developer_uid: rica40325
submission_id: rica40325-960_v2
model_name: rica40325-960_v1
model_group: rica40325/960
status: torndown
timestamp: 2025-04-21T11:20:47+00:00
num_battles: 6735
num_wins: 3124
celo_rating: 1262.6
family_friendly_score: 0.5671999999999999
family_friendly_standard_error: 0.007006913157732155
submission_type: basic
model_repo: rica40325/960
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6023720105517788, 'latency_mean': 1.660031896829605, 'latency_p50': 1.676153302192688, 'latency_p90': 1.829986834526062}, {'batch_size': 3, 'throughput': 1.118961936829146, 'latency_mean': 2.6678251671791076, 'latency_p50': 2.661614179611206, 'latency_p90': 2.9693288564682003}, {'batch_size': 5, 'throughput': 1.3422527532616126, 'latency_mean': 3.712583285570145, 'latency_p50': 3.683995008468628, 'latency_p90': 4.186937689781189}, {'batch_size': 6, 'throughput': 1.4121486585787344, 'latency_mean': 4.219767602682114, 'latency_p50': 4.230433464050293, 'latency_p90': 4.782316470146179}, {'batch_size': 8, 'throughput': 1.4864972183606653, 'latency_mean': 5.35227821469307, 'latency_p50': 5.341875910758972, 'latency_p90': 6.053126096725464}, {'batch_size': 10, 'throughput': 1.529542404347454, 'latency_mean': 6.483066614866257, 'latency_p50': 6.461192488670349, 'latency_p90': 7.31966245174408}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rica40325-960_v1
is_internal_developer: False
language_model: rica40325/960
model_size: 13B
ranking_group: single
throughput_3p7s: 1.34
us_pacific_date: 2025-04-21
win_ratio: 0.4638455827765405
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 rica40325-960-v2-mkmlizer
Waiting for job on rica40325-960-v2-mkmlizer to finish
Failed to get response for submission rica40325-nsfw-filter_v8: HTTPConnectionPool(host='rica40325-nsfw-filter-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rica40325-960-v2-mkmlizer: Downloaded to shared memory in 38.971s
rica40325-960-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcehf5rj7, device:0
rica40325-960-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-960-v2-mkmlizer: quantized model in 36.484s
rica40325-960-v2-mkmlizer: Processed model rica40325/960 in 75.455s
rica40325-960-v2-mkmlizer: creating bucket guanaco-mkml-models
rica40325-960-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-960-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-960-v2
rica40325-960-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-960-v2/config.json
rica40325-960-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-960-v2/special_tokens_map.json
rica40325-960-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-960-v2/tokenizer_config.json
rica40325-960-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-960-v2/tokenizer.json
rica40325-960-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-960-v2/flywheel_model.0.safetensors
rica40325-960-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 31.94it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 50.94it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 43.58it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 42.12it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 48.23it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 45.39it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 44.20it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 49.17it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 46.10it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:09, 33.45it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:08, 33.13it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.69it/s] Loading 0: 21%|██ | 77/363 [00:01<00:06, 41.79it/s] Loading 0: 23%|██▎ | 82/363 [00:02<00:07, 35.64it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:06, 42.83it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 42.60it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:06, 42.52it/s] Loading 0: 29%|██▉ | 105/363 [00:02<00:06, 41.09it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 45.63it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 44.26it/s] Loading 0: 34%|███▎ | 122/363 [00:02<00:05, 45.57it/s] Loading 0: 35%|███▍ | 127/363 [00:03<00:06, 37.84it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:05, 44.72it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:05, 44.57it/s] Loading 0: 40%|███▉ | 144/363 [00:03<00:07, 28.10it/s] Loading 0: 41%|████ | 149/363 [00:03<00:06, 30.67it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 37.48it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:05, 38.76it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:04, 40.43it/s] Loading 0: 47%|████▋ | 172/363 [00:04<00:04, 40.00it/s] Loading 0: 49%|████▉ | 177/363 [00:04<00:04, 39.76it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 43.32it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:04, 43.58it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 43.88it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:04, 40.55it/s] Loading 0: 56%|█████▌ | 204/363 [00:05<00:04, 39.74it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 43.99it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 44.24it/s] Loading 0: 61%|██████ | 221/363 [00:05<00:02, 47.81it/s] Loading 0: 62%|██████▏ | 226/363 [00:05<00:04, 28.91it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:04, 29.60it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 35.66it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 37.22it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:02, 39.03it/s] Loading 0: 70%|██████▉ | 253/363 [00:06<00:02, 38.99it/s] Loading 0: 71%|███████ | 258/363 [00:06<00:02, 38.96it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 42.71it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 43.29it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:02, 42.79it/s] Loading 0: 77%|███████▋ | 280/363 [00:06<00:02, 41.02it/s] Loading 0: 79%|███████▊ | 285/363 [00:07<00:01, 39.67it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 42.73it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 40.84it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:01, 41.70it/s] Loading 0: 84%|████████▍ | 306/363 [00:14<00:23, 2.42it/s] Loading 0: 85%|████████▌ | 310/363 [00:14<00:16, 3.14it/s] Loading 0: 87%|████████▋ | 314/363 [00:14<00:11, 4.14it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 6.20it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:04, 8.69it/s] Loading 0: 91%|█████████ | 330/363 [00:14<00:03, 10.62it/s] Loading 0: 93%|█████████▎| 338/363 [00:15<00:01, 16.31it/s] Loading 0: 95%|█████████▍| 344/363 [00:15<00:00, 19.96it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 23.24it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 29.69it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.20it/s]
Job rica40325-960-v2-mkmlizer completed after 103.83s with status: succeeded
Stopping job with name rica40325-960-v2-mkmlizer
Pipeline stage MKMLizer completed in 104.27s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-960-v2
Waiting for inference service rica40325-960-v2 to be ready
Inference service rica40325-960-v2 ready after 130.70314478874207s
Pipeline stage MKMLDeployer completed in 131.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3676817417144775s
Received healthy response to inference request in 1.6743438243865967s
Received healthy response to inference request in 1.8158552646636963s
Received healthy response to inference request in 1.7826097011566162s
Received healthy response to inference request in 1.5277493000030518s
5 requests
0 failed requests
5th percentile: 1.5570682048797608
10th percentile: 1.5863871097564697
20th percentile: 1.6450249195098876
30th percentile: 1.6959969997406006
40th percentile: 1.7393033504486084
50th percentile: 1.7826097011566162
60th percentile: 1.7959079265594482
70th percentile: 1.8092061519622802
80th percentile: 1.9262205600738527
90th percentile: 2.146951150894165
95th percentile: 2.2573164463043214
99th percentile: 2.3456086826324465
mean time: 1.8336479663848877
Pipeline stage StressChecker completed in 10.58s
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 0.62s
Shutdown handler de-registered
rica40325-960_v2 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-960-v2-profiler
Waiting for inference service rica40325-960-v2-profiler to be ready
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 2737.08s
Shutdown handler de-registered
rica40325-960_v2 status is now inactive due to auto deactivation removed underperforming models
rica40325-960_v2 status is now torndown due to DeploymentManager action