submission_id: rinen0721-mistral12b-exp5_v2
developer_uid: rinen0721
best_of: 8
celo_rating: 1243.6
display_name: rinen0721-mistral12b-exp5_v2
family_friendly_score: 0.569
family_friendly_standard_error: 0.007003413453452538
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': 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}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: rinen0721/Mistral12b-exp5
latencies: [{'batch_size': 1, 'throughput': 0.6084481031671684, 'latency_mean': 1.6434283757209778, 'latency_p50': 1.6507861614227295, 'latency_p90': 1.806963610649109}, {'batch_size': 3, 'throughput': 1.1090809739754568, 'latency_mean': 2.69287070274353, 'latency_p50': 2.694333076477051, 'latency_p90': 2.9268035888671875}, {'batch_size': 5, 'throughput': 1.3405923052248496, 'latency_mean': 3.7093093514442446, 'latency_p50': 3.7241432666778564, 'latency_p90': 4.1297527074813845}, {'batch_size': 6, 'throughput': 1.3839381221243305, 'latency_mean': 4.319367293119431, 'latency_p50': 4.3216001987457275, 'latency_p90': 4.804960560798645}, {'batch_size': 8, 'throughput': 1.4577281685960852, 'latency_mean': 5.4463931453228, 'latency_p50': 5.464907169342041, 'latency_p90': 6.166172480583191}, {'batch_size': 10, 'throughput': 1.4840192065366273, 'latency_mean': 6.697527233362198, 'latency_p50': 6.717881083488464, 'latency_p90': 7.458625960350036}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: rinen0721/Mistral12b-exp
model_name: rinen0721-mistral12b-exp5_v2
model_num_parameters: 12772070400.0
model_repo: rinen0721/Mistral12b-exp5
model_size: 13B
num_battles: 22461
num_wins: 11181
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.35
timestamp: 2024-11-11T15:30:45+00:00
us_pacific_date: 2024-11-11
win_ratio: 0.49779618004541204
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 rinen0721-mistral12b-exp5-v2-mkmlizer
Waiting for job on rinen0721-mistral12b-exp5-v2-mkmlizer to finish
rinen0721-mistral12b-exp5-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-mistral12b-exp5-v2-mkmlizer: ║ _____ __ __ ║
rinen0721-mistral12b-exp5-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rinen0721-mistral12b-exp5-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rinen0721-mistral12b-exp5-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rinen0721-mistral12b-exp5-v2-mkmlizer: ║ /___/ ║
rinen0721-mistral12b-exp5-v2-mkmlizer: ║ ║
rinen0721-mistral12b-exp5-v2-mkmlizer: ║ Version: 0.11.33 ║
rinen0721-mistral12b-exp5-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rinen0721-mistral12b-exp5-v2-mkmlizer: ║ https://mk1.ai ║
rinen0721-mistral12b-exp5-v2-mkmlizer: ║ ║
rinen0721-mistral12b-exp5-v2-mkmlizer: ║ The license key for the current software has been verified as ║
rinen0721-mistral12b-exp5-v2-mkmlizer: ║ belonging to: ║
rinen0721-mistral12b-exp5-v2-mkmlizer: ║ ║
rinen0721-mistral12b-exp5-v2-mkmlizer: ║ Chai Research Corp. ║
rinen0721-mistral12b-exp5-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rinen0721-mistral12b-exp5-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
rinen0721-mistral12b-exp5-v2-mkmlizer: ║ ║
rinen0721-mistral12b-exp5-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Retrying (%r) after connection broken by '%r': %s
Failed to get response for submission jic062-dpo-v3-0-nemo_v1: ('http://jic062-dpo-v3-0-nemo-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
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
rinen0721-mistral12b-exp5-v2-mkmlizer: Downloaded to shared memory in 95.766s
rinen0721-mistral12b-exp5-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwzl2ljd_, device:0
rinen0721-mistral12b-exp5-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-mistral12b-exp5-v2-mkmlizer: quantized model in 37.311s
rinen0721-mistral12b-exp5-v2-mkmlizer: Processed model rinen0721/Mistral12b-exp5 in 133.077s
rinen0721-mistral12b-exp5-v2-mkmlizer: creating bucket guanaco-mkml-models
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
rinen0721-mistral12b-exp5-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-mistral12b-exp5-v2/config.json
rinen0721-mistral12b-exp5-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-mistral12b-exp5-v2/special_tokens_map.json
rinen0721-mistral12b-exp5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-mistral12b-exp5-v2/tokenizer_config.json
rinen0721-mistral12b-exp5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-mistral12b-exp5-v2/tokenizer.json
rinen0721-mistral12b-exp5-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-mistral12b-exp5-v2/flywheel_model.0.safetensors
