submission_id: rica40325-10-14dpo_v6
developer_uid: rica40325
best_of: 8
celo_rating: 1293.74
display_name: rica40325-10-14dpo_v1
family_friendly_score: 0.5631999999999999
family_friendly_standard_error: 0.007014353284515972
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}
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', 'Bot:', 'User:', 'You:', 'Me:', '####'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: rica40325/10_14dpo
latencies: [{'batch_size': 1, 'throughput': 0.6064777384011372, 'latency_mean': 1.6487725174427033, 'latency_p50': 1.6425272226333618, 'latency_p90': 1.8183834314346314}, {'batch_size': 3, 'throughput': 1.1121790420351756, 'latency_mean': 2.6894053423404696, 'latency_p50': 2.676719069480896, 'latency_p90': 2.9674614667892456}, {'batch_size': 5, 'throughput': 1.3256333545253896, 'latency_mean': 3.7547917234897614, 'latency_p50': 3.7744487524032593, 'latency_p90': 4.168982315063476}, {'batch_size': 6, 'throughput': 1.420905711972334, 'latency_mean': 4.198366655111313, 'latency_p50': 4.204331398010254, 'latency_p90': 4.667846965789795}, {'batch_size': 8, 'throughput': 1.4730091463480268, 'latency_mean': 5.397047694921493, 'latency_p50': 5.384958386421204, 'latency_p90': 6.142484354972839}, {'batch_size': 10, 'throughput': 1.5156321965234847, 'latency_mean': 6.541167447566986, 'latency_p50': 6.476431727409363, 'latency_p90': 7.399344468116761}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: rica40325/10_14dpo
model_name: rica40325-10-14dpo_v1
model_num_parameters: 12772070400.0
model_repo: rica40325/10_14dpo
model_size: 13B
num_battles: 12472
num_wins: 6968
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.32
timestamp: 2024-11-12T08:12:54+00:00
us_pacific_date: 2024-11-12
win_ratio: 0.5586914688903143
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 rica40325-10-14dpo-v6-mkmlizer
Waiting for job on rica40325-10-14dpo-v6-mkmlizer to finish
rica40325-10-14dpo-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-10-14dpo-v6-mkmlizer: ║ _____ __ __ ║
rica40325-10-14dpo-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rica40325-10-14dpo-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rica40325-10-14dpo-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rica40325-10-14dpo-v6-mkmlizer: ║ /___/ ║
rica40325-10-14dpo-v6-mkmlizer: ║ ║
rica40325-10-14dpo-v6-mkmlizer: ║ Version: 0.11.33 ║
rica40325-10-14dpo-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rica40325-10-14dpo-v6-mkmlizer: ║ https://mk1.ai ║
rica40325-10-14dpo-v6-mkmlizer: ║ ║
rica40325-10-14dpo-v6-mkmlizer: ║ The license key for the current software has been verified as ║
rica40325-10-14dpo-v6-mkmlizer: ║ belonging to: ║
rica40325-10-14dpo-v6-mkmlizer: ║ ║
rica40325-10-14dpo-v6-mkmlizer: ║ Chai Research Corp. ║
rica40325-10-14dpo-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rica40325-10-14dpo-v6-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
rica40325-10-14dpo-v6-mkmlizer: ║ ║
rica40325-10-14dpo-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-10-14dpo-v6-mkmlizer: Downloaded to shared memory in 94.282s
rica40325-10-14dpo-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjttymqlo, device:0
rica40325-10-14dpo-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
rica40325-10-14dpo-v6-mkmlizer: quantized model in 41.946s
rica40325-10-14dpo-v6-mkmlizer: Processed model rica40325/10_14dpo in 136.228s
rica40325-10-14dpo-v6-mkmlizer: creating bucket guanaco-mkml-models
rica40325-10-14dpo-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-10-14dpo-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-10-14dpo-v6
