developer_uid: rica40325
submission_id: rica40325-sft-from-dpov1_v2
model_name: rica40325-sft-from-dpov1_v2
model_group: rica40325/sft-from-dpov1
status: torndown
timestamp: 2025-05-07T05:44:39+00:00
num_battles: 8079
num_wins: 3729
celo_rating: 1253.4
family_friendly_score: 0.6664
family_friendly_standard_error: 0.0066679988002398445
submission_type: basic
model_repo: rica40325/sft-from-dpov1
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6019990458461292, 'latency_mean': 1.6610295581817627, 'latency_p50': 1.6633861064910889, 'latency_p90': 1.832377552986145}, {'batch_size': 3, 'throughput': 1.129790446792759, 'latency_mean': 2.646985721588135, 'latency_p50': 2.6443400382995605, 'latency_p90': 2.9220247745513914}, {'batch_size': 5, 'throughput': 1.3410129653398355, 'latency_mean': 3.7237553429603576, 'latency_p50': 3.7273439168930054, 'latency_p90': 4.1664296865463255}, {'batch_size': 6, 'throughput': 1.4292568579358356, 'latency_mean': 4.175558738708496, 'latency_p50': 4.175777554512024, 'latency_p90': 4.701858401298523}, {'batch_size': 8, 'throughput': 1.4861432194000765, 'latency_mean': 5.348465142250061, 'latency_p50': 5.341486215591431, 'latency_p90': 6.031249046325684}, {'batch_size': 10, 'throughput': 1.5223868408423207, 'latency_mean': 6.5087952959537505, 'latency_p50': 6.544376969337463, 'latency_p90': 7.342964744567871}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rica40325-sft-from-dpov1_v2
is_internal_developer: False
language_model: rica40325/sft-from-dpov1
model_size: 13B
ranking_group: single
throughput_3p7s: 1.34
us_pacific_date: 2025-05-06
win_ratio: 0.46156702562198293
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-sft-from-dpov1-v2-mkmlizer
Waiting for job on rica40325-sft-from-dpov1-v2-mkmlizer to finish
rica40325-sft-from-dpov1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-sft-from-dpov1-v2-mkmlizer: ║ _____ __ __ ║
rica40325-sft-from-dpov1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rica40325-sft-from-dpov1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rica40325-sft-from-dpov1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rica40325-sft-from-dpov1-v2-mkmlizer: ║ /___/ ║
rica40325-sft-from-dpov1-v2-mkmlizer: ║ ║
rica40325-sft-from-dpov1-v2-mkmlizer: ║ Version: 0.12.8 ║
rica40325-sft-from-dpov1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rica40325-sft-from-dpov1-v2-mkmlizer: ║ https://mk1.ai ║
rica40325-sft-from-dpov1-v2-mkmlizer: ║ ║
rica40325-sft-from-dpov1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
rica40325-sft-from-dpov1-v2-mkmlizer: ║ belonging to: ║
rica40325-sft-from-dpov1-v2-mkmlizer: ║ ║
rica40325-sft-from-dpov1-v2-mkmlizer: ║ Chai Research Corp. ║
rica40325-sft-from-dpov1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rica40325-sft-from-dpov1-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rica40325-sft-from-dpov1-v2-mkmlizer: ║ ║
rica40325-sft-from-dpov1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-sft-from-dpov1-v2-mkmlizer: Downloaded to shared memory in 40.353s
rica40325-sft-from-dpov1-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8dmk3vqc, device:0
rica40325-sft-from-dpov1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-sft-from-dpov1-v2-mkmlizer: quantized model in 36.372s
rica40325-sft-from-dpov1-v2-mkmlizer: Processed model rica40325/sft-from-dpov1 in 76.725s
rica40325-sft-from-dpov1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-sft-from-dpov1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-sft-from-dpov1-v2
rica40325-sft-from-dpov1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-sft-from-dpov1-v2/config.json
rica40325-sft-from-dpov1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-sft-from-dpov1-v2/special_tokens_map.json
rica40325-sft-from-dpov1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-sft-from-dpov1-v2/tokenizer_config.json
rica40325-sft-from-dpov1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-sft-from-dpov1-v2/tokenizer.json
rica40325-sft-from-dpov1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-sft-from-dpov1-v2/flywheel_model.0.safetensors
rica40325-sft-from-dpov1-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 31.78it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 51.37it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 46.13it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 44.24it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 48.92it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 44.35it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 42.64it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:06, 46.96it/s] Loading 0: 15%|█▍ | 53/363 [00:01<00:06, 46.56it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:06, 45.80it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 31.23it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 37.45it/s] Loading 0: 21%|██ | 77/363 [00:01<00:07, 39.97it/s] Loading 0: 23%|██▎ | 82/363 [00:02<00:08, 