rinen0721-mistral12b-exp5-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 28.15it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 46.66it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:08, 42.34it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 40.87it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 47.55it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 45.36it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 43.67it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 49.02it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 46.18it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 33.70it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 32.83it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:07, 38.33it/s] Loading 0: 21%|██ | 76/363 [00:01<00:07, 39.72it/s] Loading 0: 22%|██▏ | 81/363 [00:01<00:06, 41.97it/s] Loading 0: 24%|██▍ | 87/363 [00:02<00:06, 41.69it/s] Loading 0: 25%|██▌ | 92/363 [00:02<00:06, 40.83it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:05, 45.60it/s] Loading 0: 29%|██▊ | 104/363 [00:02<00:05, 44.91it/s] Loading 0: 30%|███ | 109/363 [00:02<00:05, 44.05it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:06, 36.59it/s] Loading 0: 33%|███▎ | 118/363 [00:02<00:07, 34.69it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:05, 41.69it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 41.05it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 41.40it/s] Loading 0: 39%|███▊ | 140/363 [00:03<00:05, 43.13it/s] Loading 0: 40%|███▉ | 145/363 [00:03<00:08, 26.58it/s] Loading 0: 41%|████ | 149/363 [00:03<00:07, 26.93it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:06, 33.95it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 35.58it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:05, 37.67it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 39.49it/s] Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 32.58it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 39.86it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:04, 40.60it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:04, 40.91it/s] Loading 0: 55%|█████▍ | 198/363 [00:05<00:03, 41.79it/s] Loading 0: 56%|█████▌ | 203/363 [00:05<00:04, 34.24it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 40.75it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 40.48it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:03, 41.91it/s] Loading 0: 62%|██████▏ | 225/363 [00:05<00:05, 26.31it/s] Loading 0: 63%|██████▎ | 230/363 [00:06<00:04, 28.72it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 35.61it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 36.34it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:03, 37.73it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 39.94it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:03, 33.36it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 40.74it/s] Loading 0: 74%|███████▍ | 269/363 [00:07<00:02, 40.64it/s] Loading 0: 75%|███████▌ | 274/363 [00:07<00:02, 40.61it/s] Loading 0: 77%|███████▋ | 279/363 [00:07<00:02, 40.63it/s] Loading 0: 78%|███████▊ | 284/363 [00:07<00:02, 34.78it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 41.58it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 40.84it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:01, 43.02it/s] Loading 0: 84%|████████▍ | 306/363 [00:14<00:23, 2.44it/s] Loading 0: 85%|████████▌ | 310/363 [00:14<00:16, 3.16it/s] Loading 0: 87%|████████▋ | 314/363 [00:14<00:11, 4.14it/s] Loading 0: 88%|████████▊ | 320/363 [00:15<00:06, 6.19it/s] Loading 0: 90%|████████▉ | 326/363 [00:15<00:04, 8.67it/s] Loading 0: 91%|█████████ | 330/363 [00:15<00:03, 10.51it/s] Loading 0: 93%|█████████▎| 337/363 [00:15<00:01, 15.43it/s] Loading 0: 94%|█████████▍| 342/363 [00:15<00:01, 18.72it/s] Loading 0: 96%|█████████▌| 347/363 [00:15<00:00, 22.56it/s] Loading 0: 97%|█████████▋| 352/363 [00:15<00:00, 26.23it/s] Loading 0: 98%|█████████▊| 357/363 [00:15<00:00, 25.34it/s]
Job rinen0721-mistral12b-exp5-v2-mkmlizer completed after 166.09s with status: succeeded
Stopping job with name rinen0721-mistral12b-exp5-v2-mkmlizer
Pipeline stage MKMLizer completed in 166.61s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rinen0721-mistral12b-exp5-v2
Waiting for inference service rinen0721-mistral12b-exp5-v2 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
Inference service rinen0721-mistral12b-exp5-v2 ready after 180.868958234787s
Pipeline stage MKMLDeployer completed in 181.49s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7584493160247803s
Received healthy response to inference request in 1.9673669338226318s
Received healthy response to inference request in 1.7512381076812744s
Received healthy response to inference request in 1.4715898036956787s
Received healthy response to inference request in 1.7152156829833984s
5 requests
0 failed requests
5th percentile: 1.5203149795532227
10th percentile: 1.5690401554107667
20th percentile: 1.6664905071258544
30th percentile: 1.7224201679229736
40th percentile: 1.7368291378021241
50th percentile: 1.7512381076812744
60th percentile: 1.7541225910186768
70th percentile: 1.757007074356079
80th percentile: 1.8002328395843505
90th percentile: 1.8837998867034913
95th percentile: 1.9255834102630616
99th percentile: 1.9590102291107179
mean time: 1.7327719688415528
Pipeline stage StressChecker completed in 10.26s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%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
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
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 5.80s
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 2.61s
Shutdown handler de-registered
rinen0721-mistral12b-exp5_v2 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 2906.81s
Shutdown handler de-registered
rinen0721-mistral12b-exp5_v2 status is now inactive due to auto deactivation removed underperforming models
rinen0721-mistral12b-exp5_v2 status is now torndown due to DeploymentManager action