developer_uid: rirv938
submission_id: rirv938-v77-pref-plus-03_2336_v1
model_name: rirv938-v77-pref-plus-03_2336_v1
model_group: rirv938/v77_pref_plus_03
status: torndown
timestamp: 2024-12-27T04:55:50+00:00
num_battles: 18974
num_wins: 9795
celo_rating: 1272.42
family_friendly_score: 0.6
family_friendly_standard_error: 0.0069282032302755096
submission_type: basic
model_repo: rirv938/v77_pref_plus_03_mistral_1116_v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.7267918166972243, 'latency_mean': 1.3758497941493988, 'latency_p50': 1.3576732873916626, 'latency_p90': 1.5570152521133422}, {'batch_size': 5, 'throughput': 2.1644238572805152, 'latency_mean': 2.2970927023887633, 'latency_p50': 2.2998058795928955, 'latency_p90': 2.595477557182312}, {'batch_size': 10, 'throughput': 2.877771557047098, 'latency_mean': 3.4387878131866456, 'latency_p50': 3.440890669822693, 'latency_p90': 3.8482845783233643}, {'batch_size': 15, 'throughput': 3.1111890492124687, 'latency_mean': 4.764602998495102, 'latency_p50': 4.791270732879639, 'latency_p90': 5.390679335594177}, {'batch_size': 20, 'throughput': 3.253005043238816, 'latency_mean': 6.063416848182678, 'latency_p50': 6.071664929389954, 'latency_p90': 6.9805388927459715}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-v77-pref-plus-03_2336_v1
is_internal_developer: True
language_model: rirv938/v77_pref_plus_03_mistral_1116_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 2.97
us_pacific_date: 2024-12-26
win_ratio: 0.5162327395383156
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
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-v77-pref-plus-03-2336-v1-mkmlizer
Waiting for job on rirv938-v77-pref-plus-03-2336-v1-mkmlizer to finish
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ║       /___/                                                         ║
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ║                                                                     ║
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ║                                                                     ║
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ║                                                                     ║
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ║                                                                     ║
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: Downloaded to shared memory in 97.624s
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxpj4d_ff, device:0
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: quantized model in 40.349s
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: Processed model rirv938/v77_pref_plus_03_mistral_1116_v2 in 137.973s
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-v77-pref-plus-03-2336-v1
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-v77-pref-plus-03-2336-v1/config.json
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-v77-pref-plus-03-2336-v1/special_tokens_map.json
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-v77-pref-plus-03-2336-v1/tokenizer_config.json
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-v77-pref-plus-03-2336-v1/tokenizer.json
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-v77-pref-plus-03-2336-v1/flywheel_model.0.safetensors
rirv938-v77-pref-plus-03-2336-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.44it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:11, 29.69it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 26.82it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:08, 38.43it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:14, 22.86it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:12, 25.56it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 31.66it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 30.48it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 33.02it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 32.20it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:09, 32.37it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 28.15it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 25.99it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 30.92it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 30.33it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.37it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:08, 32.40it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:08, 31.26it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:07, 33.99it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 32.45it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:09, 26.79it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 22.65it/s]
Loading 0:  31%|███       | 111/363 [00:03<00:08, 29.91it/s]
