developer_uid: cloudyu
submission_id: cloudyu-chaiml-nemo-dpo-v4_v3
model_name: cloudyu-chaiml-nemo-dpo-v4_v3
model_group: cloudyu/ChaiML-Nemo-DPO-
status: inactive
timestamp: 2024-11-24T09:44:04+00:00
num_battles: 17398
num_wins: 8626
celo_rating: 1253.09
family_friendly_score: 0.577
family_friendly_standard_error: 0.006986715966747181
submission_type: basic
model_repo: cloudyu/ChaiML-Nemo-DPO-V4
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6176107189847889, 'latency_mean': 1.619045408964157, 'latency_p50': 1.6153178215026855, 'latency_p90': 1.780269169807434}, {'batch_size': 3, 'throughput': 1.1374505108278241, 'latency_mean': 2.630189962387085, 'latency_p50': 2.6289079189300537, 'latency_p90': 2.88255889415741}, {'batch_size': 5, 'throughput': 1.3673680589046329, 'latency_mean': 3.642483298778534, 'latency_p50': 3.613037347793579, 'latency_p90': 4.122937154769898}, {'batch_size': 6, 'throughput': 1.4344389962247133, 'latency_mean': 4.160729287862778, 'latency_p50': 4.176616072654724, 'latency_p90': 4.699882650375367}, {'batch_size': 8, 'throughput': 1.4934707726307341, 'latency_mean': 5.314038956165314, 'latency_p50': 5.360633373260498, 'latency_p90': 6.035131597518921}, {'batch_size': 10, 'throughput': 1.547404831672994, 'latency_mean': 6.411089346408844, 'latency_p50': 6.440113306045532, 'latency_p90': 7.192086410522461}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-chaiml-nemo-dpo-v4_v3
is_internal_developer: False
language_model: cloudyu/ChaiML-Nemo-DPO-V4
model_size: 13B
ranking_group: single
throughput_3p7s: 1.38
us_pacific_date: 2024-11-24
win_ratio: 0.495804115415565
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, '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-v4-v3-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ║     _____            __           __                                ║
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ║       /___/                                                         ║
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ║  belonging to:                                                      ║
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: Downloaded to shared memory in 34.457s
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp10pkwhmv, device:0
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: quantized model in 37.781s
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V4 in 72.238s
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v4-v3
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v4-v3/config.json
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v4-v3/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v4-v3/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v4-v3/tokenizer.json
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v4-v3/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.84it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 47.66it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 43.81it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 42.52it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 46.04it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 44.03it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 44.72it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:06, 46.10it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 37.50it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 42.95it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.39it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 30.92it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 38.02it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 38.66it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:07, 39.05it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 44.89it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:06, 44.46it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:07, 34.40it/s]
Loading 0:  29%|██▉       | 107/363 [00:02<00:06, 41.80it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 43.24it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 41.65it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:05, 42.65it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 35.77it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 43.72it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:04, 45.16it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 28.59it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.24it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 35.79it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 37.08it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 39.56it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 41.86it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 34.90it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 42.52it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 43.04it/s]
Loading 0:  53%|█████▎    | 194/363 [00:04<00:04, 39.81it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:03, 46.69it/s]
Loading 0:  57%|█████▋    | 207/363 [00:05<00:03, 47.43it/s]
Loading 0:  59%|█████▊    | 213/363 [00:05<00:03, 41.63it/s]
Loading 0:  60%|██████    | 219/363 [00:05<00:03, 45.80it/s]
Loading 0:  62%|██████▏   | 224/363 [00:05<00:04, 33.91it/s]
Loading 0:  63%|██████▎   | 229/363 [00:05<00:03, 34.44it/s]
Loading 0:  65%|██████▍   | 235/363 [00:05<00:03, 36.32it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 35.83it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 44.17it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 43.23it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 42.41it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 47.70it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 45.45it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 43.28it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 47.67it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:01, 48.21it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:01, 39.13it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 43.25it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:24,  2.40it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:17,  3.08it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:12,  4.00it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:06,  6.63it/s]
Loading 0:  90%|████████▉ | 326/363 [00:15<00:04,  8.95it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:02, 11.38it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 15.96it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:01, 19.38it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 21.07it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 28.99it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 31.35it/s]
                                                            

Job cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer completed after 103.97s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v4-v3-mkmlizer
Pipeline stage MKMLizer completed in 104.49s
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-v4-v3
Waiting for inference service cloudyu-chaiml-nemo-dpo-v4-v3 to be ready
Inference service cloudyu-chaiml-nemo-dpo-v4-v3 ready after 120.41842937469482s
Pipeline stage MKMLDeployer completed in 120.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.323573112487793s
Received healthy response to inference request in 1.6175894737243652s
Received healthy response to inference request in 1.7633538246154785s
Received healthy response to inference request in 1.8146963119506836s
Received healthy response to inference request in 1.7147181034088135s
5 requests
0 failed requests
5th percentile: 1.637015199661255
10th percentile: 1.6564409255981445
20th percentile: 1.6952923774719237
30th percentile: 1.7244452476501464
40th percentile: 1.7438995361328125
50th percentile: 1.7633538246154785
60th percentile: 1.7838908195495606
70th percentile: 1.8044278144836425
80th percentile: 1.9164716720581056
90th percentile: 2.1200223922729493
95th percentile: 2.221797752380371
99th percentile: 2.3032180404663087
mean time: 1.8467861652374267
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 2.32s
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 2.11s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v4_v3 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 2705.41s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v4_v3 status is now inactive due to auto deactivation removed underperforming models