35.04it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:06, 41.07it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 40.81it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:06, 40.95it/s] Loading 0: 29%|██▉ | 105/363 [00:02<00:06, 40.17it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 44.94it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 43.18it/s] Loading 0: 34%|███▎ | 122/363 [00:02<00:05, 43.83it/s] Loading 0: 35%|███▍ | 127/363 [00:03<00:06, 37.56it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:05, 44.59it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:05, 43.96it/s] Loading 0: 40%|███▉ | 144/363 [00:03<00:07, 28.73it/s] Loading 0: 41%|████ | 149/363 [00:03<00:06, 30.90it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 37.90it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 38.49it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:05, 39.14it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 40.22it/s] Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 34.38it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 41.74it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:04, 42.21it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 42.50it/s] Loading 0: 55%|█████▍ | 198/363 [00:04<00:03, 44.33it/s] Loading 0: 56%|█████▌ | 203/363 [00:05<00:04, 37.14it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 43.40it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 43.47it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:03, 44.59it/s] Loading 0: 62%|██████▏ | 225/363 [00:05<00:04, 27.61it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:04, 29.22it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 35.25it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 35.60it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:03, 37.24it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 39.93it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:03, 33.69it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 41.08it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 42.25it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:02, 40.81it/s] Loading 0: 77%|███████▋ | 279/363 [00:07<00:01, 42.86it/s] Loading 0: 78%|███████▊ | 284/363 [00:07<00:02, 36.45it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 43.05it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 42.62it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:01, 44.12it/s] Loading 0: 84%|████████▍ | 306/363 [00:14<00:22, 2.49it/s] Loading 0: 85%|████████▌ | 310/363 [00:14<00:16, 3.23it/s] Loading 0: 87%|████████▋ | 314/363 [00:14<00:11, 4.24it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 6.33it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:04, 8.85it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 11.45it/s] Loading 0: 93%|█████████▎| 338/363 [00:15<00:01, 16.30it/s] Loading 0: 94%|█████████▍| 343/363 [00:15<00:01, 19.77it/s] Loading 0: 96%|█████████▌| 348/363 [00:15<00:00, 21.52it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 29.60it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 31.65it/s]
Job rica40325-sft-from-dpov1-v2-mkmlizer completed after 104.5s with status: succeeded
Stopping job with name rica40325-sft-from-dpov1-v2-mkmlizer
Pipeline stage MKMLizer completed in 105.01s
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 rica40325-sft-from-dpov1-v2
Waiting for inference service rica40325-sft-from-dpov1-v2 to be ready
Inference service rica40325-sft-from-dpov1-v2 ready after 150.56073641777039s
Pipeline stage MKMLDeployer completed in 151.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1631646156311035s
Received healthy response to inference request in 1.5736205577850342s
Received healthy response to inference request in 1.5852046012878418s
Received healthy response to inference request in 1.5899126529693604s
Received healthy response to inference request in 1.7489776611328125s
5 requests
0 failed requests
5th percentile: 1.5759373664855958
10th percentile: 1.5782541751861572
20th percentile: 1.5828877925872802
30th percentile: 1.5861462116241456
40th percentile: 1.588029432296753
50th percentile: 1.5899126529693604
60th percentile: 1.6535386562347412
70th percentile: 1.717164659500122
80th percentile: 1.8318150520324707
90th percentile: 1.9974898338317872
95th percentile: 2.080327224731445
99th percentile: 2.1465971374511716
mean time: 1.7321760177612304
Pipeline stage StressChecker completed in 10.13s
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 0.80s
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 0.73s
Shutdown handler de-registered
rica40325-sft-from-dpov1_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
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 4839.30s
Shutdown handler de-registered
rica40325-sft-from-dpov1_v2 status is now inactive due to auto deactivation removed underperforming models
rica40325-sft-from-dpov1_v2 status is now torndown due to DeploymentManager action