rica40325-10-14dpo-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-10-14dpo-v6/config.json
rica40325-10-14dpo-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-10-14dpo-v6/special_tokens_map.json
rica40325-10-14dpo-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-10-14dpo-v6/tokenizer_config.json
rica40325-10-14dpo-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-10-14dpo-v6/tokenizer.json
rica40325-10-14dpo-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-10-14dpo-v6/flywheel_model.0.safetensors
rica40325-10-14dpo-v6-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:16, 21.20it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:12, 27.52it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:14, 24.22it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:09, 35.14it/s] Loading 0: 7%|▋ | 26/363 [00:01<00:16, 19.85it/s] Loading 0: 9%|▊ | 31/363 [00:01<00:13, 24.47it/s] Loading 0: 10%|▉ | 35/363 [00:01<00:12, 26.36it/s] Loading 0: 11%|█ | 39/363 [00:01<00:11, 28.13it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:11, 27.72it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:10, 29.87it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:11, 27.86it/s] Loading 0: 15%|█▌ | 56/363 [00:02<00:10, 27.98it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:12, 23.88it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:14, 21.12it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:10, 27.79it/s] Loading 0: 21%|██ | 75/363 [00:02<00:10, 27.37it/s] Loading 0: 21%|██▏ | 78/363 [00:03<00:11, 24.91it/s] Loading 0: 23%|██▎ | 84/363 [00:03<00:09, 28.66it/s] Loading 0: 24%|██▍ | 87/363 [00:03<00:11, 24.76it/s] Loading 0: 26%|██▌ | 93/363 [00:03<00:09, 29.10it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:09, 27.74it/s] Loading 0: 28%|██▊ | 101/363 [00:03<00:11, 22.74it/s] Loading 0: 29%|██▊ | 104/363 [00:04<00:12, 20.08it/s] Loading 0: 31%|███ | 111/363 [00:04<00:09, 27.02it/s] Loading 0: 31%|███▏ | 114/363 [00:04<00:09, 25.61it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 30.20it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:08, 29.22it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 31.66it/s] Loading 0: 37%|███▋ | 133/363 [00:05<00:07, 28.78it/s] Loading 0: 37%|███▋ | 136/363 [00:05<00:07, 28.86it/s] Loading 0: 39%|███▉ | 141/363 [00:05<00:07, 30.80it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:10, 21.24it/s] Loading 0: 41%|████ | 149/363 [00:05<00:10, 21.30it/s] Loading 0: 43%|████▎ | 156/363 [00:05<00:07, 27.35it/s] Loading 0: 44%|████▍ | 160/363 [00:06<00:07, 27.49it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:06, 30.34it/s] Loading 0: 47%|████▋ | 169/363 [00:06<00:06, 28.22it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:06, 30.98it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:06, 29.17it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:07, 24.02it/s] Loading 0: 51%|█████ | 185/363 [00:07<00:08, 20.93it/s] Loading 0: 53%|█████▎ | 192/363 [00:07<00:06, 28.03it/s] Loading 0: 54%|█████▍ | 196/363 [00:07<00:05, 28.11it/s] Loading 0: 55%|█████▌ | 201/363 [00:07<00:05, 31.16it/s] Loading 0: 56%|█████▋ | 205/363 [00:07<00:05, 30.13it/s] Loading 0: 58%|█████▊ | 210/363 [00:07<00:04, 32.26it/s] Loading 0: 59%|█████▉ | 214/363 [00:07<00:04, 29.93it/s] Loading 0: 60%|██████ | 218/363 [00:08<00:04, 29.03it/s] Loading 0: 61%|██████ | 222/363 [00:08<00:04, 31.39it/s] Loading 0: 62%|██████▏ | 226/363 [00:08<00:06, 21.81it/s] Loading 0: 