developer_uid: rica40325
submission_id: rica40325-v4sft_v1
model_name: rica40325-v4sft_v1
model_group: rica40325/v4sft
status: torndown
timestamp: 2025-07-15T18:09:34+00:00
num_battles: 9269
num_wins: 4401
celo_rating: 1270.51
family_friendly_score: 0.5920000000000001
family_friendly_standard_error: 0.006950338121271511
submission_type: basic
model_repo: rica40325/v4sft
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': 0.5955925343905246, 'latency_mean': 1.6788417553901673, 'latency_p50': 1.6697355508804321, 'latency_p90': 1.8585376739501953}, {'batch_size': 3, 'throughput': 1.0634389187622193, 'latency_mean': 2.8059774124622345, 'latency_p50': 2.8302290439605713, 'latency_p90': 3.0892844915390016}, {'batch_size': 5, 'throughput': 1.2694599992046625, 'latency_mean': 3.924223551750183, 'latency_p50': 3.9188108444213867, 'latency_p90': 4.387627291679382}, {'batch_size': 6, 'throughput': 1.3305791643010865, 'latency_mean': 4.478713712692261, 'latency_p50': 4.457288384437561, 'latency_p90': 5.001596760749817}, {'batch_size': 8, 'throughput': 1.3918620795845822, 'latency_mean': 5.7123724973201755, 'latency_p50': 5.737906098365784, 'latency_p90': 6.398702096939087}, {'batch_size': 10, 'throughput': 1.4240196588199772, 'latency_mean': 6.971150676012039, 'latency_p50': 6.941047310829163, 'latency_p90': 7.908215451240539}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rica40325-v4sft_v1
is_internal_developer: False
language_model: rica40325/v4sft
model_size: 13B
ranking_group: single
throughput_3p7s: 1.24
us_pacific_date: 2025-07-15
win_ratio: 0.4748085014564678
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-v4sft-v1-mkmlizer
Waiting for job on rica40325-v4sft-v1-mkmlizer to finish
rica40325-v4sft-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-v4sft-v1-mkmlizer: ║ ║
rica40325-v4sft-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
rica40325-v4sft-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
rica40325-v4sft-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
rica40325-v4sft-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
rica40325-v4sft-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
rica40325-v4sft-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
rica40325-v4sft-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
rica40325-v4sft-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
rica40325-v4sft-v1-mkmlizer: ║ ║
rica40325-v4sft-v1-mkmlizer: ║ Version: 0.29.15 ║
rica40325-v4sft-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
rica40325-v4sft-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
rica40325-v4sft-v1-mkmlizer: ║ https://mk1.ai ║
rica40325-v4sft-v1-mkmlizer: ║ ║
rica40325-v4sft-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rica40325-v4sft-v1-mkmlizer: ║ belonging to: ║
rica40325-v4sft-v1-mkmlizer: ║ ║
rica40325-v4sft-v1-mkmlizer: ║ Chai Research Corp. ║
rica40325-v4sft-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rica40325-v4sft-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rica40325-v4sft-v1-mkmlizer: ║ ║
rica40325-v4sft-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-v4sft-v1-mkmlizer: Downloaded to shared memory in 45.384s
rica40325-v4sft-v1-mkmlizer: Checking if rica40325/v4sft already exists in ChaiML
rica40325-v4sft-v1-mkmlizer: Creating repo ChaiML/v4sft and uploading /tmp/tmppjqa6vkk to it
rica40325-v4sft-v1-mkmlizer: 0%| | 0/6 [00:00<?, ?it/s] 17%|█▋ | 1/6 [00:06<00:34, 6.82s/it] 33%|███▎ | 2/6 [00:13<00:28, 7.01s/it] 50%|█████ | 3/6 [00:22<00:22, 7.53s/it] 67%|██████▋ | 4/6 [00:26<00:12, 6.26s/it] 83%|████████▎ | 5/6 [00:30<00:05, 5.36s/it] 100%|██████████| 6/6 [00:31<00:00, 3.89s/it] 100%|██████████| 6/6 [00:31<00:00, 5.20s/it]
rica40325-v4sft-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppjqa6vkk, device:0
rica40325-v4sft-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-v4sft-v1-mkmlizer: quantized model in 29.747s
rica40325-v4sft-v1-mkmlizer: Processed model rica40325/v4sft in 131.340s
rica40325-v4sft-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-v4sft-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-v4sft-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-v4sft-v1/nvidia
rica40325-v4sft-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-v4sft-v1/nvidia/config.json
rica40325-v4sft-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-v4sft-v1/nvidia/special_tokens_map.json
rica40325-v4sft-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-v4sft-v1/nvidia/tokenizer_config.json
rica40325-v4sft-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-v4sft-v1/nvidia/tokenizer.json
rica40325-v4sft-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-v4sft-v1/nvidia/flywheel_model.0.safetensors
