th percentile: 2.0596517086029054
99th percentile: 2.07326361656189
mean time: 1.8673189163208008
Pipeline stage StressChecker completed in 10.64s
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 2.13s
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-chaiml-nemo-dpo-v6_v15 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-chaiml-nemo-dpo-v6-v15-profiler
Waiting for inference service cloudyu-chaiml-nemo-dpo-v6-v15-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 2558.95s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v6_v15 status is now inactive due to auto deactivation removed underperforming models