rica40325-filter-fullsf_45536

developer_uid: rica40325

submission_id: rica40325-filter-fullsf_45536_v5

model_name: rica40325-filter-fullsf_45536_v5

model_group: rica40325/filter-fullsft

status: torndown

timestamp: 2025-06-24T06:38:43+00:00

num_battles: 7927

num_wins: 3740

celo_rating: 1254.68

family_friendly_score: 0.5158

family_friendly_standard_error: 0.007067536487348332

submission_type: basic

model_repo: rica40325/filter-fullsftfpo-1500

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5986626632777688, 'latency_mean': 1.6702858471870423, 'latency_p50': 1.6720330715179443, 'latency_p90': 1.8554675579071045}, {'batch_size': 3, 'throughput': 1.065997781632343, 'latency_mean': 2.807828789949417, 'latency_p50': 2.8305612802505493, 'latency_p90': 3.0875786781311034}, {'batch_size': 5, 'throughput': 1.2740421248202358, 'latency_mean': 3.8998507761955263, 'latency_p50': 3.8840060234069824, 'latency_p90': 4.367023038864136}, {'batch_size': 6, 'throughput': 1.3442790721589764, 'latency_mean': 4.442252044677734, 'latency_p50': 4.430758953094482, 'latency_p90': 4.974838614463806}, {'batch_size': 8, 'throughput': 1.390524725639751, 'latency_mean': 5.7106762528419495, 'latency_p50': 5.703012943267822, 'latency_p90': 6.336008238792419}, {'batch_size': 10, 'throughput': 1.4466324774769026, 'latency_mean': 6.861082956790924, 'latency_p50': 6.878777265548706, 'latency_p90': 7.772349953651428}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rica40325-filter-fullsf_45536_v5