63%|██████▎ | 230/363 [00:08<00:06, 21.13it/s] Loading 0: 65%|██████▌ | 237/363 [00:08<00:04, 27.68it/s] Loading 0: 66%|██████▋ | 241/363 [00:09<00:04, 27.04it/s] Loading 0: 67%|██████▋ | 244/363 [00:09<00:04, 27.61it/s] Loading 0: 68%|██████▊ | 248/363 [00:09<00:04, 24.53it/s] Loading 0: 70%|███████ | 255/363 [00:09<00:03, 30.92it/s] Loading 0: 71%|███████▏ | 259/363 [00:09<00:03, 29.10it/s] Loading 0: 72%|███████▏ | 263/363 [00:09<00:04, 23.27it/s] Loading 0: 73%|███████▎ | 266/363 [00:10<00:04, 20.55it/s] Loading 0: 75%|███████▍ | 271/363 [00:10<00:03, 25.38it/s] Loading 0: 76%|███████▌ | 275/363 [00:10<00:03, 23.05it/s] Loading 0: 77%|███████▋ | 280/363 [00:10<00:03, 27.61it/s] Loading 0: 78%|███████▊ | 284/363 [00:10<00:03, 24.39it/s] Loading 0: 80%|███████▉ | 289/363 [00:10<00:02, 29.01it/s] Loading 0: 81%|████████ | 293/363 [00:11<00:02, 25.78it/s] Loading 0: 82%|████████▏ | 298/363 [00:11<00:02, 30.44it/s] Loading 0: 83%|████████▎ | 303/363 [00:11<00:01, 31.09it/s] Loading 0: 85%|████████▍ | 307/363 [00:11<00:02, 21.60it/s] Loading 0: 86%|████████▌ | 311/363 [00:11<00:02, 20.83it/s] Loading 0: 87%|████████▋ | 316/363 [00:11<00:01, 25.63it/s] Loading 0: 88%|████████▊ | 320/363 [00:12<00:01, 23.28it/s] Loading 0: 90%|████████▉ | 325/363 [00:12<00:01, 28.20it/s] Loading 0: 91%|█████████ | 329/363 [00:12<00:01, 24.77it/s] Loading 0: 92%|█████████▏| 334/363 [00:12<00:00, 29.62it/s] Loading 0: 93%|█████████▎| 338/363 [00:12<00:01, 24.98it/s] Loading 0: 94%|█████████▍| 343/363 [00:12<00:00, 29.38it/s] Loading 0: 96%|█████████▌| 347/363 [00:20<00:08, 1.95it/s] Loading 0: 96%|█████████▋| 350/363 [00:20<00:05, 2.46it/s] Loading 0: 97%|█████████▋| 353/363 [00:20<00:03, 3.15it/s] Loading 0: 98%|█████████▊| 357/363 [00:20<00:01, 4.33it/s]
Job rica40325-10-14dpo-v6-mkmlizer completed after 165.12s with status: succeeded
Stopping job with name rica40325-10-14dpo-v6-mkmlizer
Pipeline stage MKMLizer completed in 165.64s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-10-14dpo-v6
Waiting for inference service rica40325-10-14dpo-v6 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service rica40325-10-14dpo-v6 ready after 180.736159324646s
Pipeline stage MKMLDeployer completed in 181.33s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.086836814880371s
Received healthy response to inference request in 1.6502561569213867s
Received healthy response to inference request in 1.4545989036560059s
Received healthy response to inference request in 1.662487268447876s
Received healthy response to inference request in 1.5214855670928955s
5 requests
0 failed requests
5th percentile: 1.4679762363433837
10th percentile: 1.4813535690307618
20th percentile: 1.5081082344055177
30th percentile: 1.5472396850585937
40th percentile: 1.5987479209899902
50th percentile: 1.6502561569213867
60th percentile: 1.6551486015319825
70th percentile: 1.660041046142578
80th percentile: 1.747357177734375
90th percentile: 1.9170969963073732
95th percentile: 2.001966905593872
99th percentile: 2.069862833023071
mean time: 1.675132942199707
Pipeline stage StressChecker completed in 9.77s
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 2.14s
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 2.26s
Shutdown handler de-registered
rica40325-10-14dpo_v6 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3163.23s
Shutdown handler de-registered
rica40325-10-14dpo_v6 status is now inactive due to auto deactivation removed underperforming models
rica40325-10-14dpo_v6 status is now torndown due to DeploymentManager action