bbchicago-m49-multi-langs-dpo

developer_uid: Bbbrun0

submission_id: bbchicago-m49-multi-langs-dpo_v1

model_name: nitral-ai-captain-bmo-12b_v1

model_group: BBChicago/m49_multi_lang

status: inactive

timestamp: 2024-12-04T07:44:45+00:00

num_battles: 10673

num_wins: 5752

celo_rating: 1286.06

family_friendly_score: 0.571

family_friendly_standard_error: 0.006999414261207862

submission_type: basic

model_repo: BBChicago/m49_multi_langs_dpo

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.614822627362873, 'latency_mean': 1.6263872361183167, 'latency_p50': 1.6184841394424438, 'latency_p90': 1.8138479471206665}, {'batch_size': 3, 'throughput': 1.1251319647387417, 'latency_mean': 2.663049795627594, 'latency_p50': 2.663166642189026, 'latency_p90': 2.946651768684387}, {'batch_size': 5, 'throughput': 1.3568210611191067, 'latency_mean': 3.6592163145542145, 'latency_p50': 3.6897060871124268, 'latency_p90': 4.108161520957947}, {'batch_size': 6, 'throughput': 1.427205560888171, 'latency_mean': 4.190426698923111, 'latency_p50': 4.177318572998047, 'latency_p90': 4.651177549362182}, {'batch_size': 8, 'throughput': 1.4903162695019168, 'latency_mean': 5.330472550392151, 'latency_p50': 5.295420169830322, 'latency_p90': 5.966486382484436}, {'batch_size': 10, 'throughput': 1.5196862038483165, 'latency_mean': 6.529100295305252, 'latency_p50': 6.590882062911987, 'latency_p90': 7.422832751274109}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: nitral-ai-captain-bmo-12b_v1

is_internal_developer: False

language_model: BBChicago/m49_multi_langs_dpo

model_size: 13B

ranking_group: single

throughput_3p7s: 1.37

us_pacific_date: 2024-12-03

win_ratio: 0.5389300103063805

generation_params: {'temperature': 1.25, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', '\n\n', '\nYou:', '<|im_end|>', '[/INST]'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '[INST]system\n{memory}[/INST]\n', 'prompt_template': '[INST]user\n{prompt}[/INST]\n', 'bot_template': '[INST]assistant\n{bot_name}: {message}[/INST]\n', 'user_template': '[INST]user\n{user_name}: {message}[/INST]\n', 'response_template': '[INST]assistant\n{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 bbchicago-m49-multi-langs-dpo-v1-mkmlizer
Waiting for job on bbchicago-m49-multi-langs-dpo-v1-mkmlizer to finish
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ║     _____            __           __                                ║
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ║       /___/                                                         ║
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ║                                                                     ║
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ║                                                                     ║
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ║  belonging to:                                                      ║
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ║                                                                     ║
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ║                                                                     ║
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: Downloaded to shared memory in 45.842s
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvgl_l4h4, device:0
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: quantized model in 35.964s
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: Processed model BBChicago/m49_multi_langs_dpo in 81.806s
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-m49-multi-langs-dpo-v1
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-m49-multi-langs-dpo-v1/special_tokens_map.json
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-m49-multi-langs-dpo-v1/config.json
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-m49-multi-langs-dpo-v1/flywheel_model.0.safetensors
bbchicago-m49-multi-langs-dpo-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.34it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 53.02it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:06, 49.74it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 50.93it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 53.38it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 50.54it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 51.05it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 52.87it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 50.46it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.92it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 37.49it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 41.65it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 40.57it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 41.29it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 46.75it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 45.27it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 43.26it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 51.67it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 47.54it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 43.81it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 45.11it/s]
Loading 0:  36%|███▌      | 130/363 [00:02<00:05, 44.65it/s]
Loading 0:  37%|███▋      | 135/363 [00:02<00:05, 45.25it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:04, 45.77it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 27.97it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.42it/s]
Loading 0:  42%|████▏     | 154/363 [00:03<00:06, 31.98it/s]
Loading 0:  44%|████▎     | 158/363 [00:03<00:06, 31.87it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 41.50it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 40.07it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 40.69it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 44.89it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 46.09it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 46.87it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 45.42it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 43.53it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 47.91it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 45.88it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 45.28it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 31.85it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 31.99it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 37.86it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 39.76it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 41.86it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 42.84it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 42.98it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 47.06it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 44.89it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 44.86it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 43.54it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 41.34it/s]
Loading 0:  80%|████████  | 291/363 [00:06<00:01, 45.00it/s]
Loading 0:  82%|████████▏ | 296/363 [00:06<00:01, 43.43it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 44.46it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:21,  2.57it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:15,  3.28it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:08,  5.31it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:05,  7.19it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.21it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.11it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.60it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 19.83it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 26.14it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.79it/s]
                                                            
Job bbchicago-m49-multi-langs-dpo-v1-mkmlizer completed after 104.37s with status: succeeded
Stopping job with name bbchicago-m49-multi-langs-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.93s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service bbchicago-m49-multi-langs-dpo-v1
Waiting for inference service bbchicago-m49-multi-langs-dpo-v1 to be ready
Inference service bbchicago-m49-multi-langs-dpo-v1 ready after 150.5220844745636s
Pipeline stage MKMLDeployer completed in 151.11s
run pipeline stage %s
Running pipeline stage StressChecker
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 2.346461772918701s
Received healthy response to inference request in 2.1021389961242676s
Received healthy response to inference request in 1.6574952602386475s
Received healthy response to inference request in 1.707789421081543s
Received healthy response to inference request in 1.7173240184783936s
5 requests
0 failed requests
5th percentile: 1.6675540924072265
10th percentile: 1.6776129245758056
20th percentile: 1.697730588912964
30th percentile: 1.7096963405609131
40th percentile: 1.7135101795196532
50th percentile: 1.7173240184783936
60th percentile: 1.8712500095367433
70th percentile: 2.0251760005950925
80th percentile: 2.1510035514831545
90th percentile: 2.248732662200928
95th percentile: 2.2975972175598143
99th percentile: 2.3366888618469237
mean time: 1.9062418937683105
Pipeline stage StressChecker completed in 11.04s
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 2.30s
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 2.09s
Shutdown handler de-registered
bbchicago-m49-multi-langs-dpo_v1 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 0.10s
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 bbchicago-m49-multi-langs-dpo-v1-profiler
Waiting for inference service bbchicago-m49-multi-langs-dpo-v1-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 2628.40s
Shutdown handler de-registered
bbchicago-m49-multi-langs-dpo_v1 status is now inactive due to auto deactivation removed underperforming models