is_internal_developer: False

language_model: rica40325/filter-fullsftfpo-1500

model_size: 13B

ranking_group: single

throughput_3p7s: 1.25

us_pacific_date: 2025-06-23

win_ratio: 0.4718052226567428

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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 rica40325-filter-fullsf-45536-v5-mkmlizer
Waiting for job on rica40325-filter-fullsf-45536-v5-mkmlizer to finish
rica40325-filter-fullsf-45536-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-filter-fullsf-45536-v5-mkmlizer: ║                                                                     ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║                                                                     ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║  Version: 0.29.3                                                    ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║                                                                     ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║  belonging to:                                                      ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║                                                                     ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ║                                                                     ║
rica40325-filter-fullsf-45536-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-filter-fullsf-45536-v5-mkmlizer: Downloaded to shared memory in 32.306s
rica40325-filter-fullsf-45536-v5-mkmlizer: Checking if rica40325/filter-fullsftfpo-1500 already exists in ChaiML
rica40325-filter-fullsf-45536-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7i87pac9, device:0
rica40325-filter-fullsf-45536-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-filter-fullsf-45536-v5-mkmlizer: quantized model in 32.077s
rica40325-filter-fullsf-45536-v5-mkmlizer: Processed model rica40325/filter-fullsftfpo-1500 in 64.480s
rica40325-filter-fullsf-45536-v5-mkmlizer: creating bucket guanaco-mkml-models
rica40325-filter-fullsf-45536-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-filter-fullsf-45536-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-filter-fullsf-45536-v5
rica40325-filter-fullsf-45536-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-filter-fullsf-45536-v5/config.json
rica40325-filter-fullsf-45536-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-filter-fullsf-45536-v5/special_tokens_map.json
rica40325-filter-fullsf-45536-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-filter-fullsf-45536-v5/tokenizer_config.json
rica40325-filter-fullsf-45536-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-filter-fullsf-45536-v5/tokenizer.json
rica40325-filter-fullsf-45536-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-filter-fullsf-45536-v5/flywheel_model.0.safetensors
rica40325-filter-fullsf-45536-v5-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 27.39it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 42.65it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 41.88it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:07, 43.85it/s]
Loading 0:   8%|▊         | 28/363 [00:00<00:07, 42.19it/s]
Loading 0:   9%|▉         | 33/363 [00:00<00:07, 41.78it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:06, 47.84it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:07, 44.35it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:07, 43.10it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:06, 49.59it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:11, 26.91it/s]
Loading 0:  19%|█▉        | 69/363 [00:01<00:09, 30.05it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:09, 30.38it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:08, 31.80it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:09, 29.67it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:08, 33.60it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 31.63it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:07, 35.26it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:08, 31.41it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:07, 34.88it/s]
Loading 0:  30%|███       | 110/363 [00:03<00:07, 35.77it/s]
Loading 0:  31%|███▏      | 114/363 [00:03<00:07, 32.81it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:08, 29.47it/s]
Loading 0:  34%|███▍      | 123/363 [00:03<00:09, 26.58it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:09, 26.01it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:07, 30.80it/s]
Loading 0:  37%|███▋      | 136/363 [00:04<00:07, 30.34it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:08, 27.11it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:08, 25.61it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 26.46it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 34.19it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 34.20it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 37.05it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:05, 36.86it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:04, 38.95it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 36.16it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 37.28it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 34.14it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:04, 34.40it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:05, 29.50it/s]
Loading 0:  55%|█████▍    | 199/363 [00:05<00:05, 31.02it/s]
Loading 0:  56%|█████▌    | 203/363 [00:06<00:05, 28.91it/s]
Loading 0:  57%|█████▋    | 208/363 [00:06<00:04, 32.96it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:05, 29.96it/s]
Loading 0:  60%|█████▉    | 217/363 [00:06<00:04, 34.50it/s]
Loading 0:  61%|██████    | 222/363 [00:06<00:03, 35.31it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:06, 22.52it/s]
Loading 0:  63%|██████▎   | 230/363 [00:07<00:05, 23.07it/s]
Loading 0:  65%|██████▍   | 235/363 [00:07<00:04, 27.46it/s]
Loading 0:  66%|██████▌   | 239/363 [00:07<00:04, 26.05it/s]
Loading 0:  67%|██████▋   | 244/363 [00:07<00:03, 30.24it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:04, 28.23it/s]
Loading 0:  70%|██████▉   | 253/363 [00:07<00:03, 32.37it/s]
Loading 0:  71%|███████   | 257/363 [00:07<00:03, 30.38it/s]
Loading 0:  73%|███████▎  | 264/363 [00:08<00:02, 37.45it/s]
Loading 0:  74%|███████▍  | 269/363 [00:08<00:02, 38.54it/s]
Loading 0:  75%|███████▌  | 274/363 [00:08<00:02, 39.99it/s]
Loading 0:  77%|███████▋  | 279/363 [00:08<00:01, 42.44it/s]
Loading 0:  78%|███████▊  | 284/363 [00:08<00:02, 35.44it/s]
Loading 0:  80%|████████  | 291/363 [00:08<00:01, 42.65it/s]
Loading 0:  82%|████████▏ | 296/363 [00:08<00:01, 42.93it/s]
Loading 0:  83%|████████▎ | 301/363 [00:08<00:01, 44.47it/s]
Loading 0:  84%|████████▍ | 306/363 [00:09<00:02, 24.20it/s]
Loading 0:  85%|████████▌ | 310/363 [00:09<00:02, 25.09it/s]
Loading 0:  87%|████████▋ | 314/363 [00:09<00:01, 27.61it/s]
Loading 0:  88%|████████▊ | 320/363 [00:09<00:01, 33.40it/s]
Loading 0:  90%|████████▉ | 326/363 [00:09<00:01, 35.23it/s]
Loading 0:  91%|█████████ | 331/363 [00:10<00:00, 36.51it/s]
Loading 0:  93%|█████████▎| 338/363 [00:10<00:00, 42.54it/s]
Loading 0:  95%|█████████▍| 344/363 [00:10<00:00, 40.83it/s]
Loading 0:  96%|█████████▌| 349/363 [00:10<00:00, 40.80it/s]
Loading 0:  98%|█████████▊| 355/363 [00:10<00:00, 44.76it/s]
Loading 0:  99%|█████████▉| 360/363 [00:10<00:00, 44.09it/s]
                                                            
Job rica40325-filter-fullsf-45536-v5-mkmlizer completed after 104.82s with status: succeeded
Stopping job with name rica40325-filter-fullsf-45536-v5-mkmlizer
Pipeline stage MKMLizer completed in 105.30s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-filter-fullsf-45536-v5
Waiting for inference service rica40325-filter-fullsf-45536-v5 to be ready
Failed to get response for submission chaiml-giyu-disabled-hu_13897_v2: ('http://chaiml-giyu-disabled-hu-13897-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-giyu-disabled-hu_13897_v2: ('http://chaiml-giyu-disabled-hu-13897-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service rica40325-filter-fullsf-45536-v5 ready after 110.44762587547302s
Pipeline stage MKMLDeployer completed in 110.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.583439826965332s
Received healthy response to inference request in 1.485483169555664s
Received healthy response to inference request in 1.5872728824615479s
Received healthy response to inference request in 1.6484127044677734s
Received healthy response to inference request in 1.7971110343933105s
5 requests
0 failed requests
5th percentile: 1.505841112136841
10th percentile: 1.5261990547180175
20th percentile: 1.566914939880371
30th percentile: 1.599500846862793
40th percentile: 1.6239567756652833
50th percentile: 1.6484127044677734
60th percentile: 1.7078920364379884
70th percentile: 1.767371368408203
80th percentile: 1.954376792907715
90th percentile: 2.2689083099365233
95th percentile: 2.4261740684509276
99th percentile: 2.551986675262451
mean time: 1.8203439235687255
Pipeline stage StressChecker completed in 10.39s
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 0.71s
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 0.78s
Shutdown handler de-registered
rica40325-filter-fullsf_45536_v5 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 5248.92s
Shutdown handler de-registered
rica40325-filter-fullsf_45536_v5 status is now inactive due to auto deactivation removed underperforming models
rica40325-filter-fullsf_45536_v5 status is now torndown due to DeploymentManager action