Loading 0:  32%|███▏      | 115/363 [00:03<00:08, 28.99it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 31.40it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.25it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 32.87it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.80it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 30.96it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:08, 26.40it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:08, 24.43it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.28it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 30.51it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 30.05it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.38it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.76it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.58it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.19it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 26.85it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:07, 23.22it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 30.16it/s]
Loading 0:  54%|█████▍    | 196/363 [00:06<00:05, 29.01it/s]
Loading 0:  55%|█████▌    | 201/363 [00:06<00:05, 32.18it/s]
Loading 0:  56%|█████▋    | 205/363 [00:06<00:05, 31.14it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 33.31it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 31.93it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 32.42it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:04, 28.28it/s]
Loading 0:  62%|██████▏   | 226/363 [00:07<00:05, 25.98it/s]
Loading 0:  63%|██████▎   | 230/363 [00:07<00:05, 25.03it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:03, 31.96it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:03, 31.11it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 33.81it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 32.64it/s]
Loading 0:  70%|███████   | 255/363 [00:08<00:03, 34.08it/s]
Loading 0:  71%|███████▏  | 259/363 [00:08<00:03, 32.22it/s]
Loading 0:  72%|███████▏  | 263/363 [00:08<00:03, 26.60it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 22.90it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:02, 30.41it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:02, 29.06it/s]
Loading 0:  78%|███████▊  | 282/363 [00:09<00:02, 30.98it/s]
Loading 0:  79%|███████▉  | 286/363 [00:09<00:02, 29.75it/s]
Loading 0:  80%|████████  | 291/363 [00:09<00:02, 32.73it/s]
Loading 0:  81%|████████▏ | 295/363 [00:09<00:02, 31.80it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 31.81it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 27.77it/s]
Loading 0:  85%|████████▍ | 307/363 [00:10<00:02, 25.82it/s]
Loading 0:  86%|████████▌ | 311/363 [00:10<00:02, 24.74it/s]
Loading 0:  88%|████████▊ | 318/363 [00:10<00:01, 32.48it/s]
Loading 0:  89%|████████▊ | 322/363 [00:10<00:01, 31.93it/s]
Loading 0:  90%|█████████ | 327/363 [00:10<00:01, 34.56it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:00, 32.78it/s]
Loading 0:  93%|█████████▎| 336/363 [00:11<00:00, 35.25it/s]
Loading 0:  94%|█████████▎| 340/363 [00:11<00:00, 33.39it/s]
Loading 0:  95%|█████████▍| 344/363 [00:18<00:09,  1.99it/s]
Loading 0:  96%|█████████▌| 348/363 [00:18<00:05,  2.68it/s]
Loading 0:  97%|█████████▋| 353/363 [00:18<00:02,  3.89it/s]
Loading 0:  98%|█████████▊| 357/363 [00:18<00:01,  5.03it/s]
                                                            

Job rirv938-v77-pref-plus-03-2336-v1-mkmlizer completed after 166.87s with status: succeeded
Stopping job with name rirv938-v77-pref-plus-03-2336-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.36s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-v77-pref-plus-03-2336-v1
Waiting for inference service rirv938-v77-pref-plus-03-2336-v1 to be ready
Inference service rirv938-v77-pref-plus-03-2336-v1 ready after 280.9485282897949s
Pipeline stage MKMLDeployer completed in 281.48s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5576016902923584s
Received healthy response to inference request in 1.246687650680542s
Received healthy response to inference request in 1.4896001815795898s
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
Received healthy response to inference request in 1.324002742767334s
Received healthy response to inference request in 1.4633619785308838s
5 requests
0 failed requests
5th percentile: 1.2621506690979003
10th percentile: 1.2776136875152588
20th percentile: 1.3085397243499757
30th percentile: 1.351874589920044
40th percentile: 1.4076182842254639
50th percentile: 1.4633619785308838
60th percentile: 1.4738572597503663
70th percentile: 1.4843525409698486
80th percentile: 1.5032004833221435
90th percentile: 1.530401086807251
95th percentile: 1.5440013885498047
99th percentile: 1.5548816299438477
mean time: 1.4162508487701415
Pipeline stage StressChecker completed in 8.65s
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 0.75s
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 0.72s
Shutdown handler de-registered
rirv938-v77-pref-plus-03_2336_v1 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 2386.84s
Shutdown handler de-registered
rirv938-v77-pref-plus-03_2336_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-v77-pref-plus-03_2336_v1 status is now torndown due to DeploymentManager action
rirv938-v77-pref-plus-03_2336_v1 status is now torndown due to DeploymentManager action
rirv938-v77-pref-plus-03_2336_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1