developer_uid: Riverise
submission_id: rica40325-linear-merge-1113_v1
model_name: rica40325-linear-merge-1113_v1
model_group: rica40325/linear_merge_1
status: torndown
timestamp: 2024-11-12T09:09:26+00:00
num_battles: 14932
num_wins: 8572
celo_rating: 1296.5
family_friendly_score: 0.5631999999999999
family_friendly_standard_error: 0.007014353284515972
submission_type: basic
model_repo: rica40325/linear_merge_1113
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6030464775354568, 'latency_mean': 1.6581869292259217, 'latency_p50': 1.6730263233184814, 'latency_p90': 1.8335637092590331}, {'batch_size': 3, 'throughput': 1.1046210985417773, 'latency_mean': 2.7105687975883486, 'latency_p50': 2.709075093269348, 'latency_p90': 3.0121355056762695}, {'batch_size': 5, 'throughput': 1.3203753374943181, 'latency_mean': 3.7765466499328615, 'latency_p50': 3.7871994972229004, 'latency_p90': 4.294636154174805}, {'batch_size': 6, 'throughput': 1.375720653462128, 'latency_mean': 4.344354957342148, 'latency_p50': 4.375416874885559, 'latency_p90': 4.883691334724427}, {'batch_size': 8, 'throughput': 1.456440041720684, 'latency_mean': 5.463795080184936, 'latency_p50': 5.455050587654114, 'latency_p90': 6.194182324409485}, {'batch_size': 10, 'throughput': 1.4828056391762696, 'latency_mean': 6.688793309926987, 'latency_p50': 6.6998573541641235, 'latency_p90': 7.514251637458801}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rica40325-linear-merge-1113_v1
is_internal_developer: False
language_model: rica40325/linear_merge_1113
model_size: 13B
ranking_group: single
throughput_3p7s: 1.31
us_pacific_date: 2024-11-12
win_ratio: 0.5740691133136887
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, '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-linear-merge-1113-v1-mkmlizer
Waiting for job on rica40325-linear-merge-1113-v1-mkmlizer to finish
rica40325-linear-merge-1113-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-linear-merge-1113-v1-mkmlizer: ║     _____            __           __                                ║
rica40325-linear-merge-1113-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-linear-merge-1113-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-linear-merge-1113-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-linear-merge-1113-v1-mkmlizer: ║       /___/                                                         ║
rica40325-linear-merge-1113-v1-mkmlizer: ║                                                                     ║
rica40325-linear-merge-1113-v1-mkmlizer: ║  Version: 0.11.33                                                   ║
rica40325-linear-merge-1113-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-linear-merge-1113-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-linear-merge-1113-v1-mkmlizer: ║                                                                     ║
rica40325-linear-merge-1113-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-linear-merge-1113-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-linear-merge-1113-v1-mkmlizer: ║                                                                     ║
rica40325-linear-merge-1113-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-linear-merge-1113-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-linear-merge-1113-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
rica40325-linear-merge-1113-v1-mkmlizer: ║                                                                     ║
rica40325-linear-merge-1113-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
rica40325-linear-merge-1113-v1-mkmlizer: Downloaded to shared memory in 46.804s
rica40325-linear-merge-1113-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphzzoxh_g, device:0
rica40325-linear-merge-1113-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-linear-merge-1113-v1-mkmlizer: quantized model in 37.428s
rica40325-linear-merge-1113-v1-mkmlizer: Processed model rica40325/linear_merge_1113 in 84.232s
rica40325-linear-merge-1113-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-linear-merge-1113-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-linear-merge-1113-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-linear-merge-1113-v1
rica40325-linear-merge-1113-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-linear-merge-1113-v1/special_tokens_map.json
rica40325-linear-merge-1113-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-linear-merge-1113-v1/config.json
rica40325-linear-merge-1113-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-linear-merge-1113-v1/tokenizer_config.json
rica40325-linear-merge-1113-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-linear-merge-1113-v1/tokenizer.json
rica40325-linear-merge-1113-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-linear-merge-1113-v1/flywheel_model.0.safetensors
rica40325-linear-merge-1113-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:39,  3.10s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:59,  1.19it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:46,  3.28it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:12,  4.79it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:43,  7.79it/s]
Loading 0:   8%|▊         | 28/363 [00:06<00:31, 10.67it/s]
Loading 0:   9%|▉         | 33/363 [00:07<00:25, 13.05it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:20, 16.07it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:17, 18.47it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:13, 23.68it/s]
