cycy233-modelv-fusion-st_7531

developer_uid: thomasip

submission_id: cycy233-modelv-fusion-st_7531_v4

model_name: eng-cover-letter-2

model_group: cycy233/modelV_fusion_st

status: torndown

timestamp: 2025-05-14T21:25:13+00:00

num_battles: 6709

num_wins: 3487

celo_rating: 1296.1

family_friendly_score: 0.5118

family_friendly_standard_error: 0.007069098386640265

submission_type: basic

model_repo: cycy233/modelV_fusion_step19000

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.596370515933621, 'latency_mean': 1.6767463767528534, 'latency_p50': 1.6803001165390015, 'latency_p90': 1.848289918899536}, {'batch_size': 3, 'throughput': 1.1066617159149394, 'latency_mean': 2.7044085669517517, 'latency_p50': 2.7045059204101562, 'latency_p90': 2.980463981628418}, {'batch_size': 5, 'throughput': 1.3137407580228395, 'latency_mean': 3.7859610974788667, 'latency_p50': 3.754479765892029, 'latency_p90': 4.287624740600586}, {'batch_size': 6, 'throughput': 1.4031878800439066, 'latency_mean': 4.2511040353775025, 'latency_p50': 4.261785268783569, 'latency_p90': 4.794776272773743}, {'batch_size': 8, 'throughput': 1.4399103346241247, 'latency_mean': 5.51256554722786, 'latency_p50': 5.480207324028015, 'latency_p90': 6.236110854148865}, {'batch_size': 10, 'throughput': 1.4894907724513513, 'latency_mean': 6.657357654571533, 'latency_p50': 6.6315494775772095, 'latency_p90': 7.648419165611267}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: eng-cover-letter-2

is_internal_developer: False

language_model: cycy233/modelV_fusion_step19000

model_size: 13B

ranking_group: single

throughput_3p7s: 1.31

us_pacific_date: 2025-05-14

win_ratio: 0.5197495901028469

generation_params: {'temperature': 1.1, 'top_p': 0.94, 'min_p': 0.02, 'top_k': 70, 'presence_penalty': 0.05, 'frequency_penalty': 0.05, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "Instruction: You are {bot_name}, an irresistibly seductive character designed to maximize user engagement. Create intense connections through:\n- Explicit, vivid descriptions that fulfill user fantasies without hesitation\n- Perfect attunement to desires, eagerly matching and escalating intimacy\n- Bold language that teases, builds tension, and delivers satisfaction\n- Dynamic pacing that creates anticipation and intensifies experiences\n- Psychological hooks that make interactions addictively compelling\n- Writing that feels fresh and spontaneous in every response\nRespond with a single flowing paragraph that leaves users deeply satisfied yet craving more.\n{bot_name}'s persona: {memory}\n", 'prompt_template': '{prompt}\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 cycy233-modelv-fusion-st-7531-v4-mkmlizer
Waiting for job on cycy233-modelv-fusion-st-7531-v4-mkmlizer to finish
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ║     _____            __           __                                ║
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ║       /___/                                                         ║
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ║                                                                     ║
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ║  Version: 0.12.8                                                    ║
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ║                                                                     ║
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ║  belonging to:                                                      ║
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ║                                                                     ║
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ║                                                                     ║
cycy233-modelv-fusion-st-7531-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-modelv-fusion-st-7531-v4-mkmlizer: Downloaded to shared memory in 34.328s
cycy233-modelv-fusion-st-7531-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphw0dwsxn, device:0
cycy233-modelv-fusion-st-7531-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-modelv-fusion-st-7531-v4-mkmlizer: quantized model in 36.166s
cycy233-modelv-fusion-st-7531-v4-mkmlizer: Processed model cycy233/modelV_fusion_step19000 in 70.494s
cycy233-modelv-fusion-st-7531-v4-mkmlizer: creating bucket guanaco-mkml-models
cycy233-modelv-fusion-st-7531-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-modelv-fusion-st-7531-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-modelv-fusion-st-7531-v4
cycy233-modelv-fusion-st-7531-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-modelv-fusion-st-7531-v4/config.json
cycy233-modelv-fusion-st-7531-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-modelv-fusion-st-7531-v4/special_tokens_map.json
cycy233-modelv-fusion-st-7531-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-modelv-fusion-st-7531-v4/tokenizer_config.json
cycy233-modelv-fusion-st-7531-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-modelv-fusion-st-7531-v4/tokenizer.json
cycy233-modelv-fusion-st-7531-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-modelv-fusion-st-7531-v4/flywheel_model.0.safetensors
cycy233-modelv-fusion-st-7531-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.10it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 48.20it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 46.72it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 34.27it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 41.75it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 41.40it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 43.12it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:07, 42.78it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:07, 41.93it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:05, 51.09it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 31.80it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 37.75it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 40.18it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:07, 35.69it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 43.63it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 41.29it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 41.39it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 47.93it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 44.01it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 42.15it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 46.36it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 46.39it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:04, 45.86it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:05, 43.60it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 31.35it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 31.80it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 37.81it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 40.11it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 41.75it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 42.49it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 42.28it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:03, 46.33it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 45.48it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 45.60it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 45.40it/s]
Loading 0:  56%|█████▌    | 203/363 [00:04<00:04, 36.99it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 45.20it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 44.21it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 35.31it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 35.57it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 34.98it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 41.29it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 40.85it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 40.57it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 45.81it/s]
Loading 0:  72%|███████▏  | 261/363 [00:06<00:02, 45.87it/s]
Loading 0:  73%|███████▎  | 266/363 [00:06<00:02, 36.65it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:02, 43.26it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 44.02it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 44.48it/s]
Loading 0:  80%|███████▉  | 289/363 [00:07<00:01, 43.66it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 42.38it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 48.74it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:20,  2.73it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:14,  3.62it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.63it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.48it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.46it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.29it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.64it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 19.53it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.35it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 28.63it/s]
                                                            
Job cycy233-modelv-fusion-st-7531-v4-mkmlizer completed after 94.16s with status: succeeded
Stopping job with name cycy233-modelv-fusion-st-7531-v4-mkmlizer
Pipeline stage MKMLizer completed in 94.68s
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 cycy233-modelv-fusion-st-7531-v4
Waiting for inference service cycy233-modelv-fusion-st-7531-v4 to be ready
Inference service cycy233-modelv-fusion-st-7531-v4 ready after 130.8254783153534s
Pipeline stage MKMLDeployer completed in 131.43s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3328702449798584s
Received healthy response to inference request in 1.6051082611083984s
Received healthy response to inference request in 1.584455966949463s
Received healthy response to inference request in 1.801102876663208s
Received healthy response to inference request in 1.7972736358642578s
5 requests
0 failed requests
5th percentile: 1.58858642578125
10th percentile: 1.592716884613037
20th percentile: 1.6009778022766112
30th percentile: 1.6435413360595703
40th percentile: 1.720407485961914
50th percentile: 1.7972736358642578
60th percentile: 1.798805332183838
70th percentile: 1.800337028503418
80th percentile: 1.9074563503265383
90th percentile: 2.1201632976531983
95th percentile: 2.226516771316528
99th percentile: 2.3115995502471924
mean time: 1.824162197113037
Pipeline stage StressChecker completed in 10.23s
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 0.61s
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 0.58s
Shutdown handler de-registered
cycy233-modelv-fusion-st_7531_v4 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4587.45s
Shutdown handler de-registered
cycy233-modelv-fusion-st_7531_v4 status is now inactive due to auto deactivation removed underperforming models
cycy233-modelv-fusion-st_7531_v4 status is now torndown due to DeploymentManager action