developer_uid: rirv938
submission_id: rirv938-mistral-12b-dpo_88376_v1
model_name: rirv938-mistral-12b-dpo_88376_v1
model_group: rirv938/mistral_12b_dpo_
status: torndown
timestamp: 2025-02-25T02:27:31+00:00
num_battles: 5586
num_wins: 1765
celo_rating: 1127.26
family_friendly_score: 0.6514
family_friendly_standard_error: 0.0067391103270387255
submission_type: basic
model_repo: rirv938/mistral_12b_dpo_40k_1187_32_output_tokens_v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 32
latencies: [{'batch_size': 1, 'throughput': 1.0984025233688692, 'latency_mean': 0.910347330570221, 'latency_p50': 0.9175112247467041, 'latency_p90': 1.075030779838562}, {'batch_size': 4, 'throughput': 2.0452541614022803, 'latency_mean': 1.9515077030658723, 'latency_p50': 1.920502781867981, 'latency_p90': 2.3321169137954714}, {'batch_size': 5, 'throughput': 2.129107973189316, 'latency_mean': 2.335601409673691, 'latency_p50': 2.3606719970703125, 'latency_p90': 2.8131511211395264}, {'batch_size': 8, 'throughput': 2.290487960108184, 'latency_mean': 3.471315482854843, 'latency_p50': 3.5047117471694946, 'latency_p90': 4.1804612159729}, {'batch_size': 10, 'throughput': 2.3586020064197575, 'latency_mean': 4.21191665649414, 'latency_p50': 4.162233591079712, 'latency_p90': 5.135920453071594}, {'batch_size': 12, 'throughput': 2.405322143642177, 'latency_mean': 4.9418868529796605, 'latency_p50': 4.916140675544739, 'latency_p90': 5.873705911636352}, {'batch_size': 15, 'throughput': 2.375087641545091, 'latency_mean': 6.216547385454178, 'latency_p50': 6.226086258888245, 'latency_p90': 7.2042378902435305}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-mistral-12b-dpo_88376_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: rirv938/mistral_12b_dpo_40k_1187_32_output_tokens_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 2.33
us_pacific_date: 2025-02-24
win_ratio: 0.315968492660222
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.6, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '###', 'You:'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 32}
formatter: {'memory_template': '', 'prompt_template': '', '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 rirv938-mistral-12b-dpo-88376-v1-mkmlizer
Waiting for job on rirv938-mistral-12b-dpo-88376-v1-mkmlizer to finish
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: Downloaded to shared memory in 115.354s
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxbtaqwry, device:0
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: quantized model in 42.471s
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: Processed model rirv938/mistral_12b_dpo_40k_1187_32_output_tokens_v2 in 157.826s
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-88376-v1
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-88376-v1/config.json
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-88376-v1/special_tokens_map.json
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-88376-v1/tokenizer_config.json
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-88376-v1/tokenizer.json
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-12b-dpo-88376-v1/flywheel_model.0.safetensors
rirv938-mistral-12b-dpo-88376-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.44it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 26.47it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 23.55it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 30.12it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:15, 21.72it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:17, 19.38it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 25.09it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 26.91it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.20it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.40it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:12, 26.39it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:11, 26.99it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:11, 26.96it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.22it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 24.42it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 21.29it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 28.60it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 28.22it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:10, 26.65it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 30.72it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 28.28it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 30.57it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 28.80it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.62it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 20.85it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:09, 25.86it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 23.51it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.89it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.87it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.11it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:07, 28.94it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 28.27it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 30.78it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:10, 21.34it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:10, 20.82it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 27.05it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 26.45it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 28.70it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 25.97it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:07, 25.72it/s]
Loading 0:  48%|████▊     | 176/363 [00:06<00:08, 23.19it/s]
Loading 0:  50%|████▉     | 181/363 [00:06<00:06, 28.36it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 19.00it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.66it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:07, 21.73it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 27.92it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 26.57it/s]
Loading 0:  58%|█████▊    | 209/363 [00:08<00:05, 29.14it/s]
Loading 0:  59%|█████▊    | 213/363 [00:08<00:05, 25.15it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:05, 27.67it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 28.98it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:06, 21.09it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 20.95it/s]
Loading 0:  65%|██████▌   | 237/363 [00:09<00:04, 27.42it/s]
Loading 0:  66%|██████▋   | 241/363 [00:09<00:04, 26.69it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 29.49it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 28.63it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 31.26it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 29.54it/s]
Loading 0:  72%|███████▏  | 263/363 [00:10<00:04, 24.53it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 21.58it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 28.49it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 27.67it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 30.15it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.37it/s]
Loading 0:  80%|████████  | 291/363 [00:11<00:02, 31.95it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 30.65it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 30.43it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 26.38it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 24.45it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.22it/s]
Loading 0:  88%|████████▊ | 318/363 [00:12<00:01, 29.96it/s]
Loading 0:  89%|████████▊ | 322/363 [00:12<00:01, 26.70it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 29.60it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 28.54it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 30.55it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.40it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.96it/s]
Loading 0:  96%|█████████▌| 348/363 [00:20<00:05,  2.63it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:02,  3.80it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.89it/s]
Loading 0: 100%|█████████▉| 362/363 [00:20<00:00,  6.96it/s]
                                                            

Job rirv938-mistral-12b-dpo-88376-v1-mkmlizer completed after 185.6s with status: succeeded
Stopping job with name rirv938-mistral-12b-dpo-88376-v1-mkmlizer
Pipeline stage MKMLizer completed in 186.08s
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 rirv938-mistral-12b-dpo-88376-v1
Waiting for inference service rirv938-mistral-12b-dpo-88376-v1 to be ready
Inference service rirv938-mistral-12b-dpo-88376-v1 ready after 250.95584988594055s
Pipeline stage MKMLDeployer completed in 251.47s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3245594501495361s
Received healthy response to inference request in 0.9910004138946533s
Received healthy response to inference request in 0.8191266059875488s
Received healthy response to inference request in 0.866680383682251s
Received healthy response to inference request in 0.8135859966278076s
5 requests
0 failed requests
5th percentile: 0.8146941184997558
10th percentile: 0.8158022403717041
20th percentile: 0.8180184841156006
30th percentile: 0.8286373615264893
40th percentile: 0.8476588726043701
50th percentile: 0.866680383682251
60th percentile: 0.9164083957672119
70th percentile: 0.9661364078521728
80th percentile: 1.05771222114563
90th percentile: 1.191135835647583
95th percentile: 1.2578476428985594
99th percentile: 1.3112170886993408
mean time: 0.9629905700683594
Pipeline stage StressChecker completed in 6.09s
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 0.68s
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 0.61s
Shutdown handler de-registered
rirv938-mistral-12b-dpo_88376_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 rirv938-mistral-12b-dpo-88376-v1-profiler
Waiting for inference service rirv938-mistral-12b-dpo-88376-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 1861.50s
Shutdown handler de-registered
rirv938-mistral-12b-dpo_88376_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-12b-dpo_88376_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1