rica40325-v4sft-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 30.71it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 51.64it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 46.98it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 45.51it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 51.52it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 47.47it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 45.71it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 51.01it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 47.87it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 36.39it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 36.69it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 40.96it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:06, 40.81it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:07, 39.92it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:06, 44.57it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 44.22it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:05, 45.23it/s] Loading 0: 29%|██▊ | 104/363 [00:02<00:05, 45.82it/s] Loading 0: 30%|███ | 109/363 [00:02<00:05, 46.51it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:06, 38.52it/s] Loading 0: 33%|███▎ | 119/363 [00:02<00:06, 38.32it/s] Loading 0: 34%|███▍ | 125/363 [00:02<00:05, 43.17it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 43.37it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 44.19it/s] Loading 0: 39%|███▉ | 141/363 [00:03<00:05, 43.01it/s] Loading 0: 40%|████ | 146/363 [00:03<00:07, 30.99it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 31.02it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 36.53it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:05, 38.29it/s] Loading 0: 46%|████▌ | 166/363 [00:03<00:04, 40.54it/s] Loading 0: 47%|████▋ | 172/363 [00:04<00:04, 40.24it/s] Loading 0: 49%|████▉ | 177/363 [00:04<00:04, 40.30it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:03, 45.46it/s] Loading 0: 52%|█████▏ | 190/363 [00:04<00:04, 43.05it/s] Loading 0: 54%|█████▎ | 195/363 [00:04<00:04, 41.55it/s] Loading 0: 56%|█████▌ | 202/363 [00:04<00:03, 46.20it/s] Loading 0: 57%|█████▋ | 207/363 [00:04<00:03, 47.14it/s] Loading 0: 58%|█████▊ | 212/363 [00:05<00:04, 37.54it/s] Loading 0: 60%|██████ | 218/363 [00:05<00:03, 41.93it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:04, 33.21it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 33.22it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 31.58it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 35.93it/s] Loading 0: 66%|██████▋ | 241/363 [00:05<00:03, 35.36it/s] Loading 0: 68%|██████▊ | 246/363 [00:06<00:03, 38.84it/s] Loading 0: 69%|██████▉ | 251/363 [00:06<00:02, 39.45it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 40.72it/s] Loading 0: 72%|███████▏ | 261/363 [00:06<00:02, 42.74it/s] Loading 0: 73%|███████▎ | 266/363 [00:06<00:02, 35.43it/s] Loading 0: 75%|███████▌ | 273/363 [00:06<00:02, 42.87it/s] Loading 0: 77%|███████▋ | 278/363 [00:06<00:02, 42.09it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 42.36it/s] Loading 0: 79%|███████▉ | 288/363 [00:07<00:01, 43.21it/s] Loading 0: 81%|████████ | 293/363 [00:07<00:01, 35.24it/s] Loading 0: 82%|████████▏ | 299/363 [00:07<00:01, 40.11it/s] Loading 0: 84%|████████▎ | 304/363 [00:07<00:02, 23.42it/s] Loading 0: 85%|████████▍ | 308/363 [00:07<00:02, 25.69it/s] Loading 0: 86%|████████▌ | 312/363 [00:08<00:01, 26.20it/s] Loading 0: 88%|████████▊ | 320/363 [00:08<00:01, 36.16it/s] Loading 0: 90%|████████▉ | 326/363 [00:08<00:00, 37.95it/s] Loading 0: 91%|█████████ | 331/363 [00:08<00:00, 39.60it/s] Loading 0: 93%|█████████▎| 338/363 [00:08<00:00, 45.55it/s] Loading 0: 95%|█████████▍| 344/363 [00:08<00:00, 43.48it/s] Loading 0: 96%|█████████▌| 349/363 [00:08<00:00, 43.11it/s] Loading 0: 98%|█████████▊| 356/363 [00:08<00:00, 48.14it/s] Loading 0: 100%|█████████▉| 362/363 [00:09<00:00, 45.27it/s]
Job rica40325-v4sft-v1-mkmlizer completed after 158.46s with status: succeeded
Stopping job with name rica40325-v4sft-v1-mkmlizer
Pipeline stage MKMLizer completed in 159.29s
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 rica40325-v4sft-v1
Waiting for inference service rica40325-v4sft-v1 to be ready
Inference service rica40325-v4sft-v1 ready after 251.37358403205872s
Pipeline stage MKMLDeployer completed in 252.74s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3971328735351562s
Received healthy response to inference request in 1.7927305698394775s
Received healthy response to inference request in 1.7775382995605469s
Received healthy response to inference request in 1.7657513618469238s
Received healthy response to inference request in 2.378631830215454s
5 requests
0 failed requests
5th percentile: 1.7681087493896483
10th percentile: 1.770466136932373
20th percentile: 1.7751809120178224
30th percentile: 1.780576753616333
40th percentile: 1.7866536617279052
50th percentile: 1.7927305698394775
60th percentile: 2.027091073989868
70th percentile: 2.261451578140259
80th percentile: 2.3823320388793947
90th percentile: 2.3897324562072755
95th percentile: 2.3934326648712156
99th percentile: 2.396392831802368
mean time: 2.0223569869995117
Pipeline stage StressChecker completed in 11.48s
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 1.02s
Shutdown handler de-registered
rica40325-v4sft_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-v4sft-v1-profiler
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 5395.59s
Shutdown handler de-registered
rica40325-v4sft_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-v4sft_v1 status is now torndown due to DeploymentManager action
rica40325-v4sft_v1 status is now torndown due to DeploymentManager action