Loading 0:  15%|█▌        | 55/363 [00:07<00:11, 27.70it/s]
Loading 0:  17%|█▋        | 60/363 [00:07<00:10, 27.80it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:08, 35.46it/s]
Loading 0:  20%|█▉        | 72/363 [00:08<00:07, 36.42it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:07, 37.83it/s]
Loading 0:  23%|██▎       | 83/363 [00:08<00:07, 37.92it/s]
Loading 0:  24%|██▍       | 88/363 [00:08<00:07, 38.39it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:06, 43.13it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:06, 43.50it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:05, 44.74it/s]
Loading 0:  30%|███       | 110/363 [00:08<00:05, 43.26it/s]
Loading 0:  32%|███▏      | 115/363 [00:09<00:06, 40.68it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:07, 30.66it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:07, 30.81it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 35.48it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:06, 36.42it/s]
Loading 0:  38%|███▊      | 139/363 [00:09<00:06, 36.38it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:06, 34.82it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:05, 37.13it/s]
Loading 0:  42%|████▏     | 152/363 [00:10<00:05, 35.34it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 37.75it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:05, 37.88it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 41.92it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:04, 41.69it/s]
Loading 0:  49%|████▉     | 178/363 [00:10<00:04, 41.06it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:03, 45.84it/s]
Loading 0:  52%|█████▏    | 189/363 [00:11<00:03, 45.43it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:03, 44.47it/s]
Loading 0:  55%|█████▍    | 199/363 [00:11<00:03, 44.69it/s]
Loading 0:  56%|█████▌    | 204/363 [00:11<00:06, 26.35it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:04, 34.72it/s]
Loading 0:  60%|██████    | 218/363 [00:11<00:04, 36.19it/s]
Loading 0:  61%|██████▏   | 223/363 [00:12<00:03, 36.45it/s]
Loading 0:  63%|██████▎   | 230/363 [00:12<00:03, 41.71it/s]
Loading 0:  65%|██████▍   | 235/363 [00:12<00:02, 43.59it/s]
Loading 0:  66%|██████▌   | 240/363 [00:12<00:03, 35.81it/s]
Loading 0:  68%|██████▊   | 247/363 [00:12<00:02, 42.25it/s]
Loading 0:  69%|██████▉   | 252/363 [00:12<00:02, 41.80it/s]
Loading 0:  71%|███████   | 257/363 [00:12<00:02, 43.32it/s]
Loading 0:  72%|███████▏  | 263/363 [00:12<00:02, 42.48it/s]
Loading 0:  74%|███████▍  | 268/363 [00:13<00:02, 41.62it/s]
Loading 0:  75%|███████▌  | 274/363 [00:13<00:01, 46.00it/s]
Loading 0:  77%|███████▋  | 279/363 [00:13<00:01, 45.54it/s]
Loading 0:  78%|███████▊  | 284/363 [00:13<00:02, 30.79it/s]
Loading 0:  79%|███████▉  | 288/363 [00:13<00:02, 32.22it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:02, 32.44it/s]
Loading 0:  82%|████████▏ | 296/363 [00:13<00:02, 32.99it/s]
Loading 0:  83%|████████▎ | 301/363 [00:14<00:01, 36.93it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:01, 37.16it/s]
Loading 0:  86%|████████▌ | 311/363 [00:14<00:01, 41.00it/s]
Loading 0:  87%|████████▋ | 317/363 [00:14<00:01, 40.62it/s]
Loading 0:  89%|████████▊ | 322/363 [00:14<00:01, 40.88it/s]
Loading 0:  90%|█████████ | 328/363 [00:14<00:00, 45.62it/s]
Loading 0:  92%|█████████▏| 333/363 [00:14<00:00, 45.83it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 46.54it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 44.39it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 42.86it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 47.76it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 44.54it/s]
                                                            

Job rica40325-linear-merge-1113-v1-mkmlizer completed after 114.73s with status: succeeded
Stopping job with name rica40325-linear-merge-1113-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.27s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-linear-merge-1113-v1
Waiting for inference service rica40325-linear-merge-1113-v1 to be ready
Inference service rica40325-linear-merge-1113-v1 ready after 190.7074213027954s
Pipeline stage MKMLDeployer completed in 191.33s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.402947425842285s
Received healthy response to inference request in 1.7444536685943604s
Received healthy response to inference request in 1.9021766185760498s
Received healthy response to inference request in 1.8319571018218994s
Received healthy response to inference request in 1.5049293041229248s
5 requests
0 failed requests
5th percentile: 1.5528341770172118
10th percentile: 1.600739049911499
20th percentile: 1.6965487957000733
30th percentile: 1.7619543552398682
40th percentile: 1.7969557285308837
50th percentile: 1.8319571018218994
60th percentile: 1.8600449085235595
70th percentile: 1.8881327152252196
80th percentile: 2.002330780029297
90th percentile: 2.202639102935791
95th percentile: 2.302793264389038
99th percentile: 2.3829165935516357
mean time: 1.8772928237915039
Pipeline stage StressChecker completed in 10.75s
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 2.45s
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 2.56s
Shutdown handler de-registered
rica40325-linear-merge-1113_v1 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 2912.45s
Shutdown handler de-registered
rica40325-linear-merge-1113_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-linear-merge-1113_v1 status is now torndown due to DeploymentManager action