submission_id: cgato-nemo-12b-thespice-_1853_v2
developer_uid: c.gato
best_of: 8
celo_rating: 1272.32
display_name: cgato-nemo-12b-thespice-_1853_v2
family_friendly_score: 0.5611999999999999
family_friendly_standard_error: 0.0070178994008178825
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}
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: cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-v0.3-Small-2k
latencies: [{'batch_size': 1, 'throughput': 0.6046854611546094, 'latency_mean': 1.6536843073368073, 'latency_p50': 1.659724473953247, 'latency_p90': 1.8278503656387328}, {'batch_size': 3, 'throughput': 1.1028625927851492, 'latency_mean': 2.711977950334549, 'latency_p50': 2.7127933502197266, 'latency_p90': 3.0035254478454587}, {'batch_size': 5, 'throughput': 1.325323174872387, 'latency_mean': 3.7609102380275727, 'latency_p50': 3.775881052017212, 'latency_p90': 4.203470611572266}, {'batch_size': 6, 'throughput': 1.4023808832453728, 'latency_mean': 4.26119416475296, 'latency_p50': 4.266811728477478, 'latency_p90': 4.770461440086365}, {'batch_size': 8, 'throughput': 1.4478426479911126, 'latency_mean': 5.473211576938629, 'latency_p50': 5.49855899810791, 'latency_p90': 6.142393326759338}, {'batch_size': 10, 'throughput': 1.4906713959723237, 'latency_mean': 6.659835771322251, 'latency_p50': 6.627294421195984, 'latency_p90': 7.53564715385437}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: cgato/Nemo-12b-TheSpice-
model_name: cgato-nemo-12b-thespice-_1853_v2
model_num_parameters: 12772121600.0
model_repo: cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-v0.3-Small-2k
model_size: 13B
num_battles: 15267
num_wins: 8243
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.32
timestamp: 2024-11-13T01:04:23+00:00
us_pacific_date: 2024-11-12
win_ratio: 0.5399227091111548
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 cgato-nemo-12b-thespice-1853-v2-mkmlizer
Waiting for job on cgato-nemo-12b-thespice-1853-v2-mkmlizer to finish
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ║ _____ __ __ ║
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ║ /___/ ║
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ║ ║
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ║ Version: 0.11.33 ║
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ║ https://mk1.ai ║
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ║ ║
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ║ belonging to: ║
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ║ ║
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ║ ║
cgato-nemo-12b-thespice-1853-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-nemo-12b-thespice-1853-v2-mkmlizer: Downloaded to shared memory in 63.045s
cgato-nemo-12b-thespice-1853-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdsgcxpz5, device:0
cgato-nemo-12b-thespice-1853-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-nemo-12b-thespice-1853-v2-mkmlizer: quantized model in 36.518s
cgato-nemo-12b-thespice-1853-v2-mkmlizer: Processed model cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-v0.3-Small-2k in 99.564s
cgato-nemo-12b-thespice-1853-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-nemo-12b-thespice-1853-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-nemo-12b-thespice-1853-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v2
cgato-nemo-12b-thespice-1853-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v2/config.json
cgato-nemo-12b-thespice-1853-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v2/special_tokens_map.json
cgato-nemo-12b-thespice-1853-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v2/tokenizer_config.json
cgato-nemo-12b-thespice-1853-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v2/tokenizer.json
cgato-nemo-12b-thespice-1853-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v2/flywheel_model.0.safetensors
cgato-nemo-12b-thespice-1853-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 30.18it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 50.59it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 46.80it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 43.84it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 48.73it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 45.39it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 43.76it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 49.00it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 45.02it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 33.71it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 32.79it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.71it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 39.65it/s] Loading 0: 23%|██▎ | 83/363 [00:02<00:06, 40.35it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 45.47it/s] Loading 0: 26%|██▌ | 95/363 [00:02<00:05, 45.55it/s] Loading 0: 28%|██▊ | 100/363 [00:02<00:06, 39.39it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:05, 43.97it/s] Loading 0: 31%|███ | 113/363 [00:02<00:05, 42.92it/s] Loading 0: 33%|███▎ | 118/363 [00:02<00:05, 41.93it/s] Loading 0: 34%|███▍ | 125/363 [00:02<00:04, 48.43it/s] Loading 0: 36%|███▌ | 131/363 [00:03<00:04, 48.81it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 42.87it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 32.73it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 33.33it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 32.51it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 38.98it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:05, 39.25it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:04, 39.95it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 45.29it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 43.59it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 42.83it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 47.73it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 45.69it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 44.55it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 48.99it/s] Loading 0: 60%|█████▉ | 216/363 [00:05<00:03, 47.96it/s] Loading 0: 61%|██████ | 221/363 [00:05<00:03, 46.80it/s] Loading 0: 62%|██████▏ | 226/363 [00:05<00:04, 28.68it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:04, 29.04it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 36.41it/s] Loading 0: 67%|██████▋ | 242/363 [00:05<00:03, 38.13it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:02, 39.39it/s] Loading 0: 70%|██████▉ | 253/363 [00:06<00:02, 39.77it/s] Loading 0: 71%|███████ | 258/363 [00:06<00:02, 40.21it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 45.58it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:02, 43.60it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:02, 40.83it/s] Loading 0: 78%|███████▊ | 282/363 [00:06<00:01, 45.21it/s] Loading 0: 79%|███████▉ | 287/363 [00:06<00:01, 45.19it/s] Loading 0: 80%|████████ | 292/363 [00:07<00:01, 45.34it/s] Loading 0: 82%|████████▏ | 298/363 [00:07<00:01, 43.55it/s] Loading 0: 84%|████████▎ | 304/363 [00:14<00:22, 2.62it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:16, 3.34it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:12, 4.24it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 6.97it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.37it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 11.83it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 16.51it/s] Loading 0: 95%|█████████▍| 344/363 [00:15<00:00, 20.21it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 23.48it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 29.83it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.43it/s]
Job cgato-nemo-12b-thespice-1853-v2-mkmlizer completed after 124.77s with status: succeeded
Stopping job with name cgato-nemo-12b-thespice-1853-v2-mkmlizer
Pipeline stage MKMLizer completed in 125.35s
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 cgato-nemo-12b-thespice-1853-v2
Waiting for inference service cgato-nemo-12b-thespice-1853-v2 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cgato-nemo-12b-thespice-1853-v2 ready after 190.84873032569885s
Pipeline stage MKMLDeployer completed in 191.41s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1340537071228027s
Received healthy response to inference request in 1.7497234344482422s
Received healthy response to inference request in 1.5647339820861816s
Received healthy response to inference request in 1.454197883605957s
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
Received healthy response to inference request in 1.5663578510284424s
5 requests
0 failed requests
5th percentile: 1.476305103302002
10th percentile: 1.4984123229980468
20th percentile: 1.5426267623901366
30th percentile: 1.5650587558746338
40th percentile: 1.565708303451538
50th percentile: 1.5663578510284424
60th percentile: 1.6397040843963624
70th percentile: 1.7130503177642822
80th percentile: 1.8265894889831544
90th percentile: 1.9803215980529785
95th percentile: 2.0571876525878907
99th percentile: 2.1186804962158203
mean time: 1.6938133716583252
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 2.71s
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 3.28s
Shutdown handler de-registered
cgato-nemo-12b-thespice-_1853_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 2936.90s
Shutdown handler de-registered
cgato-nemo-12b-thespice-_1853_v2 status is now inactive due to auto deactivation removed underperforming models
cgato-nemo-12b-thespice-_1853_v2 status is now torndown due to DeploymentManager action